| 179 3 1184 1175 84 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #include <linux/nexthop.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/lwtunnel.h> #include <net/ndisc.h> #include <net/nexthop.h> #include <net/route.h> #include <net/sock.h> static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo); #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, [NHA_GROUP_TYPE] = { .type = NLA_U16 }, [NHA_BLACKHOLE] = { .type = NLA_FLAG }, [NHA_OIF] = { .type = NLA_U32 }, [NHA_GATEWAY] = { .type = NLA_BINARY }, [NHA_ENCAP_TYPE] = { .type = NLA_U16 }, [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, }; static int call_nexthop_notifiers(struct net *net, enum nexthop_event_type event_type, struct nexthop *nh) { int err; err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, event_type, nh); return notifier_to_errno(err); } static unsigned int nh_dev_hashfn(unsigned int val) { unsigned int mask = NH_DEV_HASHSIZE - 1; return (val ^ (val >> NH_DEV_HASHBITS) ^ (val >> (NH_DEV_HASHBITS * 2))) & mask; } static void nexthop_devhash_add(struct net *net, struct nh_info *nhi) { struct net_device *dev = nhi->fib_nhc.nhc_dev; struct hlist_head *head; unsigned int hash; WARN_ON(!dev); hash = nh_dev_hashfn(dev->ifindex); head = &net->nexthop.devhash[hash]; hlist_add_head(&nhi->dev_hash, head); } static void nexthop_free_mpath(struct nexthop *nh) { struct nh_group *nhg; int i; nhg = rcu_dereference_raw(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); nexthop_put(nhge->nh); } WARN_ON(nhg->spare == nhg); kfree(nhg->spare); kfree(nhg); } static void nexthop_free_single(struct nexthop *nh) { struct nh_info *nhi; nhi = rcu_dereference_raw(nh->nh_info); switch (nhi->family) { case AF_INET: fib_nh_release(nh->net, &nhi->fib_nh); break; case AF_INET6: ipv6_stub->fib6_nh_release(&nhi->fib6_nh); break; } kfree(nhi); } void nexthop_free_rcu(struct rcu_head *head) { struct nexthop *nh = container_of(head, struct nexthop, rcu); if (nh->is_group) nexthop_free_mpath(nh); else nexthop_free_single(nh); kfree(nh); } EXPORT_SYMBOL_GPL(nexthop_free_rcu); static struct nexthop *nexthop_alloc(void) { struct nexthop *nh; nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL); if (nh) { INIT_LIST_HEAD(&nh->fi_list); INIT_LIST_HEAD(&nh->f6i_list); INIT_LIST_HEAD(&nh->grp_list); INIT_LIST_HEAD(&nh->fdb_list); } return nh; } static struct nh_group *nexthop_grp_alloc(u16 num_nh) { struct nh_group *nhg; nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; return nhg; } static void nh_base_seq_inc(struct net *net) { while (++net->nexthop.seq == 0) ; } /* no reference taken; rcu lock or rtnl must be held */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id) { struct rb_node **pp, *parent = NULL, *next; pp = &net->nexthop.rb_root.rb_node; while (1) { struct nexthop *nh; next = rcu_dereference_raw(*pp); if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (id < nh->id) pp = &next->rb_left; else if (id > nh->id) pp = &next->rb_right; else return nh; } return NULL; } EXPORT_SYMBOL_GPL(nexthop_find_by_id); /* used for auto id allocation; called with rtnl held */ static u32 nh_find_unused_id(struct net *net) { u32 id_start = net->nexthop.last_id_allocated; while (1) { net->nexthop.last_id_allocated++; if (net->nexthop.last_id_allocated == id_start) break; if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated)) return net->nexthop.last_id_allocated; } return 0; } static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) { struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; int i; if (nhg->mpath) group_type = NEXTHOP_GRP_TYPE_MPATH; if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type)) goto nla_put_failure; nla = nla_reserve(skb, NHA_GROUP, len); if (!nla) goto nla_put_failure; p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { p->id = nhg->nh_entries[i].nh->id; p->weight = nhg->nh_entries[i].weight - 1; p += 1; } return 0; nla_put_failure: return -EMSGSIZE; } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, int event, u32 portid, u32 seq, unsigned int nlflags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; struct nlmsghdr *nlh; struct nh_info *nhi; struct nhmsg *nhm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags); if (!nlh) return -EMSGSIZE; nhm = nlmsg_data(nlh); nhm->nh_family = AF_UNSPEC; nhm->nh_flags = nh->nh_flags; nhm->nh_protocol = nh->protocol; nhm->nh_scope = 0; nhm->resvd = 0; if (nla_put_u32(skb, NHA_ID, nh->id)) goto nla_put_failure; if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; if (nla_put_nh_group(skb, nhg)) goto nla_put_failure; goto out; } nhi = rtnl_dereference(nh->nh_info); nhm->nh_family = nhi->family; if (nhi->reject_nh) { if (nla_put_flag(skb, NHA_BLACKHOLE)) goto nla_put_failure; goto out; } else if (nhi->fdb_nh) { if (nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; } else { const struct net_device *dev; dev = nhi->fib_nhc.nhc_dev; if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex)) goto nla_put_failure; } nhm->nh_scope = nhi->fib_nhc.nhc_scope; switch (nhi->family) { case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; case AF_INET6: fib6_nh = &nhi->fib6_nh; if (fib6_nh->fib_nh_gw_family && nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6)) goto nla_put_failure; break; } if (nhi->fib_nhc.nhc_lwtstate && lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate, NHA_ENCAP, NHA_ENCAP_TYPE) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static size_t nh_nlmsg_size_grp(struct nexthop *nh) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh; return nla_total_size(sz) + nla_total_size(2); /* NHA_GROUP_TYPE */ } static size_t nh_nlmsg_size_single(struct nexthop *nh) { struct nh_info *nhi = rtnl_dereference(nh->nh_info); size_t sz; /* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE * are mutually exclusive */ sz = nla_total_size(4); /* NHA_OIF */ switch (nhi->family) { case AF_INET: if (nhi->fib_nh.fib_nh_gw_family) sz += nla_total_size(4); /* NHA_GATEWAY */ break; case AF_INET6: /* NHA_GATEWAY */ if (nhi->fib6_nh.fib_nh_gw_family) sz += nla_total_size(sizeof(const struct in6_addr)); break; } if (nhi->fib_nhc.nhc_lwtstate) { sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate); sz += nla_total_size(2); /* NHA_ENCAP_TYPE */ } return sz; } static size_t nh_nlmsg_size(struct nexthop *nh) { size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg)); sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) sz += nh_nlmsg_size_grp(nh); else sz += nh_nlmsg_size_single(nh); return sz; } static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) { unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any()); if (!skb) goto errout; err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP, info->nlh, gfp_any()); return; errout: if (err < 0) rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, bool *is_fdb, struct netlink_ext_ack *extack) { if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); /* nested multipath (group within a group) is not * supported */ if (nhg->mpath) { NL_SET_ERR_MSG(extack, "Multipath group can not be a nexthop within a group"); return false; } *is_fdb = nhg->fdb_nh; } else { struct nh_info *nhi = rtnl_dereference(nh->nh_info); if (nhi->reject_nh && npaths > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be used in a group with more than 1 path"); return false; } *is_fdb = nhi->fdb_nh; } return true; } static int nh_check_attr_fdb_group(struct nexthop *nh, u8 *nh_family, struct netlink_ext_ack *extack) { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (!nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "FDB nexthop group can only have fdb nexthops"); return -EINVAL; } if (*nh_family == AF_UNSPEC) { *nh_family = nhi->family; } else if (*nh_family != nhi->family) { NL_SET_ERR_MSG(extack, "FDB nexthop group cannot have mixed family nexthops"); return -EINVAL; } return 0; } static int nh_check_attr_group(struct net *net, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int i, j; u8 nhg_fdb = 0; if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; } /* convert len to number of nexthop ids */ len /= sizeof(*nhg); nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { if (nhg[i].resvd1 || nhg[i].resvd2) { NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0"); return -EINVAL; } if (nhg[i].weight > 254) { NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } for (j = i + 1; j < len; ++j) { if (nhg[i].id == nhg[j].id) { NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group"); return -EINVAL; } } } if (tb[NHA_FDB]) nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { struct nexthop *nh; bool is_fdb_nh; nh = nexthop_find_by_id(net, nhg[i].id); if (!nh) { NL_SET_ERR_MSG(extack, "Invalid nexthop id"); return -EINVAL; } if (!valid_group_nh(nh, len, &is_fdb_nh, extack)) return -EINVAL; if (nhg_fdb && nh_check_attr_fdb_group(nh, &nh_family, extack)) return -EINVAL; if (!nhg_fdb && is_fdb_nh) { NL_SET_ERR_MSG(extack, "Non FDB nexthop group cannot have fdb nexthops"); return -EINVAL; } } for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) { if (!tb[i]) continue; if (i == NHA_FDB) continue; NL_SET_ERR_MSG(extack, "No other attributes can be set in nexthop groups"); return -EINVAL; } return 0; } static bool ipv6_good_nh(const struct fib6_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); if (n) state = n->nud_state; rcu_read_unlock_bh(); return !!(state & NUD_VALID); } static bool ipv4_good_nh(const struct fib_nh *nh) { int state = NUD_REACHABLE; struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); if (n) state = n->nud_state; rcu_read_unlock_bh(); return !!(state & NUD_VALID); } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash) { struct nexthop *rc = NULL; struct nh_group *nhg; int i; if (!nh->is_group) return nh; nhg = rcu_dereference(nh->nh_grp); for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; if (hash > atomic_read(&nhge->upper_bound)) continue; nhi = rcu_dereference(nhge->nh->nh_info); if (nhi->fdb_nh) return nhge->nh; /* nexthops always check if it is good and does * not rely on a sysctl for this behavior */ switch (nhi->family) { case AF_INET: if (ipv4_good_nh(&nhi->fib_nh)) return nhge->nh; break; case AF_INET6: if (ipv6_good_nh(&nhi->fib6_nh)) return nhge->nh; break; } if (!rc) rc = nhge->nh; } return rc; } EXPORT_SYMBOL_GPL(nexthop_select_path); int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg) { struct nh_info *nhi; int err; if (nh->is_group) { struct nh_group *nhg; int i; nhg = rcu_dereference_rtnl(nh->nh_grp); for (i = 0; i < nhg->num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; nhi = rcu_dereference_rtnl(nhge->nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } } else { nhi = rcu_dereference_rtnl(nh->nh_info); err = cb(&nhi->fib6_nh, arg); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh); static int check_src_addr(const struct in6_addr *saddr, struct netlink_ext_ack *extack) { if (!ipv6_addr_any(saddr)) { NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects"); return -EINVAL; } return 0; } int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; bool is_fdb_nh; /* fib6_src is unique to a fib6_info and limits the ability to cache * routes in fib6_nh within a nexthop that is potentially shared * across multiple fib entries. If the config wants to use source * routing it can not use nexthop objects. mlxsw also does not allow * fib6_src on routes. */ if (cfg && check_src_addr(&cfg->fc_src, extack) < 0) return -EINVAL; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->has_v4) goto no_v4_nh; is_fdb_nh = nhg->fdb_nh; } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->family == AF_INET) goto no_v4_nh; is_fdb_nh = nhi->fdb_nh; } if (is_fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); return -EINVAL; } return 0; no_v4_nh: NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop"); return -EINVAL; } EXPORT_SYMBOL_GPL(fib6_check_nexthop); /* if existing nexthop has ipv6 routes linked to it, need * to verify this new spec works with ipv6 */ static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib6_info *f6i; if (list_empty(&old->f6i_list)) return 0; list_for_each_entry(f6i, &old->f6i_list, nh_list) { if (check_src_addr(&f6i->fib6_src.addr, extack) < 0) return -EINVAL; } return fib6_check_nexthop(new, NULL, extack); } static int nexthop_check_scope(struct nh_info *nhi, u8 scope, struct netlink_ext_ack *extack) { if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); return -EINVAL; } if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) { NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop"); return -EINVAL; } return 0; } /* Invoked by fib add code to verify nexthop by id is ok with * config for prefix; parts of fib_check_nh not done when nexthop * object is used. */ int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack) { struct nh_info *nhi; int err = 0; if (nh->is_group) { struct nh_group *nhg; nhg = rtnl_dereference(nh->nh_grp); if (nhg->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } if (scope == RT_SCOPE_HOST) { NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); err = -EINVAL; goto out; } /* all nexthops in a group have the same scope */ nhi = rtnl_dereference(nhg->nh_entries[0].nh->nh_info); err = nexthop_check_scope(nhi, scope, extack); } else { nhi = rtnl_dereference(nh->nh_info); if (nhi->fdb_nh) { NL_SET_ERR_MSG(extack, "Route cannot point to a fdb nexthop"); err = -EINVAL; goto out; } err = nexthop_check_scope(nhi, scope, extack); } out: return err; } static int fib_check_nh_list(struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct fib_info *fi; list_for_each_entry(fi, &old->fi_list, nh_list) { int err; err = fib_check_nexthop(new, fi->fib_scope, extack); if (err) return err; } return 0; } static void nh_group_rebalance(struct nh_group *nhg) { int total = 0; int w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) total += nhg->nh_entries[i].weight; for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; int upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; atomic_set(&nhge->upper_bound, upper_bound); } } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, struct nl_info *nlinfo) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; int i, j; WARN_ON(!nh); nhg = rtnl_dereference(nhp->nh_grp); newg = nhg->spare; /* last entry, keep it visible and remove the parent */ if (nhg->num_nh == 1) { remove_nexthop(net, nhp, nlinfo); return; } newg->has_v4 = false; newg->mpath = nhg->mpath; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; /* copy old entries to new except the one getting removed */ nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { struct nh_info *nhi; /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) newg->has_v4 = true; list_del(&nhges[i].nh_list); new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; list_add(&new_nhges[j].nh_list, &new_nhges[j].nh->grp_list); j++; } nh_group_rebalance(newg); rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); nexthop_put(nhge->nh); if (nlinfo) nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) remove_nh_grp_entry(net, nhge, nlinfo); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); int i, num_nh = nhg->num_nh; for (i = 0; i < num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; if (WARN_ON(!nhge->nh)) continue; list_del_init(&nhge->nh_list); } } /* not called for nexthop replace */ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) { struct fib6_info *f6i, *tmp; bool do_flush = false; struct fib_info *fi; list_for_each_entry(fi, &nh->fi_list, nh_list) { fi->fib_flags |= RTNH_F_DEAD; do_flush = true; } if (do_flush) fib_flush(net); /* ip6_del_rt removes the entry from this list hence the _safe */ list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) { /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); ipv6_stub->ip6_del_rt(net, f6i, !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); } } static void __remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { __remove_nexthop_fib(net, nh); if (nh->is_group) { remove_nexthop_group(nh, nlinfo); } else { struct nh_info *nhi; nhi = rtnl_dereference(nh->nh_info); if (nhi->fib_nhc.nhc_dev) hlist_del(&nhi->dev_hash); remove_nexthop_from_groups(net, nh, nlinfo); } } static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh); /* remove from the tree */ rb_erase(&nh->rb_node, &net->nexthop.rb_root); if (nlinfo) nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo); __remove_nexthop(net, nh, nlinfo); nh_base_seq_inc(net); nexthop_put(nh); } /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) { struct fib6_info *f6i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); } static int replace_nexthop_grp(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct nh_group *oldg, *newg; int i; if (!new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop."); return -EINVAL; } oldg = rtnl_dereference(old->nh_grp); newg = rtnl_dereference(new->nh_grp); /* update parents - used by nexthop code for cleanup */ for (i = 0; i < newg->num_nh; i++) newg->nh_entries[i].nh_parent = old; rcu_assign_pointer(old->nh_grp, newg); for (i = 0; i < oldg->num_nh; i++) oldg->nh_entries[i].nh_parent = new; rcu_assign_pointer(new->nh_grp, oldg); return 0; } static void nh_group_v4_update(struct nh_group *nhg) { struct nh_grp_entry *nhges; bool has_v4 = false; int i; nhges = nhg->nh_entries; for (i = 0; i < nhg->num_nh; i++) { struct nh_info *nhi; nhi = rtnl_dereference(nhges[i].nh->nh_info); if (nhi->family == AF_INET) has_v4 = true; } nhg->has_v4 = has_v4; } static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { struct nh_info *oldi, *newi; if (new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group."); return -EINVAL; } oldi = rtnl_dereference(old->nh_info); newi = rtnl_dereference(new->nh_info); newi->nh_parent = old; oldi->nh_parent = new; old->protocol = new->protocol; old->nh_flags = new->nh_flags; rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially * update IPv4 indication in all the groups using the nexthop. */ if (oldi->family == AF_INET && newi->family == AF_INET6) { struct nh_grp_entry *nhge; list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; struct nh_group *nhg; nhg = rtnl_dereference(nhp->nh_grp); nh_group_v4_update(nhg); } } return 0; } static void __nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct fib6_info *f6i; if (!list_empty(&nh->fi_list)) { struct fib_info *fi; /* expectation is a few fib_info per nexthop and then * a lot of routes per fib_info. So mark the fib_info * and then walk the fib tables once */ list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = true; fib_info_notify_update(net, info); list_for_each_entry(fi, &nh->fi_list, nh_list) fi->nh_updated = false; } list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_rt_update(net, f6i, info); } /* send RTM_NEWROUTE with REPLACE flag set for all FIB entries * linked to this nexthop and for all groups that the nexthop * is a member of */ static void nexthop_replace_notify(struct net *net, struct nexthop *nh, struct nl_info *info) { struct nh_grp_entry *nhge; __nexthop_replace_notify(net, nh, info); list_for_each_entry(nhge, &nh->grp_list, nh_list) __nexthop_replace_notify(net, nhge->nh_parent, info); } static int replace_nexthop(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { bool new_is_reject = false; struct nh_grp_entry *nhge; int err; /* check that existing FIB entries are ok with the * new nexthop definition */ err = fib_check_nh_list(old, new, extack); if (err) return err; err = fib6_check_nh_list(old, new, extack); if (err) return err; if (!new->is_group) { struct nh_info *nhi = rtnl_dereference(new->nh_info); new_is_reject = nhi->reject_nh; } list_for_each_entry(nhge, &old->grp_list, nh_list) { /* if new nexthop is a blackhole, any groups using this * nexthop cannot have more than 1 path */ if (new_is_reject && nexthop_num_path(nhge->nh_parent) > 1) { NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path"); return -EINVAL; } err = fib_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; err = fib6_check_nh_list(nhge->nh_parent, new, extack); if (err) return err; } if (old->is_group) err = replace_nexthop_grp(net, old, new, extack); else err = replace_nexthop_single(net, old, new, extack); if (!err) { nh_rt_cache_flush(net, old); __remove_nexthop(net, new, NULL); nexthop_put(new); } return err; } /* called with rtnl_lock held */ static int insert_nexthop(struct net *net, struct nexthop *new_nh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct rb_node **pp, *parent = NULL, *next; struct rb_root *root = &net->nexthop.rb_root; bool replace = !!(cfg->nlflags & NLM_F_REPLACE); bool create = !!(cfg->nlflags & NLM_F_CREATE); u32 new_id = new_nh->id; int replace_notify = 0; int rc = -EEXIST; pp = &root->rb_node; while (1) { struct nexthop *nh; next = *pp; if (!next) break; parent = next; nh = rb_entry(parent, struct nexthop, rb_node); if (new_id < nh->id) { pp = &next->rb_left; } else if (new_id > nh->id) { pp = &next->rb_right; } else if (replace) { rc = replace_nexthop(net, nh, new_nh, extack); if (!rc) { new_nh = nh; /* send notification with old nh */ replace_notify = 1; } goto out; } else { /* id already exists and not a replace */ goto out; } } if (replace && !create) { NL_SET_ERR_MSG(extack, "Replace specified without create and no entry exists"); rc = -ENOENT; goto out; } rb_link_node_rcu(&new_nh->rb_node, parent, pp); rb_insert_color(&new_nh->rb_node, root); rc = 0; out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); if (replace_notify && READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } return rc; } /* rtnl */ /* remove all nexthops tied to a device being deleted */ static void nexthop_flush_dev(struct net_device *dev, unsigned long event) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev != dev) continue; if (nhi->reject_nh && (event == NETDEV_DOWN || event == NETDEV_CHANGE)) continue; remove_nexthop(net, nhi->nh_parent, NULL); } } /* rtnl; called when net namespace is deleted */ static void flush_all_nexthops(struct net *net) { struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; struct nexthop *nh; while ((node = rb_first(root))) { nh = rb_entry(node, struct nexthop, rb_node); remove_nexthop(net, nh, NULL); cond_resched(); } } static struct nexthop *nexthop_create_group(struct net *net, struct nh_config *cfg) { struct nlattr *grps_attr = cfg->nh_grp; struct nexthop_grp *entry = nla_data(grps_attr); u16 num_nh = nla_len(grps_attr) / sizeof(*entry); struct nh_group *nhg; struct nexthop *nh; int i; if (WARN_ON(!num_nh)) return ERR_PTR(-EINVAL); nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nh->is_group = 1; nhg = nexthop_grp_alloc(num_nh); if (!nhg) { kfree(nh); return ERR_PTR(-ENOMEM); } /* spare group used for removals */ nhg->spare = nexthop_grp_alloc(num_nh); if (!nhg->spare) { kfree(nhg); kfree(nh); return ERR_PTR(-ENOMEM); } nhg->spare->spare = nhg; for (i = 0; i < nhg->num_nh; ++i) { struct nexthop *nhe; struct nh_info *nhi; nhe = nexthop_find_by_id(net, entry[i].id); if (!nexthop_get(nhe)) goto out_no_nh; nhi = rtnl_dereference(nhe->nh_info); if (nhi->family == AF_INET) nhg->has_v4 = true; nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = entry[i].weight + 1; list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) { nhg->mpath = 1; nh_group_rebalance(nhg); } if (cfg->nh_fdb) nhg->fdb_nh = 1; rcu_assign_pointer(nh->nh_grp, nhg); return nh; out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); nexthop_put(nhg->nh_entries[i].nh); } kfree(nhg->spare); kfree(nhg); kfree(nh); return ERR_PTR(-ENOENT); } static int nh_create_ipv4(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib_nh *fib_nh = &nhi->fib_nh; struct fib_config fib_cfg = { .fc_oif = cfg->nh_ifindex, .fc_gw4 = cfg->gw.ipv4, .fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, }; u32 tb_id = (cfg->dev ? l3mdev_fib_table(cfg->dev) : RT_TABLE_MAIN); int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); if (err) { fib_nh_release(net, fib_nh); goto out; } if (nhi->fdb_nh) goto out; /* sets nh_dev if successful */ err = fib_check_nh(net, fib_nh, tb_id, 0, extack); if (!err) { nh->nh_flags = fib_nh->fib_nh_flags; fib_info_update_nhc_saddr(net, &fib_nh->nh_common, fib_nh->fib_nh_scope); } else { fib_nh_release(net, fib_nh); } out: return err; } static int nh_create_ipv6(struct net *net, struct nexthop *nh, struct nh_info *nhi, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct fib6_nh *fib6_nh = &nhi->fib6_nh; struct fib6_config fib6_cfg = { .fc_table = l3mdev_fib_table(cfg->dev), .fc_ifindex = cfg->nh_ifindex, .fc_gateway = cfg->gw.ipv6, .fc_flags = cfg->nh_flags, .fc_nlinfo = cfg->nlinfo, .fc_encap = cfg->nh_encap, .fc_encap_type = cfg->nh_encap_type, .fc_is_fdb = cfg->nh_fdb, }; int err; if (!ipv6_addr_any(&cfg->gw.ipv6)) fib6_cfg.fc_flags |= RTF_GATEWAY; /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); if (err) { /* IPv6 is not enabled, don't call fib6_nh_release */ if (err == -EAFNOSUPPORT) goto out; ipv6_stub->fib6_nh_release(fib6_nh); } else { nh->nh_flags = fib6_nh->fib_nh_flags; } out: return err; } static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nh_info *nhi; struct nexthop *nh; int err = 0; nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); nhi = kzalloc(sizeof(*nhi), GFP_KERNEL); if (!nhi) { kfree(nh); return ERR_PTR(-ENOMEM); } nh->nh_flags = cfg->nh_flags; nh->net = net; nhi->nh_parent = nh; nhi->family = cfg->nh_family; nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK; if (cfg->nh_fdb) nhi->fdb_nh = 1; if (cfg->nh_blackhole) { nhi->reject_nh = 1; cfg->nh_ifindex = net->loopback_dev->ifindex; } switch (cfg->nh_family) { case AF_INET: err = nh_create_ipv4(net, nh, nhi, cfg, extack); break; case AF_INET6: err = nh_create_ipv6(net, nh, nhi, cfg, extack); break; } if (err) { kfree(nhi); kfree(nh); return ERR_PTR(err); } /* add the entry to the device based hash */ if (!nhi->fdb_nh) nexthop_devhash_add(net, nhi); rcu_assign_pointer(nh->nh_info, nhi); return nh; } /* called with rtnl lock held */ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nexthop *nh; int err; if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) { NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); return ERR_PTR(-EINVAL); } if (!cfg->nh_id) { cfg->nh_id = nh_find_unused_id(net); if (!cfg->nh_id) { NL_SET_ERR_MSG(extack, "No unused id"); return ERR_PTR(-EINVAL); } } if (cfg->nh_grp) nh = nexthop_create_group(net, cfg); else nh = nexthop_create(net, cfg, extack); if (IS_ERR(nh)) return nh; refcount_set(&nh->refcnt, 1); nh->id = cfg->nh_id; nh->protocol = cfg->nh_protocol; nh->net = net; err = insert_nexthop(net, nh, cfg, extack); if (err) { __remove_nexthop(net, nh, NULL); nexthop_put(nh); nh = ERR_PTR(err); } return nh; } static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); struct nlattr *tb[NHA_MAX + 1]; int err; err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, extack); if (err < 0) return err; err = -EINVAL; if (nhm->resvd || nhm->nh_scope) { NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); goto out; } if (nhm->nh_flags & ~NEXTHOP_VALID_USER_FLAGS) { NL_SET_ERR_MSG(extack, "Invalid nexthop flags in ancillary header"); goto out; } switch (nhm->nh_family) { case AF_INET: case AF_INET6: break; case AF_UNSPEC: if (tb[NHA_GROUP]) break; fallthrough; default: NL_SET_ERR_MSG(extack, "Invalid address family"); goto out; } if (tb[NHA_GROUPS] || tb[NHA_MASTER]) { NL_SET_ERR_MSG(extack, "Invalid attributes in request"); goto out; } memset(cfg, 0, sizeof(*cfg)); cfg->nlflags = nlh->nlmsg_flags; cfg->nlinfo.portid = NETLINK_CB(skb).portid; cfg->nlinfo.nlh = nlh; cfg->nlinfo.nl_net = net; cfg->nh_family = nhm->nh_family; cfg->nh_protocol = nhm->nh_protocol; cfg->nh_flags = nhm->nh_flags; if (tb[NHA_ID]) cfg->nh_id = nla_get_u32(tb[NHA_ID]); if (tb[NHA_FDB]) { if (tb[NHA_OIF] || tb[NHA_BLACKHOLE] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "Fdb attribute can not be used with encap, oif or blackhole"); goto out; } if (nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Unsupported nexthop flags in ancillary header"); goto out; } cfg->nh_fdb = nla_get_flag(tb[NHA_FDB]); } if (tb[NHA_GROUP]) { if (nhm->nh_family != AF_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid family for group"); goto out; } cfg->nh_grp = tb[NHA_GROUP]; cfg->nh_grp_type = NEXTHOP_GRP_TYPE_MPATH; if (tb[NHA_GROUP_TYPE]) cfg->nh_grp_type = nla_get_u16(tb[NHA_GROUP_TYPE]); if (cfg->nh_grp_type > NEXTHOP_GRP_TYPE_MAX) { NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } err = nh_check_attr_group(net, tb, extack); /* no other attributes should be set */ goto out; } if (tb[NHA_BLACKHOLE]) { if (tb[NHA_GATEWAY] || tb[NHA_OIF] || tb[NHA_ENCAP] || tb[NHA_ENCAP_TYPE] || tb[NHA_FDB]) { NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway, oif, encap or fdb"); goto out; } cfg->nh_blackhole = 1; err = 0; goto out; } if (!cfg->nh_fdb && !tb[NHA_OIF]) { NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole and non-fdb nexthops"); goto out; } if (!cfg->nh_fdb && tb[NHA_OIF]) { cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); if (cfg->nh_ifindex) cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); if (!cfg->dev) { NL_SET_ERR_MSG(extack, "Invalid device index"); goto out; } else if (!(cfg->dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } else if (!netif_carrier_ok(cfg->dev)) { NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); err = -ENETDOWN; goto out; } } err = -EINVAL; if (tb[NHA_GATEWAY]) { struct nlattr *gwa = tb[NHA_GATEWAY]; switch (cfg->nh_family) { case AF_INET: if (nla_len(gwa) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv4 = nla_get_be32(gwa); break; case AF_INET6: if (nla_len(gwa) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid gateway"); goto out; } cfg->gw.ipv6 = nla_get_in6_addr(gwa); break; default: NL_SET_ERR_MSG(extack, "Unknown address family for gateway"); goto out; } } else { /* device only nexthop (no gateway) */ if (cfg->nh_flags & RTNH_F_ONLINK) { NL_SET_ERR_MSG(extack, "ONLINK flag can not be set for nexthop without a gateway"); goto out; } } if (tb[NHA_ENCAP]) { cfg->nh_encap = tb[NHA_ENCAP]; if (!tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation type is missing"); goto out; } cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack); if (err < 0) goto out; } else if (tb[NHA_ENCAP_TYPE]) { NL_SET_ERR_MSG(extack, "LWT encapsulation attribute is missing"); goto out; } err = 0; out: return err; } /* rtnl */ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nh_config cfg; struct nexthop *nh; int err; err = rtm_to_nh_config(net, skb, nlh, &cfg, extack); if (!err) { nh = nexthop_add(net, &cfg, extack); if (IS_ERR(nh)) err = PTR_ERR(nh); } return err; } static int nh_valid_get_del_req(struct nlmsghdr *nlh, u32 *id, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); struct nlattr *tb[NHA_MAX + 1]; int err, i; err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, extack); if (err < 0) return err; err = -EINVAL; for (i = 0; i < __NHA_MAX; ++i) { if (!tb[i]) continue; switch (i) { case NHA_ID: break; default: NL_SET_ERR_MSG_ATTR(extack, tb[i], "Unexpected attribute in request"); goto out; } } if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header"); goto out; } if (!tb[NHA_ID]) { NL_SET_ERR_MSG(extack, "Nexthop id is missing"); goto out; } *id = nla_get_u32(tb[NHA_ID]); if (!(*id)) NL_SET_ERR_MSG(extack, "Invalid nexthop id"); else err = 0; out: return err; } /* rtnl */ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nl_info nlinfo = { .nlh = nlh, .nl_net = net, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; int err; u32 id; err = nh_valid_get_del_req(nlh, &id, extack); if (err) return err; nh = nexthop_find_by_id(net, id); if (!nh) return -ENOENT; remove_nexthop(net, nh, &nlinfo); return 0; } /* rtnl */ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct sk_buff *skb = NULL; struct nexthop *nh; int err; u32 id; err = nh_valid_get_del_req(nlh, &id, extack); if (err) return err; err = -ENOBUFS; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) goto out; err = -ENOENT; nh = nexthop_find_by_id(net, id); if (!nh) goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); out: return err; errout_free: kfree_skb(skb); goto out; } static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx, bool group_filter, u8 family) { const struct net_device *dev; const struct nh_info *nhi; if (group_filter && !nh->is_group) return true; if (!dev_idx && !master_idx && !family) return false; if (nh->is_group) return true; nhi = rtnl_dereference(nh->nh_info); if (family && nhi->family != family) return true; dev = nhi->fib_nhc.nhc_dev; if (dev_idx && (!dev || dev->ifindex != dev_idx)) return true; if (master_idx) { struct net_device *master; if (!dev) return true; master = netdev_master_upper_dev_get((struct net_device *)dev); if (!master || master->ifindex != master_idx) return true; } return false; } static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx, int *master_idx, bool *group_filter, bool *fdb_filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NHA_MAX + 1]; struct nhmsg *nhm; int err, i; u32 idx; err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy, NULL); if (err < 0) return err; for (i = 0; i <= NHA_MAX; ++i) { if (!tb[i]) continue; switch (i) { case NHA_OIF: idx = nla_get_u32(tb[i]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid device index"); return -EINVAL; } *dev_idx = idx; break; case NHA_MASTER: idx = nla_get_u32(tb[i]); if (idx > INT_MAX) { NL_SET_ERR_MSG(extack, "Invalid master device index"); return -EINVAL; } *master_idx = idx; break; case NHA_GROUPS: *group_filter = true; break; case NHA_FDB: *fdb_filter = true; break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } nhm = nlmsg_data(nlh); if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for nexthop dump request"); return -EINVAL; } return 0; } /* rtnl */ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) { bool group_filter = false, fdb_filter = false; struct nhmsg *nhm = nlmsg_data(cb->nlh); int dev_filter_idx = 0, master_idx = 0; struct net *net = sock_net(skb->sk); struct rb_root *root = &net->nexthop.rb_root; struct rb_node *node; int idx = 0, s_idx; int err; err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx, &group_filter, &fdb_filter, cb); if (err < 0) return err; s_idx = cb->args[0]; for (node = rb_first(root); node; node = rb_next(node)) { struct nexthop *nh; if (idx < s_idx) goto cont; nh = rb_entry(node, struct nexthop, rb_node); if (nh_dump_filtered(nh, dev_filter_idx, master_idx, group_filter, nhm->nh_family)) goto cont; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); if (err < 0) { if (likely(skb->len)) goto out; goto out_err; } cont: idx++; } out: err = skb->len; out_err: cb->args[0] = idx; cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; } static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu) { unsigned int hash = nh_dev_hashfn(dev->ifindex); struct net *net = dev_net(dev); struct hlist_head *head = &net->nexthop.devhash[hash]; struct hlist_node *n; struct nh_info *nhi; hlist_for_each_entry_safe(nhi, n, head, dev_hash) { if (nhi->fib_nhc.nhc_dev == dev) { if (nhi->family == AF_INET) fib_nhc_update_mtu(&nhi->fib_nhc, dev->mtu, orig_mtu); } } } /* rtnl */ static int nh_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_info_ext *info_ext; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: info_ext = ptr; nexthop_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(dev_net(dev)); break; } return NOTIFY_DONE; } static struct notifier_block nh_netdev_notifier = { .notifier_call = nh_netdev_event, }; int register_nexthop_notifier(struct net *net, struct notifier_block *nb) { return blocking_notifier_chain_register(&net->nexthop.notifier_chain, nb); } EXPORT_SYMBOL(register_nexthop_notifier); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) { return blocking_notifier_chain_unregister(&net->nexthop.notifier_chain, nb); } EXPORT_SYMBOL(unregister_nexthop_notifier); static void __net_exit nexthop_net_exit(struct net *net) { rtnl_lock(); flush_all_nexthops(net); rtnl_unlock(); kfree(net->nexthop.devhash); } static int __net_init nexthop_net_init(struct net *net) { size_t sz = sizeof(struct hlist_head) * NH_DEV_HASHSIZE; net->nexthop.rb_root = RB_ROOT; net->nexthop.devhash = kzalloc(sz, GFP_KERNEL); if (!net->nexthop.devhash) return -ENOMEM; BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain); return 0; } static struct pernet_operations nexthop_net_ops = { .init = nexthop_net_init, .exit = nexthop_net_exit, }; static int __init nexthop_init(void) { register_pernet_subsys(&nexthop_net_ops); register_netdevice_notifier(&nh_netdev_notifier); rtnl_register(PF_UNSPEC, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELNEXTHOP, rtm_del_nexthop, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETNEXTHOP, rtm_get_nexthop, rtm_dump_nexthop, 0); rtnl_register(PF_INET, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_INET, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); rtnl_register(PF_INET6, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0); rtnl_register(PF_INET6, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0); return 0; } subsys_initcall(nexthop_init); |
| 20 20 854 891 45 44 11 11 5 3 6 3 11 5 5 5 1 5 11 11 11 98 86 11 28 24 4 4 14 3 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 | /* * net/tipc/msg.c: TIPC message header routines * * Copyright (c) 2000-2006, 2014-2015, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * 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. */ #include <net/sock.h> #include "core.h" #include "msg.h" #include "addr.h" #include "name_table.h" #include "crypto.h" #define MAX_FORWARD_SIZE 1024 #ifdef CONFIG_TIPC_CRYPTO #define BUF_HEADROOM ALIGN(((LL_MAX_HEADER + 48) + EHDR_MAX_SIZE), 16) #define BUF_OVERHEAD (BUF_HEADROOM + TIPC_AES_GCM_TAG_SIZE) #else #define BUF_HEADROOM (LL_MAX_HEADER + 48) #define BUF_OVERHEAD BUF_HEADROOM #endif const int one_page_mtu = PAGE_SIZE - SKB_DATA_ALIGN(BUF_OVERHEAD) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); static unsigned int align(unsigned int i) { return (i + 3) & ~3u; } /** * tipc_buf_acquire - creates a TIPC message buffer * @size: message size (including TIPC header) * * Returns a new buffer with data pointers set to the specified size. * * NOTE: Headroom is reserved to allow prepending of a data link header. * There may also be unrequested tailroom present at the buffer's end. */ struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp) { struct sk_buff *skb; skb = alloc_skb_fclone(BUF_OVERHEAD + size, gfp); if (skb) { skb_reserve(skb, BUF_HEADROOM); skb_put(skb, size); skb->next = NULL; } return skb; } void tipc_msg_init(u32 own_node, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 dnode) { memset(m, 0, hsize); msg_set_version(m); msg_set_user(m, user); msg_set_hdr_sz(m, hsize); msg_set_size(m, hsize); msg_set_prevnode(m, own_node); msg_set_type(m, type); if (hsize > SHORT_H_SIZE) { msg_set_orignode(m, own_node); msg_set_destnode(m, dnode); } } struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode) { struct tipc_msg *msg; struct sk_buff *buf; buf = tipc_buf_acquire(hdr_sz + data_sz, GFP_ATOMIC); if (unlikely(!buf)) return NULL; msg = buf_msg(buf); tipc_msg_init(onode, msg, user, type, hdr_sz, dnode); msg_set_size(msg, hdr_sz + data_sz); msg_set_origport(msg, oport); msg_set_destport(msg, dport); msg_set_errcode(msg, errcode); if (hdr_sz > SHORT_H_SIZE) { msg_set_orignode(msg, onode); msg_set_destnode(msg, dnode); } return buf; } /* tipc_buf_append(): Append a buffer to the fragment list of another buffer * @*headbuf: in: NULL for first frag, otherwise value returned from prev call * out: set when successful non-complete reassembly, otherwise NULL * @*buf: in: the buffer to append. Always defined * out: head buf after successful complete reassembly, otherwise NULL * Returns 1 when reassembly complete, otherwise 0 */ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) { struct sk_buff *head = *headbuf; struct sk_buff *frag = *buf; struct sk_buff *tail = NULL; struct tipc_msg *msg; u32 fragid; int delta; bool headstolen; if (!frag) goto err; msg = buf_msg(frag); fragid = msg_type(msg); frag->next = NULL; skb_pull(frag, msg_hdr_sz(msg)); if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; *buf = NULL; if (skb_has_frag_list(frag) && __skb_linearize(frag)) goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; TIPC_SKB_CB(head)->tail = NULL; return 0; } if (!head) goto err; if (skb_try_coalesce(head, frag, &headstolen, &delta)) { kfree_skb_partial(frag, headstolen); } else { tail = TIPC_SKB_CB(head)->tail; if (!skb_has_frag_list(head)) skb_shinfo(head)->frag_list = frag; else tail->next = frag; head->truesize += frag->truesize; head->data_len += frag->len; head->len += frag->len; TIPC_SKB_CB(head)->tail = frag; } if (fragid == LAST_FRAGMENT) { TIPC_SKB_CB(head)->validated = 0; if (unlikely(!tipc_msg_validate(&head))) goto err; *buf = head; TIPC_SKB_CB(head)->tail = NULL; *headbuf = NULL; return 1; } *buf = NULL; return 0; err: kfree_skb(*buf); kfree_skb(*headbuf); *buf = *headbuf = NULL; return 0; } /** * tipc_msg_append(): Append data to tail of an existing buffer queue * @_hdr: header to be used * @m: the data to be appended * @mss: max allowable size of buffer * @dlen: size of data to be appended * @txq: queue to appand to * Returns the number og 1k blocks appended or errno value */ int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen, int mss, struct sk_buff_head *txq) { struct sk_buff *skb; int accounted, total, curr; int mlen, cpy, rem = dlen; struct tipc_msg *hdr; skb = skb_peek_tail(txq); accounted = skb ? msg_blocks(buf_msg(skb)) : 0; total = accounted; do { if (!skb || skb->len >= mss) { skb = tipc_buf_acquire(mss, GFP_KERNEL); if (unlikely(!skb)) return -ENOMEM; skb_orphan(skb); skb_trim(skb, MIN_H_SIZE); hdr = buf_msg(skb); skb_copy_to_linear_data(skb, _hdr, MIN_H_SIZE); msg_set_hdr_sz(hdr, MIN_H_SIZE); msg_set_size(hdr, MIN_H_SIZE); __skb_queue_tail(txq, skb); total += 1; } hdr = buf_msg(skb); curr = msg_blocks(hdr); mlen = msg_size(hdr); cpy = min_t(size_t, rem, mss - mlen); if (cpy != copy_from_iter(skb->data + mlen, cpy, &m->msg_iter)) return -EFAULT; msg_set_size(hdr, mlen + cpy); skb_put(skb, cpy); rem -= cpy; total += msg_blocks(hdr) - curr; } while (rem > 0); return total - accounted; } /* tipc_msg_validate - validate basic format of received message * * This routine ensures a TIPC message has an acceptable header, and at least * as much data as the header indicates it should. The routine also ensures * that the entire message header is stored in the main fragment of the message * buffer, to simplify future access to message header fields. * * Note: Having extra info present in the message header or data areas is OK. * TIPC will ignore the excess, under the assumption that it is optional info * introduced by a later release of the protocol. */ bool tipc_msg_validate(struct sk_buff **_skb) { struct sk_buff *skb = *_skb; struct tipc_msg *hdr; int msz, hsz; /* Ensure that flow control ratio condition is satisfied */ if (unlikely(skb->truesize / buf_roundup_len(skb) >= 4)) { skb = skb_copy_expand(skb, BUF_HEADROOM, 0, GFP_ATOMIC); if (!skb) return false; kfree_skb(*_skb); *_skb = skb; } if (unlikely(TIPC_SKB_CB(skb)->validated)) return true; if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE))) return false; hsz = msg_hdr_sz(buf_msg(skb)); if (unlikely(hsz < MIN_H_SIZE) || (hsz > MAX_H_SIZE)) return false; if (unlikely(!pskb_may_pull(skb, hsz))) return false; hdr = buf_msg(skb); if (unlikely(msg_version(hdr) != TIPC_VERSION)) return false; msz = msg_size(hdr); if (unlikely(msz < hsz)) return false; if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE)) return false; if (unlikely(skb->len < msz)) return false; TIPC_SKB_CB(skb)->validated = 1; return true; } /** * tipc_msg_fragment - build a fragment skb list for TIPC message * * @skb: TIPC message skb * @hdr: internal msg header to be put on the top of the fragments * @pktmax: max size of a fragment incl. the header * @frags: returned fragment skb list * * Returns 0 if the fragmentation is successful, otherwise: -EINVAL * or -ENOMEM */ int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, int pktmax, struct sk_buff_head *frags) { int pktno, nof_fragms, dsz, dmax, eat; struct tipc_msg *_hdr; struct sk_buff *_skb; u8 *data; /* Non-linear buffer? */ if (skb_linearize(skb)) return -ENOMEM; data = (u8 *)skb->data; dsz = msg_size(buf_msg(skb)); dmax = pktmax - INT_H_SIZE; if (dsz <= dmax || !dmax) return -EINVAL; nof_fragms = dsz / dmax + 1; for (pktno = 1; pktno <= nof_fragms; pktno++) { if (pktno < nof_fragms) eat = dmax; else eat = dsz % dmax; /* Allocate a new fragment */ _skb = tipc_buf_acquire(INT_H_SIZE + eat, GFP_ATOMIC); if (!_skb) goto error; skb_orphan(_skb); __skb_queue_tail(frags, _skb); /* Copy header & data to the fragment */ skb_copy_to_linear_data(_skb, hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(_skb, INT_H_SIZE, data, eat); data += eat; /* Update the fragment's header */ _hdr = buf_msg(_skb); msg_set_fragm_no(_hdr, pktno); msg_set_nof_fragms(_hdr, nof_fragms); msg_set_size(_hdr, INT_H_SIZE + eat); } return 0; error: __skb_queue_purge(frags); __skb_queue_head_init(frags); return -ENOMEM; } /** * tipc_msg_build - create buffer chain containing specified header and data * @mhdr: Message header, to be prepended to data * @m: User message * @dsz: Total length of user data * @pktmax: Max packet size that can be used * @list: Buffer or chain of buffers to be returned to caller * * Note that the recursive call we are making here is safe, since it can * logically go only one further level down. * * Returns message data size or errno: -ENOMEM, -EFAULT */ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int pktmax, struct sk_buff_head *list) { int mhsz = msg_hdr_sz(mhdr); struct tipc_msg pkthdr; int msz = mhsz + dsz; int pktrem = pktmax; struct sk_buff *skb; int drem = dsz; int pktno = 1; char *pktpos; int pktsz; int rc; msg_set_size(mhdr, msz); /* No fragmentation needed? */ if (likely(msz <= pktmax)) { skb = tipc_buf_acquire(msz, GFP_KERNEL); /* Fall back to smaller MTU if node local message */ if (unlikely(!skb)) { if (pktmax != MAX_MSG_SIZE) return -ENOMEM; rc = tipc_msg_build(mhdr, m, offset, dsz, one_page_mtu, list); if (rc != dsz) return rc; if (tipc_msg_assemble(list)) return dsz; return -ENOMEM; } skb_orphan(skb); __skb_queue_tail(list, skb); skb_copy_to_linear_data(skb, mhdr, mhsz); pktpos = skb->data + mhsz; if (copy_from_iter_full(pktpos, dsz, &m->msg_iter)) return dsz; rc = -EFAULT; goto error; } /* Prepare reusable fragment header */ tipc_msg_init(msg_prevnode(mhdr), &pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr)); msg_set_size(&pkthdr, pktmax); msg_set_fragm_no(&pkthdr, pktno); msg_set_importance(&pkthdr, msg_importance(mhdr)); /* Prepare first fragment */ skb = tipc_buf_acquire(pktmax, GFP_KERNEL); if (!skb) return -ENOMEM; skb_orphan(skb); __skb_queue_tail(list, skb); pktpos = skb->data; skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE); pktpos += INT_H_SIZE; pktrem -= INT_H_SIZE; skb_copy_to_linear_data_offset(skb, INT_H_SIZE, mhdr, mhsz); pktpos += mhsz; pktrem -= mhsz; do { if (drem < pktrem) pktrem = drem; if (!copy_from_iter_full(pktpos, pktrem, &m->msg_iter)) { rc = -EFAULT; goto error; } drem -= pktrem; if (!drem) break; /* Prepare new fragment: */ if (drem < (pktmax - INT_H_SIZE)) pktsz = drem + INT_H_SIZE; else pktsz = pktmax; skb = tipc_buf_acquire(pktsz, GFP_KERNEL); if (!skb) { rc = -ENOMEM; goto error; } skb_orphan(skb); __skb_queue_tail(list, skb); msg_set_type(&pkthdr, FRAGMENT); msg_set_size(&pkthdr, pktsz); msg_set_fragm_no(&pkthdr, ++pktno); skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE); pktpos = skb->data + INT_H_SIZE; pktrem = pktsz - INT_H_SIZE; } while (1); msg_set_type(buf_msg(skb), LAST_FRAGMENT); return dsz; error: __skb_queue_purge(list); __skb_queue_head_init(list); return rc; } /** * tipc_msg_bundle - Append contents of a buffer to tail of an existing one * @bskb: the bundle buffer to append to * @msg: message to be appended * @max: max allowable size for the bundle buffer * * Returns "true" if bundling has been performed, otherwise "false" */ static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg, u32 max) { struct tipc_msg *bmsg = buf_msg(bskb); u32 msz, bsz, offset, pad; msz = msg_size(msg); bsz = msg_size(bmsg); offset = align(bsz); pad = offset - bsz; if (unlikely(skb_tailroom(bskb) < (pad + msz))) return false; if (unlikely(max < (offset + msz))) return false; skb_put(bskb, pad + msz); skb_copy_to_linear_data_offset(bskb, offset, msg, msz); msg_set_size(bmsg, offset + msz); msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1); return true; } /** * tipc_msg_try_bundle - Try to bundle a new message to the last one * @tskb: the last/target message to which the new one will be appended * @skb: the new message skb pointer * @mss: max message size (header inclusive) * @dnode: destination node for the message * @new_bundle: if this call made a new bundle or not * * Return: "true" if the new message skb is potential for bundling this time or * later, in the case a bundling has been done this time, the skb is consumed * (the skb pointer = NULL). * Otherwise, "false" if the skb cannot be bundled at all. */ bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss, u32 dnode, bool *new_bundle) { struct tipc_msg *msg, *inner, *outer; u32 tsz; /* First, check if the new buffer is suitable for bundling */ msg = buf_msg(*skb); if (msg_user(msg) == MSG_FRAGMENTER) return false; if (msg_user(msg) == TUNNEL_PROTOCOL) return false; if (msg_user(msg) == BCAST_PROTOCOL) return false; if (mss <= INT_H_SIZE + msg_size(msg)) return false; /* Ok, but the last/target buffer can be empty? */ if (unlikely(!tskb)) return true; /* Is it a bundle already? Try to bundle the new message to it */ if (msg_user(buf_msg(tskb)) == MSG_BUNDLER) { *new_bundle = false; goto bundle; } /* Make a new bundle of the two messages if possible */ tsz = msg_size(buf_msg(tskb)); if (unlikely(mss < align(INT_H_SIZE + tsz) + msg_size(msg))) return true; if (unlikely(pskb_expand_head(tskb, INT_H_SIZE, mss - tsz - INT_H_SIZE, GFP_ATOMIC))) return true; inner = buf_msg(tskb); skb_push(tskb, INT_H_SIZE); outer = buf_msg(tskb); tipc_msg_init(msg_prevnode(inner), outer, MSG_BUNDLER, 0, INT_H_SIZE, dnode); msg_set_importance(outer, msg_importance(inner)); msg_set_size(outer, INT_H_SIZE + tsz); msg_set_msgcnt(outer, 1); *new_bundle = true; bundle: if (likely(tipc_msg_bundle(tskb, msg, mss))) { consume_skb(*skb); *skb = NULL; } return true; } /** * tipc_msg_extract(): extract bundled inner packet from buffer * @skb: buffer to be extracted from. * @iskb: extracted inner buffer, to be returned * @pos: position in outer message of msg to be extracted. * Returns position of next msg * Consumes outer buffer when last packet extracted * Returns true when there is an extracted buffer, otherwise false */ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) { struct tipc_msg *hdr, *ihdr; int imsz; *iskb = NULL; if (unlikely(skb_linearize(skb))) goto none; hdr = buf_msg(skb); if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE))) goto none; ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos); imsz = msg_size(ihdr); if ((*pos + imsz) > msg_data_sz(hdr)) goto none; *iskb = tipc_buf_acquire(imsz, GFP_ATOMIC); if (!*iskb) goto none; skb_copy_to_linear_data(*iskb, ihdr, imsz); if (unlikely(!tipc_msg_validate(iskb))) goto none; *pos += align(imsz); return true; none: kfree_skb(skb); kfree_skb(*iskb); *iskb = NULL; return false; } /** * tipc_msg_reverse(): swap source and destination addresses and add error code * @own_node: originating node id for reversed message * @skb: buffer containing message to be reversed; will be consumed * @err: error code to be set in message, if any * Replaces consumed buffer with new one when successful * Returns true if success, otherwise false */ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) { struct sk_buff *_skb = *skb; struct tipc_msg *_hdr, *hdr; int hlen, dlen; if (skb_linearize(_skb)) goto exit; _hdr = buf_msg(_skb); dlen = min_t(uint, msg_data_sz(_hdr), MAX_FORWARD_SIZE); hlen = msg_hdr_sz(_hdr); if (msg_dest_droppable(_hdr)) goto exit; if (msg_errcode(_hdr)) goto exit; /* Never return SHORT header */ if (hlen == SHORT_H_SIZE) hlen = BASIC_H_SIZE; /* Don't return data along with SYN+, - sender has a clone */ if (msg_is_syn(_hdr) && err == TIPC_ERR_OVERLOAD) dlen = 0; /* Allocate new buffer to return */ *skb = tipc_buf_acquire(hlen + dlen, GFP_ATOMIC); if (!*skb) goto exit; memcpy((*skb)->data, _skb->data, msg_hdr_sz(_hdr)); memcpy((*skb)->data + hlen, msg_data(_hdr), dlen); /* Build reverse header in new buffer */ hdr = buf_msg(*skb); msg_set_hdr_sz(hdr, hlen); msg_set_errcode(hdr, err); msg_set_non_seq(hdr, 0); msg_set_origport(hdr, msg_destport(_hdr)); msg_set_destport(hdr, msg_origport(_hdr)); msg_set_destnode(hdr, msg_prevnode(_hdr)); msg_set_prevnode(hdr, own_node); msg_set_orignode(hdr, own_node); msg_set_size(hdr, hlen + dlen); skb_orphan(_skb); kfree_skb(_skb); return true; exit: kfree_skb(_skb); *skb = NULL; return false; } bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy) { struct sk_buff *skb, *_skb; skb_queue_walk(msg, skb) { _skb = skb_clone(skb, GFP_ATOMIC); if (!_skb) { __skb_queue_purge(cpy); pr_err_ratelimited("Failed to clone buffer chain\n"); return false; } __skb_queue_tail(cpy, _skb); } return true; } /** * tipc_msg_lookup_dest(): try to find new destination for named message * @skb: the buffer containing the message. * @err: error code to be used by caller if lookup fails * Does not consume buffer * Returns true if a destination is found, false otherwise */ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err) { struct tipc_msg *msg = buf_msg(skb); u32 dport, dnode; u32 onode = tipc_own_addr(net); if (!msg_isdata(msg)) return false; if (!msg_named(msg)) return false; if (msg_errcode(msg)) return false; *err = TIPC_ERR_NO_NAME; if (skb_linearize(skb)) return false; msg = buf_msg(skb); if (msg_reroute_cnt(msg)) return false; dnode = tipc_scope2node(net, msg_lookup_scope(msg)); dport = tipc_nametbl_translate(net, msg_nametype(msg), msg_nameinst(msg), &dnode); if (!dport) return false; msg_incr_reroute_cnt(msg); if (dnode != onode) msg_set_prevnode(msg, onode); msg_set_destnode(msg, dnode); msg_set_destport(msg, dport); *err = TIPC_OK; return true; } /* tipc_msg_assemble() - assemble chain of fragments into one message */ bool tipc_msg_assemble(struct sk_buff_head *list) { struct sk_buff *skb, *tmp = NULL; if (skb_queue_len(list) == 1) return true; while ((skb = __skb_dequeue(list))) { skb->next = NULL; if (tipc_buf_append(&tmp, &skb)) { __skb_queue_tail(list, skb); return true; } if (!tmp) break; } __skb_queue_purge(list); __skb_queue_head_init(list); pr_warn("Failed do assemble buffer\n"); return false; } /* tipc_msg_reassemble() - clone a buffer chain of fragments and * reassemble the clones into one message */ bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq) { struct sk_buff *skb, *_skb; struct sk_buff *frag = NULL; struct sk_buff *head = NULL; int hdr_len; /* Copy header if single buffer */ if (skb_queue_len(list) == 1) { skb = skb_peek(list); hdr_len = skb_headroom(skb) + msg_hdr_sz(buf_msg(skb)); _skb = __pskb_copy(skb, hdr_len, GFP_ATOMIC); if (!_skb) return false; __skb_queue_tail(rcvq, _skb); return true; } /* Clone all fragments and reassemble */ skb_queue_walk(list, skb) { frag = skb_clone(skb, GFP_ATOMIC); if (!frag) goto error; frag->next = NULL; if (tipc_buf_append(&head, &frag)) break; if (!head) goto error; } __skb_queue_tail(rcvq, frag); return true; error: pr_warn("Failed do clone local mcast rcv buffer\n"); kfree_skb(head); return false; } bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg, struct sk_buff_head *cpy) { struct sk_buff *skb, *_skb; skb_queue_walk(msg, skb) { _skb = pskb_copy(skb, GFP_ATOMIC); if (!_skb) { __skb_queue_purge(cpy); return false; } msg_set_destnode(buf_msg(_skb), dst); __skb_queue_tail(cpy, _skb); } return true; } /* tipc_skb_queue_sorted(); sort pkt into list according to sequence number * @list: list to be appended to * @seqno: sequence number of buffer to add * @skb: buffer to add */ bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, struct sk_buff *skb) { struct sk_buff *_skb, *tmp; if (skb_queue_empty(list) || less(seqno, buf_seqno(skb_peek(list)))) { __skb_queue_head(list, skb); return true; } if (more(seqno, buf_seqno(skb_peek_tail(list)))) { __skb_queue_tail(list, skb); return true; } skb_queue_walk_safe(list, _skb, tmp) { if (more(seqno, buf_seqno(_skb))) continue; if (seqno == buf_seqno(_skb)) break; __skb_queue_before(list, _skb, skb); return true; } kfree_skb(skb); return false; } void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, struct sk_buff_head *xmitq) { if (tipc_msg_reverse(tipc_own_addr(net), &skb, err)) __skb_queue_tail(xmitq, skb); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2018 Facebook */ #ifndef _LINUX_BTF_H #define _LINUX_BTF_H 1 #include <linux/types.h> #include <uapi/linux/btf.h> #include <uapi/linux/bpf.h> #define BTF_TYPE_EMIT(type) ((void)(type *)0) struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; extern const struct file_operations btf_fops; void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr); /* Figure out the size of a type_id. If type_id is a modifier * (e.g. const), it will be resolved to find out the type with size. * * For example: * In describing "const void *", type_id is "const" and "const" * refers to "void *". The return type will be "void *". * * If type_id is a simple "int", then return type will be "int". * * @btf: struct btf object * @type_id: Find out the size of type_id. The type_id of the return * type is set to *type_id. * @ret_size: It can be NULL. If not NULL, the size of the return * type is set to *ret_size. * Return: The btf_type (resolved to another type with size info if needed). * NULL is returned if type_id itself does not have size info * (e.g. void) or it cannot be resolved to another type that * has size info. * *type_id and *ret_size will not be changed in the * NULL return case. */ const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size); /* * Options to control show behaviour. * - BTF_SHOW_COMPACT: no formatting around type information * - BTF_SHOW_NONAME: no struct/union member names/types * - BTF_SHOW_PTR_RAW: show raw (unobfuscated) pointer values; * equivalent to %px. * - BTF_SHOW_ZERO: show zero-valued struct/union members; they * are not displayed by default * - BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read * data before displaying it. */ #define BTF_SHOW_COMPACT BTF_F_COMPACT #define BTF_SHOW_NONAME BTF_F_NONAME #define BTF_SHOW_PTR_RAW BTF_F_PTR_RAW #define BTF_SHOW_ZERO BTF_F_ZERO #define BTF_SHOW_UNSAFE (1ULL << 4) void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m); int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m, u64 flags); /* * Copy len bytes of string representation of obj of BTF type_id into buf. * * @btf: struct btf object * @type_id: type id of type obj points to * @obj: pointer to typed data * @buf: buffer to write to * @len: maximum length to write to buf * @flags: show options (see above) * * Return: length that would have been/was copied as per snprintf, or * negative error. */ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, char *buf, int len, u64 flags); int btf_get_fd_by_id(u32 id); u32 btf_id(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id); const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size); #define for_each_member(i, struct_type, member) \ for (i = 0, member = btf_type_member(struct_type); \ i < btf_type_vlen(struct_type); \ i++, member++) #define for_each_vsi(i, datasec_type, member) \ for (i = 0, member = btf_type_var_secinfo(datasec_type); \ i < btf_type_vlen(datasec_type); \ i++, member++) static inline bool btf_type_is_ptr(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; } static inline bool btf_type_is_int(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } static inline bool btf_type_is_small_int(const struct btf_type *t) { return btf_type_is_int(t) && t->size <= sizeof(u64); } static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } static inline bool btf_type_is_typedef(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; } static inline bool btf_type_is_func(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; } static inline bool btf_type_is_func_proto(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; } static inline bool btf_type_is_var(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } /* union is only a special case of struct: * all its offsetof(member) == 0 */ static inline bool btf_type_is_struct(const struct btf_type *t) { u8 kind = BTF_INFO_KIND(t->info); return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } static inline u16 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); } static inline u16 btf_func_linkage(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); } static inline bool btf_type_kflag(const struct btf_type *t) { return BTF_INFO_KFLAG(t->info); } static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) : member->offset; } static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) : 0; } static inline const struct btf_member *btf_type_member(const struct btf_type *t) { return (const struct btf_member *)(t + 1); } static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { return (const struct btf_var_secinfo *)(t + 1); } #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { return NULL; } static inline const char *btf_name_by_offset(const struct btf *btf, u32 offset) { return NULL; } #endif #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 | /* 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 { atomic_t count; struct ns_common ns; struct mount * root; /* * Traversal and modification of .list is protected by either * - taking namespace_sem for write, OR * - taking namespace_sem for read AND taking .ns_lock. */ struct list_head list; spinlock_t ns_lock; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_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 */ 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 */ 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); extern bool 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) { atomic_inc(&ns->count); } extern seqlock_t mount_lock; static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); struct mount cursor; }; 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; } extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_GENERIC_NETLINK_H #define __NET_GENERIC_NETLINK_H #include <linux/genetlink.h> #include <linux/android_kabi.h> #include <net/netlink.h> #include <net/net_namespace.h> #define GENLMSG_DEFAULT_SIZE (NLMSG_DEFAULT_SIZE - GENL_HDRLEN) /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family */ struct genl_multicast_group { char name[GENL_NAMSIZ]; }; struct genl_ops; struct genl_info; /** * struct genl_family - generic netlink family * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version * @maxattr: maximum number of attributes supported * @policy: netlink policy * @netnsok: set to true if the family can handle network * namespaces and should be presented in all of them * @parallel_ops: operations can be called in parallel and aren't * synchronized by the core genetlink code * @pre_doit: called before an operation's doit callback, it may * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family */ struct genl_family { int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; unsigned int mcgrp_offset; /* private */ u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; u8 n_small_ops; u8 n_mcgrps; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); void (*post_doit)(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; const struct genl_small_ops *small_ops; const struct genl_multicast_group *mcgrps; struct module *module; ANDROID_KABI_RESERVE(1); }; /** * struct genl_info - receiving information * @snd_seq: sending sequence number * @snd_portid: netlink portid of sender * @nlhdr: netlink message header * @genlhdr: generic netlink message header * @userhdr: user specific header * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers * @extack: extended ACK report struct */ struct genl_info { u32 snd_seq; u32 snd_portid; struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; void * userhdr; struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; struct netlink_ext_ack *extack; }; static inline struct net *genl_info_net(struct genl_info *info) { return read_pnet(&info->_net); } static inline void genl_info_net_set(struct genl_info *info, struct net *net) { write_pnet(&info->_net, net); } #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) enum genl_validate_flags { GENL_DONT_VALIDATE_STRICT = BIT(0), GENL_DONT_VALIDATE_DUMP = BIT(1), GENL_DONT_VALIDATE_DUMP_STRICT = BIT(2), }; /** * struct genl_small_ops - generic netlink operations (small version) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @dumpit: callback for dumpers * * This is a cut-down version of struct genl_ops for users who don't need * most of the ancillary infra and want to save space. */ struct genl_small_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); u8 cmd; u8 internal_flags; u8 flags; u8 validate; }; /** * struct genl_ops - generic netlink operations * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags * @maxattr: maximum number of attributes supported * @policy: netlink policy (takes precedence over family policy) * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers * @done: completion callback for dumps */ struct genl_ops { int (*doit)(struct sk_buff *skb, struct genl_info *info); int (*start)(struct netlink_callback *cb); int (*dumpit)(struct sk_buff *skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); const struct nla_policy *policy; unsigned int maxattr; u8 cmd; u8 internal_flags; u8 flags; u8 validate; ANDROID_KABI_RESERVE(1); }; /** * struct genl_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage * @ops: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { const struct genl_family *family; struct genl_ops op; struct nlattr **attrs; }; static inline const struct genl_dumpit_info * genl_dumpit_info(struct netlink_callback *cb) { return cb->data; } int genl_register_family(struct genl_family *family); int genl_unregister_family(const struct genl_family *family); void genl_notify(const struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, const struct genl_family *family, int flags, u8 cmd); /** * genlmsg_nlhdr - Obtain netlink header from user specified header * @user_hdr: user header as returned from genlmsg_put() * * Returns pointer to netlink header. */ static inline struct nlmsghdr *genlmsg_nlhdr(void *user_hdr) { return (struct nlmsghdr *)((char *)user_hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_parse_deprecated - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse_deprecated(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * genlmsg_parse - parse attributes of a genetlink message * @nlh: netlink message header * @family: genetlink message family * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int genlmsg_parse(const struct nlmsghdr *nlh, const struct genl_family *family, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, family->hdrsize + GENL_HDRLEN, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * genl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @user_hdr: user header as returned from genlmsg_put() * * Cf. nl_dump_check_consistent(), this just provides a wrapper to make it * simpler to use with generic netlink. */ static inline void genl_dump_check_consistent(struct netlink_callback *cb, void *user_hdr) { nl_dump_check_consistent(cb, genlmsg_nlhdr(user_hdr)); } /** * genlmsg_put_reply - Add generic netlink header to a reply message * @skb: socket buffer holding the message * @info: receiver info * @family: generic netlink family * @flags: netlink message flags * @cmd: generic netlink command * * Returns pointer to user specific header */ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_info *info, const struct genl_family *family, int flags, u8 cmd) { return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, flags, cmd); } /** * genlmsg_end - Finalize a generic netlink message * @skb: socket buffer the message is stored in * @hdr: user specific header */ static inline void genlmsg_end(struct sk_buff *skb, void *hdr) { nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_cancel - Cancel construction of a generic netlink message * @skb: socket buffer the message is stored in * @hdr: generic netlink message header */ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) { if (hdr) nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_multicast_netns - multicast a netlink message to a specific netns * @family: the generic netlink family * @net: the net namespace * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast_netns(const struct genl_family *family, struct net *net, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return nlmsg_multicast(net->genl_sock, skb, portid, group, flags); } /** * genlmsg_multicast - multicast a netlink message to the default netns * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags */ static inline int genlmsg_multicast(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return genlmsg_multicast_netns(family, &init_net, skb, portid, group, flags); } /** * genlmsg_multicast_allns - multicast a netlink message to all net namespaces * @family: the generic netlink family * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: offset of multicast group in groups array * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ int genlmsg_multicast_allns(const struct genl_family *family, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags); /** * genlmsg_unicast - unicast a netlink message * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 portid) { return nlmsg_unicast(net->genl_sock, skb, portid); } /** * genlmsg_reply - reply to a request * @skb: netlink message to be sent back * @info: receiver information */ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) { return genlmsg_unicast(genl_info_net(info), skb, info->snd_portid); } /** * gennlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) { return ((unsigned char *) gnlh + GENL_HDRLEN); } /** * genlmsg_len - length of message payload * @gnlh: genetlink message header */ static inline int genlmsg_len(const struct genlmsghdr *gnlh) { struct nlmsghdr *nlh = (struct nlmsghdr *)((unsigned char *)gnlh - NLMSG_HDRLEN); return (nlh->nlmsg_len - GENL_HDRLEN - NLMSG_HDRLEN); } /** * genlmsg_msg_size - length of genetlink message not including padding * @payload: length of message payload */ static inline int genlmsg_msg_size(int payload) { return GENL_HDRLEN + payload; } /** * genlmsg_total_size - length of genetlink message including padding * @payload: length of message payload */ static inline int genlmsg_total_size(int payload) { return NLMSG_ALIGN(genlmsg_msg_size(payload)); } /** * genlmsg_new - Allocate a new generic netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. */ static inline struct sk_buff *genlmsg_new(size_t payload, gfp_t flags) { return nlmsg_new(genlmsg_total_size(payload), flags); } /** * genl_set_err - report error to genetlink broadcast listeners * @family: the generic netlink family * @net: the network namespace to report the error to * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * (this is the offset of the multicast group in the groups array) * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ static inline int genl_set_err(const struct genl_family *family, struct net *net, u32 portid, u32 group, int code) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_set_err(net->genl_sock, portid, group, code); } static inline int genl_has_listeners(const struct genl_family *family, struct net *net, unsigned int group) { if (WARN_ON_ONCE(group >= family->n_mcgrps)) return -EINVAL; group = family->mcgrp_offset + group; return netlink_has_listeners(net->genl_sock, group); } #endif /* __NET_GENERIC_NETLINK_H */ |
| 605 605 604 605 605 605 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * sd.c Copyright (C) 1992 Drew Eckhardt * Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale * * Linux scsi disk driver * Initial versions: Drew Eckhardt * Subsequent revisions: Eric Youngdale * Modification history: * - Drew Eckhardt <drew@colorado.edu> original * - Eric Youngdale <eric@andante.org> add scatter-gather, multiple * outstanding request, and other enhancements. * Support loadable low-level scsi drivers. * - Jirka Hanika <geo@ff.cuni.cz> support more scsi disks using * eight major numbers. * - Richard Gooch <rgooch@atnf.csiro.au> support devfs. * - Torben Mathiasen <tmm@image.dk> Resource allocation fixes in * sd_init and cleanups. * - Alex Davis <letmein@erols.com> Fix problem where partition info * not being read in sd_open. Fix problem where removable media * could be ejected after sd_open. * - Douglas Gilbert <dgilbert@interlog.com> cleanup for lk 2.5.x * - Badari Pulavarty <pbadari@us.ibm.com>, Matthew Wilcox * <willy@debian.org>, Kurt Garloff <garloff@suse.de>: * Support 32k/1M disks. * * Logging policy (needs CONFIG_SCSI_LOGGING defined): * - setting up transfer: SCSI_LOG_HLQUEUE levels 1 and 2 * - end of transfer (bh + scsi_lib): SCSI_LOG_HLCOMPLETE level 1 * - entering sd_ioctl: SCSI_LOG_IOCTL level 1 * - entering other commands: SCSI_LOG_HLQUEUE level 3 * Note: when the logging level is set by the user, it must be greater * than the level indicated above to trigger output. */ #include <linux/module.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/bio.h> #include <linux/genhd.h> #include <linux/hdreg.h> #include <linux/errno.h> #include <linux/idr.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/blkpg.h> #include <linux/blk-pm.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/string_helpers.h> #include <linux/async.h> #include <linux/slab.h> #include <linux/sed-opal.h> #include <linux/pm_runtime.h> #include <linux/pr.h> #include <linux/t10-pi.h> #include <linux/uaccess.h> #include <asm/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsicam.h> #include "sd.h" #include "scsi_priv.h" #include "scsi_logging.h" MODULE_AUTHOR("Eric Youngdale"); MODULE_DESCRIPTION("SCSI disk (sd) driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK0_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK1_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK2_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK3_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK4_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK5_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK6_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK7_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK8_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK9_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK10_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK11_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK12_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK13_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK14_MAJOR); MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK15_MAJOR); MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK); MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD); MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC); #if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT) #define SD_MINORS 16 #else #define SD_MINORS 0 #endif static void sd_config_discard(struct scsi_disk *, unsigned int); static void sd_config_write_same(struct scsi_disk *); static int sd_revalidate_disk(struct gendisk *); static void sd_unlock_native_capacity(struct gendisk *disk); static int sd_probe(struct device *); static int sd_remove(struct device *); static void sd_shutdown(struct device *); static int sd_suspend_system(struct device *); static int sd_suspend_runtime(struct device *); static int sd_resume(struct device *); static void sd_rescan(struct device *); static blk_status_t sd_init_command(struct scsi_cmnd *SCpnt); static void sd_uninit_command(struct scsi_cmnd *SCpnt); static int sd_done(struct scsi_cmnd *); static void sd_eh_reset(struct scsi_cmnd *); static int sd_eh_action(struct scsi_cmnd *, int); static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer); static void scsi_disk_release(struct device *cdev); static DEFINE_IDA(sd_index_ida); /* This semaphore is used to mediate the 0->1 reference get in the * face of object destruction (i.e. we can't allow a get on an * object after last put) */ static DEFINE_MUTEX(sd_ref_mutex); static struct kmem_cache *sd_cdb_cache; static mempool_t *sd_cdb_pool; static mempool_t *sd_page_pool; static const char *sd_cache_types[] = { "write through", "none", "write back", "write back, no read (daft)" }; static void sd_set_flush_flag(struct scsi_disk *sdkp) { bool wc = false, fua = false; if (sdkp->WCE) { wc = true; if (sdkp->DPOFUA) fua = true; } blk_queue_write_cache(sdkp->disk->queue, wc, fua); } static ssize_t cache_type_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ct, rcd, wce, sp; struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; char buffer[64]; char *buffer_data; struct scsi_mode_data data; struct scsi_sense_hdr sshdr; static const char temp[] = "temporary "; int len; if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC) /* no cache control on RBC devices; theoretically they * can do it, but there's probably so many exceptions * it's not worth the risk */ return -EINVAL; if (strncmp(buf, temp, sizeof(temp) - 1) == 0) { buf += sizeof(temp) - 1; sdkp->cache_override = 1; } else { sdkp->cache_override = 0; } ct = sysfs_match_string(sd_cache_types, buf); if (ct < 0) return -EINVAL; rcd = ct & 0x01 ? 1 : 0; wce = (ct & 0x02) && !sdkp->write_prot ? 1 : 0; if (sdkp->cache_override) { sdkp->WCE = wce; sdkp->RCD = rcd; sd_set_flush_flag(sdkp); return count; } if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT, sdkp->max_retries, &data, NULL)) return -EINVAL; len = min_t(size_t, sizeof(buffer), data.length - data.header_length - data.block_descriptor_length); buffer_data = buffer + data.header_length + data.block_descriptor_length; buffer_data[2] &= ~0x05; buffer_data[2] |= wce << 2 | rcd; sp = buffer_data[0] & 0x80 ? 1 : 0; buffer_data[0] &= ~0x80; /* * Ensure WP, DPOFUA, and RESERVED fields are cleared in * received mode parameter buffer before doing MODE SELECT. */ data.device_specific = 0; if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT, sdkp->max_retries, &data, &sshdr)) { if (scsi_sense_valid(&sshdr)) sd_print_sense_hdr(sdkp, &sshdr); return -EINVAL; } sd_revalidate_disk(sdkp->disk); return count; } static ssize_t manage_start_stop_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; return sprintf(buf, "%u\n", sdp->manage_start_stop); } static ssize_t manage_start_stop_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; bool v; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (kstrtobool(buf, &v)) return -EINVAL; sdp->manage_start_stop = v; return count; } static DEVICE_ATTR_RW(manage_start_stop); static ssize_t allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->device->allow_restart); } static ssize_t allow_restart_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { bool v; struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC) return -EINVAL; if (kstrtobool(buf, &v)) return -EINVAL; sdp->allow_restart = v; return count; } static DEVICE_ATTR_RW(allow_restart); static ssize_t cache_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); int ct = sdkp->RCD + 2*sdkp->WCE; return sprintf(buf, "%s\n", sd_cache_types[ct]); } static DEVICE_ATTR_RW(cache_type); static ssize_t FUA_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->DPOFUA); } static DEVICE_ATTR_RO(FUA); static ssize_t protection_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->protection_type); } static ssize_t protection_type_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); unsigned int val; int err; if (!capable(CAP_SYS_ADMIN)) return -EACCES; err = kstrtouint(buf, 10, &val); if (err) return err; if (val <= T10_PI_TYPE3_PROTECTION) sdkp->protection_type = val; return count; } static DEVICE_ATTR_RW(protection_type); static ssize_t protection_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; unsigned int dif, dix; dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type); dix = scsi_host_dix_capable(sdp->host, sdkp->protection_type); if (!dix && scsi_host_dix_capable(sdp->host, T10_PI_TYPE0_PROTECTION)) { dif = 0; dix = 1; } if (!dif && !dix) return sprintf(buf, "none\n"); return sprintf(buf, "%s%u\n", dix ? "dix" : "dif", dif); } static DEVICE_ATTR_RO(protection_mode); static ssize_t app_tag_own_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->ATO); } static DEVICE_ATTR_RO(app_tag_own); static ssize_t thin_provisioning_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->lbpme); } static DEVICE_ATTR_RO(thin_provisioning); /* sysfs_match_string() requires dense arrays */ static const char *lbp_mode[] = { [SD_LBP_FULL] = "full", [SD_LBP_UNMAP] = "unmap", [SD_LBP_WS16] = "writesame_16", [SD_LBP_WS10] = "writesame_10", [SD_LBP_ZERO] = "writesame_zero", [SD_LBP_DISABLE] = "disabled", }; static ssize_t provisioning_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%s\n", lbp_mode[sdkp->provisioning_mode]); } static ssize_t provisioning_mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; int mode; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (sd_is_zoned(sdkp)) { sd_config_discard(sdkp, SD_LBP_DISABLE); return count; } if (sdp->type != TYPE_DISK) return -EINVAL; mode = sysfs_match_string(lbp_mode, buf); if (mode < 0) return -EINVAL; sd_config_discard(sdkp, mode); return count; } static DEVICE_ATTR_RW(provisioning_mode); /* sysfs_match_string() requires dense arrays */ static const char *zeroing_mode[] = { [SD_ZERO_WRITE] = "write", [SD_ZERO_WS] = "writesame", [SD_ZERO_WS16_UNMAP] = "writesame_16_unmap", [SD_ZERO_WS10_UNMAP] = "writesame_10_unmap", }; static ssize_t zeroing_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%s\n", zeroing_mode[sdkp->zeroing_mode]); } static ssize_t zeroing_mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); int mode; if (!capable(CAP_SYS_ADMIN)) return -EACCES; mode = sysfs_match_string(zeroing_mode, buf); if (mode < 0) return -EINVAL; sdkp->zeroing_mode = mode; return count; } static DEVICE_ATTR_RW(zeroing_mode); static ssize_t max_medium_access_timeouts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->max_medium_access_timeouts); } static ssize_t max_medium_access_timeouts_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); int err; if (!capable(CAP_SYS_ADMIN)) return -EACCES; err = kstrtouint(buf, 10, &sdkp->max_medium_access_timeouts); return err ? err : count; } static DEVICE_ATTR_RW(max_medium_access_timeouts); static ssize_t max_write_same_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%u\n", sdkp->max_ws_blocks); } static ssize_t max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; unsigned long max; int err; if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC) return -EINVAL; err = kstrtoul(buf, 10, &max); if (err) return err; if (max == 0) sdp->no_write_same = 1; else if (max <= SD_MAX_WS16_BLOCKS) { sdp->no_write_same = 0; sdkp->max_ws_blocks = max; } sd_config_write_same(sdkp); return count; } static DEVICE_ATTR_RW(max_write_same_blocks); static ssize_t zoned_cap_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); if (sdkp->device->type == TYPE_ZBC) return sprintf(buf, "host-managed\n"); if (sdkp->zoned == 1) return sprintf(buf, "host-aware\n"); if (sdkp->zoned == 2) return sprintf(buf, "drive-managed\n"); return sprintf(buf, "none\n"); } static DEVICE_ATTR_RO(zoned_cap); static ssize_t max_retries_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdev = sdkp->device; int retries, err; err = kstrtoint(buf, 10, &retries); if (err) return err; if (retries == SCSI_CMD_RETRIES_NO_LIMIT || retries <= SD_MAX_RETRIES) { sdkp->max_retries = retries; return count; } sdev_printk(KERN_ERR, sdev, "max_retries must be between -1 and %d\n", SD_MAX_RETRIES); return -EINVAL; } static ssize_t max_retries_show(struct device *dev, struct device_attribute *attr, char *buf) { struct scsi_disk *sdkp = to_scsi_disk(dev); return sprintf(buf, "%d\n", sdkp->max_retries); } static DEVICE_ATTR_RW(max_retries); static struct attribute *sd_disk_attrs[] = { &dev_attr_cache_type.attr, &dev_attr_FUA.attr, &dev_attr_allow_restart.attr, &dev_attr_manage_start_stop.attr, &dev_attr_protection_type.attr, &dev_attr_protection_mode.attr, &dev_attr_app_tag_own.attr, &dev_attr_thin_provisioning.attr, &dev_attr_provisioning_mode.attr, &dev_attr_zeroing_mode.attr, &dev_attr_max_write_same_blocks.attr, &dev_attr_max_medium_access_timeouts.attr, &dev_attr_zoned_cap.attr, &dev_attr_max_retries.attr, NULL, }; ATTRIBUTE_GROUPS(sd_disk); static struct class sd_disk_class = { .name = "scsi_disk", .owner = THIS_MODULE, .dev_release = scsi_disk_release, .dev_groups = sd_disk_groups, }; static const struct dev_pm_ops sd_pm_ops = { .suspend = sd_suspend_system, .resume = sd_resume, .poweroff = sd_suspend_system, .restore = sd_resume, .runtime_suspend = sd_suspend_runtime, .runtime_resume = sd_resume, }; static struct scsi_driver sd_template = { .gendrv = { .name = "sd", .owner = THIS_MODULE, .probe = sd_probe, .probe_type = PROBE_PREFER_ASYNCHRONOUS, .remove = sd_remove, .shutdown = sd_shutdown, .pm = &sd_pm_ops, }, .rescan = sd_rescan, .init_command = sd_init_command, .uninit_command = sd_uninit_command, .done = sd_done, .eh_action = sd_eh_action, .eh_reset = sd_eh_reset, }; /* * Dummy kobj_map->probe function. * The default ->probe function will call modprobe, which is * pointless as this module is already loaded. */ static struct kobject *sd_default_probe(dev_t devt, int *partno, void *data) { return NULL; } /* * Device no to disk mapping: * * major disc2 disc p1 * |............|.............|....|....| <- dev_t * 31 20 19 8 7 4 3 0 * * Inside a major, we have 16k disks, however mapped non- * contiguously. The first 16 disks are for major0, the next * ones with major1, ... Disk 256 is for major0 again, disk 272 * for major1, ... * As we stay compatible with our numbering scheme, we can reuse * the well-know SCSI majors 8, 65--71, 136--143. */ static int sd_major(int major_idx) { switch (major_idx) { case 0: return SCSI_DISK0_MAJOR; case 1 ... 7: return SCSI_DISK1_MAJOR + major_idx - 1; case 8 ... 15: return SCSI_DISK8_MAJOR + major_idx - 8; default: BUG(); return 0; /* shut up gcc */ } } static struct scsi_disk *scsi_disk_get(struct gendisk *disk) { struct scsi_disk *sdkp = NULL; mutex_lock(&sd_ref_mutex); if (disk->private_data) { sdkp = scsi_disk(disk); if (scsi_device_get(sdkp->device) == 0) get_device(&sdkp->dev); else sdkp = NULL; } mutex_unlock(&sd_ref_mutex); return sdkp; } static void scsi_disk_put(struct scsi_disk *sdkp) { struct scsi_device *sdev = sdkp->device; mutex_lock(&sd_ref_mutex); put_device(&sdkp->dev); scsi_device_put(sdev); mutex_unlock(&sd_ref_mutex); } #ifdef CONFIG_BLK_SED_OPAL static int sd_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, bool send) { struct scsi_disk *sdkp = data; struct scsi_device *sdev = sdkp->device; u8 cdb[12] = { 0, }; int ret; cdb[0] = send ? SECURITY_PROTOCOL_OUT : SECURITY_PROTOCOL_IN; cdb[1] = secp; put_unaligned_be16(spsp, &cdb[2]); put_unaligned_be32(len, &cdb[6]); ret = scsi_execute(sdev, cdb, send ? DMA_TO_DEVICE : DMA_FROM_DEVICE, buffer, len, NULL, NULL, SD_TIMEOUT, sdkp->max_retries, 0, RQF_PM, NULL); return ret <= 0 ? ret : -EIO; } #endif /* CONFIG_BLK_SED_OPAL */ /* * Look up the DIX operation based on whether the command is read or * write and whether dix and dif are enabled. */ static unsigned int sd_prot_op(bool write, bool dix, bool dif) { /* Lookup table: bit 2 (write), bit 1 (dix), bit 0 (dif) */ static const unsigned int ops[] = { /* wrt dix dif */ SCSI_PROT_NORMAL, /* 0 0 0 */ SCSI_PROT_READ_STRIP, /* 0 0 1 */ SCSI_PROT_READ_INSERT, /* 0 1 0 */ SCSI_PROT_READ_PASS, /* 0 1 1 */ SCSI_PROT_NORMAL, /* 1 0 0 */ SCSI_PROT_WRITE_INSERT, /* 1 0 1 */ SCSI_PROT_WRITE_STRIP, /* 1 1 0 */ SCSI_PROT_WRITE_PASS, /* 1 1 1 */ }; return ops[write << 2 | dix << 1 | dif]; } /* * Returns a mask of the protection flags that are valid for a given DIX * operation. */ static unsigned int sd_prot_flag_mask(unsigned int prot_op) { static const unsigned int flag_mask[] = { [SCSI_PROT_NORMAL] = 0, [SCSI_PROT_READ_STRIP] = SCSI_PROT_TRANSFER_PI | SCSI_PROT_GUARD_CHECK | SCSI_PROT_REF_CHECK | SCSI_PROT_REF_INCREMENT, [SCSI_PROT_READ_INSERT] = SCSI_PROT_REF_INCREMENT | SCSI_PROT_IP_CHECKSUM, [SCSI_PROT_READ_PASS] = SCSI_PROT_TRANSFER_PI | SCSI_PROT_GUARD_CHECK | SCSI_PROT_REF_CHECK | SCSI_PROT_REF_INCREMENT | SCSI_PROT_IP_CHECKSUM, [SCSI_PROT_WRITE_INSERT] = SCSI_PROT_TRANSFER_PI | SCSI_PROT_REF_INCREMENT, [SCSI_PROT_WRITE_STRIP] = SCSI_PROT_GUARD_CHECK | SCSI_PROT_REF_CHECK | SCSI_PROT_REF_INCREMENT | SCSI_PROT_IP_CHECKSUM, [SCSI_PROT_WRITE_PASS] = SCSI_PROT_TRANSFER_PI | SCSI_PROT_GUARD_CHECK | SCSI_PROT_REF_CHECK | SCSI_PROT_REF_INCREMENT | SCSI_PROT_IP_CHECKSUM, }; return flag_mask[prot_op]; } static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd, unsigned int dix, unsigned int dif) { struct bio *bio = scmd->request->bio; unsigned int prot_op = sd_prot_op(rq_data_dir(scmd->request), dix, dif); unsigned int protect = 0; if (dix) { /* DIX Type 0, 1, 2, 3 */ if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM)) scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM; if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false) scmd->prot_flags |= SCSI_PROT_GUARD_CHECK; } if (dif != T10_PI_TYPE3_PROTECTION) { /* DIX/DIF Type 0, 1, 2 */ scmd->prot_flags |= SCSI_PROT_REF_INCREMENT; if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false) scmd->prot_flags |= SCSI_PROT_REF_CHECK; } if (dif) { /* DIX/DIF Type 1, 2, 3 */ scmd->prot_flags |= SCSI_PROT_TRANSFER_PI; if (bio_integrity_flagged(bio, BIP_DISK_NOCHECK)) protect = 3 << 5; /* Disable target PI checking */ else protect = 1 << 5; /* Enable target PI checking */ } scsi_set_prot_op(scmd, prot_op); scsi_set_prot_type(scmd, dif); scmd->prot_flags &= sd_prot_flag_mask(prot_op); return protect; } static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) { struct request_queue *q = sdkp->disk->queue; unsigned int logical_block_size = sdkp->device->sector_size; unsigned int max_blocks = 0; q->limits.discard_alignment = sdkp->unmap_alignment * logical_block_size; q->limits.discard_granularity = max(sdkp->physical_block_size, sdkp->unmap_granularity * logical_block_size); sdkp->provisioning_mode = mode; switch (mode) { case SD_LBP_FULL: case SD_LBP_DISABLE: blk_queue_max_discard_sectors(q, 0); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); return; case SD_LBP_UNMAP: max_blocks = min_not_zero(sdkp->max_unmap_blocks, (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS16: if (sdkp->device->unmap_limit_for_ws) max_blocks = sdkp->max_unmap_blocks; else max_blocks = sdkp->max_ws_blocks; max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS); break; case SD_LBP_WS10: if (sdkp->device->unmap_limit_for_ws) max_blocks = sdkp->max_unmap_blocks; else max_blocks = sdkp->max_ws_blocks; max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: max_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)SD_MAX_WS10_BLOCKS); break; } blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9)); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) { struct scsi_device *sdp = cmd->device; struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); unsigned int data_len = 24; char *buf; rq->special_vec.bv_page = mempool_alloc(sd_page_pool, GFP_ATOMIC); if (!rq->special_vec.bv_page) return BLK_STS_RESOURCE; clear_highpage(rq->special_vec.bv_page); rq->special_vec.bv_offset = 0; rq->special_vec.bv_len = data_len; rq->rq_flags |= RQF_SPECIAL_PAYLOAD; cmd->cmd_len = 10; cmd->cmnd[0] = UNMAP; cmd->cmnd[8] = 24; buf = page_address(rq->special_vec.bv_page); put_unaligned_be16(6 + 16, &buf[0]); put_unaligned_be16(16, &buf[2]); put_unaligned_be64(lba, &buf[8]); put_unaligned_be32(nr_blocks, &buf[16]); cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len; rq->timeout = SD_TIMEOUT; return scsi_alloc_sgtables(cmd); } static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap) { struct scsi_device *sdp = cmd->device; struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; rq->special_vec.bv_page = mempool_alloc(sd_page_pool, GFP_ATOMIC); if (!rq->special_vec.bv_page) return BLK_STS_RESOURCE; clear_highpage(rq->special_vec.bv_page); rq->special_vec.bv_offset = 0; rq->special_vec.bv_len = data_len; rq->rq_flags |= RQF_SPECIAL_PAYLOAD; cmd->cmd_len = 16; cmd->cmnd[0] = WRITE_SAME_16; if (unmap) cmd->cmnd[1] = 0x8; /* UNMAP */ put_unaligned_be64(lba, &cmd->cmnd[2]); put_unaligned_be32(nr_blocks, &cmd->cmnd[10]); cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len; rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT; return scsi_alloc_sgtables(cmd); } static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap) { struct scsi_device *sdp = cmd->device; struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; rq->special_vec.bv_page = mempool_alloc(sd_page_pool, GFP_ATOMIC); if (!rq->special_vec.bv_page) return BLK_STS_RESOURCE; clear_highpage(rq->special_vec.bv_page); rq->special_vec.bv_offset = 0; rq->special_vec.bv_len = data_len; rq->rq_flags |= RQF_SPECIAL_PAYLOAD; cmd->cmd_len = 10; cmd->cmnd[0] = WRITE_SAME; if (unmap) cmd->cmnd[1] = 0x8; /* UNMAP */ put_unaligned_be32(lba, &cmd->cmnd[2]); put_unaligned_be16(nr_blocks, &cmd->cmnd[7]); cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len; rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT; return scsi_alloc_sgtables(cmd); } static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) { struct request *rq = cmd->request; struct scsi_device *sdp = cmd->device; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); if (!(rq->cmd_flags & REQ_NOUNMAP)) { switch (sdkp->zeroing_mode) { case SD_ZERO_WS16_UNMAP: return sd_setup_write_same16_cmnd(cmd, true); case SD_ZERO_WS10_UNMAP: return sd_setup_write_same10_cmnd(cmd, true); } } if (sdp->no_write_same) { rq->rq_flags |= RQF_QUIET; return BLK_STS_TARGET; } if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff) return sd_setup_write_same16_cmnd(cmd, false); return sd_setup_write_same10_cmnd(cmd, false); } static void sd_config_write_same(struct scsi_disk *sdkp) { struct request_queue *q = sdkp->disk->queue; unsigned int logical_block_size = sdkp->device->sector_size; if (sdkp->device->no_write_same) { sdkp->max_ws_blocks = 0; goto out; } /* Some devices can not handle block counts above 0xffff despite * supporting WRITE SAME(16). Consequently we default to 64k * blocks per I/O unless the device explicitly advertises a * bigger limit. */ if (sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS) sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)SD_MAX_WS16_BLOCKS); else if (sdkp->ws16 || sdkp->ws10 || sdkp->device->no_report_opcodes) sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)SD_MAX_WS10_BLOCKS); else { sdkp->device->no_write_same = 1; sdkp->max_ws_blocks = 0; } if (sdkp->lbprz && sdkp->lbpws) sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP; else if (sdkp->lbprz && sdkp->lbpws10) sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP; else if (sdkp->max_ws_blocks) sdkp->zeroing_mode = SD_ZERO_WS; else sdkp->zeroing_mode = SD_ZERO_WRITE; if (sdkp->max_ws_blocks && sdkp->physical_block_size > logical_block_size) { /* * Reporting a maximum number of blocks that is not aligned * on the device physical size would cause a large write same * request to be split into physically unaligned chunks by * __blkdev_issue_write_zeroes() and __blkdev_issue_write_same() * even if the caller of these functions took care to align the * large request. So make sure the maximum reported is aligned * to the device physical block size. This is only an optional * optimization for regular disks, but this is mandatory to * avoid failure of large write same requests directed at * sequential write required zones of host-managed ZBC disks. */ sdkp->max_ws_blocks = round_down(sdkp->max_ws_blocks, bytes_to_logical(sdkp->device, sdkp->physical_block_size)); } out: blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks * (logical_block_size >> 9)); blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks * (logical_block_size >> 9)); } /** * sd_setup_write_same_cmnd - write the same data to multiple blocks * @cmd: command to prepare * * Will set up either WRITE SAME(10) or WRITE SAME(16) depending on * the preference indicated by the target device. **/ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) { struct request *rq = cmd->request; struct scsi_device *sdp = cmd->device; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); struct bio *bio = rq->bio; u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); blk_status_t ret; if (sdkp->device->no_write_same) return BLK_STS_TARGET; BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size); rq->timeout = SD_WRITE_SAME_TIMEOUT; if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff) { cmd->cmd_len = 16; cmd->cmnd[0] = WRITE_SAME_16; put_unaligned_be64(lba, &cmd->cmnd[2]); put_unaligned_be32(nr_blocks, &cmd->cmnd[10]); } else { cmd->cmd_len = 10; cmd->cmnd[0] = WRITE_SAME; put_unaligned_be32(lba, &cmd->cmnd[2]); put_unaligned_be16(nr_blocks, &cmd->cmnd[7]); } cmd->transfersize = sdp->sector_size; cmd->allowed = sdkp->max_retries; /* * For WRITE SAME the data transferred via the DATA OUT buffer is * different from the amount of data actually written to the target. * * We set up __data_len to the amount of data transferred via the * DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list * to transfer a single sector of data first, but then reset it to * the amount of data to be written right after so that the I/O path * knows how much to actually write. */ rq->__data_len = sdp->sector_size; ret = scsi_alloc_sgtables(cmd); rq->__data_len = blk_rq_bytes(rq); return ret; } static blk_status_t sd_setup_flush_cmnd(struct scsi_cmnd *cmd) { struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); /* flush requests don't perform I/O, zero the S/G table */ memset(&cmd->sdb, 0, sizeof(cmd->sdb)); cmd->cmnd[0] = SYNCHRONIZE_CACHE; cmd->cmd_len = 10; cmd->transfersize = 0; cmd->allowed = sdkp->max_retries; rq->timeout = rq->q->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; return BLK_STS_OK; } static blk_status_t sd_setup_rw32_cmnd(struct scsi_cmnd *cmd, bool write, sector_t lba, unsigned int nr_blocks, unsigned char flags) { cmd->cmnd = mempool_alloc(sd_cdb_pool, GFP_ATOMIC); if (unlikely(cmd->cmnd == NULL)) return BLK_STS_RESOURCE; cmd->cmd_len = SD_EXT_CDB_SIZE; memset(cmd->cmnd, 0, cmd->cmd_len); cmd->cmnd[0] = VARIABLE_LENGTH_CMD; cmd->cmnd[7] = 0x18; /* Additional CDB len */ cmd->cmnd[9] = write ? WRITE_32 : READ_32; cmd->cmnd[10] = flags; put_unaligned_be64(lba, &cmd->cmnd[12]); put_unaligned_be32(lba, &cmd->cmnd[20]); /* Expected Indirect LBA */ put_unaligned_be32(nr_blocks, &cmd->cmnd[28]); return BLK_STS_OK; } static blk_status_t sd_setup_rw16_cmnd(struct scsi_cmnd *cmd, bool write, sector_t lba, unsigned int nr_blocks, unsigned char flags) { cmd->cmd_len = 16; cmd->cmnd[0] = write ? WRITE_16 : READ_16; cmd->cmnd[1] = flags; cmd->cmnd[14] = 0; cmd->cmnd[15] = 0; put_unaligned_be64(lba, &cmd->cmnd[2]); put_unaligned_be32(nr_blocks, &cmd->cmnd[10]); return BLK_STS_OK; } static blk_status_t sd_setup_rw10_cmnd(struct scsi_cmnd *cmd, bool write, sector_t lba, unsigned int nr_blocks, unsigned char flags) { cmd->cmd_len = 10; cmd->cmnd[0] = write ? WRITE_10 : READ_10; cmd->cmnd[1] = flags; cmd->cmnd[6] = 0; cmd->cmnd[9] = 0; put_unaligned_be32(lba, &cmd->cmnd[2]); put_unaligned_be16(nr_blocks, &cmd->cmnd[7]); return BLK_STS_OK; } static blk_status_t sd_setup_rw6_cmnd(struct scsi_cmnd *cmd, bool write, sector_t lba, unsigned int nr_blocks, unsigned char flags) { /* Avoid that 0 blocks gets translated into 256 blocks. */ if (WARN_ON_ONCE(nr_blocks == 0)) return BLK_STS_IOERR; if (unlikely(flags & 0x8)) { /* * This happens only if this drive failed 10byte rw * command with ILLEGAL_REQUEST during operation and * thus turned off use_10_for_rw. */ scmd_printk(KERN_ERR, cmd, "FUA write on READ/WRITE(6) drive\n"); return BLK_STS_IOERR; } cmd->cmd_len = 6; cmd->cmnd[0] = write ? WRITE_6 : READ_6; cmd->cmnd[1] = (lba >> 16) & 0x1f; cmd->cmnd[2] = (lba >> 8) & 0xff; cmd->cmnd[3] = lba & 0xff; cmd->cmnd[4] = nr_blocks; cmd->cmnd[5] = 0; return BLK_STS_OK; } static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) { struct request *rq = cmd->request; struct scsi_device *sdp = cmd->device; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); sector_t lba = sectors_to_logical(sdp, blk_rq_pos(rq)); sector_t threshold; unsigned int nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); unsigned int mask = logical_to_sectors(sdp, 1) - 1; bool write = rq_data_dir(rq) == WRITE; unsigned char protect, fua; blk_status_t ret; unsigned int dif; bool dix; ret = scsi_alloc_sgtables(cmd); if (ret != BLK_STS_OK) return ret; ret = BLK_STS_IOERR; if (!scsi_device_online(sdp) || sdp->changed) { scmd_printk(KERN_ERR, cmd, "device offline or changed\n"); goto fail; } if (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->rq_disk)) { scmd_printk(KERN_ERR, cmd, "access beyond end of device\n"); goto fail; } if ((blk_rq_pos(rq) & mask) || (blk_rq_sectors(rq) & mask)) { scmd_printk(KERN_ERR, cmd, "request not aligned to the logical block size\n"); goto fail; } /* * Some SD card readers can't handle accesses which touch the * last one or two logical blocks. Split accesses as needed. */ threshold = sdkp->capacity - SD_LAST_BUGGY_SECTORS; if (unlikely(sdp->last_sector_bug && lba + nr_blocks > threshold)) { if (lba < threshold) { /* Access up to the threshold but not beyond */ nr_blocks = threshold - lba; } else { /* Access only a single logical block */ nr_blocks = 1; } } if (req_op(rq) == REQ_OP_ZONE_APPEND) { ret = sd_zbc_prepare_zone_append(cmd, &lba, nr_blocks); if (ret) goto fail; } fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0; dix = scsi_prot_sg_count(cmd); dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type); if (dif || dix) protect = sd_setup_protect_cmnd(cmd, dix, dif); else protect = 0; if (protect && sdkp->protection_type == T10_PI_TYPE2_PROTECTION) { ret = sd_setup_rw32_cmnd(cmd, write, lba, nr_blocks, protect | fua); } else if (sdp->use_16_for_rw || (nr_blocks > 0xffff)) { ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks, protect | fua); } else if ((nr_blocks > 0xff) || (lba > 0x1fffff) || sdp->use_10_for_rw || protect) { ret = sd_setup_rw10_cmnd(cmd, write, lba, nr_blocks, protect | fua); } else { ret = sd_setup_rw6_cmnd(cmd, write, lba, nr_blocks, protect | fua); } if (unlikely(ret != BLK_STS_OK)) goto fail; /* * We shouldn't disconnect in the middle of a sector, so with a dumb * host adapter, it's safe to assume that we can at least transfer * this many bytes between each connect / disconnect. */ cmd->transfersize = sdp->sector_size; cmd->underflow = nr_blocks << 9; cmd->allowed = sdkp->max_retries; cmd->sdb.length = nr_blocks * sdp->sector_size; SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, cmd, "%s: block=%llu, count=%d\n", __func__, (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq))); SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, cmd, "%s %d/%u 512 byte blocks.\n", write ? "writing" : "reading", nr_blocks, blk_rq_sectors(rq))); /* * This indicates that the command is ready from our end to be queued. */ return BLK_STS_OK; fail: scsi_free_sgtables(cmd); return ret; } static blk_status_t sd_init_command(struct scsi_cmnd *cmd) { struct request *rq = cmd->request; switch (req_op(rq)) { case REQ_OP_DISCARD: switch (scsi_disk(rq->rq_disk)->provisioning_mode) { case SD_LBP_UNMAP: return sd_setup_unmap_cmnd(cmd); case SD_LBP_WS16: return sd_setup_write_same16_cmnd(cmd, true); case SD_LBP_WS10: return sd_setup_write_same10_cmnd(cmd, true); case SD_LBP_ZERO: return sd_setup_write_same10_cmnd(cmd, false); default: return BLK_STS_TARGET; } case REQ_OP_WRITE_ZEROES: return sd_setup_write_zeroes_cmnd(cmd); case REQ_OP_WRITE_SAME: return sd_setup_write_same_cmnd(cmd); case REQ_OP_FLUSH: return sd_setup_flush_cmnd(cmd); case REQ_OP_READ: case REQ_OP_WRITE: case REQ_OP_ZONE_APPEND: return sd_setup_read_write_cmnd(cmd); case REQ_OP_ZONE_RESET: return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, false); case REQ_OP_ZONE_RESET_ALL: return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, true); case REQ_OP_ZONE_OPEN: return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_OPEN_ZONE, false); case REQ_OP_ZONE_CLOSE: return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_CLOSE_ZONE, false); case REQ_OP_ZONE_FINISH: return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_FINISH_ZONE, false); default: WARN_ON_ONCE(1); return BLK_STS_NOTSUPP; } } static void sd_uninit_command(struct scsi_cmnd *SCpnt) { struct request *rq = SCpnt->request; u8 *cmnd; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) mempool_free(rq->special_vec.bv_page, sd_page_pool); if (SCpnt->cmnd != scsi_req(rq)->cmd) { cmnd = SCpnt->cmnd; SCpnt->cmnd = NULL; SCpnt->cmd_len = 0; mempool_free(cmnd, sd_cdb_pool); } } static bool sd_need_revalidate(struct block_device *bdev, struct scsi_disk *sdkp) { if (sdkp->device->removable || sdkp->write_prot) { if (bdev_check_media_change(bdev)) return true; } /* * Force a full rescan after ioctl(BLKRRPART). While the disk state has * nothing to do with partitions, BLKRRPART is used to force a full * revalidate after things like a format for historical reasons. */ return test_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); } /** * sd_open - open a scsi disk device * @bdev: Block device of the scsi disk to open * @mode: FMODE_* mask * * Returns 0 if successful. Returns a negated errno value in case * of error. * * Note: This can be called from a user context (e.g. fsck(1) ) * or from within the kernel (e.g. as a result of a mount(1) ). * In the latter case @inode and @filp carry an abridged amount * of information as noted above. * * Locking: called with bdev->bd_mutex held. **/ static int sd_open(struct block_device *bdev, fmode_t mode) { struct scsi_disk *sdkp = scsi_disk_get(bdev->bd_disk); struct scsi_device *sdev; int retval; if (!sdkp) return -ENXIO; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_open\n")); sdev = sdkp->device; /* * If the device is in error recovery, wait until it is done. * If the device is offline, then disallow any access to it. */ retval = -ENXIO; if (!scsi_block_when_processing_errors(sdev)) goto error_out; if (sd_need_revalidate(bdev, sdkp)) sd_revalidate_disk(bdev->bd_disk); /* * If the drive is empty, just let the open fail. */ retval = -ENOMEDIUM; if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY)) goto error_out; /* * If the device has the write protect tab set, have the open fail * if the user expects to be able to write to the thing. */ retval = -EROFS; if (sdkp->write_prot && (mode & FMODE_WRITE)) goto error_out; /* * It is possible that the disk changing stuff resulted in * the device being taken offline. If this is the case, * report this to the user, and don't pretend that the * open actually succeeded. */ retval = -ENXIO; if (!scsi_device_online(sdev)) goto error_out; if ((atomic_inc_return(&sdkp->openers) == 1) && sdev->removable) { if (scsi_block_when_processing_errors(sdev)) scsi_set_medium_removal(sdev, SCSI_REMOVAL_PREVENT); } return 0; error_out: scsi_disk_put(sdkp); return retval; } /** * sd_release - invoked when the (last) close(2) is called on this * scsi disk. * @disk: disk to release * @mode: FMODE_* mask * * Returns 0. * * Note: may block (uninterruptible) if error recovery is underway * on this disk. * * Locking: called with bdev->bd_mutex held. **/ static void sd_release(struct gendisk *disk, fmode_t mode) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_release\n")); if (atomic_dec_return(&sdkp->openers) == 0 && sdev->removable) { if (scsi_block_when_processing_errors(sdev)) scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW); } scsi_disk_put(sdkp); } static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); struct scsi_device *sdp = sdkp->device; struct Scsi_Host *host = sdp->host; sector_t capacity = logical_to_sectors(sdp, sdkp->capacity); int diskinfo[4]; /* default to most commonly used values */ diskinfo[0] = 0x40; /* 1 << 6 */ diskinfo[1] = 0x20; /* 1 << 5 */ diskinfo[2] = capacity >> 11; /* override with calculated, extended default, or driver values */ if (host->hostt->bios_param) host->hostt->bios_param(sdp, bdev, capacity, diskinfo); else scsicam_bios_param(bdev, capacity, diskinfo); geo->heads = diskinfo[0]; geo->sectors = diskinfo[1]; geo->cylinders = diskinfo[2]; return 0; } /** * sd_ioctl - process an ioctl * @bdev: target block device * @mode: FMODE_* mask * @cmd: ioctl command number * @p: this is third argument given to ioctl(2) system call. * Often contains a pointer. * * Returns 0 if successful (some ioctls return positive numbers on * success as well). Returns a negated errno value in case of error. * * Note: most ioctls are forward onto the block subsystem or further * down in the scsi subsystem. **/ static int sd_ioctl_common(struct block_device *bdev, fmode_t mode, unsigned int cmd, void __user *p) { struct gendisk *disk = bdev->bd_disk; struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; int error; SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, " "cmd=0x%x\n", disk->disk_name, cmd)); error = scsi_verify_blk_ioctl(bdev, cmd); if (error < 0) return error; /* * If we are in the middle of error recovery, don't let anyone * else try and use this device. Also, if error recovery fails, it * may try and take the device offline, in which case all further * access to the device is prohibited. */ error = scsi_ioctl_block_when_processing_errors(sdp, cmd, (mode & FMODE_NDELAY) != 0); if (error) goto out; if (is_sed_ioctl(cmd)) return sed_ioctl(sdkp->opal_dev, cmd, p); /* * Send SCSI addressing ioctls directly to mid level, send other * ioctls to block level and then onto mid level if they can't be * resolved. */ switch (cmd) { case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: error = scsi_ioctl(sdp, cmd, p); break; default: error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p); break; } out: return error; } static void set_media_not_present(struct scsi_disk *sdkp) { if (sdkp->media_present) sdkp->device->changed = 1; if (sdkp->device->removable) { sdkp->media_present = 0; sdkp->capacity = 0; } } static int media_not_present(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) { if (!scsi_sense_valid(sshdr)) return 0; /* not invoked for commands that could return deferred errors */ switch (sshdr->sense_key) { case UNIT_ATTENTION: case NOT_READY: /* medium not present */ if (sshdr->asc == 0x3A) { set_media_not_present(sdkp); return 1; } } return 0; } /** * sd_check_events - check media events * @disk: kernel device descriptor * @clearing: disk events currently being cleared * * Returns mask of DISK_EVENT_*. * * Note: this function is invoked from the block subsystem. **/ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) { struct scsi_disk *sdkp = scsi_disk_get(disk); struct scsi_device *sdp; int retval; if (!sdkp) return 0; sdp = sdkp->device; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n")); /* * If the device is offline, don't send any commands - just pretend as * if the command failed. If the device ever comes back online, we * can deal with it then. It is only because of unrecoverable errors * that we would ever take a device offline in the first place. */ if (!scsi_device_online(sdp)) { set_media_not_present(sdkp); goto out; } /* * Using TEST_UNIT_READY enables differentiation between drive with * no cartridge loaded - NOT READY, drive with changed cartridge - * UNIT ATTENTION, or with same cartridge - GOOD STATUS. * * Drives that auto spin down. eg iomega jaz 1G, will be started * by sd_spinup_disk() from sd_revalidate_disk(), which happens whenever * sd_revalidate() is called. */ if (scsi_block_when_processing_errors(sdp)) { struct scsi_sense_hdr sshdr = { 0, }; retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, sdkp->max_retries, &sshdr); /* failed to execute TUR, assume media not present */ if (host_byte(retval)) { set_media_not_present(sdkp); goto out; } if (media_not_present(sdkp, &sshdr)) goto out; } /* * For removable scsi disk we have to recognise the presence * of a disk in the drive. */ if (!sdkp->media_present) sdp->changed = 1; sdkp->media_present = 1; out: /* * sdp->changed is set under the following conditions: * * Medium present state has changed in either direction. * Device has indicated UNIT_ATTENTION. */ retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0; sdp->changed = 0; scsi_disk_put(sdkp); return retval; } static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) { int retries, res; struct scsi_device *sdp = sdkp->device; const int timeout = sdp->request_queue->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; struct scsi_sense_hdr my_sshdr; if (!scsi_device_online(sdp)) return -ENODEV; /* caller might not be interested in sense, but we need it */ if (!sshdr) sshdr = &my_sshdr; for (retries = 3; retries > 0; --retries) { unsigned char cmd[10] = { 0 }; cmd[0] = SYNCHRONIZE_CACHE; /* * Leave the rest of the command zero to indicate * flush everything. */ res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, sshdr, timeout, sdkp->max_retries, 0, RQF_PM, NULL); if (res == 0) break; } if (res) { sd_print_result(sdkp, "Synchronize Cache(10) failed", res); if (driver_byte(res) == DRIVER_SENSE) sd_print_sense_hdr(sdkp, sshdr); /* we need to evaluate the error return */ if (scsi_sense_valid(sshdr) && (sshdr->asc == 0x3a || /* medium not present */ sshdr->asc == 0x20 || /* invalid command */ (sshdr->asc == 0x74 && sshdr->ascq == 0x71))) /* drive is password locked */ /* this is no error here */ return 0; switch (host_byte(res)) { /* ignore errors due to racing a disconnection */ case DID_BAD_TARGET: case DID_NO_CONNECT: return 0; /* signal the upper layer it might try again */ case DID_BUS_BUSY: case DID_IMM_RETRY: case DID_REQUEUE: case DID_SOFT_ERROR: return -EBUSY; default: return -EIO; } } return 0; } static void sd_rescan(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret; ret = sd_revalidate_disk(sdkp->disk); revalidate_disk_size(sdkp->disk, ret == 0); } static int sd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *p = (void __user *)arg; int ret; ret = sd_ioctl_common(bdev, mode, cmd, p); if (ret != -ENOTTY) return ret; return scsi_ioctl(scsi_disk(bdev->bd_disk)->device, cmd, p); } #ifdef CONFIG_COMPAT static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { void __user *p = compat_ptr(arg); int ret; ret = sd_ioctl_common(bdev, mode, cmd, p); if (ret != -ENOTTY) return ret; return scsi_compat_ioctl(scsi_disk(bdev->bd_disk)->device, cmd, p); } #endif static char sd_pr_type(enum pr_type type) { switch (type) { case PR_WRITE_EXCLUSIVE: return 0x01; case PR_EXCLUSIVE_ACCESS: return 0x03; case PR_WRITE_EXCLUSIVE_REG_ONLY: return 0x05; case PR_EXCLUSIVE_ACCESS_REG_ONLY: return 0x06; case PR_WRITE_EXCLUSIVE_ALL_REGS: return 0x07; case PR_EXCLUSIVE_ACCESS_ALL_REGS: return 0x08; default: return 0; } }; static int sd_pr_command(struct block_device *bdev, u8 sa, u64 key, u64 sa_key, u8 type, u8 flags) { struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); struct scsi_device *sdev = sdkp->device; struct scsi_sense_hdr sshdr; int result; u8 cmd[16] = { 0, }; u8 data[24] = { 0, }; cmd[0] = PERSISTENT_RESERVE_OUT; cmd[1] = sa; cmd[2] = type; put_unaligned_be32(sizeof(data), &cmd[5]); put_unaligned_be64(key, &data[0]); put_unaligned_be64(sa_key, &data[8]); data[20] = flags; result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data), &sshdr, SD_TIMEOUT, sdkp->max_retries, NULL); if (driver_byte(result) == DRIVER_SENSE && scsi_sense_valid(&sshdr)) { sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result); scsi_print_sense_hdr(sdev, NULL, &sshdr); } return result; } static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key, u32 flags) { if (flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00, old_key, new_key, 0, (1 << 0) /* APTPL */); } static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, u32 flags) { if (flags) return -EOPNOTSUPP; return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0); } static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type) { return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0); } static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, enum pr_type type, bool abort) { return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key, sd_pr_type(type), 0); } static int sd_pr_clear(struct block_device *bdev, u64 key) { return sd_pr_command(bdev, 0x03, key, 0, 0, 0); } static const struct pr_ops sd_pr_ops = { .pr_register = sd_pr_register, .pr_reserve = sd_pr_reserve, .pr_release = sd_pr_release, .pr_preempt = sd_pr_preempt, .pr_clear = sd_pr_clear, }; static const struct block_device_operations sd_fops = { .owner = THIS_MODULE, .open = sd_open, .release = sd_release, .ioctl = sd_ioctl, .getgeo = sd_getgeo, #ifdef CONFIG_COMPAT .compat_ioctl = sd_compat_ioctl, #endif .check_events = sd_check_events, .unlock_native_capacity = sd_unlock_native_capacity, .report_zones = sd_zbc_report_zones, .pr_ops = &sd_pr_ops, }; /** * sd_eh_reset - reset error handling callback * @scmd: sd-issued command that has failed * * This function is called by the SCSI midlayer before starting * SCSI EH. When counting medium access failures we have to be * careful to register it only only once per device and SCSI EH run; * there might be several timed out commands which will cause the * 'max_medium_access_timeouts' counter to trigger after the first * SCSI EH run already and set the device to offline. * So this function resets the internal counter before starting SCSI EH. **/ static void sd_eh_reset(struct scsi_cmnd *scmd) { struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk); /* New SCSI EH run, reset gate variable */ sdkp->ignore_medium_access_errors = false; } /** * sd_eh_action - error handling callback * @scmd: sd-issued command that has failed * @eh_disp: The recovery disposition suggested by the midlayer * * This function is called by the SCSI midlayer upon completion of an * error test command (currently TEST UNIT READY). The result of sending * the eh command is passed in eh_disp. We're looking for devices that * fail medium access commands but are OK with non access commands like * test unit ready (so wrongly see the device as having a successful * recovery) **/ static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) { struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk); struct scsi_device *sdev = scmd->device; if (!scsi_device_online(sdev) || !scsi_medium_access_command(scmd) || host_byte(scmd->result) != DID_TIME_OUT || eh_disp != SUCCESS) return eh_disp; /* * The device has timed out executing a medium access command. * However, the TEST UNIT READY command sent during error * handling completed successfully. Either the device is in the * process of recovering or has it suffered an internal failure * that prevents access to the storage medium. */ if (!sdkp->ignore_medium_access_errors) { sdkp->medium_access_timed_out++; sdkp->ignore_medium_access_errors = true; } /* * If the device keeps failing read/write commands but TEST UNIT * READY always completes successfully we assume that medium * access is no longer possible and take the device offline. */ if (sdkp->medium_access_timed_out >= sdkp->max_medium_access_timeouts) { scmd_printk(KERN_ERR, scmd, "Medium access timeout failure. Offlining disk!\n"); mutex_lock(&sdev->state_mutex); scsi_device_set_state(sdev, SDEV_OFFLINE); mutex_unlock(&sdev->state_mutex); return SUCCESS; } return eh_disp; } static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) { struct request *req = scmd->request; struct scsi_device *sdev = scmd->device; unsigned int transferred, good_bytes; u64 start_lba, end_lba, bad_lba; /* * Some commands have a payload smaller than the device logical * block size (e.g. INQUIRY on a 4K disk). */ if (scsi_bufflen(scmd) <= sdev->sector_size) return 0; /* Check if we have a 'bad_lba' information */ if (!scsi_get_sense_info_fld(scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE, &bad_lba)) return 0; /* * If the bad lba was reported incorrectly, we have no idea where * the error is. */ start_lba = sectors_to_logical(sdev, blk_rq_pos(req)); end_lba = start_lba + bytes_to_logical(sdev, scsi_bufflen(scmd)); if (bad_lba < start_lba || bad_lba >= end_lba) return 0; /* * resid is optional but mostly filled in. When it's unused, * its value is zero, so we assume the whole buffer transferred */ transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd); /* This computation should always be done in terms of the * resolution of the device's medium. */ good_bytes = logical_to_bytes(sdev, bad_lba - start_lba); return min(good_bytes, transferred); } /** * sd_done - bottom half handler: called when the lower level * driver has completed (successfully or otherwise) a scsi command. * @SCpnt: mid-level's per command structure. * * Note: potentially run from within an ISR. Must not block. **/ static int sd_done(struct scsi_cmnd *SCpnt) { int result = SCpnt->result; unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt); unsigned int sector_size = SCpnt->device->sector_size; unsigned int resid; struct scsi_sense_hdr sshdr; struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk); struct request *req = SCpnt->request; int sense_valid = 0; int sense_deferred = 0; switch (req_op(req)) { case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE_SAME: case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_RESET_ALL: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: if (!result) { good_bytes = blk_rq_bytes(req); scsi_set_resid(SCpnt, 0); } else { good_bytes = 0; scsi_set_resid(SCpnt, blk_rq_bytes(req)); } break; default: /* * In case of bogus fw or device, we could end up having * an unaligned partial completion. Check this here and force * alignment. */ resid = scsi_get_resid(SCpnt); if (resid & (sector_size - 1)) { sd_printk(KERN_INFO, sdkp, "Unaligned partial completion (resid=%u, sector_sz=%u)\n", resid, sector_size); scsi_print_command(SCpnt); resid = min(scsi_bufflen(SCpnt), round_up(resid, sector_size)); scsi_set_resid(SCpnt, resid); } } if (result) { sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr); if (sense_valid) sense_deferred = scsi_sense_is_deferred(&sshdr); } sdkp->medium_access_timed_out = 0; if (driver_byte(result) != DRIVER_SENSE && (!sense_valid || sense_deferred)) goto out; switch (sshdr.sense_key) { case HARDWARE_ERROR: case MEDIUM_ERROR: good_bytes = sd_completed_bytes(SCpnt); break; case RECOVERED_ERROR: good_bytes = scsi_bufflen(SCpnt); break; case NO_SENSE: /* This indicates a false check condition, so ignore it. An * unknown amount of data was transferred so treat it as an * error. */ SCpnt->result = 0; memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); break; case ABORTED_COMMAND: if (sshdr.asc == 0x10) /* DIF: Target detected corruption */ good_bytes = sd_completed_bytes(SCpnt); break; case ILLEGAL_REQUEST: switch (sshdr.asc) { case 0x10: /* DIX: Host detected corruption */ good_bytes = sd_completed_bytes(SCpnt); break; case 0x20: /* INVALID COMMAND OPCODE */ case 0x24: /* INVALID FIELD IN CDB */ switch (SCpnt->cmnd[0]) { case UNMAP: sd_config_discard(sdkp, SD_LBP_DISABLE); break; case WRITE_SAME_16: case WRITE_SAME: if (SCpnt->cmnd[1] & 8) { /* UNMAP */ sd_config_discard(sdkp, SD_LBP_DISABLE); } else { sdkp->device->no_write_same = 1; sd_config_write_same(sdkp); req->rq_flags |= RQF_QUIET; } break; } } break; default: break; } out: if (sd_is_zoned(sdkp)) good_bytes = sd_zbc_complete(SCpnt, good_bytes, &sshdr); SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt, "sd_done: completed %d of %d bytes\n", good_bytes, scsi_bufflen(SCpnt))); return good_bytes; } /* * spinup disk - called only in sd_revalidate_disk() */ static void sd_spinup_disk(struct scsi_disk *sdkp) { unsigned char cmd[10]; unsigned long spintime_expire = 0; int retries, spintime; unsigned int the_result; struct scsi_sense_hdr sshdr; int sense_valid = 0; spintime = 0; /* Spin up drives, as required. Only do this at boot time */ /* Spinup needs to be done for module loads too. */ do { retries = 0; do { cmd[0] = TEST_UNIT_READY; memset((void *) &cmd[1], 0, 9); the_result = scsi_execute_req(sdkp->device, cmd, DMA_NONE, NULL, 0, &sshdr, SD_TIMEOUT, sdkp->max_retries, NULL); /* * If the drive has indicated to us that it * doesn't have any media in it, don't bother * with any more polling. */ if (media_not_present(sdkp, &sshdr)) return; if (the_result) sense_valid = scsi_sense_valid(&sshdr); retries++; } while (retries < 3 && (!scsi_status_is_good(the_result) || ((driver_byte(the_result) == DRIVER_SENSE) && sense_valid && sshdr.sense_key == UNIT_ATTENTION))); if (driver_byte(the_result) != DRIVER_SENSE) { /* no sense, TUR either succeeded or failed * with a status error */ if(!spintime && !scsi_status_is_good(the_result)) { sd_print_result(sdkp, "Test Unit Ready failed", the_result); } break; } /* * The device does not want the automatic start to be issued. */ if (sdkp->device->no_start_on_add) break; if (sense_valid && sshdr.sense_key == NOT_READY) { if (sshdr.asc == 4 && sshdr.ascq == 3) break; /* manual intervention required */ if (sshdr.asc == 4 && sshdr.ascq == 0xb) break; /* standby */ if (sshdr.asc == 4 && sshdr.ascq == 0xc) break; /* unavailable */ if (sshdr.asc == 4 && sshdr.ascq == 0x1b) break; /* sanitize in progress */ /* * Issue command to spin up drive when not ready */ if (!spintime) { sd_printk(KERN_NOTICE, sdkp, "Spinning up disk..."); cmd[0] = START_STOP; cmd[1] = 1; /* Return immediately */ memset((void *) &cmd[2], 0, 8); cmd[4] = 1; /* Start spin cycle */ if (sdkp->device->start_stop_pwr_cond) cmd[4] |= 1 << 4; scsi_execute_req(sdkp->device, cmd, DMA_NONE, NULL, 0, &sshdr, SD_TIMEOUT, sdkp->max_retries, NULL); spintime_expire = jiffies + 100 * HZ; spintime = 1; } /* Wait 1 second for next try */ msleep(1000); printk(KERN_CONT "."); /* * Wait for USB flash devices with slow firmware. * Yes, this sense key/ASC combination shouldn't * occur here. It's characteristic of these devices. */ } else if (sense_valid && sshdr.sense_key == UNIT_ATTENTION && sshdr.asc == 0x28) { if (!spintime) { spintime_expire = jiffies + 5 * HZ; spintime = 1; } /* Wait 1 second for next try */ msleep(1000); } else { /* we don't understand the sense code, so it's * probably pointless to loop */ if(!spintime) { sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n"); sd_print_sense_hdr(sdkp, &sshdr); } break; } } while (spintime && time_before_eq(jiffies, spintime_expire)); if (spintime) { if (scsi_status_is_good(the_result)) printk(KERN_CONT "ready\n"); else printk(KERN_CONT "not responding...\n"); } } /* * Determine whether disk supports Data Integrity Field. */ static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer) { struct scsi_device *sdp = sdkp->device; u8 type; int ret = 0; if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) { sdkp->protection_type = 0; return ret; } type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ if (type > T10_PI_TYPE3_PROTECTION) ret = -ENODEV; else if (scsi_host_dif_capable(sdp->host, type)) ret = 1; if (sdkp->first_scan || type != sdkp->protection_type) switch (ret) { case -ENODEV: sd_printk(KERN_ERR, sdkp, "formatted with unsupported" \ " protection type %u. Disabling disk!\n", type); break; case 1: sd_printk(KERN_NOTICE, sdkp, "Enabling DIF Type %u protection\n", type); break; case 0: sd_printk(KERN_NOTICE, sdkp, "Disabling DIF Type %u protection\n", type); break; } sdkp->protection_type = type; return ret; } static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, struct scsi_sense_hdr *sshdr, int sense_valid, int the_result) { if (driver_byte(the_result) == DRIVER_SENSE) sd_print_sense_hdr(sdkp, sshdr); else sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n"); /* * Set dirty bit for removable devices if not ready - * sometimes drives will not report this properly. */ if (sdp->removable && sense_valid && sshdr->sense_key == NOT_READY) set_media_not_present(sdkp); /* * We used to set media_present to 0 here to indicate no media * in the drive, but some drives fail read capacity even with * media present, so we can't do that. */ sdkp->capacity = 0; /* unknown mapped to zero - as usual */ } #define RC16_LEN 32 #if RC16_LEN > SD_BUF_SIZE #error RC16_LEN must not be more than SD_BUF_SIZE #endif #define READ_CAPACITY_RETRIES_ON_RESET 10 static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { unsigned char cmd[16]; struct scsi_sense_hdr sshdr; int sense_valid = 0; int the_result; int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET; unsigned int alignment; unsigned long long lba; unsigned sector_size; if (sdp->no_read_capacity_16) return -EINVAL; do { memset(cmd, 0, 16); cmd[0] = SERVICE_ACTION_IN_16; cmd[1] = SAI_READ_CAPACITY_16; cmd[13] = RC16_LEN; memset(buffer, 0, RC16_LEN); the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE, buffer, RC16_LEN, &sshdr, SD_TIMEOUT, sdkp->max_retries, NULL); if (media_not_present(sdkp, &sshdr)) return -ENODEV; if (the_result) { sense_valid = scsi_sense_valid(&sshdr); if (sense_valid && sshdr.sense_key == ILLEGAL_REQUEST && (sshdr.asc == 0x20 || sshdr.asc == 0x24) && sshdr.ascq == 0x00) /* Invalid Command Operation Code or * Invalid Field in CDB, just retry * silently with RC10 */ return -EINVAL; if (sense_valid && sshdr.sense_key == UNIT_ATTENTION && sshdr.asc == 0x29 && sshdr.ascq == 0x00) /* Device reset might occur several times, * give it one more chance */ if (--reset_retries > 0) continue; } retries--; } while (the_result && retries); if (the_result) { sd_print_result(sdkp, "Read Capacity(16) failed", the_result); read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result); return -EINVAL; } sector_size = get_unaligned_be32(&buffer[8]); lba = get_unaligned_be64(&buffer[0]); if (sd_read_protection_type(sdkp, buffer) < 0) { sdkp->capacity = 0; return -ENODEV; } /* Logical blocks per physical block exponent */ sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size; /* RC basis */ sdkp->rc_basis = (buffer[12] >> 4) & 0x3; /* Lowest aligned logical block */ alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size; blk_queue_alignment_offset(sdp->request_queue, alignment); if (alignment && sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "physical block alignment offset: %u\n", alignment); if (buffer[14] & 0x80) { /* LBPME */ sdkp->lbpme = 1; if (buffer[14] & 0x40) /* LBPRZ */ sdkp->lbprz = 1; sd_config_discard(sdkp, SD_LBP_WS16); } sdkp->capacity = lba + 1; return sector_size; } static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { unsigned char cmd[16]; struct scsi_sense_hdr sshdr; int sense_valid = 0; int the_result; int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET; sector_t lba; unsigned sector_size; do { cmd[0] = READ_CAPACITY; memset(&cmd[1], 0, 9); memset(buffer, 0, 8); the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE, buffer, 8, &sshdr, SD_TIMEOUT, sdkp->max_retries, NULL); if (media_not_present(sdkp, &sshdr)) return -ENODEV; if (the_result) { sense_valid = scsi_sense_valid(&sshdr); if (sense_valid && sshdr.sense_key == UNIT_ATTENTION && sshdr.asc == 0x29 && sshdr.ascq == 0x00) /* Device reset might occur several times, * give it one more chance */ if (--reset_retries > 0) continue; } retries--; } while (the_result && retries); if (the_result) { sd_print_result(sdkp, "Read Capacity(10) failed", the_result); read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result); return -EINVAL; } sector_size = get_unaligned_be32(&buffer[4]); lba = get_unaligned_be32(&buffer[0]); if (sdp->no_read_capacity_16 && (lba == 0xffffffff)) { /* Some buggy (usb cardreader) devices return an lba of 0xffffffff when the want to report a size of 0 (with which they really mean no media is present) */ sdkp->capacity = 0; sdkp->physical_block_size = sector_size; return sector_size; } sdkp->capacity = lba + 1; sdkp->physical_block_size = sector_size; return sector_size; } static int sd_try_rc16_first(struct scsi_device *sdp) { if (sdp->host->max_cmd_len < 16) return 0; if (sdp->try_rc_10_first) return 0; if (sdp->scsi_level > SCSI_SPC_2) return 1; if (scsi_device_protection(sdp)) return 1; return 0; } /* * read disk capacity */ static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) { int sector_size; struct scsi_device *sdp = sdkp->device; if (sd_try_rc16_first(sdp)) { sector_size = read_capacity_16(sdkp, sdp, buffer); if (sector_size == -EOVERFLOW) goto got_data; if (sector_size == -ENODEV) return; if (sector_size < 0) sector_size = read_capacity_10(sdkp, sdp, buffer); if (sector_size < 0) return; } else { sector_size = read_capacity_10(sdkp, sdp, buffer); if (sector_size == -EOVERFLOW) goto got_data; if (sector_size < 0) return; if ((sizeof(sdkp->capacity) > 4) && (sdkp->capacity > 0xffffffffULL)) { int old_sector_size = sector_size; sd_printk(KERN_NOTICE, sdkp, "Very big device. " "Trying to use READ CAPACITY(16).\n"); sector_size = read_capacity_16(sdkp, sdp, buffer); if (sector_size < 0) { sd_printk(KERN_NOTICE, sdkp, "Using 0xffffffff as device size\n"); sdkp->capacity = 1 + (sector_t) 0xffffffff; sector_size = old_sector_size; goto got_data; } /* Remember that READ CAPACITY(16) succeeded */ sdp->try_rc_10_first = 0; } } /* Some devices are known to return the total number of blocks, * not the highest block number. Some devices have versions * which do this and others which do not. Some devices we might * suspect of doing this but we don't know for certain. * * If we know the reported capacity is wrong, decrement it. If * we can only guess, then assume the number of blocks is even * (usually true but not always) and err on the side of lowering * the capacity. */ if (sdp->fix_capacity || (sdp->guess_capacity && (sdkp->capacity & 0x01))) { sd_printk(KERN_INFO, sdkp, "Adjusting the sector count " "from its reported value: %llu\n", (unsigned long long) sdkp->capacity); --sdkp->capacity; } got_data: if (sector_size == 0) { sector_size = 512; sd_printk(KERN_NOTICE, sdkp, "Sector size 0 reported, " "assuming 512.\n"); } if (sector_size != 512 && sector_size != 1024 && sector_size != 2048 && sector_size != 4096) { sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n", sector_size); /* * The user might want to re-format the drive with * a supported sectorsize. Once this happens, it * would be relatively trivial to set the thing up. * For this reason, we leave the thing in the table. */ sdkp->capacity = 0; /* * set a bogus sector size so the normal read/write * logic in the block layer will eventually refuse any * request on this device without tripping over power * of two sector size assumptions */ sector_size = 512; } blk_queue_logical_block_size(sdp->request_queue, sector_size); blk_queue_physical_block_size(sdp->request_queue, sdkp->physical_block_size); sdkp->device->sector_size = sector_size; if (sdkp->capacity > 0xffffffff) sdp->use_16_for_rw = 1; } /* * Print disk capacity */ static void sd_print_capacity(struct scsi_disk *sdkp, sector_t old_capacity) { int sector_size = sdkp->device->sector_size; char cap_str_2[10], cap_str_10[10]; if (!sdkp->first_scan && old_capacity == sdkp->capacity) return; string_get_size(sdkp->capacity, sector_size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); string_get_size(sdkp->capacity, sector_size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); sd_printk(KERN_NOTICE, sdkp, "%llu %d-byte logical blocks: (%s/%s)\n", (unsigned long long)sdkp->capacity, sector_size, cap_str_10, cap_str_2); if (sdkp->physical_block_size != sector_size) sd_printk(KERN_NOTICE, sdkp, "%u-byte physical blocks\n", sdkp->physical_block_size); } /* called with buffer of length 512 */ static inline int sd_do_mode_sense(struct scsi_disk *sdkp, int dbd, int modepage, unsigned char *buffer, int len, struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr) { return scsi_mode_sense(sdkp->device, dbd, modepage, buffer, len, SD_TIMEOUT, sdkp->max_retries, data, sshdr); } /* * read write protect setting, if possible - called only in sd_revalidate_disk() * called with buffer of length SD_BUF_SIZE */ static void sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) { int res; struct scsi_device *sdp = sdkp->device; struct scsi_mode_data data; int old_wp = sdkp->write_prot; set_disk_ro(sdkp->disk, 0); if (sdp->skip_ms_page_3f) { sd_first_printk(KERN_NOTICE, sdkp, "Assuming Write Enabled\n"); return; } if (sdp->use_192_bytes_for_3f) { res = sd_do_mode_sense(sdkp, 0, 0x3F, buffer, 192, &data, NULL); } else { /* * First attempt: ask for all pages (0x3F), but only 4 bytes. * We have to start carefully: some devices hang if we ask * for more than is available. */ res = sd_do_mode_sense(sdkp, 0, 0x3F, buffer, 4, &data, NULL); /* * Second attempt: ask for page 0 When only page 0 is * implemented, a request for page 3F may return Sense Key * 5: Illegal Request, Sense Code 24: Invalid field in * CDB. */ if (res < 0) res = sd_do_mode_sense(sdkp, 0, 0, buffer, 4, &data, NULL); /* * Third attempt: ask 255 bytes, as we did earlier. */ if (res < 0) res = sd_do_mode_sense(sdkp, 0, 0x3F, buffer, 255, &data, NULL); } if (res < 0) { sd_first_printk(KERN_WARNING, sdkp, "Test WP failed, assume Write Enabled\n"); } else { sdkp->write_prot = ((data.device_specific & 0x80) != 0); set_disk_ro(sdkp->disk, sdkp->write_prot); if (sdkp->first_scan || old_wp != sdkp->write_prot) { sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n", sdkp->write_prot ? "on" : "off"); sd_printk(KERN_DEBUG, sdkp, "Mode Sense: %4ph\n", buffer); } } } /* * sd_read_cache_type - called only from sd_revalidate_disk() * called with buffer of length SD_BUF_SIZE */ static void sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) { int len = 0, res; struct scsi_device *sdp = sdkp->device; int dbd; int modepage; int first_len; struct scsi_mode_data data; struct scsi_sense_hdr sshdr; int old_wce = sdkp->WCE; int old_rcd = sdkp->RCD; int old_dpofua = sdkp->DPOFUA; if (sdkp->cache_override) return; first_len = 4; if (sdp->skip_ms_page_8) { if (sdp->type == TYPE_RBC) goto defaults; else { if (sdp->skip_ms_page_3f) goto defaults; modepage = 0x3F; if (sdp->use_192_bytes_for_3f) first_len = 192; dbd = 0; } } else if (sdp->type == TYPE_RBC) { modepage = 6; dbd = 8; } else { modepage = 8; dbd = 0; } /* cautiously ask */ res = sd_do_mode_sense(sdkp, dbd, modepage, buffer, first_len, &data, &sshdr); if (res < 0) goto bad_sense; if (!data.header_length) { modepage = 6; first_len = 0; sd_first_printk(KERN_ERR, sdkp, "Missing header in MODE_SENSE response\n"); } /* that went OK, now ask for the proper length */ len = data.length; /* * We're only interested in the first three bytes, actually. * But the data cache page is defined for the first 20. */ if (len < 3) goto bad_sense; else if (len > SD_BUF_SIZE) { sd_first_printk(KERN_NOTICE, sdkp, "Truncating mode parameter " "data from %d to %d bytes\n", len, SD_BUF_SIZE); len = SD_BUF_SIZE; } if (modepage == 0x3F && sdp->use_192_bytes_for_3f) len = 192; /* Get the data */ if (len > first_len) res = sd_do_mode_sense(sdkp, dbd, modepage, buffer, len, &data, &sshdr); if (!res) { int offset = data.header_length + data.block_descriptor_length; while (offset < len) { u8 page_code = buffer[offset] & 0x3F; u8 spf = buffer[offset] & 0x40; if (page_code == 8 || page_code == 6) { /* We're interested only in the first 3 bytes. */ if (len - offset <= 2) { sd_first_printk(KERN_ERR, sdkp, "Incomplete mode parameter " "data\n"); goto defaults; } else { modepage = page_code; goto Page_found; } } else { /* Go to the next page */ if (spf && len - offset > 3) offset += 4 + (buffer[offset+2] << 8) + buffer[offset+3]; else if (!spf && len - offset > 1) offset += 2 + buffer[offset+1]; else { sd_first_printk(KERN_ERR, sdkp, "Incomplete mode " "parameter data\n"); goto defaults; } } } sd_first_printk(KERN_ERR, sdkp, "No Caching mode page found\n"); goto defaults; Page_found: if (modepage == 8) { sdkp->WCE = ((buffer[offset + 2] & 0x04) != 0); sdkp->RCD = ((buffer[offset + 2] & 0x01) != 0); } else { sdkp->WCE = ((buffer[offset + 2] & 0x01) == 0); sdkp->RCD = 0; } sdkp->DPOFUA = (data.device_specific & 0x10) != 0; if (sdp->broken_fua) { sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n"); sdkp->DPOFUA = 0; } else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw && !sdkp->device->use_16_for_rw) { sd_first_printk(KERN_NOTICE, sdkp, "Uses READ/WRITE(6), disabling FUA\n"); sdkp->DPOFUA = 0; } /* No cache flush allowed for write protected devices */ if (sdkp->WCE && sdkp->write_prot) sdkp->WCE = 0; if (sdkp->first_scan || old_wce != sdkp->WCE || old_rcd != sdkp->RCD || old_dpofua != sdkp->DPOFUA) sd_printk(KERN_NOTICE, sdkp, "Write cache: %s, read cache: %s, %s\n", sdkp->WCE ? "enabled" : "disabled", sdkp->RCD ? "disabled" : "enabled", sdkp->DPOFUA ? "supports DPO and FUA" : "doesn't support DPO or FUA"); return; } bad_sense: if (scsi_sense_valid(&sshdr) && sshdr.sense_key == ILLEGAL_REQUEST && sshdr.asc == 0x24 && sshdr.ascq == 0x0) /* Invalid field in CDB */ sd_first_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n"); else sd_first_printk(KERN_ERR, sdkp, "Asking for cache data failed\n"); defaults: if (sdp->wce_default_on) { sd_first_printk(KERN_NOTICE, sdkp, "Assuming drive cache: write back\n"); sdkp->WCE = 1; } else { sd_first_printk(KERN_ERR, sdkp, "Assuming drive cache: write through\n"); sdkp->WCE = 0; } sdkp->RCD = 0; sdkp->DPOFUA = 0; } /* * The ATO bit indicates whether the DIF application tag is available * for use by the operating system. */ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) { int res, offset; struct scsi_device *sdp = sdkp->device; struct scsi_mode_data data; struct scsi_sense_hdr sshdr; if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC) return; if (sdkp->protection_type == 0) return; res = scsi_mode_sense(sdp, 1, 0x0a, buffer, 36, SD_TIMEOUT, sdkp->max_retries, &data, &sshdr); if (res < 0 || !data.header_length || data.length < 6) { sd_first_printk(KERN_WARNING, sdkp, "getting Control mode page failed, assume no ATO\n"); if (scsi_sense_valid(&sshdr)) sd_print_sense_hdr(sdkp, &sshdr); return; } offset = data.header_length + data.block_descriptor_length; if ((buffer[offset] & 0x3f) != 0x0a) { sd_first_printk(KERN_ERR, sdkp, "ATO Got wrong page\n"); return; } if ((buffer[offset + 5] & 0x80) == 0) return; sdkp->ATO = 1; return; } /** * sd_read_block_limits - Query disk device for preferred I/O sizes. * @sdkp: disk to query */ static void sd_read_block_limits(struct scsi_disk *sdkp) { unsigned int sector_sz = sdkp->device->sector_size; const int vpd_len = 64; unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL); if (!buffer || /* Block Limits VPD */ scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len)) goto out; blk_queue_io_min(sdkp->disk->queue, get_unaligned_be16(&buffer[6]) * sector_sz); sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]); sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]); if (buffer[3] == 0x3c) { unsigned int lba_count, desc_count; sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]); if (!sdkp->lbpme) goto out; lba_count = get_unaligned_be32(&buffer[20]); desc_count = get_unaligned_be32(&buffer[24]); if (lba_count && desc_count) sdkp->max_unmap_blocks = lba_count; sdkp->unmap_granularity = get_unaligned_be32(&buffer[28]); if (buffer[32] & 0x80) sdkp->unmap_alignment = get_unaligned_be32(&buffer[32]) & ~(1 << 31); if (!sdkp->lbpvpd) { /* LBP VPD page not provided */ if (sdkp->max_unmap_blocks) sd_config_discard(sdkp, SD_LBP_UNMAP); else sd_config_discard(sdkp, SD_LBP_WS16); } else { /* LBP VPD page tells us what to use */ if (sdkp->lbpu && sdkp->max_unmap_blocks) sd_config_discard(sdkp, SD_LBP_UNMAP); else if (sdkp->lbpws) sd_config_discard(sdkp, SD_LBP_WS16); else if (sdkp->lbpws10) sd_config_discard(sdkp, SD_LBP_WS10); else sd_config_discard(sdkp, SD_LBP_DISABLE); } } out: kfree(buffer); } /** * sd_read_block_characteristics - Query block dev. characteristics * @sdkp: disk to query */ static void sd_read_block_characteristics(struct scsi_disk *sdkp) { struct request_queue *q = sdkp->disk->queue; unsigned char *buffer; u16 rot; const int vpd_len = 64; buffer = kmalloc(vpd_len, GFP_KERNEL); if (!buffer || /* Block Device Characteristics VPD */ scsi_get_vpd_page(sdkp->device, 0xb1, buffer, vpd_len)) goto out; rot = get_unaligned_be16(&buffer[4]); if (rot == 1) { blk_queue_flag_set(QUEUE_FLAG_NONROT, q); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); } if (sdkp->device->type == TYPE_ZBC) { /* Host-managed */ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM); } else { sdkp->zoned = (buffer[8] >> 4) & 3; if (sdkp->zoned == 1) { /* Host-aware */ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HA); } else { /* Regular disk or drive managed disk */ blk_queue_set_zoned(sdkp->disk, BLK_ZONED_NONE); } } if (!sdkp->first_scan) goto out; if (blk_queue_is_zoned(q)) { sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n", q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware"); } else { if (sdkp->zoned == 1) sd_printk(KERN_NOTICE, sdkp, "Host-aware SMR disk used as regular disk\n"); else if (sdkp->zoned == 2) sd_printk(KERN_NOTICE, sdkp, "Drive-managed SMR disk\n"); } out: kfree(buffer); } /** * sd_read_block_provisioning - Query provisioning VPD page * @sdkp: disk to query */ static void sd_read_block_provisioning(struct scsi_disk *sdkp) { unsigned char *buffer; const int vpd_len = 8; if (sdkp->lbpme == 0) return; buffer = kmalloc(vpd_len, GFP_KERNEL); if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb2, buffer, vpd_len)) goto out; sdkp->lbpvpd = 1; sdkp->lbpu = (buffer[5] >> 7) & 1; /* UNMAP */ sdkp->lbpws = (buffer[5] >> 6) & 1; /* WRITE SAME(16) with UNMAP */ sdkp->lbpws10 = (buffer[5] >> 5) & 1; /* WRITE SAME(10) with UNMAP */ out: kfree(buffer); } static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) { struct scsi_device *sdev = sdkp->device; if (sdev->host->no_write_same) { sdev->no_write_same = 1; return; } if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) { /* too large values might cause issues with arcmsr */ int vpd_buf_len = 64; sdev->no_report_opcodes = 1; /* Disable WRITE SAME if REPORT SUPPORTED OPERATION * CODES is unsupported and the device has an ATA * Information VPD page (SAT). */ if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len)) sdev->no_write_same = 1; } if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1) sdkp->ws16 = 1; if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1) sdkp->ws10 = 1; } static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer) { struct scsi_device *sdev = sdkp->device; if (!sdev->security_supported) return; if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, SECURITY_PROTOCOL_IN) == 1 && scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, SECURITY_PROTOCOL_OUT) == 1) sdkp->security = 1; } /* * Determine the device's preferred I/O size for reads and writes * unless the reported value is unreasonably small, large, not a * multiple of the physical block size, or simply garbage. */ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, unsigned int dev_max) { struct scsi_device *sdp = sdkp->device; unsigned int opt_xfer_bytes = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); if (sdkp->opt_xfer_blocks == 0) return false; if (sdkp->opt_xfer_blocks > dev_max) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u logical blocks " \ "> dev_max (%u logical blocks)\n", sdkp->opt_xfer_blocks, dev_max); return false; } if (sdkp->opt_xfer_blocks > SD_DEF_XFER_BLOCKS) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u logical blocks " \ "> sd driver limit (%u logical blocks)\n", sdkp->opt_xfer_blocks, SD_DEF_XFER_BLOCKS); return false; } if (opt_xfer_bytes < PAGE_SIZE) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u bytes < " \ "PAGE_SIZE (%u bytes)\n", opt_xfer_bytes, (unsigned int)PAGE_SIZE); return false; } if (opt_xfer_bytes & (sdkp->physical_block_size - 1)) { sd_first_printk(KERN_WARNING, sdkp, "Optimal transfer size %u bytes not a " \ "multiple of physical block size (%u bytes)\n", opt_xfer_bytes, sdkp->physical_block_size); return false; } sd_first_printk(KERN_INFO, sdkp, "Optimal transfer size %u bytes\n", opt_xfer_bytes); return true; } /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. * @disk: struct gendisk we care about **/ static int sd_revalidate_disk(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; struct request_queue *q = sdkp->disk->queue; sector_t old_capacity = sdkp->capacity; unsigned char *buffer; unsigned int dev_max, rw_max; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_revalidate_disk\n")); /* * If the device is offline, don't try and read capacity or any * of the other niceties. */ if (!scsi_device_online(sdp)) goto out; buffer = kmalloc(SD_BUF_SIZE, GFP_KERNEL); if (!buffer) { sd_printk(KERN_WARNING, sdkp, "sd_revalidate_disk: Memory " "allocation failure.\n"); goto out; } sd_spinup_disk(sdkp); /* * Without media there is no reason to ask; moreover, some devices * react badly if we do. */ if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); /* * set the default to rotational. All non-rotational devices * support the block characteristics VPD page, which will * cause this to be updated correctly and any device which * doesn't support it should be treated as rotational. */ blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); if (scsi_device_supports_vpd(sdp)) { sd_read_block_provisioning(sdkp); sd_read_block_limits(sdkp); sd_read_block_characteristics(sdkp); sd_zbc_read_zones(sdkp, buffer); } sd_print_capacity(sdkp, old_capacity); sd_read_write_protect_flag(sdkp, buffer); sd_read_cache_type(sdkp, buffer); sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); } /* * We now have all cache related info, determine how we deal * with flush requests. */ sd_set_flush_flag(sdkp); /* Initial block count limit based on CDB TRANSFER LENGTH field size. */ dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS; /* Some devices report a maximum block count for READ/WRITE requests. */ dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks); q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); if (sd_validate_opt_xfer_size(sdkp, dev_max)) { q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); } else { q->limits.io_opt = 0; rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), (sector_t)BLK_DEF_MAX_SECTORS); } /* Do not exceed controller limit */ rw_max = min(rw_max, queue_max_hw_sectors(q)); /* * Only update max_sectors if previously unset or if the current value * exceeds the capabilities of the hardware. */ if (sdkp->first_scan || q->limits.max_sectors > q->limits.max_dev_sectors || q->limits.max_sectors > q->limits.max_hw_sectors) q->limits.max_sectors = rw_max; sdkp->first_scan = 0; set_capacity_revalidate_and_notify(disk, logical_to_sectors(sdp, sdkp->capacity), false); sd_config_write_same(sdkp); kfree(buffer); /* * For a zoned drive, revalidating the zones can be done only once * the gendisk capacity is set. So if this fails, set back the gendisk * capacity to 0. */ if (sd_zbc_revalidate_zones(sdkp)) set_capacity_revalidate_and_notify(disk, 0, false); out: return 0; } /** * sd_unlock_native_capacity - unlock native capacity * @disk: struct gendisk to set capacity for * * Block layer calls this function if it detects that partitions * on @disk reach beyond the end of the device. If the SCSI host * implements ->unlock_native_capacity() method, it's invoked to * give it a chance to adjust the device capacity. * * CONTEXT: * Defined by block layer. Might sleep. */ static void sd_unlock_native_capacity(struct gendisk *disk) { struct scsi_device *sdev = scsi_disk(disk)->device; if (sdev->host->hostt->unlock_native_capacity) sdev->host->hostt->unlock_native_capacity(sdev); } /** * sd_format_disk_name - format disk name * @prefix: name prefix - ie. "sd" for SCSI disks * @index: index of the disk to format name for * @buf: output buffer * @buflen: length of the output buffer * * SCSI disk names starts at sda. The 26th device is sdz and the * 27th is sdaa. The last one for two lettered suffix is sdzz * which is followed by sdaaa. * * This is basically 26 base counting with one extra 'nil' entry * at the beginning from the second digit on and can be * determined using similar method as 26 base conversion with the * index shifted -1 after each digit is computed. * * CONTEXT: * Don't care. * * RETURNS: * 0 on success, -errno on failure. */ static int sd_format_disk_name(char *prefix, int index, char *buf, int buflen) { const int base = 'z' - 'a' + 1; char *begin = buf + strlen(prefix); char *end = buf + buflen; char *p; int unit; p = end - 1; *p = '\0'; unit = base; do { if (p == begin) return -EINVAL; *--p = 'a' + (index % unit); index = (index / unit) - 1; } while (index >= 0); memmove(begin, p, end - p); memcpy(buf, prefix, strlen(prefix)); return 0; } /** * sd_probe - called during driver initialization and whenever a * new scsi device is attached to the system. It is called once * for each scsi device (not just disks) present. * @dev: pointer to device object * * Returns 0 if successful (or not interested in this scsi device * (e.g. scanner)); 1 when there is an error. * * Note: this function is invoked from the scsi mid-level. * This function sets up the mapping between a given * <host,channel,id,lun> (found in sdp) and new device name * (e.g. /dev/sda). More precisely it is the block device major * and minor number that is chosen here. * * Assume sd_probe is not re-entrant (for time being) * Also think about sd_probe() and sd_remove() running coincidentally. **/ static int sd_probe(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); struct scsi_disk *sdkp; struct gendisk *gd; int index; int error; scsi_autopm_get_device(sdp); error = -ENODEV; if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC && sdp->type != TYPE_MOD && sdp->type != TYPE_RBC) goto out; #ifndef CONFIG_BLK_DEV_ZONED if (sdp->type == TYPE_ZBC) goto out; #endif SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp, "sd_probe\n")); error = -ENOMEM; sdkp = kzalloc(sizeof(*sdkp), GFP_KERNEL); if (!sdkp) goto out; gd = alloc_disk(SD_MINORS); if (!gd) goto out_free; index = ida_alloc(&sd_index_ida, GFP_KERNEL); if (index < 0) { sdev_printk(KERN_WARNING, sdp, "sd_probe: memory exhausted.\n"); goto out_put; } error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN); if (error) { sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n"); goto out_free_index; } sdkp->device = sdp; sdkp->driver = &sd_template; sdkp->disk = gd; sdkp->index = index; sdkp->max_retries = SD_MAX_RETRIES; atomic_set(&sdkp->openers, 0); atomic_set(&sdkp->device->ioerr_cnt, 0); if (!sdp->request_queue->rq_timeout) { if (sdp->type != TYPE_MOD) blk_queue_rq_timeout(sdp->request_queue, SD_TIMEOUT); else blk_queue_rq_timeout(sdp->request_queue, SD_MOD_TIMEOUT); } device_initialize(&sdkp->dev); sdkp->dev.parent = get_device(dev); sdkp->dev.class = &sd_disk_class; dev_set_name(&sdkp->dev, "%s", dev_name(dev)); error = device_add(&sdkp->dev); if (error) { put_device(&sdkp->dev); goto out; } dev_set_drvdata(dev, sdkp); gd->major = sd_major((index & 0xf0) >> 4); gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00); gd->fops = &sd_fops; gd->private_data = &sdkp->driver; gd->queue = sdkp->device->request_queue; /* defaults, until the device tells us otherwise */ sdp->sector_size = 512; sdkp->capacity = 0; sdkp->media_present = 1; sdkp->write_prot = 0; sdkp->cache_override = 0; sdkp->WCE = 0; sdkp->RCD = 0; sdkp->ATO = 0; sdkp->first_scan = 1; sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS; sd_revalidate_disk(gd); gd->flags = GENHD_FL_EXT_DEVT; if (sdp->removable) { gd->flags |= GENHD_FL_REMOVABLE; gd->events |= DISK_EVENT_MEDIA_CHANGE; gd->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; } blk_pm_runtime_init(sdp->request_queue, dev); if (sdp->rpm_autosuspend) { pm_runtime_set_autosuspend_delay(dev, sdp->host->hostt->rpm_autosuspend_delay); } device_add_disk(dev, gd, NULL); if (sdkp->capacity) sd_dif_config_host(sdkp); sd_revalidate_disk(gd); if (sdkp->security) { sdkp->opal_dev = init_opal_dev(sdkp, &sd_sec_submit); if (sdkp->opal_dev) sd_printk(KERN_NOTICE, sdkp, "supports TCG Opal\n"); } sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", sdp->removable ? "removable " : ""); scsi_autopm_put_device(sdp); return 0; out_free_index: ida_free(&sd_index_ida, index); out_put: put_disk(gd); out_free: kfree(sdkp); out: scsi_autopm_put_device(sdp); return error; } /** * sd_remove - called whenever a scsi disk (previously recognized by * sd_probe) is detached from the system. It is called (potentially * multiple times) during sd module unload. * @dev: pointer to device object * * Note: this function is invoked from the scsi mid-level. * This function potentially frees up a device name (e.g. /dev/sdc) * that could be re-used by a subsequent sd_probe(). * This function is not called when the built-in sd driver is "exit-ed". **/ static int sd_remove(struct device *dev) { struct scsi_disk *sdkp; dev_t devt; sdkp = dev_get_drvdata(dev); devt = disk_devt(sdkp->disk); scsi_autopm_get_device(sdkp->device); async_synchronize_full_domain(&scsi_sd_pm_domain); device_del(&sdkp->dev); del_gendisk(sdkp->disk); sd_shutdown(dev); free_opal_dev(sdkp->opal_dev); blk_register_region(devt, SD_MINORS, NULL, sd_default_probe, NULL, NULL); mutex_lock(&sd_ref_mutex); dev_set_drvdata(dev, NULL); put_device(&sdkp->dev); mutex_unlock(&sd_ref_mutex); return 0; } /** * scsi_disk_release - Called to free the scsi_disk structure * @dev: pointer to embedded class device * * sd_ref_mutex must be held entering this routine. Because it is * called on last put, you should always use the scsi_disk_get() * scsi_disk_put() helpers which manipulate the semaphore directly * and never do a direct put_device. **/ static void scsi_disk_release(struct device *dev) { struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; struct request_queue *q = disk->queue; ida_free(&sd_index_ida, sdkp->index); /* * Wait until all requests that are in progress have completed. * This is necessary to avoid that e.g. scsi_end_request() crashes * due to clearing the disk->private_data pointer. Wait from inside * scsi_disk_release() instead of from sd_release() to avoid that * freezing and unfreezing the request queue affects user space I/O * in case multiple processes open a /dev/sd... node concurrently. */ blk_mq_freeze_queue(q); blk_mq_unfreeze_queue(q); disk->private_data = NULL; put_disk(disk); put_device(&sdkp->device->sdev_gendev); sd_zbc_release_disk(sdkp); kfree(sdkp); } static int sd_start_stop_device(struct scsi_disk *sdkp, int start) { unsigned char cmd[6] = { START_STOP }; /* START_VALID */ struct scsi_sense_hdr sshdr; struct scsi_device *sdp = sdkp->device; int res; if (start) cmd[4] |= 1; /* START */ if (sdp->start_stop_pwr_cond) cmd[4] |= start ? 1 << 4 : 3 << 4; /* Active or Standby */ if (!scsi_device_online(sdp)) return -ENODEV; res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, SD_TIMEOUT, sdkp->max_retries, 0, RQF_PM, NULL); if (res) { sd_print_result(sdkp, "Start/Stop Unit failed", res); if (driver_byte(res) == DRIVER_SENSE) sd_print_sense_hdr(sdkp, &sshdr); if (scsi_sense_valid(&sshdr) && /* 0x3a is medium not present */ sshdr.asc == 0x3a) res = 0; } /* SCSI error codes must not go to the generic layer */ if (res) return -EIO; return 0; } /* * Send a SYNCHRONIZE CACHE instruction down to the device through * the normal SCSI command structure. Wait for the command to * complete. */ static void sd_shutdown(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); if (!sdkp) return; /* this can happen */ if (pm_runtime_suspended(dev)) return; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); sd_sync_cache(sdkp, NULL); } if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) { sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } } static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) { struct scsi_disk *sdkp = dev_get_drvdata(dev); struct scsi_sense_hdr sshdr; int ret = 0; if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ return 0; if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); ret = sd_sync_cache(sdkp, &sshdr); if (ret) { /* ignore OFFLINE device */ if (ret == -ENODEV) return 0; if (!scsi_sense_valid(&sshdr) || sshdr.sense_key != ILLEGAL_REQUEST) return ret; /* * sshdr.sense_key == ILLEGAL_REQUEST means this drive * doesn't support sync. There's not much to do and * suspend shouldn't fail. */ ret = 0; } } if (sdkp->device->manage_start_stop) { sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); /* an error is not worth aborting a system sleep */ ret = sd_start_stop_device(sdkp, 0); if (ignore_stop_errors) ret = 0; } return ret; } static int sd_suspend_system(struct device *dev) { return sd_suspend_common(dev, true); } static int sd_suspend_runtime(struct device *dev) { return sd_suspend_common(dev, false); } static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; if (!sdkp->device->manage_start_stop) return 0; sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); if (!ret) opal_unlock_from_suspend(sdkp->opal_dev); return ret; } /** * init_sd - entry point for this driver (both when built in or when * a module). * * Note: this function registers this driver with the scsi mid-level. **/ static int __init init_sd(void) { int majors = 0, i, err; SCSI_LOG_HLQUEUE(3, printk("init_sd: sd driver entry point\n")); for (i = 0; i < SD_MAJORS; i++) { if (register_blkdev(sd_major(i), "sd") != 0) continue; majors++; blk_register_region(sd_major(i), SD_MINORS, NULL, sd_default_probe, NULL, NULL); } if (!majors) return -ENODEV; err = class_register(&sd_disk_class); if (err) goto err_out; sd_cdb_cache = kmem_cache_create("sd_ext_cdb", SD_EXT_CDB_SIZE, 0, 0, NULL); if (!sd_cdb_cache) { printk(KERN_ERR "sd: can't init extended cdb cache\n"); err = -ENOMEM; goto err_out_class; } sd_cdb_pool = mempool_create_slab_pool(SD_MEMPOOL_SIZE, sd_cdb_cache); if (!sd_cdb_pool) { printk(KERN_ERR "sd: can't init extended cdb pool\n"); err = -ENOMEM; goto err_out_cache; } sd_page_pool = mempool_create_page_pool(SD_MEMPOOL_SIZE, 0); if (!sd_page_pool) { printk(KERN_ERR "sd: can't init discard page pool\n"); err = -ENOMEM; goto err_out_ppool; } err = scsi_register_driver(&sd_template.gendrv); if (err) goto err_out_driver; return 0; err_out_driver: mempool_destroy(sd_page_pool); err_out_ppool: mempool_destroy(sd_cdb_pool); err_out_cache: kmem_cache_destroy(sd_cdb_cache); err_out_class: class_unregister(&sd_disk_class); err_out: for (i = 0; i < SD_MAJORS; i++) unregister_blkdev(sd_major(i), "sd"); return err; } /** * exit_sd - exit point for this driver (when it is a module). * * Note: this function unregisters this driver from the scsi mid-level. **/ static void __exit exit_sd(void) { int i; SCSI_LOG_HLQUEUE(3, printk("exit_sd: exiting sd driver\n")); scsi_unregister_driver(&sd_template.gendrv); mempool_destroy(sd_cdb_pool); mempool_destroy(sd_page_pool); kmem_cache_destroy(sd_cdb_cache); class_unregister(&sd_disk_class); for (i = 0; i < SD_MAJORS; i++) { blk_unregister_region(sd_major(i), SD_MINORS); unregister_blkdev(sd_major(i), "sd"); } } module_init(init_sd); module_exit(exit_sd); void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) { scsi_print_sense_hdr(sdkp->device, sdkp->disk ? sdkp->disk->disk_name : NULL, sshdr); } void sd_print_result(const struct scsi_disk *sdkp, const char *msg, int result) { const char *hb_string = scsi_hostbyte_string(result); const char *db_string = scsi_driverbyte_string(result); if (hb_string || db_string) sd_printk(KERN_INFO, sdkp, "%s: Result: hostbyte=%s driverbyte=%s\n", msg, hb_string ? hb_string : "invalid", db_string ? db_string : "invalid"); else sd_printk(KERN_INFO, sdkp, "%s: Result: hostbyte=0x%02x driverbyte=0x%02x\n", msg, host_byte(result), driver_byte(result)); } |
| 845 14 29 55 118 66 3 18 42 92 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 | /* * net/tipc/trace.h: TIPC tracepoints * * Copyright (c) 2018, 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 "ASIS" * 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. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM tipc #if !defined(_TIPC_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TIPC_TRACE_H #include <linux/tracepoint.h> #include "core.h" #include "link.h" #include "socket.h" #include "node.h" #define SKB_LMIN (100) #define SKB_LMAX (SKB_LMIN * 2) #define LIST_LMIN (SKB_LMIN * 3) #define LIST_LMAX (SKB_LMIN * 11) #define SK_LMIN (SKB_LMIN * 2) #define SK_LMAX (SKB_LMIN * 11) #define LINK_LMIN (SKB_LMIN) #define LINK_LMAX (SKB_LMIN * 16) #define NODE_LMIN (SKB_LMIN) #define NODE_LMAX (SKB_LMIN * 11) #ifndef __TIPC_TRACE_ENUM #define __TIPC_TRACE_ENUM enum { TIPC_DUMP_NONE = 0, TIPC_DUMP_TRANSMQ = 1, TIPC_DUMP_BACKLOGQ = (1 << 1), TIPC_DUMP_DEFERDQ = (1 << 2), TIPC_DUMP_INPUTQ = (1 << 3), TIPC_DUMP_WAKEUP = (1 << 4), TIPC_DUMP_SK_SNDQ = (1 << 8), TIPC_DUMP_SK_RCVQ = (1 << 9), TIPC_DUMP_SK_BKLGQ = (1 << 10), TIPC_DUMP_ALL = 0xffffu }; #endif /* Link & Node FSM states: */ #define state_sym(val) \ __print_symbolic(val, \ {(0xe), "ESTABLISHED" },\ {(0xe << 4), "ESTABLISHING" },\ {(0x1 << 8), "RESET" },\ {(0x2 << 12), "RESETTING" },\ {(0xd << 16), "PEER_RESET" },\ {(0xf << 20), "FAILINGOVER" },\ {(0xc << 24), "SYNCHING" },\ {(0xdd), "SELF_DOWN_PEER_DOWN" },\ {(0xaa), "SELF_UP_PEER_UP" },\ {(0xd1), "SELF_DOWN_PEER_LEAVING" },\ {(0xac), "SELF_UP_PEER_COMING" },\ {(0xca), "SELF_COMING_PEER_UP" },\ {(0x1d), "SELF_LEAVING_PEER_DOWN" },\ {(0xf0), "FAILINGOVER" },\ {(0xcc), "SYNCHING" }) /* Link & Node FSM events: */ #define evt_sym(val) \ __print_symbolic(val, \ {(0xec1ab1e), "ESTABLISH_EVT" },\ {(0x9eed0e), "PEER_RESET_EVT" },\ {(0xfa110e), "FAILURE_EVT" },\ {(0x10ca1d0e), "RESET_EVT" },\ {(0xfa110bee), "FAILOVER_BEGIN_EVT" },\ {(0xfa110ede), "FAILOVER_END_EVT" },\ {(0xc1ccbee), "SYNCH_BEGIN_EVT" },\ {(0xc1ccede), "SYNCH_END_EVT" },\ {(0xece), "SELF_ESTABL_CONTACT_EVT" },\ {(0x1ce), "SELF_LOST_CONTACT_EVT" },\ {(0x9ece), "PEER_ESTABL_CONTACT_EVT" },\ {(0x91ce), "PEER_LOST_CONTACT_EVT" },\ {(0xfbe), "FAILOVER_BEGIN_EVT" },\ {(0xfee), "FAILOVER_END_EVT" },\ {(0xcbe), "SYNCH_BEGIN_EVT" },\ {(0xcee), "SYNCH_END_EVT" }) /* Bearer, net device events: */ #define dev_evt_sym(val) \ __print_symbolic(val, \ {(NETDEV_CHANGE), "NETDEV_CHANGE" },\ {(NETDEV_GOING_DOWN), "NETDEV_GOING_DOWN" },\ {(NETDEV_UP), "NETDEV_UP" },\ {(NETDEV_CHANGEMTU), "NETDEV_CHANGEMTU" },\ {(NETDEV_CHANGEADDR), "NETDEV_CHANGEADDR" },\ {(NETDEV_UNREGISTER), "NETDEV_UNREGISTER" },\ {(NETDEV_CHANGENAME), "NETDEV_CHANGENAME" }) extern unsigned long sysctl_tipc_sk_filter[5] __read_mostly; int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf); int tipc_list_dump(struct sk_buff_head *list, bool more, char *buf); int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf); int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf); int tipc_node_dump(struct tipc_node *n, bool more, char *buf); bool tipc_sk_filtering(struct sock *sk); DECLARE_EVENT_CLASS(tipc_skb_class, TP_PROTO(struct sk_buff *skb, bool more, const char *header), TP_ARGS(skb, more, header), TP_STRUCT__entry( __string(header, header) __dynamic_array(char, buf, (more) ? SKB_LMAX : SKB_LMIN) ), TP_fast_assign( __assign_str(header, header); tipc_skb_dump(skb, more, __get_str(buf)); ), TP_printk("%s\n%s", __get_str(header), __get_str(buf)) ) #define DEFINE_SKB_EVENT(name) \ DEFINE_EVENT(tipc_skb_class, name, \ TP_PROTO(struct sk_buff *skb, bool more, const char *header), \ TP_ARGS(skb, more, header)) DEFINE_SKB_EVENT(tipc_skb_dump); DEFINE_SKB_EVENT(tipc_proto_build); DEFINE_SKB_EVENT(tipc_proto_rcv); DECLARE_EVENT_CLASS(tipc_list_class, TP_PROTO(struct sk_buff_head *list, bool more, const char *header), TP_ARGS(list, more, header), TP_STRUCT__entry( __string(header, header) __dynamic_array(char, buf, (more) ? LIST_LMAX : LIST_LMIN) ), TP_fast_assign( __assign_str(header, header); tipc_list_dump(list, more, __get_str(buf)); ), TP_printk("%s\n%s", __get_str(header), __get_str(buf)) ); #define DEFINE_LIST_EVENT(name) \ DEFINE_EVENT(tipc_list_class, name, \ TP_PROTO(struct sk_buff_head *list, bool more, const char *header), \ TP_ARGS(list, more, header)) DEFINE_LIST_EVENT(tipc_list_dump); DECLARE_EVENT_CLASS(tipc_sk_class, TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, const char *header), TP_ARGS(sk, skb, dqueues, header), TP_STRUCT__entry( __string(header, header) __field(u32, portid) __dynamic_array(char, buf, (dqueues) ? SK_LMAX : SK_LMIN) __dynamic_array(char, skb_buf, (skb) ? SKB_LMIN : 1) ), TP_fast_assign( __assign_str(header, header); __entry->portid = tipc_sock_get_portid(sk); tipc_sk_dump(sk, dqueues, __get_str(buf)); if (skb) tipc_skb_dump(skb, false, __get_str(skb_buf)); else *(__get_str(skb_buf)) = '\0'; ), TP_printk("<%u> %s\n%s%s", __entry->portid, __get_str(header), __get_str(skb_buf), __get_str(buf)) ); #define DEFINE_SK_EVENT_FILTER(name) \ DEFINE_EVENT_CONDITION(tipc_sk_class, name, \ TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \ const char *header), \ TP_ARGS(sk, skb, dqueues, header), \ TP_CONDITION(tipc_sk_filtering(sk))) DEFINE_SK_EVENT_FILTER(tipc_sk_dump); DEFINE_SK_EVENT_FILTER(tipc_sk_create); DEFINE_SK_EVENT_FILTER(tipc_sk_sendmcast); DEFINE_SK_EVENT_FILTER(tipc_sk_sendmsg); DEFINE_SK_EVENT_FILTER(tipc_sk_sendstream); DEFINE_SK_EVENT_FILTER(tipc_sk_poll); DEFINE_SK_EVENT_FILTER(tipc_sk_filter_rcv); DEFINE_SK_EVENT_FILTER(tipc_sk_advance_rx); DEFINE_SK_EVENT_FILTER(tipc_sk_rej_msg); DEFINE_SK_EVENT_FILTER(tipc_sk_drop_msg); DEFINE_SK_EVENT_FILTER(tipc_sk_release); DEFINE_SK_EVENT_FILTER(tipc_sk_shutdown); #define DEFINE_SK_EVENT_FILTER_COND(name, cond) \ DEFINE_EVENT_CONDITION(tipc_sk_class, name, \ TP_PROTO(struct sock *sk, struct sk_buff *skb, u16 dqueues, \ const char *header), \ TP_ARGS(sk, skb, dqueues, header), \ TP_CONDITION(tipc_sk_filtering(sk) && (cond))) DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit1, tipc_sk_overlimit1(sk, skb)); DEFINE_SK_EVENT_FILTER_COND(tipc_sk_overlimit2, tipc_sk_overlimit2(sk, skb)); DECLARE_EVENT_CLASS(tipc_link_class, TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), TP_ARGS(l, dqueues, header), TP_STRUCT__entry( __string(header, header) __array(char, name, TIPC_MAX_LINK_NAME) __dynamic_array(char, buf, (dqueues) ? LINK_LMAX : LINK_LMIN) ), TP_fast_assign( __assign_str(header, header); memcpy(__entry->name, tipc_link_name(l), TIPC_MAX_LINK_NAME); tipc_link_dump(l, dqueues, __get_str(buf)); ), TP_printk("<%s> %s\n%s", __entry->name, __get_str(header), __get_str(buf)) ); #define DEFINE_LINK_EVENT(name) \ DEFINE_EVENT(tipc_link_class, name, \ TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \ TP_ARGS(l, dqueues, header)) DEFINE_LINK_EVENT(tipc_link_dump); DEFINE_LINK_EVENT(tipc_link_conges); DEFINE_LINK_EVENT(tipc_link_timeout); DEFINE_LINK_EVENT(tipc_link_reset); #define DEFINE_LINK_EVENT_COND(name, cond) \ DEFINE_EVENT_CONDITION(tipc_link_class, name, \ TP_PROTO(struct tipc_link *l, u16 dqueues, const char *header), \ TP_ARGS(l, dqueues, header), \ TP_CONDITION(cond)) DEFINE_LINK_EVENT_COND(tipc_link_too_silent, tipc_link_too_silent(l)); DECLARE_EVENT_CLASS(tipc_link_transmq_class, TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq), TP_ARGS(r, f, t, tq), TP_STRUCT__entry( __array(char, name, TIPC_MAX_LINK_NAME) __field(u16, from) __field(u16, to) __field(u32, len) __field(u16, fseqno) __field(u16, lseqno) ), TP_fast_assign( memcpy(__entry->name, tipc_link_name(r), TIPC_MAX_LINK_NAME); __entry->from = f; __entry->to = t; __entry->len = skb_queue_len(tq); __entry->fseqno = __entry->len ? msg_seqno(buf_msg(skb_peek(tq))) : 0; __entry->lseqno = __entry->len ? msg_seqno(buf_msg(skb_peek_tail(tq))) : 0; ), TP_printk("<%s> retrans req: [%u-%u] transmq: %u [%u-%u]\n", __entry->name, __entry->from, __entry->to, __entry->len, __entry->fseqno, __entry->lseqno) ); DEFINE_EVENT_CONDITION(tipc_link_transmq_class, tipc_link_retrans, TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq), TP_ARGS(r, f, t, tq), TP_CONDITION(less_eq(f, t)) ); DEFINE_EVENT_PRINT(tipc_link_transmq_class, tipc_link_bc_ack, TP_PROTO(struct tipc_link *r, u16 f, u16 t, struct sk_buff_head *tq), TP_ARGS(r, f, t, tq), TP_printk("<%s> acked: %u gap: %u transmq: %u [%u-%u]\n", __entry->name, __entry->from, __entry->to, __entry->len, __entry->fseqno, __entry->lseqno) ); DECLARE_EVENT_CLASS(tipc_node_class, TP_PROTO(struct tipc_node *n, bool more, const char *header), TP_ARGS(n, more, header), TP_STRUCT__entry( __string(header, header) __field(u32, addr) __dynamic_array(char, buf, (more) ? NODE_LMAX : NODE_LMIN) ), TP_fast_assign( __assign_str(header, header); __entry->addr = tipc_node_get_addr(n); tipc_node_dump(n, more, __get_str(buf)); ), TP_printk("<%x> %s\n%s", __entry->addr, __get_str(header), __get_str(buf)) ); #define DEFINE_NODE_EVENT(name) \ DEFINE_EVENT(tipc_node_class, name, \ TP_PROTO(struct tipc_node *n, bool more, const char *header), \ TP_ARGS(n, more, header)) DEFINE_NODE_EVENT(tipc_node_dump); DEFINE_NODE_EVENT(tipc_node_create); DEFINE_NODE_EVENT(tipc_node_delete); DEFINE_NODE_EVENT(tipc_node_lost_contact); DEFINE_NODE_EVENT(tipc_node_timeout); DEFINE_NODE_EVENT(tipc_node_link_up); DEFINE_NODE_EVENT(tipc_node_link_down); DEFINE_NODE_EVENT(tipc_node_reset_links); DEFINE_NODE_EVENT(tipc_node_check_state); DECLARE_EVENT_CLASS(tipc_fsm_class, TP_PROTO(const char *name, u32 os, u32 ns, int evt), TP_ARGS(name, os, ns, evt), TP_STRUCT__entry( __string(name, name) __field(u32, os) __field(u32, ns) __field(u32, evt) ), TP_fast_assign( __assign_str(name, name); __entry->os = os; __entry->ns = ns; __entry->evt = evt; ), TP_printk("<%s> %s--(%s)->%s\n", __get_str(name), state_sym(__entry->os), evt_sym(__entry->evt), state_sym(__entry->ns)) ); #define DEFINE_FSM_EVENT(fsm_name) \ DEFINE_EVENT(tipc_fsm_class, fsm_name, \ TP_PROTO(const char *name, u32 os, u32 ns, int evt), \ TP_ARGS(name, os, ns, evt)) DEFINE_FSM_EVENT(tipc_link_fsm); DEFINE_FSM_EVENT(tipc_node_fsm); TRACE_EVENT(tipc_l2_device_event, TP_PROTO(struct net_device *dev, struct tipc_bearer *b, unsigned long evt), TP_ARGS(dev, b, evt), TP_STRUCT__entry( __string(dev_name, dev->name) __string(b_name, b->name) __field(unsigned long, evt) __field(u8, b_up) __field(u8, carrier) __field(u8, oper) ), TP_fast_assign( __assign_str(dev_name, dev->name); __assign_str(b_name, b->name); __entry->evt = evt; __entry->b_up = test_bit(0, &b->up); __entry->carrier = netif_carrier_ok(dev); __entry->oper = netif_oper_up(dev); ), TP_printk("%s on: <%s>/<%s> oper: %s carrier: %s bearer: %s\n", dev_evt_sym(__entry->evt), __get_str(dev_name), __get_str(b_name), (__entry->oper) ? "up" : "down", (__entry->carrier) ? "ok" : "notok", (__entry->b_up) ? "up" : "down") ); #endif /* _TIPC_TRACE_H */ /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 409 673 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_MQ_SCHED_H #define BLK_MQ_SCHED_H #include "blk-mq.h" #include "blk-mq-tag.h" void blk_mq_sched_assign_ioc(struct request *rq); void blk_mq_sched_request_inserted(struct request *rq); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs); bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_insert_request(struct request *rq, bool at_head, bool run_queue, bool async); void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list, bool run_queue_async); void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx); int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e); void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e); void blk_mq_sched_free_requests(struct request_queue *q); static inline bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { if (blk_queue_nomerges(q) || !bio_mergeable(bio)) return false; return __blk_mq_sched_bio_merge(q, bio, nr_segs); } static inline bool blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { struct elevator_queue *e = q->elevator; if (e && e->type->ops.allow_merge) return e->type->ops.allow_merge(q, rq, bio); return true; } static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) { struct elevator_queue *e = rq->q->elevator; if (e && e->type->ops.completed_request) e->type->ops.completed_request(rq, now); } static inline void blk_mq_sched_requeue_request(struct request *rq) { struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request) e->type->ops.requeue_request(rq); } static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx) { struct elevator_queue *e = hctx->queue->elevator; if (e && e->type->ops.has_work) return e->type->ops.has_work(hctx); return false; } static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx) { return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } #endif |
| 1938 1940 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BH_H #define _LINUX_BH_H #include <linux/preempt.h> #ifdef CONFIG_TRACE_IRQFLAGS extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); #else static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { preempt_count_add(cnt); barrier(); } #endif static inline void local_bh_disable(void) { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } extern void _local_bh_enable(void); extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt); static inline void local_bh_enable_ip(unsigned long ip) { __local_bh_enable_ip(ip, SOFTIRQ_DISABLE_OFFSET); } static inline void local_bh_enable(void) { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); } #endif /* _LINUX_BH_H */ |
| 19 1 16 20 20 20 2 16 1 15 15 8 12 16 16 16 20 20 20 18 2 14 14 21 14 1 14 18 18 25 14 20 14 14 22 1 1 20 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 | // SPDX-License-Identifier: GPL-2.0 /* * uprobes-based tracing events * * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ #define pr_fmt(fmt) "trace_uprobe: " fmt #include <linux/security.h> #include <linux/ctype.h> #include <linux/module.h> #include <linux/uaccess.h> #include <linux/uprobes.h> #include <linux/namei.h> #include <linux/string.h> #include <linux/rculist.h> #include "trace_dynevent.h" #include "trace_probe.h" #include "trace_probe_tmpl.h" #define UPROBE_EVENT_SYSTEM "uprobes" struct uprobe_trace_entry_head { struct trace_entry ent; unsigned long vaddr[]; }; #define SIZEOF_TRACE_ENTRY(is_return) \ (sizeof(struct uprobe_trace_entry_head) + \ sizeof(unsigned long) * (is_return ? 2 : 1)) #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) static int trace_uprobe_create(int argc, const char **argv); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); static bool trace_uprobe_is_busy(struct dyn_event *ev); static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations trace_uprobe_ops = { .create = trace_uprobe_create, .show = trace_uprobe_show, .is_busy = trace_uprobe_is_busy, .free = trace_uprobe_release, .match = trace_uprobe_match, }; /* * uprobe event core functions */ struct trace_uprobe { struct dyn_event devent; struct uprobe_consumer consumer; struct path path; struct inode *inode; char *filename; unsigned long offset; unsigned long ref_ctr_offset; unsigned long nhit; struct trace_probe tp; }; static bool is_trace_uprobe(struct dyn_event *ev) { return ev->ops == &trace_uprobe_ops; } static struct trace_uprobe *to_trace_uprobe(struct dyn_event *ev) { return container_of(ev, struct trace_uprobe, devent); } /** * for_each_trace_uprobe - iterate over the trace_uprobe list * @pos: the struct trace_uprobe * for each entry * @dpos: the struct dyn_event * to use as a loop cursor */ #define for_each_trace_uprobe(pos, dpos) \ for_each_dyn_event(dpos) \ if (is_trace_uprobe(dpos) && (pos = to_trace_uprobe(dpos))) #define SIZEOF_TRACE_UPROBE(n) \ (offsetof(struct trace_uprobe, tp.args) + \ (sizeof(struct probe_arg) * (n))) static int register_uprobe_event(struct trace_uprobe *tu); static int unregister_uprobe_event(struct trace_uprobe *tu); struct uprobe_dispatch_data { struct trace_uprobe *tu; unsigned long bp_addr; }; static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs); static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs); #ifdef CONFIG_STACK_GROWSUP static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr - (n * sizeof(long)); } #else static unsigned long adjust_stack_addr(unsigned long addr, unsigned int n) { return addr + (n * sizeof(long)); } #endif static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long ret; unsigned long addr = user_stack_pointer(regs); addr = adjust_stack_addr(addr, n); if (copy_from_user(&ret, (void __force __user *) addr, sizeof(ret))) return 0; return ret; } /* * Uprobes-specific fetch functions */ static nokprobe_inline int probe_mem_read(void *dest, void *src, size_t size) { void __user *vaddr = (void __force __user *)src; return copy_from_user(dest, vaddr, size) ? -EFAULT : 0; } static nokprobe_inline int probe_mem_read_user(void *dest, void *src, size_t size) { return probe_mem_read(dest, src, size); } /* * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max * length and relative data location. */ static nokprobe_inline int fetch_store_string(unsigned long addr, void *dest, void *base) { long ret; u32 loc = *(u32 *)dest; int maxlen = get_loc_len(loc); u8 *dst = get_loc_data(dest, base); void __user *src = (void __force __user *) addr; if (unlikely(!maxlen)) return -ENOMEM; if (addr == FETCH_TOKEN_COMM) ret = strlcpy(dst, current->comm, maxlen); else ret = strncpy_from_user(dst, src, maxlen); if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; else /* * Include the terminating null byte. In this case it * was copied by strncpy_from_user but not accounted * for in ret. */ ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } return ret; } static nokprobe_inline int fetch_store_string_user(unsigned long addr, void *dest, void *base) { return fetch_store_string(addr, dest, base); } /* Return the length of string -- including null terminal byte */ static nokprobe_inline int fetch_store_strlen(unsigned long addr) { int len; void __user *vaddr = (void __force __user *) addr; if (addr == FETCH_TOKEN_COMM) len = strlen(current->comm) + 1; else len = strnlen_user(vaddr, MAX_STRING_SIZE); return (len > MAX_STRING_SIZE) ? 0 : len; } static nokprobe_inline int fetch_store_strlen_user(unsigned long addr) { return fetch_store_strlen(addr); } static unsigned long translate_user_vaddr(unsigned long file_offset) { unsigned long base_addr; struct uprobe_dispatch_data *udd; udd = (void *) current->utask->vaddr; base_addr = udd->bp_addr - udd->tu->offset; return base_addr + file_offset; } /* Note that we don't verify it, since the code does not come from user space */ static int process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest, void *base) { unsigned long val; /* 1st stage: get value from context */ switch (code->op) { case FETCH_OP_REG: val = regs_get_register(regs, code->param); break; case FETCH_OP_STACK: val = get_user_stack_nth(regs, code->param); break; case FETCH_OP_STACKP: val = user_stack_pointer(regs); break; case FETCH_OP_RETVAL: val = regs_return_value(regs); break; case FETCH_OP_IMM: val = code->immediate; break; case FETCH_OP_COMM: val = FETCH_TOKEN_COMM; break; case FETCH_OP_DATA: val = (unsigned long)code->data; break; case FETCH_OP_FOFFS: val = translate_user_vaddr(code->immediate); break; default: return -EILSEQ; } code++; return process_fetch_insn_bottom(code, val, dest, base); } NOKPROBE_SYMBOL(process_fetch_insn) static inline void init_trace_uprobe_filter(struct trace_uprobe_filter *filter) { rwlock_init(&filter->rwlock); filter->nr_systemwide = 0; INIT_LIST_HEAD(&filter->perf_events); } static inline bool uprobe_filter_is_empty(struct trace_uprobe_filter *filter) { return !filter->nr_systemwide && list_empty(&filter->perf_events); } static inline bool is_ret_probe(struct trace_uprobe *tu) { return tu->consumer.ret_handler != NULL; } static bool trace_uprobe_is_busy(struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return trace_probe_is_enabled(&tu->tp); } static bool trace_uprobe_match_command_head(struct trace_uprobe *tu, int argc, const char **argv) { char buf[MAX_ARGSTR_LEN + 1]; int len; if (!argc) return true; len = strlen(tu->filename); if (strncmp(tu->filename, argv[0], len) || argv[0][len] != ':') return false; if (tu->ref_ctr_offset == 0) snprintf(buf, sizeof(buf), "0x%0*lx", (int)(sizeof(void *) * 2), tu->offset); else snprintf(buf, sizeof(buf), "0x%0*lx(0x%lx)", (int)(sizeof(void *) * 2), tu->offset, tu->ref_ctr_offset); if (strcmp(buf, &argv[0][len + 1])) return false; argc--; argv++; return trace_probe_match_command_args(&tu->tp, argc, argv); } static bool trace_uprobe_match(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return strcmp(trace_probe_name(&tu->tp), event) == 0 && (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) && trace_uprobe_match_command_head(tu, argc, argv); } static nokprobe_inline struct trace_uprobe * trace_uprobe_primary_from_call(struct trace_event_call *call) { struct trace_probe *tp; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return NULL; return container_of(tp, struct trace_uprobe, tp); } /* * Allocate new trace_uprobe and initialize it (including uprobes). */ static struct trace_uprobe * alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) { struct trace_uprobe *tu; int ret; tu = kzalloc(SIZEOF_TRACE_UPROBE(nargs), GFP_KERNEL); if (!tu) return ERR_PTR(-ENOMEM); ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; dyn_event_init(&tu->devent, &trace_uprobe_ops); tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: kfree(tu); return ERR_PTR(ret); } static void free_trace_uprobe(struct trace_uprobe *tu) { if (!tu) return; path_put(&tu->path); trace_probe_cleanup(&tu->tp); kfree(tu->filename); kfree(tu); } static struct trace_uprobe *find_probe_event(const char *event, const char *group) { struct dyn_event *pos; struct trace_uprobe *tu; for_each_trace_uprobe(tu, pos) if (strcmp(trace_probe_name(&tu->tp), event) == 0 && strcmp(trace_probe_group_name(&tu->tp), group) == 0) return tu; return NULL; } /* Unregister a trace_uprobe and probe_event */ static int unregister_trace_uprobe(struct trace_uprobe *tu) { int ret; if (trace_probe_has_sibling(&tu->tp)) goto unreg; ret = unregister_uprobe_event(tu); if (ret) return ret; unreg: dyn_event_remove(&tu->devent); trace_probe_unlink(&tu->tp); free_trace_uprobe(tu); return 0; } static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, struct trace_uprobe *comp) { struct trace_probe_event *tpe = orig->tp.event; struct trace_probe *pos; struct inode *comp_inode = d_real_inode(comp->path.dentry); int i; list_for_each_entry(pos, &tpe->probes, list) { orig = container_of(pos, struct trace_uprobe, tp); if (comp_inode != d_real_inode(orig->path.dentry) || comp->offset != orig->offset) continue; /* * trace_probe_compare_arg_type() ensured that nr_args and * each argument name and type are same. Let's compare comm. */ for (i = 0; i < orig->tp.nr_args; i++) { if (strcmp(orig->tp.args[i].comm, comp->tp.args[i].comm)) break; } if (i == orig->tp.nr_args) return true; } return false; } static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to) { int ret; ret = trace_probe_compare_arg_type(&tu->tp, &to->tp); if (ret) { /* Note that argument starts index = 2 */ trace_probe_log_set_index(ret + 1); trace_probe_log_err(0, DIFF_ARG_TYPE); return -EEXIST; } if (trace_uprobe_has_same_uprobe(to, tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, SAME_PROBE); return -EEXIST; } /* Append to existing event */ ret = trace_probe_append(&tu->tp, &to->tp); if (!ret) dyn_event_add(&tu->devent); return ret; } /* * Uprobe with multiple reference counter is not allowed. i.e. * If inode and offset matches, reference counter offset *must* * match as well. Though, there is one exception: If user is * replacing old trace_uprobe with new one(same group/event), * then we allow same uprobe with new reference counter as far * as the new one does not conflict with any other existing * ones. */ static int validate_ref_ctr_offset(struct trace_uprobe *new) { struct dyn_event *pos; struct trace_uprobe *tmp; struct inode *new_inode = d_real_inode(new->path.dentry); for_each_trace_uprobe(tmp, pos) { if (new_inode == d_real_inode(tmp->path.dentry) && new->offset == tmp->offset && new->ref_ctr_offset != tmp->ref_ctr_offset) { pr_warn("Reference counter offset mismatch."); return -EINVAL; } } return 0; } /* Register a trace_uprobe and probe_event */ static int register_trace_uprobe(struct trace_uprobe *tu) { struct trace_uprobe *old_tu; int ret; mutex_lock(&event_mutex); ret = validate_ref_ctr_offset(tu); if (ret) goto end; /* register as an event */ old_tu = find_probe_event(trace_probe_name(&tu->tp), trace_probe_group_name(&tu->tp)); if (old_tu) { if (is_ret_probe(tu) != is_ret_probe(old_tu)) { trace_probe_log_set_index(0); trace_probe_log_err(0, DIFF_PROBE_TYPE); ret = -EEXIST; } else { ret = append_trace_uprobe(tu, old_tu); } goto end; } ret = register_uprobe_event(tu); if (ret) { if (ret == -EEXIST) { trace_probe_log_set_index(0); trace_probe_log_err(0, EVENT_EXIST); } else pr_warn("Failed to register probe event(%d)\n", ret); goto end; } dyn_event_add(&tu->devent); end: mutex_unlock(&event_mutex); return ret; } /* * Argument syntax: * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET[%return][(REF)] [FETCHARGS] */ static int trace_uprobe_create(int argc, const char **argv) { struct trace_uprobe *tu; const char *event = NULL, *group = UPROBE_EVENT_SYSTEM; char *arg, *filename, *rctr, *rctr_end, *tmp; char buf[MAX_EVENT_NAME_LEN]; struct path path; unsigned long offset, ref_ctr_offset; bool is_return = false; int i, ret; ret = 0; ref_ctr_offset = 0; switch (argv[0][0]) { case 'r': is_return = true; break; case 'p': break; default: return -ECANCELED; } if (argc < 2) return -ECANCELED; if (argv[0][1] == ':') event = &argv[0][2]; if (!strchr(argv[1], '/')) return -ECANCELED; filename = kstrdup(argv[1], GFP_KERNEL); if (!filename) return -ENOMEM; /* Find the last occurrence, in case the path contains ':' too. */ arg = strrchr(filename, ':'); if (!arg || !isdigit(arg[1])) { kfree(filename); return -ECANCELED; } trace_probe_log_init("trace_uprobe", argc, argv); trace_probe_log_set_index(1); /* filename is the 2nd argument */ *arg++ = '\0'; ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) { trace_probe_log_err(0, FILE_NOT_FOUND); kfree(filename); trace_probe_log_clear(); return ret; } if (!d_is_reg(path.dentry)) { trace_probe_log_err(0, NO_REGULAR_FILE); ret = -EINVAL; goto fail_address_parse; } /* Parse reference counter offset if specified. */ rctr = strchr(arg, '('); if (rctr) { rctr_end = strchr(rctr, ')'); if (!rctr_end) { ret = -EINVAL; rctr_end = rctr + strlen(rctr); trace_probe_log_err(rctr_end - filename, REFCNT_OPEN_BRACE); goto fail_address_parse; } else if (rctr_end[1] != '\0') { ret = -EINVAL; trace_probe_log_err(rctr_end + 1 - filename, BAD_REFCNT_SUFFIX); goto fail_address_parse; } *rctr++ = '\0'; *rctr_end = '\0'; ret = kstrtoul(rctr, 0, &ref_ctr_offset); if (ret) { trace_probe_log_err(rctr - filename, BAD_REFCNT); goto fail_address_parse; } } /* Check if there is %return suffix */ tmp = strchr(arg, '%'); if (tmp) { if (!strcmp(tmp, "%return")) { *tmp = '\0'; is_return = true; } else { trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX); ret = -EINVAL; goto fail_address_parse; } } /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); if (ret) { trace_probe_log_err(arg - filename, BAD_UPROBE_OFFS); goto fail_address_parse; } /* setup a probe */ trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, buf, event - argv[0]); if (ret) goto fail_address_parse; } else { char *tail; char *ptr; tail = kstrdup(kbasename(filename), GFP_KERNEL); if (!tail) { ret = -ENOMEM; goto fail_address_parse; } ptr = strpbrk(tail, ".-_"); if (ptr) *ptr = '\0'; snprintf(buf, MAX_EVENT_NAME_LEN, "%c_%s_0x%lx", 'p', tail, offset); event = buf; kfree(tail); } argc -= 2; argv += 2; tu = alloc_trace_uprobe(group, event, argc, is_return); if (IS_ERR(tu)) { ret = PTR_ERR(tu); /* This must return -ENOMEM otherwise there is a bug */ WARN_ON_ONCE(ret != -ENOMEM); goto fail_address_parse; } tu->offset = offset; tu->ref_ctr_offset = ref_ctr_offset; tu->path = path; tu->filename = filename; /* parse arguments */ for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { tmp = kstrdup(argv[i], GFP_KERNEL); if (!tmp) { ret = -ENOMEM; goto error; } trace_probe_log_set_index(i + 2); ret = traceprobe_parse_probe_arg(&tu->tp, i, tmp, is_return ? TPARG_FL_RETURN : 0); kfree(tmp); if (ret) goto error; } ret = traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)); if (ret < 0) goto error; ret = register_trace_uprobe(tu); if (!ret) goto out; error: free_trace_uprobe(tu); out: trace_probe_log_clear(); return ret; fail_address_parse: trace_probe_log_clear(); path_put(&path); kfree(filename); return ret; } static int create_or_delete_trace_uprobe(int argc, char **argv) { int ret; if (argv[0][0] == '-') return dyn_event_release(argc, argv, &trace_uprobe_ops); ret = trace_uprobe_create(argc, (const char **)argv); return ret == -ECANCELED ? -EINVAL : ret; } static int trace_uprobe_release(struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return unregister_trace_uprobe(tu); } /* Probes listing interfaces */ static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); char c = is_ret_probe(tu) ? 'r' : 'p'; int i; seq_printf(m, "%c:%s/%s %s:0x%0*lx", c, trace_probe_group_name(&tu->tp), trace_probe_name(&tu->tp), tu->filename, (int)(sizeof(void *) * 2), tu->offset); if (tu->ref_ctr_offset) seq_printf(m, "(0x%lx)", tu->ref_ctr_offset); for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); seq_putc(m, '\n'); return 0; } static int probes_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; if (!is_trace_uprobe(ev)) return 0; return trace_uprobe_show(m, ev); } static const struct seq_operations probes_seq_op = { .start = dyn_event_seq_start, .next = dyn_event_seq_next, .stop = dyn_event_seq_stop, .show = probes_seq_show }; static int probes_open(struct inode *inode, struct file *file) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) return ret; } return seq_open(file, &probes_seq_op); } static ssize_t probes_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { return trace_parse_run_command(file, buffer, count, ppos, create_or_delete_trace_uprobe); } static const struct file_operations uprobe_events_ops = { .owner = THIS_MODULE, .open = probes_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, .write = probes_write, }; /* Probes profiling interfaces */ static int probes_profile_seq_show(struct seq_file *m, void *v) { struct dyn_event *ev = v; struct trace_uprobe *tu; if (!is_trace_uprobe(ev)) return 0; tu = to_trace_uprobe(ev); seq_printf(m, " %s %-44s %15lu\n", tu->filename, trace_probe_name(&tu->tp), tu->nhit); return 0; } static const struct seq_operations profile_seq_op = { .start = dyn_event_seq_start, .next = dyn_event_seq_next, .stop = dyn_event_seq_stop, .show = probes_profile_seq_show }; static int profile_open(struct inode *inode, struct file *file) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; return seq_open(file, &profile_seq_op); } static const struct file_operations uprobe_profile_ops = { .owner = THIS_MODULE, .open = profile_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; struct uprobe_cpu_buffer { struct mutex mutex; void *buf; }; static struct uprobe_cpu_buffer __percpu *uprobe_cpu_buffer; static int uprobe_buffer_refcnt; static int uprobe_buffer_init(void) { int cpu, err_cpu; uprobe_cpu_buffer = alloc_percpu(struct uprobe_cpu_buffer); if (uprobe_cpu_buffer == NULL) return -ENOMEM; for_each_possible_cpu(cpu) { struct page *p = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0); if (p == NULL) { err_cpu = cpu; goto err; } per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf = page_address(p); mutex_init(&per_cpu_ptr(uprobe_cpu_buffer, cpu)->mutex); } return 0; err: for_each_possible_cpu(cpu) { if (cpu == err_cpu) break; free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); } free_percpu(uprobe_cpu_buffer); return -ENOMEM; } static int uprobe_buffer_enable(void) { int ret = 0; BUG_ON(!mutex_is_locked(&event_mutex)); if (uprobe_buffer_refcnt++ == 0) { ret = uprobe_buffer_init(); if (ret < 0) uprobe_buffer_refcnt--; } return ret; } static void uprobe_buffer_disable(void) { int cpu; BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { for_each_possible_cpu(cpu) free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, cpu)->buf); free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } } static struct uprobe_cpu_buffer *uprobe_buffer_get(void) { struct uprobe_cpu_buffer *ucb; int cpu; cpu = raw_smp_processor_id(); ucb = per_cpu_ptr(uprobe_cpu_buffer, cpu); /* * Use per-cpu buffers for fastest access, but we might migrate * so the mutex makes sure we have sole access to it. */ mutex_lock(&ucb->mutex); return ucb; } static void uprobe_buffer_put(struct uprobe_cpu_buffer *ucb) { mutex_unlock(&ucb->mutex); } static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; struct trace_buffer *buffer; struct ring_buffer_event *event; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); if (WARN_ON_ONCE(tu->tp.size + dsize > PAGE_SIZE)) return; if (trace_trigger_soft_disabled(trace_file)) return; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; event = trace_event_buffer_lock_reserve(&buffer, trace_file, call->event.type, size, 0, 0); if (!event) return; entry = ring_buffer_event_data(event); if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, true); } else { entry->vaddr[0] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, false); } memcpy(data, ucb->buf, tu->tp.size + dsize); event_trigger_unlock_commit(trace_file, buffer, event, entry, 0, 0); } /* uprobe handler */ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { struct event_file_link *link; if (is_ret_probe(tu)) return 0; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, 0, regs, ucb, dsize, link->file); rcu_read_unlock(); return 0; } static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { struct event_file_link *link; rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) __uprobe_trace_func(tu, func, regs, ucb, dsize, link->file); rcu_read_unlock(); } /* Event entry printers */ static enum print_line_t print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { struct uprobe_trace_entry_head *entry; struct trace_seq *s = &iter->seq; struct trace_uprobe *tu; u8 *data; entry = (struct uprobe_trace_entry_head *)iter->ent; tu = trace_uprobe_primary_from_call( container_of(event, struct trace_event_call, event)); if (unlikely(!tu)) goto out; if (is_ret_probe(tu)) { trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", trace_probe_name(&tu->tp), entry->vaddr[1], entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, true); } else { trace_seq_printf(s, "%s: (0x%lx)", trace_probe_name(&tu->tp), entry->vaddr[0]); data = DATAOF_TRACE_ENTRY(entry, false); } if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) goto out; trace_seq_putc(s, '\n'); out: return trace_handle_return(s); } typedef bool (*filter_func_t)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) { int ret; tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); if (tu->ref_ctr_offset) ret = uprobe_register_refctr(tu->inode, tu->offset, tu->ref_ctr_offset, &tu->consumer); else ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); if (ret) tu->inode = NULL; return ret; } static void __probe_event_disable(struct trace_probe *tp) { struct trace_probe *pos; struct trace_uprobe *tu; tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } } static int probe_event_enable(struct trace_event_call *call, struct trace_event_file *file, filter_func_t filter) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; bool enabled; int ret; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; enabled = trace_probe_is_enabled(tp); /* This may also change "enabled" state */ if (file) { if (trace_probe_test_flag(tp, TP_FLAG_PROFILE)) return -EINTR; ret = trace_probe_add_file(tp, file); if (ret < 0) return ret; } else { if (trace_probe_test_flag(tp, TP_FLAG_TRACE)) return -EINTR; trace_probe_set_flag(tp, TP_FLAG_PROFILE); } tu = container_of(tp, struct trace_uprobe, tp); WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; ret = uprobe_buffer_enable(); if (ret) goto err_flags; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); ret = trace_uprobe_enable(tu, filter); if (ret) { __probe_event_disable(tp); goto err_buffer; } } return 0; err_buffer: uprobe_buffer_disable(); err_flags: if (file) trace_probe_remove_file(tp, file); else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); return ret; } static void probe_event_disable(struct trace_event_call *call, struct trace_event_file *file) { struct trace_probe *tp; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return; if (!trace_probe_is_enabled(tp)) return; if (file) { if (trace_probe_remove_file(tp, file) < 0) return; if (trace_probe_is_enabled(tp)) return; } else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); __probe_event_disable(tp); uprobe_buffer_disable(); } static int uprobe_event_define_fields(struct trace_event_call *event_call) { int ret, size; struct uprobe_trace_entry_head field; struct trace_uprobe *tu; tu = trace_uprobe_primary_from_call(event_call); if (unlikely(!tu)) return -ENODEV; if (is_ret_probe(tu)) { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); DEFINE_FIELD(unsigned long, vaddr[1], FIELD_STRING_RETIP, 0); size = SIZEOF_TRACE_ENTRY(true); } else { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_IP, 0); size = SIZEOF_TRACE_ENTRY(false); } return traceprobe_define_arg_fields(event_call, size, &tu->tp); } #ifdef CONFIG_PERF_EVENTS static bool __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) { struct perf_event *event; if (filter->nr_systemwide) return true; list_for_each_entry(event, &filter->perf_events, hw.tp_list) { if (event->hw.target->mm == mm) return true; } return false; } static inline bool trace_uprobe_filter_event(struct trace_uprobe_filter *filter, struct perf_event *event) { return __uprobe_perf_filter(filter, event->hw.target->mm); } static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, struct perf_event *event) { bool done; write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || trace_uprobe_filter_event(filter, event); } else { filter->nr_systemwide--; done = filter->nr_systemwide; } write_unlock(&filter->rwlock); return done; } /* This returns true if the filter always covers target mm */ static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, struct perf_event *event) { bool done; write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid * uprobe_apply(). current->mm must be probed and we can rely * on dup_mmap() which preserves the already installed bp's. * * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || trace_uprobe_filter_event(filter, event); list_add(&event->hw.tp_list, &filter->perf_events); } else { done = filter->nr_systemwide; filter->nr_systemwide++; } write_unlock(&filter->rwlock); return done; } static int uprobe_perf_close(struct trace_event_call *call, struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; int ret = 0; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; tu = container_of(tp, struct trace_uprobe, tp); if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } static int uprobe_perf_open(struct trace_event_call *call, struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; int err = 0; tp = trace_probe_primary_from_call(call); if (WARN_ON_ONCE(!tp)) return -ENODEV; tu = container_of(tp, struct trace_uprobe, tp); if (trace_uprobe_filter_add(tu->tp.event->filter, event)) return 0; list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); if (err) { uprobe_perf_close(call, event); break; } } return err; } static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); filter = tu->tp.event->filter; read_lock(&filter->rwlock); ret = __uprobe_perf_filter(filter, mm); read_unlock(&filter->rwlock); return ret; } static void __uprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); struct uprobe_trace_entry_head *entry; struct hlist_head *head; void *data; int size, esize; int rctx; if (bpf_prog_array_valid(call)) { u32 ret; preempt_disable(); ret = trace_call_bpf(call, regs); preempt_enable(); if (!ret) return; } esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); size = esize + tu->tp.size + dsize; size = ALIGN(size + sizeof(u32), sizeof(u64)) - sizeof(u32); if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE, "profile buffer not large enough")) return; preempt_disable(); head = this_cpu_ptr(call->perf_events); if (hlist_empty(head)) goto out; entry = perf_trace_buf_alloc(size, NULL, &rctx); if (!entry) goto out; if (is_ret_probe(tu)) { entry->vaddr[0] = func; entry->vaddr[1] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, true); } else { entry->vaddr[0] = instruction_pointer(regs); data = DATAOF_TRACE_ENTRY(entry, false); } memcpy(data, ucb->buf, tu->tp.size + dsize); if (size - esize > tu->tp.size + dsize) { int len = tu->tp.size + dsize; memset(data + len, 0, size - esize - len); } perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); out: preempt_enable(); } /* uprobe profile handler */ static int uprobe_perf_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { if (!uprobe_perf_filter(&tu->consumer, 0, current->mm)) return UPROBE_HANDLER_REMOVE; if (!is_ret_probe(tu)) __uprobe_perf_func(tu, 0, regs, ucb, dsize); return 0; } static void uretprobe_perf_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, struct uprobe_cpu_buffer *ucb, int dsize) { __uprobe_perf_func(tu, func, regs, ucb, dsize); } int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, u64 *probe_offset, bool perf_type_tracepoint) { const char *pevent = trace_event_name(event->tp_event); const char *group = event->tp_event->class->system; struct trace_uprobe *tu; if (perf_type_tracepoint) tu = find_probe_event(pevent, group); else tu = trace_uprobe_primary_from_call(event->tp_event); if (!tu) return -EINVAL; *fd_type = is_ret_probe(tu) ? BPF_FD_TYPE_URETPROBE : BPF_FD_TYPE_UPROBE; *filename = tu->filename; *probe_offset = tu->offset; return 0; } #endif /* CONFIG_PERF_EVENTS */ static int trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, void *data) { struct trace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: return probe_event_enable(event, file, NULL); case TRACE_REG_UNREGISTER: probe_event_disable(event, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: return probe_event_enable(event, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: probe_event_disable(event, NULL); return 0; case TRACE_REG_PERF_OPEN: return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: return uprobe_perf_close(event, data); #endif default: return 0; } } static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; int dsize, esize; int ret = 0; tu = container_of(con, struct trace_uprobe, consumer); tu->nhit++; udd.tu = tu; udd.bp_addr = instruction_pointer(regs); current->utask->vaddr = (unsigned long) &udd; if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; dsize = __get_data_size(&tu->tp, regs); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) ret |= uprobe_trace_func(tu, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) ret |= uprobe_perf_func(tu, regs, ucb, dsize); #endif uprobe_buffer_put(ucb); return ret; } static int uretprobe_dispatcher(struct uprobe_consumer *con, unsigned long func, struct pt_regs *regs) { struct trace_uprobe *tu; struct uprobe_dispatch_data udd; struct uprobe_cpu_buffer *ucb; int dsize, esize; tu = container_of(con, struct trace_uprobe, consumer); udd.tu = tu; udd.bp_addr = func; current->utask->vaddr = (unsigned long) &udd; if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; dsize = __get_data_size(&tu->tp, regs); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) uretprobe_trace_func(tu, func, regs, ucb, dsize); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) uretprobe_perf_func(tu, func, regs, ucb, dsize); #endif uprobe_buffer_put(ucb); return 0; } static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; static struct trace_event_fields uprobe_fields_array[] = { { .type = TRACE_FUNCTION_TYPE, .define_fields = uprobe_event_define_fields }, {} }; static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); call->event.funcs = &uprobe_funcs; call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; } static int register_uprobe_event(struct trace_uprobe *tu) { init_trace_event_call(tu); return trace_probe_register_event_call(&tu->tp); } static int unregister_uprobe_event(struct trace_uprobe *tu) { return trace_probe_unregister_event_call(&tu->tp); } #ifdef CONFIG_PERF_EVENTS struct trace_event_call * create_local_trace_uprobe(char *name, unsigned long offs, unsigned long ref_ctr_offset, bool is_return) { struct trace_uprobe *tu; struct path path; int ret; ret = kern_path(name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); if (!d_is_reg(path.dentry)) { path_put(&path); return ERR_PTR(-EINVAL); } /* * local trace_kprobes are not added to dyn_event, so they are never * searched in find_trace_kprobe(). Therefore, there is no concern of * duplicated name "DUMMY_EVENT" here. */ tu = alloc_trace_uprobe(UPROBE_EVENT_SYSTEM, "DUMMY_EVENT", 0, is_return); if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); path_put(&path); return ERR_CAST(tu); } tu->offset = offs; tu->path = path; tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); init_trace_event_call(tu); if (traceprobe_set_print_fmt(&tu->tp, is_ret_probe(tu)) < 0) { ret = -ENOMEM; goto error; } return trace_probe_event_call(&tu->tp); error: free_trace_uprobe(tu); return ERR_PTR(ret); } void destroy_local_trace_uprobe(struct trace_event_call *event_call) { struct trace_uprobe *tu; tu = trace_uprobe_primary_from_call(event_call); free_trace_uprobe(tu); } #endif /* CONFIG_PERF_EVENTS */ /* Make a trace interface for controling probe points */ static __init int init_uprobe_trace(void) { int ret; ret = dyn_event_register(&trace_uprobe_ops); if (ret) return ret; ret = tracing_init_dentry(); if (ret) return 0; trace_create_file("uprobe_events", 0644, NULL, NULL, &uprobe_events_ops); /* Profile interface */ trace_create_file("uprobe_profile", 0444, NULL, NULL, &uprobe_profile_ops); return 0; } fs_initcall(init_uprobe_trace); |
| 5825 5825 5824 5821 5823 4365 4369 5686 5682 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 | // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/memblock.h> #include <linux/stacktrace.h> #include <linux/page_owner.h> #include <linux/jump_label.h> #include <linux/migrate.h> #include <linux/stackdepot.h> #include <linux/seq_file.h> #include <linux/sched/clock.h> #include "internal.h" /* * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack) * to use off stack temporal storage */ #define PAGE_OWNER_STACK_DEPTH (16) struct page_owner { unsigned short order; short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; depot_stack_handle_t free_handle; u64 ts_nsec; u64 free_ts_nsec; pid_t pid; }; bool page_owner_enabled; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; static depot_stack_handle_t early_handle; static void init_early_allocated_pages(void); static int __init early_page_owner_param(char *buf) { if (!buf) return -EINVAL; if (strcmp(buf, "on") == 0) page_owner_enabled = true; return 0; } early_param("page_owner", early_page_owner_param); static bool need_page_owner(void) { return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) { unsigned long entries[4]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); return stack_depot_save(entries, nr_entries, GFP_KERNEL); } static noinline void register_dummy_stack(void) { dummy_handle = create_dummy_stack(); } static noinline void register_failure_stack(void) { failure_handle = create_dummy_stack(); } static noinline void register_early_stack(void) { early_handle = create_dummy_stack(); } static void init_page_owner(void) { if (!page_owner_enabled) return; register_dummy_stack(); register_failure_stack(); register_early_stack(); static_branch_enable(&page_owner_inited); init_early_allocated_pages(); } struct page_ext_operations page_owner_ops = { .size = sizeof(struct page_owner), .need = need_page_owner, .init = init_page_owner, }; struct page_owner *get_page_owner(struct page_ext *page_ext) { return (void *)page_ext + page_owner_ops.offset; } EXPORT_SYMBOL_GPL(get_page_owner); depot_stack_handle_t get_page_owner_handle(struct page_ext *page_ext, unsigned long pfn) { struct page_owner *page_owner; depot_stack_handle_t handle; if (!page_owner_enabled) return 0; page_owner = get_page_owner(page_ext); /* skip handle for tail pages of higher order allocations */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) return 0; handle = READ_ONCE(page_owner->handle); return handle; } EXPORT_SYMBOL_GPL(get_page_owner_handle); static inline bool check_recursive_alloc(unsigned long *entries, unsigned int nr_entries, unsigned long ip) { unsigned int i; for (i = 0; i < nr_entries; i++) { if (entries[i] == ip) return true; } return false; } static noinline depot_stack_handle_t save_stack(gfp_t flags) { unsigned long entries[PAGE_OWNER_STACK_DEPTH]; depot_stack_handle_t handle; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2); /* * We need to check recursion here because our request to * stackdepot could trigger memory allocation to save new * entry. New memory allocation would reach here and call * stack_depot_save_entries() again if we don't catch it. There is * still not enough memory in stackdepot so it would try to * allocate memory again and loop forever. */ if (check_recursive_alloc(entries, nr_entries, _RET_IP_)) return dummy_handle; handle = stack_depot_save(entries, nr_entries, flags); if (!handle) handle = failure_handle; return handle; } void __reset_page_owner(struct page *page, unsigned int order) { int i; struct page_ext *page_ext; depot_stack_handle_t handle = 0; struct page_owner *page_owner; u64 free_ts_nsec = local_clock(); handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) return; for (i = 0; i < (1 << order); i++) { __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_owner = get_page_owner(page_ext); page_owner->free_handle = handle; page_owner->free_ts_nsec = free_ts_nsec; page_ext = page_ext_next(page_ext); } } static inline void __set_page_owner_handle(struct page *page, struct page_ext *page_ext, depot_stack_handle_t handle, unsigned int order, gfp_t gfp_mask) { struct page_owner *page_owner; int i; for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->handle = handle; page_owner->order = order; page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; page_owner->pid = current->pid; page_owner->ts_nsec = local_clock(); __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_ext = page_ext_next(page_ext); } } noinline void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { struct page_ext *page_ext = lookup_page_ext(page); depot_stack_handle_t handle; if (unlikely(!page_ext)) return; handle = save_stack(gfp_mask); __set_page_owner_handle(page, page_ext, handle, order, gfp_mask); } void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; page_owner = get_page_owner(page_ext); page_owner->last_migrate_reason = reason; } void __split_page_owner(struct page *page, unsigned int nr) { int i; struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; for (i = 0; i < nr; i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; page_ext = page_ext_next(page_ext); } } void __copy_page_owner(struct page *oldpage, struct page *newpage) { struct page_ext *old_ext = lookup_page_ext(oldpage); struct page_ext *new_ext = lookup_page_ext(newpage); struct page_owner *old_page_owner, *new_page_owner; if (unlikely(!old_ext || !new_ext)) return; old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); new_page_owner->order = old_page_owner->order; new_page_owner->gfp_mask = old_page_owner->gfp_mask; new_page_owner->last_migrate_reason = old_page_owner->last_migrate_reason; new_page_owner->handle = old_page_owner->handle; new_page_owner->pid = old_page_owner->pid; new_page_owner->ts_nsec = old_page_owner->ts_nsec; new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; /* * We don't clear the bit on the oldpage as it's going to be freed * after migration. Until then, the info can be useful in case of * a bug, and the overal stats will be off a bit only temporarily. * Also, migrate_misplaced_transhuge_page() can still fail the * migration and then we want the oldpage to retain the info. But * in that case we also don't need to explicitly clear the info from * the new page, which will be freed. */ __set_bit(PAGE_EXT_OWNER, &new_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; unsigned long pfn = zone->zone_start_pfn, block_end_pfn; unsigned long end_pfn = pfn + zone->spanned_pages; unsigned long count[MIGRATE_TYPES] = { 0, }; int pageblock_mt, page_mt; int i; /* Scan block by block. First and last block may be incomplete */ pfn = zone->zone_start_pfn; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { page = pfn_to_online_page(pfn); if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { if (!pfn_valid_within(pfn)) continue; /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) continue; if (PageBuddy(page)) { unsigned long freepage_order; freepage_order = buddy_order_unsafe(page); if (freepage_order < MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } if (PageReserved(page)) continue; page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) continue; if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); page_mt = gfp_migratetype(page_owner->gfp_mask); if (pageblock_mt != page_mt) { if (is_migrate_cma(pageblock_mt)) count[MIGRATE_MOVABLE]++; else count[pageblock_mt]++; pfn = block_end_pfn; break; } pfn += (1UL << page_owner->order) - 1; } } /* Print counts */ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (i = 0; i < MIGRATE_TYPES; i++) seq_printf(m, "%12lu ", count[i]); seq_putc(m, '\n'); } static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, struct page *page, struct page_owner *page_owner, depot_stack_handle_t handle) { int ret, pageblock_mt, page_mt; unsigned long *entries; unsigned int nr_entries; char *kbuf; count = min_t(size_t, count, PAGE_SIZE); kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) return -ENOMEM; ret = snprintf(kbuf, count, "Page allocated via order %u, mask %#x(%pGg), pid %d, ts %llu ns, free_ts %llu ns\n", page_owner->order, page_owner->gfp_mask, &page_owner->gfp_mask, page_owner->pid, page_owner->ts_nsec, page_owner->free_ts_nsec); if (ret >= count) goto err; /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); page_mt = gfp_migratetype(page_owner->gfp_mask); ret += snprintf(kbuf + ret, count - ret, "PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n", pfn, migratetype_names[page_mt], pfn >> pageblock_order, migratetype_names[pageblock_mt], page->flags, &page->flags); if (ret >= count) goto err; nr_entries = stack_depot_fetch(handle, &entries); ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0); if (ret >= count) goto err; if (page_owner->last_migrate_reason != -1) { ret += snprintf(kbuf + ret, count - ret, "Page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); if (ret >= count) goto err; } ret += snprintf(kbuf + ret, count - ret, "\n"); if (ret >= count) goto err; if (copy_to_user(buf, kbuf, ret)) ret = -EFAULT; kfree(kbuf); return ret; err: kfree(kbuf); return -ENOMEM; } void __dump_page_owner(struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; depot_stack_handle_t handle; unsigned long *entries; unsigned int nr_entries; gfp_t gfp_mask; int mt; if (unlikely(!page_ext)) { pr_alert("There is not page extension available.\n"); return; } page_owner = get_page_owner(page_ext); gfp_mask = page_owner->gfp_mask; mt = gfp_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not present (never set?)\n"); return; } if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, ts %llu, free_ts %llu\n", page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask, page_owner->pid, page_owner->ts_nsec, page_owner->free_ts_nsec); handle = READ_ONCE(page_owner->handle); if (!handle) { pr_alert("page_owner allocation stack trace missing\n"); } else { nr_entries = stack_depot_fetch(handle, &entries); stack_trace_print(entries, nr_entries, 0); } handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { nr_entries = stack_depot_fetch(handle, &entries); pr_alert("page last free stack trace:\n"); stack_trace_print(entries, nr_entries, 0); } if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); } static ssize_t read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long pfn; struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) return -EINVAL; page = NULL; pfn = min_low_pfn + *ppos; /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) pfn++; drain_all_pages(NULL); /* Find an allocated page */ for (; pfn < max_pfn; pfn++) { /* * If the new page is in a new MAX_ORDER_NR_PAGES area, * validate the area as existing, skip it if not */ if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { pfn += MAX_ORDER_NR_PAGES - 1; continue; } /* Check for holes within a MAX_ORDER area */ if (!pfn_valid_within(pfn)) continue; page = pfn_to_page(pfn); if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); if (freepage_order < MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) continue; /* * Some pages could be missed by concurrent allocation or free, * because we don't hold the zone lock. */ if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; /* * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); /* * Don't print "tail" pages of high-order allocations as that * would inflate the stats. */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) continue; /* * Access to page_ext->handle isn't synchronous so we should * be careful to access it. */ handle = READ_ONCE(page_owner->handle); if (!handle) continue; /* Record the next PFN to read in the file offset */ *ppos = (pfn - min_low_pfn) + 1; return print_page_owner(buf, count, pfn, page, page_owner, handle); } return 0; } static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) { unsigned long pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count = 0; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { unsigned long block_end_pfn; if (!pfn_valid(pfn)) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); for (; pfn < block_end_pfn; pfn++) { struct page *page; struct page_ext *page_ext; if (!pfn_valid_within(pfn)) continue; page = pfn_to_page(pfn); if (page_zone(page) != zone) continue; /* * To avoid having to grab zone->lock, be a little * careful when reading buddy page order. The only * danger is that we skip too much and potentially miss * some early allocated pages, which is better than * heavy lock contention. */ if (PageBuddy(page)) { unsigned long order = buddy_order_unsafe(page); if (order > 0 && order < MAX_ORDER) pfn += (1UL << order) - 1; continue; } if (PageReserved(page)) continue; page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) continue; /* Maybe overlapping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; /* Found early allocated page */ __set_page_owner_handle(page, page_ext, early_handle, 0, 0); count++; } cond_resched(); } pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", pgdat->node_id, zone->name, count); } static void init_zones_in_node(pg_data_t *pgdat) { struct zone *zone; struct zone *node_zones = pgdat->node_zones; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; init_pages_in_zone(pgdat, zone); } } static void init_early_allocated_pages(void) { pg_data_t *pgdat; for_each_online_pgdat(pgdat) init_zones_in_node(pgdat); } static const struct file_operations proc_page_owner_operations = { .read = read_page_owner, }; static int __init pageowner_init(void) { if (!static_branch_unlikely(&page_owner_inited)) { pr_info("page_owner is disabled\n"); return 0; } debugfs_create_file("page_owner", 0400, NULL, NULL, &proc_page_owner_operations); return 0; } late_initcall(pageowner_init) |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 | #ifndef __LINUX_ERSPAN_H #define __LINUX_ERSPAN_H /* * GRE header for ERSPAN type I encapsulation (4 octets [34:37]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |0|0|0|0|0|00000|000000000|00000| Protocol Type for ERSPAN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * The Type I ERSPAN frame format is based on the barebones IP + GRE * encapsulation (as described above) on top of the raw mirrored frame. * There is no extra ERSPAN header. * * * GRE header for ERSPAN type II and II encapsulation (8 octets [34:41]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |0|0|0|1|0|00000|000000000|00000| Protocol Type for ERSPAN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Sequence Number (increments per packet per session) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Note that in the above GRE header [RFC1701] out of the C, R, K, S, * s, Recur, Flags, Version fields only S (bit 03) is set to 1. The * other fields are set to zero, so only a sequence number follows. * * ERSPAN Version 1 (Type II) header (8 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ver | VLAN | COS | En|T| Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Reserved | Index | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * * ERSPAN Version 2 (Type III) header (12 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ver | VLAN | COS |BSO|T| Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Timestamp | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | SGT |P| FT | Hw ID |D|Gra|O| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Platform Specific SubHeader (8 octets, optional) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Platf ID | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * GRE proto ERSPAN type I/II = 0x88BE, type III = 0x22EB */ #include <uapi/linux/erspan.h> #define ERSPAN_VERSION 0x1 /* ERSPAN type II */ #define VER_MASK 0xf000 #define VLAN_MASK 0x0fff #define COS_MASK 0xe000 #define EN_MASK 0x1800 #define T_MASK 0x0400 #define ID_MASK 0x03ff #define INDEX_MASK 0xfffff #define ERSPAN_VERSION2 0x2 /* ERSPAN type III*/ #define BSO_MASK EN_MASK #define SGT_MASK 0xffff0000 #define P_MASK 0x8000 #define FT_MASK 0x7c00 #define HWID_MASK 0x03f0 #define DIR_MASK 0x0008 #define GRA_MASK 0x0006 #define O_MASK 0x0001 #define HWID_OFFSET 4 #define DIR_OFFSET 3 enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 #define ERSPAN_V2_MDSIZE 8 struct erspan_base_hdr { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 vlan_upper:4, ver:4; __u8 vlan:8; __u8 session_id_upper:2, t:1, en:2, cos:3; __u8 session_id:8; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 ver: 4, vlan_upper:4; __u8 vlan:8; __u8 cos:3, en:2, t:1, session_id_upper:2; __u8 session_id:8; #else #error "Please fix <asm/byteorder.h>" #endif }; static inline void set_session_id(struct erspan_base_hdr *ershdr, u16 id) { ershdr->session_id = id & 0xff; ershdr->session_id_upper = (id >> 8) & 0x3; } static inline u16 get_session_id(const struct erspan_base_hdr *ershdr) { return (ershdr->session_id_upper << 8) + ershdr->session_id; } static inline void set_vlan(struct erspan_base_hdr *ershdr, u16 vlan) { ershdr->vlan = vlan & 0xff; ershdr->vlan_upper = (vlan >> 8) & 0xf; } static inline u16 get_vlan(const struct erspan_base_hdr *ershdr) { return (ershdr->vlan_upper << 8) + ershdr->vlan; } static inline void set_hwid(struct erspan_md2 *md2, u8 hwid) { md2->hwid = hwid & 0xf; md2->hwid_upper = (hwid >> 4) & 0x3; } static inline u8 get_hwid(const struct erspan_md2 *md2) { return (md2->hwid_upper << 4) + md2->hwid; } static inline int erspan_hdr_len(int version) { if (version == 0) return 0; return sizeof(struct erspan_base_hdr) + (version == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); } static inline u8 tos_to_cos(u8 tos) { u8 dscp, cos; dscp = tos >> 2; cos = dscp >> 3; return cos; } static inline void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4) { struct ethhdr *eth = (struct ethhdr *)skb->data; enum erspan_encap_type enc_type; struct erspan_base_hdr *ershdr; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 tos; __be32 *idx; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + (ipv6_hdr(skb)->flow_lbl[0] >> 4); enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and * perserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); vlan_tci = ntohs(qp->tci); enc_type = ERSPAN_ENCAP_INFRAME; } skb_push(skb, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); ershdr = (struct erspan_base_hdr *)skb->data; memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); /* Build base header */ ershdr->ver = ERSPAN_VERSION; ershdr->cos = tos_to_cos(tos); ershdr->en = enc_type; ershdr->t = truncate; set_vlan(ershdr, vlan_tci); set_session_id(ershdr, id); /* Build metadata */ idx = (__be32 *)(ershdr + 1); *idx = htonl(index & INDEX_MASK); } /* ERSPAN GRA: timestamp granularity * 00b --> granularity = 100 microseconds * 01b --> granularity = 100 nanoseconds * 10b --> granularity = IEEE 1588 * Here we only support 100 microseconds. */ static inline __be32 erspan_get_timestamp(void) { u64 h_usecs; ktime_t kt; kt = ktime_get_real(); h_usecs = ktime_divns(kt, 100 * NSEC_PER_USEC); /* ERSPAN base header only has 32-bit, * so it wraps around 4 days. */ return htonl((u32)h_usecs); } /* ERSPAN BSO (Bad/Short/Oversized), see RFC1757 * 00b --> Good frame with no error, or unknown integrity * 01b --> Payload is a Short Frame * 10b --> Payload is an Oversized Frame * 11b --> Payload is a Bad Frame with CRC or Alignment Error */ enum erspan_bso { BSO_NOERROR = 0x0, BSO_SHORT = 0x1, BSO_OVERSIZED = 0x2, BSO_BAD = 0x3, }; static inline u8 erspan_detect_bso(struct sk_buff *skb) { /* BSO_BAD is not handled because the frame CRC * or alignment error information is in FCS. */ if (skb->len < ETH_ZLEN) return BSO_SHORT; if (skb->len > ETH_FRAME_LEN) return BSO_OVERSIZED; return BSO_NOERROR; } static inline void erspan_build_header_v2(struct sk_buff *skb, u32 id, u8 direction, u16 hwid, bool truncate, bool is_ipv4) { struct ethhdr *eth = (struct ethhdr *)skb->data; struct erspan_base_hdr *ershdr; struct erspan_md2 *md2; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 gra = 0; /* 100 usec */ u8 bso = 0; /* Bad/Short/Oversized */ u8 sgt = 0; u8 tos; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + (ipv6_hdr(skb)->flow_lbl[0] >> 4); /* Unlike v1, v2 does not have En field, * so only extract vlan tci field. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); vlan_tci = ntohs(qp->tci); } bso = erspan_detect_bso(skb); skb_push(skb, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); ershdr = (struct erspan_base_hdr *)skb->data; memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); /* Build base header */ ershdr->ver = ERSPAN_VERSION2; ershdr->cos = tos_to_cos(tos); ershdr->en = bso; ershdr->t = truncate; set_vlan(ershdr, vlan_tci); set_session_id(ershdr, id); /* Build metadata */ md2 = (struct erspan_md2 *)(ershdr + 1); md2->timestamp = erspan_get_timestamp(); md2->sgt = htons(sgt); md2->p = 1; md2->ft = 0; md2->dir = direction; md2->gra = gra; md2->o = 0; set_hwid(md2, hwid); } #endif |
| 181 167 14 1056 1056 349 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 637 637 3 641 639 640 641 641 641 322 636 636 322 321 322 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <sds@tycho.nsa.gov> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[]; }; #define index_to_sid(index) (index + SECINITSID_NUM + 1) #define sid_to_index(sid) (sid - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_cmp(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; convert = s->convert; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ if (convert) { rc = -ENOMEM; dst_convert = sidtab_do_lookup(convert->target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = convert->func(context, &dst_convert->context, convert->args); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); convert->target->count = count + 1; hash_add_rcu(convert->target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = convert->func(&esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, convert->args); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(sizeof(struct sidtab_str_cache) + str_len, GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 819 819 819 961 961 961 164 164 164 1183 1183 1088 956 8 156 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/core/fib_rules.c Generic Routing Rules * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/module.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> #include <linux/indirect_call_wrapper.h> #if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) #ifdef CONFIG_IP_MULTIPLE_TABLES #define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) #endif #elif defined(CONFIG_IP_MULTIPLE_TABLES) #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__) #endif static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(0), KUIDT_INIT(~0), }; bool fib_rule_matchall(const struct fib_rule *rule) { if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) return false; if (fib_rule_port_range_set(&rule->sport_range)) return false; if (fib_rule_port_range_set(&rule->dport_range)) return false; return true; } EXPORT_SYMBOL_GPL(fib_rule_matchall); int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { struct fib_rule *r; r = kzalloc(ops->rule_size, GFP_KERNEL); if (r == NULL) return -ENOMEM; refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; r->flags = flags; r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; /* The lock is not required here, the list in unreacheable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; } EXPORT_SYMBOL(fib_default_rule_add); static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { struct list_head *pos; struct fib_rule *rule; if (!list_empty(&ops->rules_list)) { pos = ops->rules_list.next; if (pos->next != &ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; } } return 0; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family) { struct fib_rules_ops *ops; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (ops->family == family) { if (!try_module_get(ops->owner)) ops = NULL; rcu_read_unlock(); return ops; } } rcu_read_unlock(); return NULL; } static void rules_ops_put(struct fib_rules_ops *ops) { if (ops) module_put(ops->owner); } static void flush_route_cache(struct fib_rules_ops *ops) { if (ops->flush_cache) ops->flush_cache(ops); } static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; struct net *net; net = ops->fro_net; if (ops->rule_size < sizeof(struct fib_rule)) return -EINVAL; if (ops->match == NULL || ops->configure == NULL || ops->compare == NULL || ops->fill == NULL || ops->action == NULL) return -EINVAL; spin_lock(&net->rules_mod_lock); list_for_each_entry(o, &net->rules_ops, list) if (ops->family == o->family) goto errout; list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0; errout: spin_unlock(&net->rules_mod_lock); return err; } struct fib_rules_ops * fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) { struct fib_rules_ops *ops; int err; ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&ops->rules_list); ops->fro_net = net; err = __fib_rules_register(ops); if (err) { kfree(ops); ops = ERR_PTR(err); } return ops; } EXPORT_SYMBOL_GPL(fib_rules_register); static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { struct fib_rule *rule, *tmp; list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); if (ops->delete) ops->delete(rule); fib_rule_put(rule); } } void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; spin_lock(&net->rules_mod_lock); list_del_rcu(&ops->list); spin_unlock(&net->rules_mod_lock); fib_rules_cleanup_ops(ops); kfree_rcu(ops, rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); static int uid_range_set(struct fib_kuid_range *range) { return uid_valid(range->start) && uid_valid(range->end); } static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb) { struct fib_rule_uid_range *in; struct fib_kuid_range out; in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]); out.start = make_kuid(current_user_ns(), in->start); out.end = make_kuid(current_user_ns(), in->end); return out; } static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) { struct fib_rule_uid_range out = { from_kuid_munged(current_user_ns(), range->start), from_kuid_munged(current_user_ns(), range->end) }; return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); } static int nla_get_port_range(struct nlattr *pattr, struct fib_rule_port_range *port_range) { const struct fib_rule_port_range *pr = nla_data(pattr); if (!fib_rule_port_range_valid(pr)) return -EINVAL; port_range->start = pr->start; port_range->end = pr->end; return 0; } static int nla_put_port_range(struct sk_buff *skb, int attrtype, struct fib_rule_port_range *range) { return nla_put(skb, attrtype, sizeof(*range), range); } static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { int ret = 0; if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) goto out; if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) goto out; if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) goto out; if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) goto out; if (uid_lt(fl->flowi_uid, rule->uid_range.start) || uid_gt(fl->flowi_uid, rule->uid_range.end)) goto out; ret = INDIRECT_CALL_MT(ops->match, fib6_rule_match, fib4_rule_match, rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; } int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { struct fib_rule *rule; int err; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { jumped: if (!fib_rule_match(rule, ops, fl, flags, arg)) continue; if (rule->action == FR_ACT_GOTO) { struct fib_rule *target; target = rcu_dereference(rule->ctarget); if (target == NULL) { continue; } else { rule = target; goto jumped; } } else if (rule->action == FR_ACT_NOP) continue; else err = INDIRECT_CALL_MT(ops->action, fib6_rule_action, fib4_rule_action, rule, fl, flags, arg); if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, rule, flags, arg)) continue; if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(refcount_inc_not_zero(&rule->refcnt))) { arg->rule = rule; goto out; } break; } } err = -ESRCH; out: rcu_read_unlock(); return err; } EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, .info.extack = extack, .rule = rule, }; return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule, struct fib_rules_ops *ops, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = ops->family, .info.extack = extack, .rule = rule, }; ops->fib_rules_seq++; return call_fib_notifiers(net, event_type, &info.info); } /* Called with rcu_read_lock() */ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; int err = 0; ops = lookup_rules_ops(net, family); if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family, extack); if (err) break; } rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_rules_dump); unsigned int fib_rules_seq_read(struct net *net, int family) { unsigned int fib_rules_seq; struct fib_rules_ops *ops; ASSERT_RTNL(); ops = lookup_rules_ops(net, family); if (!ops) return 0; fib_rules_seq = ops->fib_rules_seq; rules_ops_put(ops); return fib_rules_seq; } EXPORT_SYMBOL_GPL(fib_rules_seq_read); static struct fib_rule *rule_find(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule, bool user_priority) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (rule->action && r->action != rule->action) continue; if (rule->table && r->table != rule->table) continue; if (user_priority && r->pref != rule->pref) continue; if (rule->iifname[0] && memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (rule->oifname[0] && memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (rule->mark && r->mark != rule->mark) continue; if (rule->suppress_ifgroup != -1 && r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (rule->suppress_prefixlen != -1 && r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; if (rule->tun_id && r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; if (uid_range_set(&rule->uid_range) && (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end))) continue; if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; if (rule->proto && r->proto != rule->proto) continue; if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return r; } return NULL; } #ifdef CONFIG_NET_L3_MASTER_DEV static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { nlrule->l3mdev = nla_get_u8(nla); if (nlrule->l3mdev != 1) { NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); return -1; } return 0; } #else static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); return -1; } #endif static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, struct nlattr *tb[], struct fib_rule **rule, bool *user_priority) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rule *nlrule = NULL; int err = -EINVAL; if (frh->src_len) if (!tb[FRA_SRC] || frh->src_len > (ops->addr_size * 8) || nla_len(tb[FRA_SRC]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid source address"); goto errout; } if (frh->dst_len) if (!tb[FRA_DST] || frh->dst_len > (ops->addr_size * 8) || nla_len(tb[FRA_DST]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid dst address"); goto errout; } nlrule = kzalloc(ops->rule_size, GFP_KERNEL); if (!nlrule) { err = -ENOMEM; goto errout; } refcount_set(&nlrule->refcnt, 1); nlrule->fr_net = net; if (tb[FRA_PRIORITY]) { nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); *user_priority = true; } else { nlrule->pref = fib_default_rule_pref(ops); } nlrule->proto = tb[FRA_PROTOCOL] ? nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; if (tb[FRA_IIFNAME]) { struct net_device *dev; nlrule->iifindex = -1; nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->iifname); if (dev) nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { struct net_device *dev; nlrule->oifindex = -1; nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->oifname); if (dev) nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ nlrule->mark_mask = 0xFFFFFFFF; } if (tb[FRA_FWMASK]) nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); if (tb[FRA_TUN_ID]) nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); err = -EINVAL; if (tb[FRA_L3MDEV] && fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) goto errout_free; nlrule->action = frh->action; nlrule->flags = frh->flags; nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else nlrule->suppress_prefixlen = -1; if (tb[FRA_SUPPRESS_IFGROUP]) nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else nlrule->suppress_ifgroup = -1; if (tb[FRA_GOTO]) { if (nlrule->action != FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; } nlrule->target = nla_get_u32(tb[FRA_GOTO]); /* Backward jumps are prohibited to avoid endless loops */ if (nlrule->target <= nlrule->pref) { NL_SET_ERR_MSG(extack, "Backward goto not supported"); goto errout_free; } } else if (nlrule->action == FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; } if (nlrule->l3mdev && nlrule->table) { NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; } if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; } nlrule->uid_range = nla_get_kuid_range(tb); if (!uid_range_set(&nlrule->uid_range) || !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; } } else { nlrule->uid_range = fib_kuid_range_unset; } if (tb[FRA_IP_PROTO]) nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], &nlrule->sport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } } if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], &nlrule->dport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } } *rule = nlrule; return 0; errout_free: kfree(nlrule); errout: return err; } static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (r->action != rule->action) continue; if (r->table != rule->table) continue; if (r->pref != rule->pref) continue; if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (r->mark != rule->mark) continue; if (r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (r->mark_mask != rule->mark_mask) continue; if (r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (r->l3mdev != rule->l3mdev) continue; if (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end)) continue; if (r->ip_proto != rule->ip_proto) continue; if (r->proto != rule->proto) continue; if (!fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return 1; } return 0; } int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *last = NULL; struct nlattr *tb[FRA_MAX + 1]; int err = -EINVAL, unresolved = 0; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (!ops) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); if (err) goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free; err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack); if (err < 0) goto errout_free; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref == rule->target) { RCU_INIT_POINTER(rule->ctarget, r); break; } } if (rcu_dereference_protected(rule->ctarget, 1) == NULL) unresolved = 1; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; } if (last) list_add_rcu(&rule->list, &last->list); else list_add_rcu(&rule->list, &ops->rules_list); if (ops->unresolved_rules) { /* * There are unresolved goto rules in the list, check if * any of them are pointing to this new rule. */ list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref && rtnl_dereference(r->ctarget) == NULL) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; } } } if (rule->action == FR_ACT_GOTO) ops->nr_goto_rules++; if (unresolved) ops->unresolved_rules++; if (rule->tun_id) ip_tunnel_need_metadata(); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; errout_free: kfree(rule); errout: rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_newrule); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; int err = -EINVAL; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); if (err) goto errout; rule = rule_find(ops, frh, tb, nlrule, user_priority); if (!rule) { err = -ENOENT; goto errout; } if (rule->flags & FIB_RULE_PERMANENT) { err = -EPERM; goto errout; } if (ops->delete) { err = ops->delete(rule); if (err) goto errout; } if (rule->tun_id) ip_tunnel_unneed_metadata(); list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; if (rtnl_dereference(rule->ctarget) == NULL) ops->unresolved_rules--; } /* * Check if this rule is a target to any of them. If so, * adjust to the next one with the same preference or * disable them. As this operation is eventually very * expensive, it is only performed if goto rules, except * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { struct fib_rule *n; n = list_next_entry(rule, list); if (&n->list == &ops->rules_list || n->pref != rule->pref) n = NULL; list_for_each_entry(r, &ops->rules_list, list) { if (rtnl_dereference(r->ctarget) != rule) continue; rcu_assign_pointer(r->ctarget, n); if (!n) ops->unresolved_rules++; } } call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); kfree(nlrule); return 0; errout: kfree(nlrule); rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_delrule); static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ + nla_total_size(sizeof(struct fib_kuid_range)) + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); return payload; } static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, u32 pid, u32 seq, int type, int flags, struct fib_rules_ops *ops) { struct nlmsghdr *nlh; struct fib_rule_hdr *frh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); if (nlh == NULL) return -EMSGSIZE; frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; frh->flags = rule->flags; if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) goto nla_put_failure; if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; if (rule->iifindex == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; if (rule->oifindex == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } if ((rule->pref && nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || (rule->mark && nla_put_u32(skb, FRA_FWMARK, rule->mark)) || ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target)) || (rule->tun_id && nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || (rule->l3mdev && nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || (uid_range_set(&rule->uid_range) && nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) goto nla_put_failure; } if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, struct fib_rules_ops *ops) { int idx = 0; struct fib_rule *rule; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops); if (err) break; skip: idx++; } rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops); return err; } static int fib_valid_dumprule_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib_rule_hdr *frh; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request"); return -EINVAL; } frh = nlmsg_data(nlh); if (frh->dst_len || frh->src_len || frh->tos || frh->table || frh->res1 || frh->res2 || frh->action || frh->flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for fib rule dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request"); return -EINVAL; } return 0; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; int idx = 0, family; if (cb->strict_check) { int err = fib_valid_dumprule_req(nlh, cb->extack); if (err < 0) return err; } family = rtnl_msg_family(nlh); if (family != AF_UNSPEC) { /* Protocol specific dump request */ ops = lookup_rules_ops(net, family); if (ops == NULL) return -EAFNOSUPPORT; dump_rules(skb, cb, ops); return skb->len; } rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (idx < cb->args[0] || !try_module_get(ops->owner)) goto skip; if (dump_rules(skb, cb, ops) < 0) break; cb->args[1] = 0; skip: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid) { struct net *net; struct sk_buff *skb; int err = -ENOMEM; net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); if (skb == NULL) goto errout; err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); if (err < 0) { /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: if (err < 0) rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) rule->iifindex = dev->ifindex; if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) rule->oifindex = dev->ifindex; } } static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) rule->iifindex = -1; if (rule->oifindex == dev->ifindex) rule->oifindex = -1; } } static int fib_rules_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 fib_rules_ops *ops; ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_CHANGENAME: list_for_each_entry(ops, &net->rules_ops, list) { detach_rules(&ops->rules_list, dev); attach_rules(&ops->rules_list, dev); } break; case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; } return NOTIFY_DONE; } static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event, }; static int __net_init fib_rules_net_init(struct net *net) { INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); return 0; } static void __net_exit fib_rules_net_exit(struct net *net) { WARN_ON_ONCE(!list_empty(&net->rules_ops)); } static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit, }; static int __init fib_rules_init(void) { int err; rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) goto fail; err = register_netdevice_notifier(&fib_rules_notifier); if (err < 0) goto fail_unregister; return 0; fail_unregister: unregister_pernet_subsys(&fib_rules_net_ops); fail: rtnl_unregister(PF_UNSPEC, RTM_NEWRULE); rtnl_unregister(PF_UNSPEC, RTM_DELRULE); rtnl_unregister(PF_UNSPEC, RTM_GETRULE); return err; } subsys_initcall(fib_rules_init); |
| 4 1 3 2 1 3 1 1 818 818 818 2 1 1 7 12 11 819 818 818 818 818 818 819 818 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support * Fred Templin <fred.l.templin@boeing.com>: isatap support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip.h> #include <net/udp.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c For comments look at net/ipv4/ip_gre.c --ANK */ #define IP6_SIT_HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) 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"); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst); static struct rtnl_link_ops sit_link_ops __read_mostly; static unsigned int sit_net_id __read_mostly; struct sit_net { struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_wc[1]; struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; static inline struct sit_net *dev_to_sit_net(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); return net_generic(t->net, sit_net_id); } /* * Must be invoked with rcu_read_lock */ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local, int sifindex) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); int ifindex = dev ? dev->ifindex : 0; for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(sitn->tunnels_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; unsigned int h = 0; int prio = 0; if (remote) { prio |= 2; h ^= HASH(remote); } if (local) { prio |= 1; h ^= HASH(local); } return &sitn->tunnels[prio][h]; } static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, struct ip_tunnel *t) { return __ipip6_bucket(sitn, &t->parms); } static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp; struct ip_tunnel *iter; for (tp = ipip6_bucket(sitn, t); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) { #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel *t = netdev_priv(dev); if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) { ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); t->ip6rd.relay_prefix = 0; t->ip6rd.prefixlen = 16; t->ip6rd.relay_prefixlen = 0; } else { struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); } #endif } static int ipip6_tunnel_create(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); int err; memcpy(dev->dev_addr, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); ipip6_tunnel_link(sitn, t); return 0; out: return err; } static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; struct ip_tunnel *t, *nt; struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct sit_net *sitn = net_generic(net, sit_net_id); for (tp = __ipip6_bucket(sitn, parms); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && parms->link == t->parms.link) { if (create) return NULL; else return t; } } if (!create) goto failed; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strlcpy(name, parms->name, IFNAMSIZ); } else { strcpy(name, "sit%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!dev) return NULL; dev_net_set(dev, net); nt = netdev_priv(dev); nt->parms = *parms; if (ipip6_tunnel_create(dev) < 0) goto failed_free; return nt; failed_free: free_netdev(dev); failed: return NULL; } #define for_each_prl_rcu(start) \ for (prl = rcu_dereference(start); \ prl; \ prl = rcu_dereference(prl->next)) static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { struct ip_tunnel_prl_entry *prl; for_each_prl_rcu(t->prl) if (prl->addr == addr) break; return prl; } static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr) { struct ip_tunnel_prl __user *a = ifr->ifr_ifru.ifru_data; struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; unsigned int cmax, c = 0, ca, len; int ret = 0; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&kprl, a, sizeof(kprl))) return -EFAULT; cmax = kprl.datalen / sizeof(kprl); if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) cmax = 1; /* For simple GET or for root users, * we try harder to allocate. */ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) : NULL; ca = min(t->prl_count, cmax); if (!kp) { /* We don't try hard to allocate much memory for * non-root users. * For root users, retry allocating enough memory for * the answer. */ kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC); if (!kp) { ret = -ENOMEM; goto out; } } rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; c++; if (kprl.addr != htonl(INADDR_ANY)) break; } rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) ret = -EFAULT; kfree(kp); out: return ret; } static int ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) { struct ip_tunnel_prl_entry *p; int err = 0; if (a->addr == htonl(INADDR_ANY)) return -EINVAL; ASSERT_RTNL(); for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { if (p->addr == a->addr) { if (chg) { p->flags = a->flags; goto out; } err = -EEXIST; goto out; } } if (chg) { err = -ENXIO; goto out; } p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL); if (!p) { err = -ENOBUFS; goto out; } p->next = t->prl; p->addr = a->addr; p->flags = a->flags; t->prl_count++; rcu_assign_pointer(t->prl, p); out: return err; } static void prl_list_destroy_rcu(struct rcu_head *head) { struct ip_tunnel_prl_entry *p, *n; p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); } static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x; struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; (x = rtnl_dereference(*p)) != NULL; p = &x->next) { if (x->addr == a->addr) { *p = x->next; kfree_rcu(x, rcu_head); t->prl_count--; goto out; } } err = -ENXIO; } else { x = rtnl_dereference(t->prl); if (x) { t->prl_count = 0; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } } out: return err; } static int ipip6_tunnel_prl_ctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl prl; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl))) return -EFAULT; switch (cmd) { case SIOCDELPRL: err = ipip6_tunnel_del_prl(t, &prl); break; case SIOCADDPRL: case SIOCCHGPRL: err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); return err; } static int isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) { struct ip_tunnel_prl_entry *p; int ok = 1; rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT; else skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT; } else { const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; if (ipv6_addr_is_isatap(addr6) && (addr6->s6_addr32[3] == iph->saddr) && ipv6_chk_prefix(addr6, t->dev)) skb->ndisc_nodetype = NDISC_NODETYPE_HOST; else ok = 0; } rcu_read_unlock(); return ok; } static void ipip6_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct sit_net *sitn = net_generic(tunnel->net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } dst_cache_reset(&tunnel->dst_cache); dev_put(dev); } static int ipip6_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; int sifindex; int err; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } err = -ENOENT; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, iph->saddr, sifindex); if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, t->parms.link, iph->protocol); err = 0; goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, iph->protocol); err = 0; goto out; } err = 0; if (__in6_dev_get(skb->dev) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) goto out; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; out: return err; } static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, const struct in6_addr *v6addr) { __be32 v4embed = 0; if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) return true; return false; } /* Checks if an address matches an address on the tunnel interface. * Used to detect the NAT of proto 41 packets and let them pass spoofing test. * Long story: * This function is called after we considered the packet as spoofed * in is_spoofed_6rd. * We may have a router that is doing NAT for proto 41 packets * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd * function will return true, dropping the packet. * But, we can still check if is spoofed against the IP * addresses associated with the interface. */ static bool only_dnatted(const struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { int prefix_len; #ifdef CONFIG_IPV6_SIT_6RD prefix_len = tunnel->ip6rd.prefixlen + 32 - tunnel->ip6rd.relay_prefixlen; #else prefix_len = 48; #endif return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); } /* Returns true if a packet is spoofed */ static bool packet_is_spoofed(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *tunnel) { const struct ipv6hdr *ipv6h; if (tunnel->dev->priv_flags & IFF_ISATAP) { if (!isatap_chksrc(skb, iph, tunnel)) return true; return false; } if (tunnel->dev->flags & IFF_POINTOPOINT) return false; ipv6h = ipv6_hdr(skb); if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) return false; if (only_dnatted(tunnel, &ipv6h->daddr)) return false; net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; int sifindex; int err; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { struct pcpu_sw_netstats *tstats; if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) goto out; skb->mac_header = skb->network_header; skb_reset_network_header(skb); IPCB(skb)->flags = 0; skb->dev = tunnel->dev; if (packet_is_spoofed(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; goto out; } if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; /* skb can be uncloned in iptunnel_pull_header, so * old iph is no longer valid */ iph = (const struct iphdr *)skb_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { ++tunnel->dev->stats.rx_frame_errors; ++tunnel->dev->stats.rx_errors; goto out; } } tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); netif_rx(skb); return 0; } /* no tunnel matched, let upstream know, ipsec may handle it */ return 1; out: kfree_skb(skb); return 0; } static const struct tnl_ptk_info ipip_tpi = { /* no tunnel info required for ipip. */ .proto = htons(ETH_P_IP), }; #if IS_ENABLED(CONFIG_MPLS) static const struct tnl_ptk_info mplsip_tpi = { /* no tunnel info required for mplsip. */ .proto = htons(ETH_P_MPLS_UC), }; #endif static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { const struct iphdr *iph; struct ip_tunnel *tunnel; int sifindex; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { const struct tnl_ptk_info *tpi; if (tunnel->parms.iph.protocol != ipproto && tunnel->parms.iph.protocol != 0) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #if IS_ENABLED(CONFIG_MPLS) if (ipproto == IPPROTO_MPLS) tpi = &mplsip_tpi; else #endif tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } return 1; drop: kfree_skb(skb); return 0; } static int ipip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_IPIP); } #if IS_ENABLED(CONFIG_MPLS) static int mplsip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_MPLS); } #endif /* * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function * stores the embedded IPv4 address in v4dst and returns true. */ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst) { #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { unsigned int pbw0, pbi0; int pbi1; u32 d; pbw0 = tunnel->ip6rd.prefixlen >> 5; pbi0 = tunnel->ip6rd.prefixlen & 0x1f; d = tunnel->ip6rd.relay_prefixlen < 32 ? (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> tunnel->ip6rd.relay_prefixlen : 0; pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; if (pbi1 > 0) d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> (32 - pbi1); *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); return true; } #else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(v4dst, &v6dst->s6_addr16[1], 4); return true; } #endif return false; } static inline __be32 try_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { __be32 dst = 0; check_6rd(tunnel, v6dst, &dst); return dst; } /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; struct flowi4 fl4; int mtu; const struct in6_addr *addr6; int addr_type; u8 ttl; u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); if (tos == 1) tos = ipv6_get_dsfield(iph6); /* ISATAP (RFC4214) - must come before 6to4 */ if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; bool do_tx_error = false; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if ((addr_type & IPV6_ADDR_UNICAST) && ipv6_addr_is_isatap(addr6)) dst = addr6->s6_addr32[3]; else do_tx_error = true; neigh_release(neigh); if (do_tx_error) goto tx_error; } if (!dst) dst = try_6rd(tunnel, &iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; bool do_tx_error = false; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) != 0) dst = addr6->s6_addr32[3]; else do_tx_error = true; neigh_release(neigh); if (do_tx_error) goto tx_error; } flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark, RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_flow(tunnel->net, &fl4, NULL); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); dev->stats.tx_carrier_errors++; goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) { ip_rt_put(rt); goto tx_error; } if (df) { mtu = dst_mtu(&rt->dst) - t_hlen; if (mtu < 68) { dev->stats.collisions++; ip_rt_put(rt); goto tx_error; } if (mtu < IPV6_MIN_MTU) { mtu = IPV6_MIN_MTU; df = 0; } if (tunnel->parms.iph.daddr) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); dev_kfree_skb(skb); skb = new_skb; iph6 = ipv6_hdr(skb); } ttl = tiph->ttl; if (ttl == 0) ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) { ip_rt_put(rt); goto tx_error; } skb_set_inner_ipproto(skb, IPPROTO_IPV6); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); dev->stats.tx_errors++; return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb, struct net_device *dev, u8 ipproto) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, ipproto); ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: kfree_skb(skb); dev->stats.tx_errors++; return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP); break; case htons(ETH_P_IPV6): ipip6_tunnel_xmit(skb, dev); break; #if IS_ENABLED(CONFIG_MPLS) case htons(ETH_P_MPLS_UC): sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS); break; #endif default: goto tx_err; } return NETDEV_TX_OK; tx_err: dev->stats.tx_errors++; kfree_skb(skb); return NETDEV_TX_OK; } static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; struct flowi4 fl4; tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; if (iph->daddr) { struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4, NULL, iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, RT_TOS(iph->tos), tunnel->parms.link); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } dev->flags |= IFF_POINTOPOINT; } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->mtu = tdev->mtu - t_hlen; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; } } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, __u32 fwmark) { struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); ipip6_tunnel_unlink(sitn, t); synchronize_net(); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; memcpy(t->dev->dev_addr, &p->iph.saddr, 4); memcpy(t->dev->broadcast, &p->iph.daddr, 4); ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { t->parms.link = p->link; t->fwmark = fwmark; ipip6_tunnel_bind_dev(t->dev); } dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); } #ifdef CONFIG_IPV6_SIT_6RD static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, struct ip_tunnel_6rd *ip6rd) { struct in6_addr prefix; __be32 relay_prefix; if (ip6rd->relay_prefixlen > 32 || ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) return -EINVAL; ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) return -EINVAL; if (ip6rd->relay_prefixlen) relay_prefix = ip6rd->relay_prefix & htonl(0xffffffffUL << (32 - ip6rd->relay_prefixlen)); else relay_prefix = 0; if (relay_prefix != ip6rd->relay_prefix) return -EINVAL; t->ip6rd.prefix = prefix; t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); return 0; } static int ipip6_tunnel_get6rd(struct net_device *dev, struct ifreq *ifr) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; struct ip_tunnel_parm p; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } if (!t) t = netdev_priv(dev); ip6rd.prefix = t->ip6rd.prefix; ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd, sizeof(ip6rd))) return -EFAULT; return 0; } static int ipip6_tunnel_6rdctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data, sizeof(ip6rd))) return -EFAULT; if (cmd != SIOCDEL6RD) { err = ipip6_tunnel_update_6rd(t, &ip6rd); if (err < 0) return err; } else ipip6_tunnel_clone_6rd(dev, dev_to_sit_net(dev)); return 0; } #endif /* CONFIG_IPV6_SIT_6RD */ static bool ipip6_valid_ip_proto(u8 ipproto) { return ipproto == IPPROTO_IPV6 || ipproto == IPPROTO_IPIP || #if IS_ENABLED(CONFIG_MPLS) ipproto == IPPROTO_MPLS || #endif ipproto == 0; } static int __ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm *p) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!ipip6_valid_ip_proto(p->iph.protocol)) return -EINVAL; if (p->iph.version != 4 || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); return 0; } static int ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) t = ipip6_tunnel_locate(t->net, p, 0); if (!t) t = netdev_priv(dev); memcpy(p, &t->parms, sizeof(*p)); return 0; } static int ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 1); if (!t) return -ENOBUFS; return 0; } static int ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 0); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (!t) return -ENOENT; } else { if (t) { if (t->dev != dev) return -EEXIST; } else { if (((dev->flags & IFF_POINTOPOINT) && !p->iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p->iph.daddr)) return -EINVAL; t = netdev_priv(dev); } ipip6_tunnel_update(t, p, t->fwmark); } return 0; } static int ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm *p) { struct ip_tunnel *t = netdev_priv(dev); if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { t = ipip6_tunnel_locate(t->net, p, 0); if (!t) return -ENOENT; if (t == netdev_priv(dev_to_sit_net(dev)->fb_tunnel_dev)) return -EPERM; dev = t->dev; } unregister_netdevice(dev); return 0; } static int ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { switch (cmd) { case SIOCGETTUNNEL: return ipip6_tunnel_get(dev, p); case SIOCADDTUNNEL: return ipip6_tunnel_add(dev, p); case SIOCCHGTUNNEL: return ipip6_tunnel_change(dev, p); case SIOCDELTUNNEL: return ipip6_tunnel_del(dev, p); default: return -EINVAL; } } static int ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { switch (cmd) { case SIOCGETTUNNEL: case SIOCADDTUNNEL: case SIOCCHGTUNNEL: case SIOCDELTUNNEL: return ip_tunnel_ioctl(dev, ifr, cmd); case SIOCGETPRL: return ipip6_tunnel_get_prl(dev, ifr); case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: return ipip6_tunnel_prl_ctl(dev, ifr, cmd); #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: return ipip6_tunnel_get6rd(dev, ifr); case SIOCADD6RD: case SIOCCHG6RD: case SIOCDEL6RD: return ipip6_tunnel_6rdctl(dev, ifr, cmd); #endif default: return -EINVAL; } } static const struct net_device_ops ipip6_netdev_ops = { .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_do_ioctl = ipip6_tunnel_ioctl, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, }; static void ipip6_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); dst_cache_destroy(&tunnel->dst_cache); free_percpu(dev->tstats); } #define SIT_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static void ipip6_tunnel_setup(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; dev->features |= NETIF_F_LLTX; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; } static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int err; tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) { free_percpu(dev->tstats); dev->tstats = NULL; return err; } dev_hold(dev); return 0; } static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); iph->version = 4; iph->protocol = IPPROTO_IPV6; iph->ihl = 5; iph->ttl = 64; rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (!ipip6_valid_ip_proto(proto)) return -EINVAL; return 0; } static void ipip6_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPV6; parms->iph.ihl = 5; parms->iph.ttl = 64; if (!data) return; if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->iph.saddr = nla_get_be32(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->iph.daddr = nla_get_be32(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) { parms->iph.ttl = nla_get_u8(data[IFLA_IPTUN_TTL]); if (parms->iph.ttl) parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_IPTUN_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]); if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); if (data[IFLA_IPTUN_FLAGS]) parms->i_flags = nla_get_be16(data[IFLA_IPTUN_FLAGS]); if (data[IFLA_IPTUN_PROTO]) parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (data[IFLA_IPTUN_FWMARK]) *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipip6_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_IPTUN_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]); } if (data[IFLA_IPTUN_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]); } if (data[IFLA_IPTUN_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]); } if (data[IFLA_IPTUN_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]); } return ret; } #ifdef CONFIG_IPV6_SIT_6RD /* This function returns true when 6RD attributes are present in the nl msg */ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], struct ip_tunnel_6rd *ip6rd) { bool ret = false; memset(ip6rd, 0, sizeof(*ip6rd)); if (!data) return ret; if (data[IFLA_IPTUN_6RD_PREFIX]) { ret = true; ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { ret = true; ip6rd->relay_prefix = nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); } if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { ret = true; ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { ret = true; ip6rd->relay_prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); } return ret; } #endif static int ipip6_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip_tunnel *nt; struct ip_tunnel_encap ipencap; #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif int err; nt = netdev_priv(dev); if (ipip6_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(nt, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &nt->parms, &nt->fwmark); if (ipip6_tunnel_locate(net, &nt->parms, 0)) return -EEXIST; err = ipip6_tunnel_create(dev); if (err < 0) return err; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu >= IPV6_MIN_MTU && mtu <= IP6_MAX_MTU - dev->hard_header_len) dev->mtu = mtu; } #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) { err = ipip6_tunnel_update_6rd(nt, &ip6rd); if (err < 0) unregister_netdevice_queue(dev, NULL); } #endif return err; } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif __u32 fwmark = t->fwmark; int err; if (dev == sitn->fb_tunnel_dev) return -EINVAL; if (ipip6_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &p, &fwmark); if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) return -EINVAL; t = ipip6_tunnel_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ipip6_tunnel_update(t, &p, fwmark); #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) return ipip6_tunnel_update_6rd(t, &ip6rd); #endif return 0; } static size_t ipip6_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(4) + /* IFLA_IPTUN_REMOTE */ nla_total_size(4) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_TOS */ nla_total_size(1) + /* IFLA_IPTUN_PMTUDISC */ nla_total_size(1) + /* IFLA_IPTUN_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + #ifdef CONFIG_IPV6_SIT_6RD /* IFLA_IPTUN_6RD_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ nla_total_size(4) + /* IFLA_IPTUN_6RD_PREFIXLEN */ nla_total_size(2) + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ nla_total_size(2) + #endif /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; #ifdef CONFIG_IPV6_SIT_6RD if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX, &tunnel->ip6rd.prefix) || nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, tunnel->ip6rd.relay_prefix) || nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, tunnel->ip6rd.prefixlen) || nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, tunnel->ip6rd.relay_prefixlen)) goto nla_put_failure; #endif if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, #ifdef CONFIG_IPV6_SIT_6RD [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, #endif [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static void ipip6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); if (dev != sitn->fb_tunnel_dev) unregister_netdevice_queue(dev, head); } static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, .policy = ipip6_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip6_tunnel_setup, .validate = ipip6_validate, .newlink = ipip6_newlink, .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, .dellink = ipip6_dellink, .get_link_net = ip_tunnel_get_link_net, }; static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, .priority = 1, }; static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip6_err, .priority = 2, }; #if IS_ENABLED(CONFIG_MPLS) static struct xfrm_tunnel mplsip_handler __read_mostly = { .handler = mplsip_rcv, .err_handler = ipip6_err, .priority = 2, }; #endif static void __net_exit sit_destroy_tunnels(struct net *net, struct list_head *head) { struct sit_net *sitn = net_generic(net, sit_net_id); struct net_device *dev, *aux; int prio; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); t = rtnl_dereference(t->next); } } } } static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; sitn->tunnels[2] = sitn->tunnels_r; sitn->tunnels[3] = sitn->tunnels_r_l; if (!net_has_fallback_tunnels(net)) return 0; sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!sitn->fb_tunnel_dev) { err = -ENOMEM; goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; err = register_netdev(sitn->fb_tunnel_dev); if (err) goto err_reg_dev; ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); t = netdev_priv(sitn->fb_tunnel_dev); strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } static void __net_exit sit_exit_batch_net(struct list_head *net_list) { LIST_HEAD(list); struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) sit_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm4_tunnel_deregister(&ipip_handler, AF_INET); #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); #endif unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) { int err; pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n"); err = register_pernet_device(&sit_net_ops); if (err < 0) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { pr_info("%s: can't register ip6ip4\n", __func__); goto xfrm_tunnel_failed; } err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { pr_info("%s: can't register ip4ip4\n", __func__); goto xfrm_tunnel4_failed; } #if IS_ENABLED(CONFIG_MPLS) err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); if (err < 0) { pr_info("%s: can't register mplsip\n", __func__); goto xfrm_tunnel_mpls_failed; } #endif err = rtnl_link_register(&sit_link_ops); if (err < 0) goto rtnl_link_failed; out: return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mpls_failed: #endif xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_tunnel4_failed: xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm_tunnel_failed: unregister_pernet_device(&sit_net_ops); goto out; } module_init(sit_init); module_exit(sit_cleanup); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); |
| 798 798 798 798 798 32 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 | // SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c Extended attribute handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com> Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fsnotify.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/posix_acl_xattr.h> #include <linux/uaccess.h> static const char * strcmp_prefix(const char *a, const char *a_prefix) { while (*a_prefix && *a == *a_prefix) { a++; a_prefix++; } return *a_prefix ? NULL : a; } /* * In order to implement different sets of xattr operations for each xattr * prefix, a filesystem should create a null-terminated array of struct * xattr_handler (one for each prefix) and hang a pointer to it off of the * s_xattr field of the superblock. */ #define for_each_xattr_handler(handlers, handler) \ if (handlers) \ for ((handler) = *(handlers)++; \ (handler) != NULL; \ (handler) = *(handlers)++) /* * Find the xattr_handler with the matching prefix. */ static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return ERR_PTR(-EIO); return ERR_PTR(-EOPNOTSUPP); } for_each_xattr_handler(handlers, handler) { const char *n; n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { if (!handler->prefix ^ !*n) { if (*n) continue; return ERR_PTR(-EINVAL); } *name = n; return handler; } } return ERR_PTR(-EOPNOTSUPP); } /* * Check permissions for extended attribute access. This is a bit complicated * because different namespaces have very different rules. */ static int xattr_permission(struct inode *inode, const char *name, int mask) { /* * We can never set or remove an extended attribute on a read-only * filesystem or on an immutable / append-only inode. */ if (mask & MAY_WRITE) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; /* * Updating an xattr will likely cause i_uid and i_gid * to be writen back improperly if their true value is * unknown to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EPERM; } /* * No restriction for security.* and system.* from the VFS. Decision * on these is left to the underlying filesystem / security module. */ if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return 0; /* * The trusted.* namespace can only be accessed by privileged users. */ if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { if (!capable(CAP_SYS_ADMIN)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; return 0; } /* * In the user.* namespace, only regular files and directories can have * extended attributes. For sticky directories, only the owner and * privileged users can write attributes. */ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && !inode_owner_or_capable(inode)) return -EPERM; } return inode_permission(inode, mask); } /* * Look for any handler that deals with the specified namespace. */ int xattr_supported_namespace(struct inode *inode, const char *prefix) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; size_t preflen; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return -EIO; return -EOPNOTSUPP; } preflen = strlen(prefix); for_each_xattr_handler(handlers, handler) { if (!strncmp(xattr_prefix(handler), prefix, preflen)) return 0; } return -EOPNOTSUPP; } EXPORT_SYMBOL(xattr_supported_namespace); int __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ return handler->set(handler, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); /** * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * * @dentry - object to perform setxattr on * @name - xattr name to set * @value - value to set @name to * @size - size of @value * @flags - flags to pass into filesystem operations * * returns the result of the internal setxattr or setsecurity operations. * * This function requires the caller to lock the inode's i_mutex before it * is executed. It also assumes that the caller will make the appropriate * permission checks. */ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { error = __vfs_setxattr(dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, size, flags); } } else { if (unlikely(is_bad_inode(inode))) return -EIO; } if (error == -EAGAIN) { error = -EOPNOTSUPP; if (issec) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; error = security_inode_setsecurity(inode, suffix, value, size, flags); if (!error) fsnotify_xattr(dentry); } } return error; } /** * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_setxattr_locked(struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_WRITE); if (error) return error; error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: return error; } EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int vfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_NS_GPL(vfs_setxattr, ANDROID_GKI_VFS_EXPORT_ONLY); static ssize_t xattr_getsecurity(struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { len = security_inode_getsecurity(inode, name, &buffer, false); goto out_noalloc; } len = security_inode_getsecurity(inode, name, &buffer, true); if (len < 0) return len; if (size < len) { len = -ERANGE; goto out; } memcpy(value, buffer, len); out: kfree(buffer); out_noalloc: return len; } /* * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr * * Allocate memory, if not already allocated, or re-allocate correct size, * before retrieving the extended attribute. * * Returns the result of alloc, if failed, or the getxattr operation. */ ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; error = xattr_permission(inode, name, MAY_READ); if (error) return error; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; error = handler->get(handler, dentry, inode, name, NULL, 0, 0); if (error < 0) return error; if (!value || (error > xattr_size)) { value = krealloc(*xattr_value, error + 1, flags); if (!value) return -ENOMEM; memset(value, 0, error + 1); } error = handler->get(handler, dentry, inode, name, value, error, 0); *xattr_value = value; return error; } ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size, int flags) { const struct xattr_handler *handler; int error; if (flags & XATTR_NOSECURITY) goto nolsm; error = xattr_permission(inode, name, MAY_READ); if (error) return error; error = security_inode_getxattr(dentry, name); if (error) return error; if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; int ret = xattr_getsecurity(inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ if (ret == -EOPNOTSUPP) goto nolsm; return ret; } nolsm: handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_getxattr); ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { return __vfs_getxattr(dentry, dentry->d_inode, name, value, size, 0); } EXPORT_SYMBOL_NS_GPL(vfs_getxattr, ANDROID_GKI_VFS_EXPORT_ONLY); ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { struct inode *inode = d_inode(dentry); ssize_t error; error = security_inode_listxattr(dentry); if (error) return error; if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); if (size && error > size) error = -ERANGE; } return error; } EXPORT_SYMBOL_NS_GPL(vfs_listxattr, ANDROID_GKI_VFS_EXPORT_ONLY); int __vfs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; return handler->set(handler, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); /** * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_removexattr_locked(struct dentry *dentry, const char *name, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_WRITE); if (error) return error; error = security_inode_removexattr(dentry, name); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_removexattr(dentry, name); if (!error) { fsnotify_xattr(dentry); evm_inode_post_removexattr(dentry, name); } out: return error; } EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int vfs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); /* * Extended attribute SET operations */ static long setxattr(struct dentry *d, const char __user *name, const void __user *value, size_t size, int flags) { int error; void *kvalue = NULL; char kname[XATTR_NAME_MAX + 1]; if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; if (size) { if (size > XATTR_SIZE_MAX) return -E2BIG; kvalue = kvmalloc(size, GFP_KERNEL); if (!kvalue) return -ENOMEM; if (copy_from_user(kvalue, value, size)) { error = -EFAULT; goto out; } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { error = cap_convert_nscap(d, &kvalue, size); if (error < 0) goto out; size = error; } } error = vfs_setxattr(d, kname, kvalue, size, flags); out: kvfree(kvalue); return error; } static int path_setxattr(const char __user *pathname, const char __user *name, const void __user *value, size_t size, int flags, unsigned int lookup_flags) { struct path path; int error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = setxattr(path.dentry, name, value, size, flags); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE5(setxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW); } SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattr(pathname, name, value, size, flags, 0); } SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { struct fd f = fdget(fd); int error = -EBADF; if (!f.file) return error; audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { error = setxattr(f.file->f_path.dentry, name, value, size, flags); mnt_drop_write_file(f.file); } fdput(f); return error; } /* * Extended attribute GET operations */ static ssize_t getxattr(struct dentry *d, const char __user *name, void __user *value, size_t size) { ssize_t error; void *kvalue = NULL; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; if (size) { if (size > XATTR_SIZE_MAX) size = XATTR_SIZE_MAX; kvalue = kvzalloc(size, GFP_KERNEL); if (!kvalue) return -ENOMEM; } error = vfs_getxattr(d, kname, kvalue, size); if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_to_user(kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(kvalue); return error; } static ssize_t path_getxattr(const char __user *pathname, const char __user *name, void __user *value, size_t size, unsigned int lookup_flags) { struct path path; ssize_t error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = getxattr(path.dentry, name, value, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(getxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW); } SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattr(pathname, name, value, size, 0); } SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { struct fd f = fdget(fd); ssize_t error = -EBADF; if (!f.file) return error; audit_file(f.file); error = getxattr(f.file->f_path.dentry, name, value, size); fdput(f); return error; } /* * Extended attribute LIST operations */ static ssize_t listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kvmalloc(size, GFP_KERNEL); if (!klist) return -ENOMEM; } error = vfs_listxattr(d, klist, size); if (error > 0) { if (size && copy_to_user(list, klist, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { /* The file system tried to returned a list bigger than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(klist); return error; } static ssize_t path_listxattr(const char __user *pathname, char __user *list, size_t size, unsigned int lookup_flags) { struct path path; ssize_t error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = listxattr(path.dentry, list, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattr(pathname, list, size, LOOKUP_FOLLOW); } SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattr(pathname, list, size, 0); } SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { struct fd f = fdget(fd); ssize_t error = -EBADF; if (!f.file) return error; audit_file(f.file); error = listxattr(f.file->f_path.dentry, list, size); fdput(f); return error; } /* * Extended attribute REMOVE operations */ static long removexattr(struct dentry *d, const char __user *name) { int error; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; return vfs_removexattr(d, kname); } static int path_removexattr(const char __user *pathname, const char __user *name, unsigned int lookup_flags) { struct path path; int error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = removexattr(path.dentry, name); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(removexattr, const char __user *, pathname, const char __user *, name) { return path_removexattr(pathname, name, LOOKUP_FOLLOW); } SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, const char __user *, name) { return path_removexattr(pathname, name, 0); } SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { struct fd f = fdget(fd); int error = -EBADF; if (!f.file) return error; audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { error = removexattr(f.file->f_path.dentry, name); mnt_drop_write_file(f.file); } fdput(f); return error; } /* * Combine the results of the list() operation from every xattr_handler in the * list. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr; unsigned int size = 0; if (!buffer) { for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; size += strlen(handler->name) + 1; } } else { char *buf = buffer; size_t len; for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; len = strlen(handler->name); if (len + 1 > buffer_size) return -ERANGE; memcpy(buf, handler->name, len + 1); buf += len + 1; buffer_size -= len + 1; } size = buf - buffer; } return size; } EXPORT_SYMBOL(generic_listxattr); /** * xattr_full_name - Compute full attribute name from suffix * * @handler: handler of the xattr_handler operation * @name: name passed to the xattr_handler operation * * The get and set xattr handler operations are called with the remainder of * the attribute name after skipping the handler's prefix: for example, "foo" * is passed to the get operation of a handler with prefix "user." to get * attribute "user.foo". The full name is still "there" in the name though. * * Note: the list xattr handler operation when called from the vfs is passed a * NULL name; some file systems use this operation internally, with varying * semantics. */ const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } EXPORT_SYMBOL(xattr_full_name); /* * Allocate new xattr and copy in the value; but leave the name to callers. */ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) { struct simple_xattr *new_xattr; size_t len; /* wrap around? */ len = sizeof(*new_xattr) + size; if (len < sizeof(*new_xattr)) return NULL; new_xattr = kvmalloc(len, GFP_KERNEL); if (!new_xattr) return NULL; new_xattr->size = size; memcpy(new_xattr->value, value, size); return new_xattr; } /* * xattr GET operation for in-memory/pseudo filesystems */ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size) { struct simple_xattr *xattr; int ret = -ENODATA; spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { if (strcmp(name, xattr->name)) continue; ret = xattr->size; if (buffer) { if (size < xattr->size) ret = -ERANGE; else memcpy(buffer, xattr->value, xattr->size); } break; } spin_unlock(&xattrs->lock); return ret; } /** * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems * @xattrs: target simple_xattr list * @name: name of the extended attribute * @value: value of the xattr. If %NULL, will remove the attribute. * @size: size of the new xattr * @flags: %XATTR_{CREATE|REPLACE} * @removed_size: returns size of the removed xattr, -1 if none removed * * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; * otherwise, fails with -ENODATA. * * Returns 0 on success, -errno on failure. */ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size) { struct simple_xattr *xattr; struct simple_xattr *new_xattr = NULL; int err = 0; if (removed_size) *removed_size = -1; /* value == NULL means remove */ if (value) { new_xattr = simple_xattr_alloc(value, size); if (!new_xattr) return -ENOMEM; new_xattr->name = kstrdup(name, GFP_KERNEL); if (!new_xattr->name) { kvfree(new_xattr); return -ENOMEM; } } spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { if (!strcmp(name, xattr->name)) { if (flags & XATTR_CREATE) { xattr = new_xattr; err = -EEXIST; } else if (new_xattr) { list_replace(&xattr->list, &new_xattr->list); if (removed_size) *removed_size = xattr->size; } else { list_del(&xattr->list); if (removed_size) *removed_size = xattr->size; } goto out; } } if (flags & XATTR_REPLACE) { xattr = new_xattr; err = -ENODATA; } else { list_add(&new_xattr->list, &xattrs->head); xattr = NULL; } out: spin_unlock(&xattrs->lock); if (xattr) { kfree(xattr->name); kvfree(xattr); } return err; } static bool xattr_is_trusted(const char *name) { return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } static int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) { size_t len = strlen(name) + 1; if (*buffer) { if (*remaining_size < len) return -ERANGE; memcpy(*buffer, name, len); *buffer += len; } *remaining_size -= len; return 0; } /* * xattr LIST operation for in-memory/pseudo filesystems */ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (IS_POSIXACL(inode)) { if (inode->i_acl) { err = xattr_list_one(&buffer, &remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(&buffer, &remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } } #endif spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; } spin_unlock(&xattrs->lock); return err ? err : size - remaining_size; } /* * Adds an extended attribute to the list */ void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr) { spin_lock(&xattrs->lock); list_add(&new_xattr->list, &xattrs->head); spin_unlock(&xattrs->lock); } |
| 14 14 6 25 1 14 7 2 14 5 29 8 5 5 3 3 3 1 1 1 10 1 7 2 2 5 3 2 1 2 3 1 1 1 3 8 7 1 1 1 2 1 1 4 2 5 3 3 1 8 1184 1092 878 78 78 156 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 | // 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> #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; 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_dtab *dtab; 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 **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_PER_CPU(struct list_head, dev_flush_list); 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_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { u32 valsize = attr->value_size; u64 cost = 0; int err; /* 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; /* 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) { dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); if (!dtab->n_buckets) /* Overflow check */ return -EINVAL; cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; } else { cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); } /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); if (err) return -EINVAL; if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) goto free_charge; 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) goto free_charge; } return 0; free_charge: bpf_map_charge_finish(&dtab->map.memory); return -ENOMEM; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); dtab = kzalloc(sizeof(*dtab), GFP_USER); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { kfree(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); int 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_clear_redirect_map(map); 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 = 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); } kfree(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; } struct bpf_dtab_netdev *__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; } bool dev_map_can_have_prog(struct bpf_map *map) { if ((map->map_type == BPF_MAP_TYPE_DEVMAP || map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) && map->value_size != offsetofend(struct bpf_devmap_val, ifindex)) return true; return false; } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; int sent = 0, drops = 0, err = 0; int i; if (unlikely(!bq->count)) return; for (i = 0; i < bq->count; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); if (sent < 0) { err = sent; sent = 0; goto error; } drops = bq->count - sent; out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); return; error: /* If ndo_xdp_xmit fails with an errno, no frames have been * xmit'ed and it's our responsibility to them free all. */ for (i = 0; i < bq->count; i++) { struct xdp_frame *xdpf = bq->q[i]; xdp_return_frame_rx_napi(xdpf); drops++; } goto out; } /* __dev_flush is called from xdp_do_flush() which _must_ be signaled * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the * net device can be torn down. On devmap tear down we ensure the flush list * is empty before completing to ensure all flush operations have completed. * When drivers update the bpf program they may need to ensure any flush ops * are also complete. Using synchronize_rcu or call_rcu will suffice for this * because both wait for napi context to exit. */ void __dev_flush(void) { struct list_head *flush_list = this_cpu_ptr(&dev_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); } /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or * update happens in parallel here a dev_put wont happen until after reading the * ifindex. */ struct bpf_dtab_netdev *__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 = READ_ONCE(dtab->netdev_map[key]); return obj; } /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); 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. */ if (!bq->dev_rx) bq->dev_rx = dev_rx; bq->q[bq->count++] = xdpf; if (!bq->flush_node.prev) list_add(&bq->flush_node, flush_list); } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx) { struct xdp_frame *xdpf; int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); if (unlikely(err)) return err; xdpf = xdp_convert_buff_to_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; bq_enqueue(dev, xdpf, dev_rx); return 0; } static struct xdp_buff *dev_map_run_prog(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct xdp_txq_info txq = { .dev = dev }; u32 act; xdp_set_data_meta_invalid(xdp); xdp->txq = &txq; act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: return xdp; case XDP_DROP: break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); break; } xdp_return_buff(xdp); return NULL; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdp, dev_rx); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx) { struct net_device *dev = dst->dev; if (dst->xdp_prog) { xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog); if (!xdp) return 0; } return __xdp_enqueue(dev, xdp, dev_rx); } 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; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); 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 int 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; int k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; /* Use call_rcu() here to ensure any rcu critical sections have * completed as well as any flush operations because call_rcu * will wait for preempt-disable region to complete, NAPI in this * context. And additionally, the driver tear down ensures all * soft irqs are complete before removing the net device in the * case of dev_put equals zero. */ old_dev = xchg(&dtab->netdev_map[k], NULL); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; } static int 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; int 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 = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __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) goto err_put_prog; } dev->idx = idx; dev->dtab = dtab; 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 int __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 = xchg(&dtab->netdev_map[i], dev); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; } static int 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 int __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 int 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 int dev_map_btf_id; const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .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_btf_name = "bpf_dtab", .map_btf_id = &dev_map_btf_id, }; static int dev_map_hash_map_btf_id; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .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_btf_name = "bpf_dtab", .map_btf_id = &dev_map_hash_map_btf_id, }; 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 = READ_ONCE(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); if (dev == odev) call_rcu(&dev->rcu, __dev_map_entry_free); } } 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) { int cpu; /* 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); for_each_possible_cpu(cpu) INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } subsys_initcall(dev_map_init); |
| 1075 1075 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 | // SPDX-License-Identifier: GPL-2.0 /* * Software nodes for the firmware node framework. * * Copyright (C) 2018, Intel Corporation * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com> */ #include <linux/device.h> #include <linux/kernel.h> #include <linux/property.h> #include <linux/slab.h> struct swnode { int id; struct kobject kobj; struct fwnode_handle fwnode; const struct software_node *node; /* hierarchy */ struct ida child_ids; struct list_head entry; struct list_head children; struct swnode *parent; unsigned int allocated:1; }; static DEFINE_IDA(swnode_root_ids); static struct kset *swnode_kset; #define kobj_to_swnode(_kobj_) container_of(_kobj_, struct swnode, kobj) static const struct fwnode_operations software_node_ops; bool is_software_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &software_node_ops; } EXPORT_SYMBOL_GPL(is_software_node); #define to_swnode(__fwnode) \ ({ \ typeof(__fwnode) __to_swnode_fwnode = __fwnode; \ \ is_software_node(__to_swnode_fwnode) ? \ container_of(__to_swnode_fwnode, \ struct swnode, fwnode) : NULL; \ }) static inline struct swnode *dev_to_swnode(struct device *dev) { struct fwnode_handle *fwnode = dev_fwnode(dev); if (!fwnode) return NULL; if (!is_software_node(fwnode)) fwnode = fwnode->secondary; return to_swnode(fwnode); } static struct swnode * software_node_to_swnode(const struct software_node *node) { struct swnode *swnode = NULL; struct kobject *k; if (!node) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (swnode->node == node) break; swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode; } const struct software_node *to_software_node(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(to_software_node); struct fwnode_handle *software_node_fwnode(const struct software_node *node) { struct swnode *swnode = software_node_to_swnode(node); return swnode ? &swnode->fwnode : NULL; } EXPORT_SYMBOL_GPL(software_node_fwnode); /* -------------------------------------------------------------------------- */ /* property_entry processing */ static const struct property_entry * property_entry_get(const struct property_entry *prop, const char *name) { if (!prop) return NULL; for (; prop->name; prop++) if (!strcmp(name, prop->name)) return prop; return NULL; } static const void *property_get_pointer(const struct property_entry *prop) { if (!prop->length) return NULL; return prop->is_inline ? &prop->value : prop->pointer; } static const void *property_entry_find(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; const void *pointer; prop = property_entry_get(props, propname); if (!prop) return ERR_PTR(-EINVAL); pointer = property_get_pointer(prop); if (!pointer) return ERR_PTR(-ENODATA); if (length > prop->length) return ERR_PTR(-EOVERFLOW); return pointer; } static int property_entry_count_elems_of_size(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; prop = property_entry_get(props, propname); if (!prop) return -EINVAL; return prop->length / length; } static int property_entry_read_int_array(const struct property_entry *props, const char *name, unsigned int elem_size, void *val, size_t nval) { const void *pointer; size_t length; if (!val) return property_entry_count_elems_of_size(props, name, elem_size); if (!is_power_of_2(elem_size) || elem_size > sizeof(u64)) return -ENXIO; length = nval * elem_size; pointer = property_entry_find(props, name, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(val, pointer, length); return 0; } static int property_entry_read_string_array(const struct property_entry *props, const char *propname, const char **strings, size_t nval) { const void *pointer; size_t length; int array_len; /* Find out the array length. */ array_len = property_entry_count_elems_of_size(props, propname, sizeof(const char *)); if (array_len < 0) return array_len; /* Return how many there are if strings is NULL. */ if (!strings) return array_len; array_len = min_t(size_t, nval, array_len); length = array_len * sizeof(*strings); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(strings, pointer, length); return array_len; } static void property_entry_free_data(const struct property_entry *p) { const char * const *src_str; size_t i, nval; if (p->type == DEV_PROP_STRING) { src_str = property_get_pointer(p); nval = p->length / sizeof(*src_str); for (i = 0; i < nval; i++) kfree(src_str[i]); } if (!p->is_inline) kfree(p->pointer); kfree(p->name); } static bool property_copy_string_array(const char **dst_ptr, const char * const *src_ptr, size_t nval) { int i; for (i = 0; i < nval; i++) { dst_ptr[i] = kstrdup(src_ptr[i], GFP_KERNEL); if (!dst_ptr[i] && src_ptr[i]) { while (--i >= 0) kfree(dst_ptr[i]); return false; } } return true; } static int property_entry_copy_data(struct property_entry *dst, const struct property_entry *src) { const void *pointer = property_get_pointer(src); void *dst_ptr; size_t nval; /* * Properties with no data should not be marked as stored * out of line. */ if (!src->is_inline && !src->length) return -ENODATA; /* * Reference properties are never stored inline as * they are too big. */ if (src->type == DEV_PROP_REF && src->is_inline) return -EINVAL; if (src->length <= sizeof(dst->value)) { dst_ptr = &dst->value; dst->is_inline = true; } else { dst_ptr = kmalloc(src->length, GFP_KERNEL); if (!dst_ptr) return -ENOMEM; dst->pointer = dst_ptr; } if (src->type == DEV_PROP_STRING) { nval = src->length / sizeof(const char *); if (!property_copy_string_array(dst_ptr, pointer, nval)) { if (!dst->is_inline) kfree(dst->pointer); return -ENOMEM; } } else { memcpy(dst_ptr, pointer, src->length); } dst->length = src->length; dst->type = src->type; dst->name = kstrdup(src->name, GFP_KERNEL); if (!dst->name) { property_entry_free_data(dst); return -ENOMEM; } return 0; } /** * property_entries_dup - duplicate array of properties * @properties: array of properties to copy * * This function creates a deep copy of the given NULL-terminated array * of property entries. */ struct property_entry * property_entries_dup(const struct property_entry *properties) { struct property_entry *p; int i, n = 0; int ret; if (!properties) return NULL; while (properties[n].name) n++; p = kcalloc(n + 1, sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); for (i = 0; i < n; i++) { ret = property_entry_copy_data(&p[i], &properties[i]); if (ret) { while (--i >= 0) property_entry_free_data(&p[i]); kfree(p); return ERR_PTR(ret); } } return p; } EXPORT_SYMBOL_GPL(property_entries_dup); /** * property_entries_free - free previously allocated array of properties * @properties: array of properties to destroy * * This function frees given NULL-terminated array of property entries, * along with their data. */ void property_entries_free(const struct property_entry *properties) { const struct property_entry *p; if (!properties) return; for (p = properties; p->name; p++) property_entry_free_data(p); kfree(properties); } EXPORT_SYMBOL_GPL(property_entries_free); /* -------------------------------------------------------------------------- */ /* fwnode operations */ static struct fwnode_handle *software_node_get(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_get(&swnode->kobj); return &swnode->fwnode; } static void software_node_put(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_put(&swnode->kobj); } static bool software_node_property_present(const struct fwnode_handle *fwnode, const char *propname) { struct swnode *swnode = to_swnode(fwnode); return !!property_entry_get(swnode->node->properties, propname); } static int software_node_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_int_array(swnode->node->properties, propname, elem_size, val, nval); } static int software_node_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_string_array(swnode->node->properties, propname, val, nval); } static const char * software_node_get_name(const struct fwnode_handle *fwnode) { const struct swnode *swnode = to_swnode(fwnode); if (!swnode) return "(null)"; return kobject_name(&swnode->kobj); } static const char * software_node_get_name_prefix(const struct fwnode_handle *fwnode) { struct fwnode_handle *parent; const char *prefix; parent = fwnode_get_parent(fwnode); if (!parent) return ""; /* Figure out the prefix from the parents. */ while (is_software_node(parent)) parent = fwnode_get_next_parent(parent); prefix = fwnode_get_name_prefix(parent); fwnode_handle_put(parent); /* Guess something if prefix was NULL. */ return prefix ?: "/"; } static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode || !swnode->parent) return NULL; return fwnode_handle_get(&swnode->parent->fwnode); } static struct fwnode_handle * software_node_get_next_child(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct swnode *p = to_swnode(fwnode); struct swnode *c = to_swnode(child); if (!p || list_empty(&p->children) || (c && list_is_last(&c->entry, &p->children))) { fwnode_handle_put(child); return NULL; } if (c) c = list_next_entry(c, entry); else c = list_first_entry(&p->children, struct swnode, entry); fwnode_handle_put(child); return fwnode_handle_get(&c->fwnode); } static struct fwnode_handle * software_node_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct swnode *swnode = to_swnode(fwnode); struct swnode *child; if (!swnode || list_empty(&swnode->children)) return NULL; list_for_each_entry(child, &swnode->children, entry) { if (!strcmp(childname, kobject_name(&child->kobj))) { kobject_get(&child->kobj); return &child->fwnode; } } return NULL; } static int software_node_get_reference_args(const struct fwnode_handle *fwnode, const char *propname, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_ref_args *ref_array; const struct software_node_ref_args *ref; const struct property_entry *prop; struct fwnode_handle *refnode; u32 nargs_prop_val; int error; int i; if (!swnode) return -ENOENT; prop = property_entry_get(swnode->node->properties, propname); if (!prop) return -ENOENT; if (prop->type != DEV_PROP_REF) return -EINVAL; /* * We expect that references are never stored inline, even * single ones, as they are too big. */ if (prop->is_inline) return -EINVAL; if (index * sizeof(*ref) >= prop->length) return -ENOENT; ref_array = prop->pointer; ref = &ref_array[index]; refnode = software_node_fwnode(ref->node); if (!refnode) return -ENOENT; if (nargs_prop) { error = property_entry_read_int_array(ref->node->properties, nargs_prop, sizeof(u32), &nargs_prop_val, 1); if (error) return error; nargs = nargs_prop_val; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; args->fwnode = software_node_get(refnode); args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = ref->args[i]; return 0; } static const struct fwnode_operations software_node_ops = { .get = software_node_get, .put = software_node_put, .property_present = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_name = software_node_get_name, .get_name_prefix = software_node_get_name_prefix, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, .get_reference_args = software_node_get_reference_args }; /* -------------------------------------------------------------------------- */ /** * software_node_find_by_name - Find software node by name * @parent: Parent of the software node * @name: Name of the software node * * The function will find a node that is child of @parent and that is named * @name. If no node is found, the function returns NULL. * * NOTE: you will need to drop the reference with fwnode_handle_put() after use. */ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name) { struct swnode *swnode = NULL; struct kobject *k; if (!name) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (parent == swnode->node->parent && swnode->node->name && !strcmp(name, swnode->node->name)) { kobject_get(&swnode->kobj); break; } swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(software_node_find_by_name); static int software_node_register_properties(struct software_node *node, const struct property_entry *properties) { struct property_entry *props; props = property_entries_dup(properties); if (IS_ERR(props)) return PTR_ERR(props); node->properties = props; return 0; } static void software_node_release(struct kobject *kobj) { struct swnode *swnode = kobj_to_swnode(kobj); if (swnode->parent) { ida_simple_remove(&swnode->parent->child_ids, swnode->id); list_del(&swnode->entry); } else { ida_simple_remove(&swnode_root_ids, swnode->id); } if (swnode->allocated) { property_entries_free(swnode->node->properties); kfree(swnode->node); } ida_destroy(&swnode->child_ids); kfree(swnode); } static struct kobj_type software_node_type = { .release = software_node_release, .sysfs_ops = &kobj_sysfs_ops, }; static struct fwnode_handle * swnode_register(const struct software_node *node, struct swnode *parent, unsigned int allocated) { struct swnode *swnode; int ret; swnode = kzalloc(sizeof(*swnode), GFP_KERNEL); if (!swnode) { ret = -ENOMEM; goto out_err; } ret = ida_simple_get(parent ? &parent->child_ids : &swnode_root_ids, 0, 0, GFP_KERNEL); if (ret < 0) { kfree(swnode); goto out_err; } swnode->id = ret; swnode->node = node; swnode->parent = parent; swnode->allocated = allocated; swnode->kobj.kset = swnode_kset; fwnode_init(&swnode->fwnode, &software_node_ops); ida_init(&swnode->child_ids); INIT_LIST_HEAD(&swnode->entry); INIT_LIST_HEAD(&swnode->children); if (node->name) ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "%s", node->name); else ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "node%d", swnode->id); if (ret) { kobject_put(&swnode->kobj); return ERR_PTR(ret); } if (parent) list_add_tail(&swnode->entry, &parent->children); kobject_uevent(&swnode->kobj, KOBJ_ADD); return &swnode->fwnode; out_err: if (allocated) property_entries_free(node->properties); return ERR_PTR(ret); } /** * software_node_register_nodes - Register an array of software nodes * @nodes: Zero terminated array of software nodes to be registered * * Register multiple software nodes at once. */ int software_node_register_nodes(const struct software_node *nodes) { int ret; int i; for (i = 0; nodes[i].name; i++) { ret = software_node_register(&nodes[i]); if (ret) { software_node_unregister_nodes(nodes); return ret; } } return 0; } EXPORT_SYMBOL_GPL(software_node_register_nodes); /** * software_node_unregister_nodes - Unregister an array of software nodes * @nodes: Zero terminated array of software nodes to be unregistered * * Unregister multiple software nodes at once. * * NOTE: Be careful using this call if the nodes had parent pointers set up in * them before registering. If so, it is wiser to remove the nodes * individually, in the correct order (child before parent) instead of relying * on the sequential order of the list of nodes in the array. */ void software_node_unregister_nodes(const struct software_node *nodes) { int i; for (i = 0; nodes[i].name; i++) software_node_unregister(&nodes[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_nodes); /** * software_node_register_node_group - Register a group of software nodes * @node_group: NULL terminated array of software node pointers to be registered * * Register multiple software nodes at once. */ int software_node_register_node_group(const struct software_node **node_group) { unsigned int i; int ret; if (!node_group) return 0; for (i = 0; node_group[i]; i++) { ret = software_node_register(node_group[i]); if (ret) { software_node_unregister_node_group(node_group); return ret; } } return 0; } EXPORT_SYMBOL_GPL(software_node_register_node_group); /** * software_node_unregister_node_group - Unregister a group of software nodes * @node_group: NULL terminated array of software node pointers to be unregistered * * Unregister multiple software nodes at once. */ void software_node_unregister_node_group(const struct software_node **node_group) { unsigned int i; if (!node_group) return; for (i = 0; node_group[i]; i++) software_node_unregister(node_group[i]); } EXPORT_SYMBOL_GPL(software_node_unregister_node_group); /** * software_node_register - Register static software node * @node: The software node to be registered */ int software_node_register(const struct software_node *node) { struct swnode *parent = software_node_to_swnode(node->parent); if (software_node_to_swnode(node)) return -EEXIST; if (node->parent && !parent) return -EINVAL; return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0)); } EXPORT_SYMBOL_GPL(software_node_register); /** * software_node_unregister - Unregister static software node * @node: The software node to be unregistered */ void software_node_unregister(const struct software_node *node) { struct swnode *swnode; swnode = software_node_to_swnode(node); if (swnode) fwnode_remove_software_node(&swnode->fwnode); } EXPORT_SYMBOL_GPL(software_node_unregister); struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent) { struct software_node *node; struct swnode *p = NULL; int ret; if (parent) { if (IS_ERR(parent)) return ERR_CAST(parent); if (!is_software_node(parent)) return ERR_PTR(-EINVAL); p = to_swnode(parent); } node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return ERR_PTR(-ENOMEM); ret = software_node_register_properties(node, properties); if (ret) { kfree(node); return ERR_PTR(ret); } node->parent = p ? p->node : NULL; return swnode_register(node, p, 1); } EXPORT_SYMBOL_GPL(fwnode_create_software_node); void fwnode_remove_software_node(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode) return; kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(fwnode_remove_software_node); /** * device_add_software_node - Assign software node to a device * @dev: The device the software node is meant for. * @node: The software node. * * This function will make @node the secondary firmware node pointer of @dev. If * @dev has no primary node, then @node will become the primary node. The * function will register @node automatically if it wasn't already registered. */ int device_add_software_node(struct device *dev, const struct software_node *node) { struct swnode *swnode; int ret; /* Only one software node per device. */ if (dev_to_swnode(dev)) return -EBUSY; swnode = software_node_to_swnode(node); if (swnode) { kobject_get(&swnode->kobj); } else { ret = software_node_register(node); if (ret) return ret; swnode = software_node_to_swnode(node); } set_secondary_fwnode(dev, &swnode->fwnode); /* * If the device has been fully registered by the time this function is * called, software_node_notify() must be called separately so that the * symlinks get created and the reference count of the node is kept in * balance. */ if (device_is_registered(dev)) software_node_notify(dev, KOBJ_ADD); return 0; } EXPORT_SYMBOL_GPL(device_add_software_node); /** * device_remove_software_node - Remove device's software node * @dev: The device with the software node. * * This function will unregister the software node of @dev. */ void device_remove_software_node(struct device *dev) { struct swnode *swnode; swnode = dev_to_swnode(dev); if (!swnode) return; if (device_is_registered(dev)) software_node_notify(dev, KOBJ_REMOVE); set_secondary_fwnode(dev, NULL); kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(device_remove_software_node); int software_node_notify(struct device *dev, unsigned long action) { struct swnode *swnode; int ret; swnode = dev_to_swnode(dev); if (!swnode) return 0; switch (action) { case KOBJ_ADD: ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); if (ret) break; ret = sysfs_create_link(&swnode->kobj, &dev->kobj, dev_name(dev)); if (ret) { sysfs_remove_link(&dev->kobj, "software_node"); break; } kobject_get(&swnode->kobj); break; case KOBJ_REMOVE: sysfs_remove_link(&swnode->kobj, dev_name(dev)); sysfs_remove_link(&dev->kobj, "software_node"); kobject_put(&swnode->kobj); break; default: break; } return 0; } static int __init software_node_init(void) { swnode_kset = kset_create_and_add("software_nodes", NULL, kernel_kobj); if (!swnode_kset) return -ENOMEM; return 0; } postcore_initcall(software_node_init); static void __exit software_node_exit(void) { ida_destroy(&swnode_root_ids); kset_unregister(swnode_kset); } __exitcall(software_node_exit); |
| 53 52 53 51 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/export.h> #include <linux/init.h> #include <linux/udp.h> #include <linux/tcp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/checksum.h> #include <linux/netfilter.h> #include <net/netfilter/nf_nat.h> #include <linux/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/ip6_route.h> #include <net/xfrm.h> #include <net/ipv6.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack.h> #include <linux/netfilter/nfnetlink_conntrack.h> static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype); static void __udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, struct udphdr *hdr, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, bool do_csum) { __be16 *portptr, newport; if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.udp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.udp.port; portptr = &hdr->dest; } if (do_csum) { nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, false); if (!hdr->check) hdr->check = CSUM_MANGLED_0; } *portptr = newport; } static bool udp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); return true; } static bool udplite_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_UDPLITE struct udphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, true); #endif return true; } static bool sctp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct sctphdr *hdr; int hdrsize = 8; /* This could be an inner header returned in imcp packet; in such * cases we cannot update the checksum field since it is outside * of the 8 bytes of transport layer headers we are guaranteed. */ if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct sctphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ hdr->source = tuple->src.u.sctp.port; } else { /* Get rid of dst port */ hdr->dest = tuple->dst.u.sctp.port; } if (hdrsize < sizeof(*hdr)) return true; if (skb->ip_summed != CHECKSUM_PARTIAL) { hdr->checksum = sctp_compute_cksum(skb, hdroff); skb->ip_summed = CHECKSUM_NONE; } #endif return true; } static bool tcp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct tcphdr *hdr; __be16 *portptr, newport, oldport; int hdrsize = 8; /* TCP connection tracking guarantees this much */ /* this could be a inner header returned in icmp packet; in such cases we cannot update the checksum field since it is outside of the 8 bytes of transport layer headers we are guaranteed */ if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct tcphdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src port */ newport = tuple->src.u.tcp.port; portptr = &hdr->source; } else { /* Get rid of dst port */ newport = tuple->dst.u.tcp.port; portptr = &hdr->dest; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, false); return true; } static bool dccp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #ifdef CONFIG_NF_CT_PROTO_DCCP struct dccp_hdr *hdr; __be16 *portptr, oldport, newport; int hdrsize = 8; /* DCCP connection tracking guarantees this much */ if (skb->len >= hdroff + sizeof(struct dccp_hdr)) hdrsize = sizeof(struct dccp_hdr); if (skb_ensure_writable(skb, hdroff + hdrsize)) return false; hdr = (struct dccp_hdr *)(skb->data + hdroff); if (maniptype == NF_NAT_MANIP_SRC) { newport = tuple->src.u.dccp.port; portptr = &hdr->dccph_sport; } else { newport = tuple->dst.u.dccp.port; portptr = &hdr->dccph_dport; } oldport = *portptr; *portptr = newport; if (hdrsize < sizeof(*hdr)) return true; nf_csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype); inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, false); #endif return true; } static bool icmp_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmphdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmphdr *)(skb->data + hdroff); switch (hdr->type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMP_INFO_REQUEST: case ICMP_INFO_REPLY: case ICMP_ADDRESS: case ICMP_ADDRESSREPLY: break; default: return true; } inet_proto_csum_replace2(&hdr->checksum, skb, hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } static bool icmpv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { struct icmp6hdr *hdr; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct icmp6hdr *)(skb->data + hdroff); nf_csum_update(skb, iphdroff, &hdr->icmp6_cksum, tuple, maniptype); if (hdr->icmp6_type == ICMPV6_ECHO_REQUEST || hdr->icmp6_type == ICMPV6_ECHO_REPLY) { inet_proto_csum_replace2(&hdr->icmp6_cksum, skb, hdr->icmp6_identifier, tuple->src.u.icmp.id, false); hdr->icmp6_identifier = tuple->src.u.icmp.id; } return true; } /* manipulate a GRE packet according to maniptype */ static bool gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) const struct gre_base_hdr *greh; struct pptp_gre_header *pgreh; /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false; greh = (void *)skb->data + hdroff; pgreh = (struct pptp_gre_header *)greh; /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->flags & GRE_VERSION) { case GRE_VERSION_0: /* We do not currently NAT any GREv0 packets. * Try to behave like "nf_nat_proto_unknown" */ break; case GRE_VERSION_1: pr_debug("call_id -> 0x%04x\n", ntohs(tuple->dst.u.gre.key)); pgreh->call_id = tuple->dst.u.gre.key; break; default: pr_debug("can't nat unknown GRE version\n"); return false; } #endif return true; } static bool l4proto_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { switch (tuple->dst.protonum) { case IPPROTO_TCP: return tcp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDP: return udp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_UDPLITE: return udplite_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_SCTP: return sctp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMP: return icmp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_ICMPV6: return icmpv6_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_DCCP: return dccp_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); case IPPROTO_GRE: return gre_manip_pkt(skb, iphdroff, hdroff, tuple, maniptype); } /* If we don't know protocol -- no error, pass it unmodified. */ return true; } static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { struct iphdr *iph; unsigned int hdroff; if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false; iph = (void *)skb->data + iphdroff; hdroff = iphdroff + iph->ihl * 4; if (!l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; iph = (void *)skb->data + iphdroff; if (maniptype == NF_NAT_MANIP_SRC) { csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); iph->saddr = target->src.u3.ip; } else { csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); iph->daddr = target->dst.u3.ip; } return true; } static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) struct ipv6hdr *ipv6h; __be16 frag_off; int hdroff; u8 nexthdr; if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false; ipv6h = (void *)skb->data + iphdroff; nexthdr = ipv6h->nexthdr; hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h), &nexthdr, &frag_off); if (hdroff < 0) goto manip_addr; if ((frag_off & htons(~0x7)) == 0 && !l4proto_manip_pkt(skb, iphdroff, hdroff, target, maniptype)) return false; /* must reload, offset might have changed */ ipv6h = (void *)skb->data + iphdroff; manip_addr: if (maniptype == NF_NAT_MANIP_SRC) ipv6h->saddr = target->src.u3.in6; else ipv6h->daddr = target->dst.u3.in6; #endif return true; } unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir) { struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (target.src.l3num) { case NFPROTO_IPV6: if (nf_nat_ipv6_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; case NFPROTO_IPV4: if (nf_nat_ipv4_manip_pkt(skb, 0, &target, mtype)) return NF_ACCEPT; break; default: WARN_ON_ONCE(1); break; } return NF_DROP; } static void nf_nat_ipv4_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); __be32 oldip, newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = iph->saddr; newip = t->src.u3.ip; } else { oldip = iph->daddr; newip = t->dst.u3.ip; } inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv6_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { #if IS_ENABLED(CONFIG_IPV6) const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff); const struct in6_addr *oldip, *newip; if (maniptype == NF_NAT_MANIP_SRC) { oldip = &ipv6h->saddr; newip = &t->src.u3.in6; } else { oldip = &ipv6h->daddr; newip = &t->dst.u3.in6; } inet_proto_csum_replace16(check, skb, oldip->s6_addr32, newip->s6_addr32, true); #endif } static void nf_csum_update(struct sk_buff *skb, unsigned int iphdroff, __sum16 *check, const struct nf_conntrack_tuple *t, enum nf_nat_manip_type maniptype) { switch (t->src.l3num) { case NFPROTO_IPV4: nf_nat_ipv4_csum_update(skb, iphdroff, check, t, maniptype); return; case NFPROTO_IPV6: nf_nat_ipv6_csum_update(skb, iphdroff, check, t, maniptype); return; } } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct iphdr *iph = ip_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + ip_hdrlen(skb); skb->csum_offset = (void *)check - data; *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #if IS_ENABLED(CONFIG_IPV6) static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { if (skb->ip_summed != CHECKSUM_PARTIAL) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + (data - (void *)skb->data); skb->csum_offset = (void *)check - data; *check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, datalen, proto, 0); } else { inet_proto_csum_replace2(check, skb, htons(oldlen), htons(datalen), true); } } #endif void nf_nat_csum_recalc(struct sk_buff *skb, u8 nfproto, u8 proto, void *data, __sum16 *check, int datalen, int oldlen) { switch (nfproto) { case NFPROTO_IPV4: nf_nat_ipv4_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: nf_nat_ipv6_csum_recalc(skb, proto, data, check, datalen, oldlen); return; #endif } WARN_ON_ONCE(1); } int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum) { struct { struct icmphdr icmp; struct iphdr ip; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); unsigned int hdrlen = ip_hdrlen(skb); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp.type == ICMP_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { /* Reloading "inside" here since manip_pkt may reallocate */ inside = (void *)skb->data + hdrlen; inside->icmp.checksum = 0; inside->icmp.checksum = csum_fold(skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); static unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; ct = nf_ct_get(skb, &ctinfo); if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, state->hook)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); return ret; } static unsigned int nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { __be32 saddr = ip_hdr(skb)->saddr; struct sock *sk = skb->sk; unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr && !inet_sk_transparent(sk)) skb_orphan(skb); /* TCP edemux obtained wrong socket */ return ret; } static unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv4_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.src.u3.ip != ct->tuplehash[!dir].tuple.dst.u3.ip || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv4_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv4_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_pre_routing, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_out, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv4_local_fn, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv4_local_in, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, }, }; int nf_nat_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_register_fn); void nf_nat_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv4_unregister_fn); #if IS_ENABLED(CONFIG_IPV6) int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen) { struct { struct icmp6hdr icmp6; struct ipv6hdr ip6; } *inside; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); struct nf_conntrack_tuple target; unsigned long statusbit; WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY); if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; inside = (void *)skb->data + hdrlen; if (inside->icmp6.icmp6_type == NDISC_REDIRECT) { if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) return 0; if (ct->status & IPS_NAT_MASK) return 0; } if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply direction */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; if (!(ct->status & statusbit)) return 1; if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6), &ct->tuplehash[!dir].tuple, !manip)) return 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { struct ipv6hdr *ipv6h = ipv6_hdr(skb); inside = (void *)skb->data + hdrlen; inside->icmp6.icmp6_cksum = 0; inside->icmp6.icmp6_cksum = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len - hdrlen, IPPROTO_ICMPV6, skb_checksum(skb, hdrlen, skb->len - hdrlen, 0)); } nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; return 1; } EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); static unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be16 frag_off; int hdrlen; u8 nexthdr; ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ if (!ct) return NF_ACCEPT; if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) { nexthdr = ipv6_hdr(skb)->nexthdr; hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, state->hook, hdrlen)) return NF_DROP; else return NF_ACCEPT; } } return nf_nat_inet_fn(priv, skb, state); } static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); return ret; } static unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { #ifdef CONFIG_XFRM const struct nf_conn *ct; enum ip_conntrack_info ctinfo; int err; #endif unsigned int ret; ret = nf_nat_ipv6_fn(priv, skb, state); #ifdef CONFIG_XFRM if (ret != NF_ACCEPT) return ret; if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, &ct->tuplehash[!dir].tuple.dst.u3) || (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } } #endif return ret; } static unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int ret; int err; ret = nf_nat_ipv6_fn(priv, skb, state); if (ret != NF_ACCEPT) return ret; ct = nf_ct_get(skb, &ctinfo); if (ct) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { err = nf_ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } #ifdef CONFIG_XFRM else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } #endif } return ret; } static const struct nf_hook_ops nf_nat_ipv6_ops[] = { /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_in, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_out, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, /* Before packet filtering, change destination */ { .hook = nf_nat_ipv6_local_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, /* After packet filtering, change source */ { .hook = nf_nat_ipv6_fn, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, }, }; int nf_nat_ipv6_register_fn(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_register_fn(net, ops->pf, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_register_fn); void nf_nat_ipv6_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, ops->pf, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_ipv6_unregister_fn); #endif /* CONFIG_IPV6 */ #if defined(CONFIG_NF_TABLES_INET) && IS_ENABLED(CONFIG_NFT_NAT) int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) { int ret; if (WARN_ON_ONCE(ops->pf != NFPROTO_INET)) return -EINVAL; ret = nf_nat_register_fn(net, NFPROTO_IPV6, ops, nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops)); if (ret) return ret; ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); void nf_nat_inet_unregister_fn(struct net *net, const struct nf_hook_ops *ops) { nf_nat_unregister_fn(net, NFPROTO_IPV4, ops, ARRAY_SIZE(nf_nat_ipv4_ops)); nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, ARRAY_SIZE(nf_nat_ipv6_ops)); } EXPORT_SYMBOL_GPL(nf_nat_inet_unregister_fn); #endif /* NFT INET NAT */ |
| 673 673 110 672 110 11 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 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 | // SPDX-License-Identifier: GPL-2.0 /* * gendisk handling */ #include <linux/module.h> #include <linux/ctype.h> #include <linux/fs.h> #include <linux/genhd.h> #include <linux/kdev_t.h> #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/kobj_map.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/log2.h> #include <linux/pm_runtime.h> #include <linux/badblocks.h> #include "blk.h" static DEFINE_MUTEX(block_class_lock); static struct kobject *block_depr; /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) /* For extended devt allocation. ext_devt_lock prevents look up * results from going away underneath its user. */ static DEFINE_SPINLOCK(ext_devt_lock); static DEFINE_IDR(ext_devt_idr); static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr); static void disk_alloc_events(struct gendisk *disk); static void disk_add_events(struct gendisk *disk); static void disk_del_events(struct gendisk *disk); static void disk_release_events(struct gendisk *disk); /* * Set disk capacity and notify if the size is not currently * zero and will not be set to zero */ bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev) { sector_t capacity = get_capacity(disk); set_capacity(disk, size); if (update_bdev) revalidate_disk_size(disk, true); if (capacity != size && capacity != 0 && size != 0) { char *envp[] = { "RESIZE=1", NULL }; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); return true; } return false; } EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify); /* * Format the device name of the indicated disk into the supplied buffer and * return a pointer to that same buffer for convenience. */ char *disk_name(struct gendisk *hd, int partno, char *buf) { if (!partno) snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name); else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno); else snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno); return buf; } const char *bdevname(struct block_device *bdev, char *buf) { return disk_name(bdev->bd_disk, bdev->bd_partno, buf); } EXPORT_SYMBOL(bdevname); static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat) { int cpu; memset(stat, 0, sizeof(struct disk_stats)); for_each_possible_cpu(cpu) { struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu); int group; for (group = 0; group < NR_STAT_GROUPS; group++) { stat->nsecs[group] += ptr->nsecs[group]; stat->sectors[group] += ptr->sectors[group]; stat->ios[group] += ptr->ios[group]; stat->merges[group] += ptr->merges[group]; } stat->io_ticks += ptr->io_ticks; } } static unsigned int part_in_flight(struct hd_struct *part) { unsigned int inflight = 0; int cpu; for_each_possible_cpu(cpu) { inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) + part_stat_local_read_cpu(part, in_flight[1], cpu); } if ((int)inflight < 0) inflight = 0; return inflight; } static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2]) { int cpu; inflight[0] = 0; inflight[1] = 0; for_each_possible_cpu(cpu) { inflight[0] += part_stat_local_read_cpu(part, in_flight[0], cpu); inflight[1] += part_stat_local_read_cpu(part, in_flight[1], cpu); } if ((int)inflight[0] < 0) inflight[0] = 0; if ((int)inflight[1] < 0) inflight[1] = 0; } struct hd_struct *__disk_get_part(struct gendisk *disk, int partno) { struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl); if (unlikely(partno < 0 || partno >= ptbl->len)) return NULL; return rcu_dereference(ptbl->part[partno]); } /** * disk_get_part - get partition * @disk: disk to look partition from * @partno: partition number * * Look for partition @partno from @disk. If found, increment * reference count and return it. * * CONTEXT: * Don't care. * * RETURNS: * Pointer to the found partition on success, NULL if not found. */ struct hd_struct *disk_get_part(struct gendisk *disk, int partno) { struct hd_struct *part; rcu_read_lock(); part = __disk_get_part(disk, partno); if (part) get_device(part_to_dev(part)); rcu_read_unlock(); return part; } /** * disk_part_iter_init - initialize partition iterator * @piter: iterator to initialize * @disk: disk to iterate over * @flags: DISK_PITER_* flags * * Initialize @piter so that it iterates over partitions of @disk. * * CONTEXT: * Don't care. */ void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk, unsigned int flags) { struct disk_part_tbl *ptbl; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); piter->disk = disk; piter->part = NULL; if (flags & DISK_PITER_REVERSE) piter->idx = ptbl->len - 1; else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) piter->idx = 0; else piter->idx = 1; piter->flags = flags; rcu_read_unlock(); } EXPORT_SYMBOL_GPL(disk_part_iter_init); /** * disk_part_iter_next - proceed iterator to the next partition and return it * @piter: iterator of interest * * Proceed @piter to the next partition and return it. * * CONTEXT: * Don't care. */ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter) { struct disk_part_tbl *ptbl; int inc, end; /* put the last partition */ disk_put_part(piter->part); piter->part = NULL; /* get part_tbl */ rcu_read_lock(); ptbl = rcu_dereference(piter->disk->part_tbl); /* determine iteration parameters */ if (piter->flags & DISK_PITER_REVERSE) { inc = -1; if (piter->flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0)) end = -1; else end = 0; } else { inc = 1; end = ptbl->len; } /* iterate to the next partition */ for (; piter->idx != end; piter->idx += inc) { struct hd_struct *part; part = rcu_dereference(ptbl->part[piter->idx]); if (!part) continue; get_device(part_to_dev(part)); piter->part = part; if (!part_nr_sects_read(part) && !(piter->flags & DISK_PITER_INCL_EMPTY) && !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 && piter->idx == 0)) { put_device(part_to_dev(part)); piter->part = NULL; continue; } piter->idx += inc; break; } rcu_read_unlock(); return piter->part; } EXPORT_SYMBOL_GPL(disk_part_iter_next); /** * disk_part_iter_exit - finish up partition iteration * @piter: iter of interest * * Called when iteration is over. Cleans up @piter. * * CONTEXT: * Don't care. */ void disk_part_iter_exit(struct disk_part_iter *piter) { disk_put_part(piter->part); piter->part = NULL; } EXPORT_SYMBOL_GPL(disk_part_iter_exit); static inline int sector_in_part(struct hd_struct *part, sector_t sector) { return part->start_sect <= sector && sector < part->start_sect + part_nr_sects_read(part); } /** * disk_map_sector_rcu - map sector to partition * @disk: gendisk of interest * @sector: sector to map * * Find out which partition @sector maps to on @disk. This is * primarily used for stats accounting. * * CONTEXT: * RCU read locked. The returned partition pointer is always valid * because its refcount is grabbed except for part0, which lifetime * is same with the disk. * * RETURNS: * Found partition on success, part0 is returned if no partition matches * or the matched partition is being deleted. */ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector) { struct disk_part_tbl *ptbl; struct hd_struct *part; int i; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); part = rcu_dereference(ptbl->last_lookup); if (part && sector_in_part(part, sector) && hd_struct_try_get(part)) goto out_unlock; for (i = 1; i < ptbl->len; i++) { part = rcu_dereference(ptbl->part[i]); if (part && sector_in_part(part, sector)) { /* * only live partition can be cached for lookup, * so use-after-free on cached & deleting partition * can be avoided */ if (!hd_struct_try_get(part)) break; rcu_assign_pointer(ptbl->last_lookup, part); goto out_unlock; } } part = &disk->part0; out_unlock: rcu_read_unlock(); return part; } /** * disk_has_partitions * @disk: gendisk of interest * * Walk through the partition table and check if valid partition exists. * * CONTEXT: * Don't care. * * RETURNS: * True if the gendisk has at least one valid non-zero size partition. * Otherwise false. */ bool disk_has_partitions(struct gendisk *disk) { struct disk_part_tbl *ptbl; int i; bool ret = false; rcu_read_lock(); ptbl = rcu_dereference(disk->part_tbl); /* Iterate partitions skipping the whole device at index 0 */ for (i = 1; i < ptbl->len; i++) { if (rcu_dereference(ptbl->part[i])) { ret = true; break; } } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(disk_has_partitions); /* * Can be deleted altogether. Later. * */ #define BLKDEV_MAJOR_HASH_SIZE 255 static struct blk_major_name { struct blk_major_name *next; int major; char name[16]; } *major_names[BLKDEV_MAJOR_HASH_SIZE]; /* index in the above - for now: assume no multimajor ranges */ static inline int major_to_index(unsigned major) { return major % BLKDEV_MAJOR_HASH_SIZE; } #ifdef CONFIG_PROC_FS void blkdev_show(struct seq_file *seqf, off_t offset) { struct blk_major_name *dp; mutex_lock(&block_class_lock); for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); mutex_unlock(&block_class_lock); } #endif /* CONFIG_PROC_FS */ /** * register_blkdev - register a new block device * * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If * @major = 0, try to allocate any unused major number. * @name: the name of the new block device as a zero terminated string * * The @name must be unique within the system. * * The return value depends on the @major input parameter: * * - if a major device number was requested in range [1..BLKDEV_MAJOR_MAX-1] * then the function returns zero on success, or a negative error code * - if any unused major number was requested with @major = 0 parameter * then the return value is the allocated major number in range * [1..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise * * See Documentation/admin-guide/devices.txt for the list of allocated * major numbers. */ int register_blkdev(unsigned int major, const char *name) { struct blk_major_name **n, *p; int index, ret = 0; mutex_lock(&block_class_lock); /* temporary */ if (major == 0) { for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) { if (major_names[index] == NULL) break; } if (index == 0) { printk("%s: failed to get major for %s\n", __func__, name); ret = -EBUSY; goto out; } major = index; ret = major; } if (major >= BLKDEV_MAJOR_MAX) { pr_err("%s: major requested (%u) is greater than the maximum (%u) for %s\n", __func__, major, BLKDEV_MAJOR_MAX-1, name); ret = -EINVAL; goto out; } p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL); if (p == NULL) { ret = -ENOMEM; goto out; } p->major = major; strlcpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); for (n = &major_names[index]; *n; n = &(*n)->next) { if ((*n)->major == major) break; } if (!*n) *n = p; else ret = -EBUSY; if (ret < 0) { printk("register_blkdev: cannot get major %u for %s\n", major, name); kfree(p); } out: mutex_unlock(&block_class_lock); return ret; } EXPORT_SYMBOL(register_blkdev); void unregister_blkdev(unsigned int major, const char *name) { struct blk_major_name **n; struct blk_major_name *p = NULL; int index = major_to_index(major); mutex_lock(&block_class_lock); for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; if (!*n || strcmp((*n)->name, name)) { WARN_ON(1); } else { p = *n; *n = p->next; } mutex_unlock(&block_class_lock); kfree(p); } EXPORT_SYMBOL(unregister_blkdev); static struct kobj_map *bdev_map; /** * blk_mangle_minor - scatter minor numbers apart * @minor: minor number to mangle * * Scatter consecutively allocated @minor number apart if MANGLE_DEVT * is enabled. Mangling twice gives the original value. * * RETURNS: * Mangled value. * * CONTEXT: * Don't care. */ static int blk_mangle_minor(int minor) { #ifdef CONFIG_DEBUG_BLOCK_EXT_DEVT int i; for (i = 0; i < MINORBITS / 2; i++) { int low = minor & (1 << i); int high = minor & (1 << (MINORBITS - 1 - i)); int distance = MINORBITS - 1 - 2 * i; minor ^= low | high; /* clear both bits */ low <<= distance; /* swap the positions */ high >>= distance; minor |= low | high; /* and set */ } #endif return minor; } /** * blk_alloc_devt - allocate a dev_t for a partition * @part: partition to allocate dev_t for * @devt: out parameter for resulting dev_t * * Allocate a dev_t for block device. * * RETURNS: * 0 on success, allocated dev_t is returned in *@devt. -errno on * failure. * * CONTEXT: * Might sleep. */ int blk_alloc_devt(struct hd_struct *part, dev_t *devt) { struct gendisk *disk = part_to_disk(part); int idx; /* in consecutive minor range? */ if (part->partno < disk->minors) { *devt = MKDEV(disk->major, disk->first_minor + part->partno); return 0; } /* allocate ext devt */ idr_preload(GFP_KERNEL); spin_lock_bh(&ext_devt_lock); idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT); spin_unlock_bh(&ext_devt_lock); idr_preload_end(); if (idx < 0) return idx == -ENOSPC ? -EBUSY : idx; *devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); return 0; } /** * blk_free_devt - free a dev_t * @devt: dev_t to free * * Free @devt which was allocated using blk_alloc_devt(). * * CONTEXT: * Might sleep. */ void blk_free_devt(dev_t devt) { if (devt == MKDEV(0, 0)) return; if (MAJOR(devt) == BLOCK_EXT_MAJOR) { spin_lock_bh(&ext_devt_lock); idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); spin_unlock_bh(&ext_devt_lock); } } /* * We invalidate devt by assigning NULL pointer for devt in idr. */ void blk_invalidate_devt(dev_t devt) { if (MAJOR(devt) == BLOCK_EXT_MAJOR) { spin_lock_bh(&ext_devt_lock); idr_replace(&ext_devt_idr, NULL, blk_mangle_minor(MINOR(devt))); spin_unlock_bh(&ext_devt_lock); } } static char *bdevt_str(dev_t devt, char *buf) { if (MAJOR(devt) <= 0xff && MINOR(devt) <= 0xff) { char tbuf[BDEVT_SIZE]; snprintf(tbuf, BDEVT_SIZE, "%02x%02x", MAJOR(devt), MINOR(devt)); snprintf(buf, BDEVT_SIZE, "%-9s", tbuf); } else snprintf(buf, BDEVT_SIZE, "%03x:%05x", MAJOR(devt), MINOR(devt)); return buf; } /* * Register device numbers dev..(dev+range-1) * range must be nonzero * The hash chain is sorted on range, so that subranges can override. */ void blk_register_region(dev_t devt, unsigned long range, struct module *module, struct kobject *(*probe)(dev_t, int *, void *), int (*lock)(dev_t, void *), void *data) { kobj_map(bdev_map, devt, range, module, probe, lock, data); } EXPORT_SYMBOL(blk_register_region); void blk_unregister_region(dev_t devt, unsigned long range) { kobj_unmap(bdev_map, devt, range); } EXPORT_SYMBOL(blk_unregister_region); static struct kobject *exact_match(dev_t devt, int *partno, void *data) { struct gendisk *p = data; return &disk_to_dev(p)->kobj; } static int exact_lock(dev_t devt, void *data) { struct gendisk *p = data; if (!get_disk_and_module(p)) return -1; return 0; } static void disk_scan_partitions(struct gendisk *disk) { struct block_device *bdev; if (!get_capacity(disk) || !disk_part_scan_enabled(disk)) return; set_bit(GD_NEED_PART_SCAN, &disk->state); bdev = blkdev_get_by_dev(disk_devt(disk), FMODE_READ, NULL); if (!IS_ERR(bdev)) blkdev_put(bdev, FMODE_READ); } static void register_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups) { struct device *ddev = disk_to_dev(disk); struct disk_part_iter piter; struct hd_struct *part; int err; ddev->parent = parent; dev_set_name(ddev, "%s", disk->disk_name); /* delay uevents, until we scanned partition table */ dev_set_uevent_suppress(ddev, 1); if (groups) { WARN_ON(ddev->groups); ddev->groups = groups; } if (device_add(ddev)) return; if (!sysfs_deprecated) { err = sysfs_create_link(block_depr, &ddev->kobj, kobject_name(&ddev->kobj)); if (err) { device_del(ddev); return; } } /* * avoid probable deadlock caused by allocating memory with * GFP_KERNEL in runtime_resume callback of its all ancestor * devices */ pm_runtime_set_memalloc_noio(ddev, true); disk->part0.holder_dir = kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); if (disk->flags & GENHD_FL_HIDDEN) return; disk_scan_partitions(disk); /* announce disk after possible partitions are created */ dev_set_uevent_suppress(ddev, 0); kobject_uevent(&ddev->kobj, KOBJ_ADD); /* announce possible partitions */ disk_part_iter_init(&piter, disk, 0); while ((part = disk_part_iter_next(&piter))) kobject_uevent(&part_to_dev(part)->kobj, KOBJ_ADD); disk_part_iter_exit(&piter); if (disk->queue->backing_dev_info->dev) { err = sysfs_create_link(&ddev->kobj, &disk->queue->backing_dev_info->dev->kobj, "bdi"); WARN_ON(err); } } /** * __device_add_disk - add disk information to kernel list * @parent: parent device for the disk * @disk: per-device partitioning information * @groups: Additional per-device sysfs groups * @register_queue: register the queue if set to true * * This function registers the partitioning information in @disk * with the kernel. * * FIXME: error handling */ static void __device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, bool register_queue) { dev_t devt; int retval; /* * The disk queue should now be all set with enough information about * the device for the elevator code to pick an adequate default * elevator if one is needed, that is, for devices requesting queue * registration. */ if (register_queue) elevator_init_mq(disk->queue); /* minors == 0 indicates to use ext devt from part0 and should * be accompanied with EXT_DEVT flag. Make sure all * parameters make sense. */ WARN_ON(disk->minors && !(disk->major || disk->first_minor)); WARN_ON(!disk->minors && !(disk->flags & (GENHD_FL_EXT_DEVT | GENHD_FL_HIDDEN))); disk->flags |= GENHD_FL_UP; retval = blk_alloc_devt(&disk->part0, &devt); if (retval) { WARN_ON(1); return; } disk->major = MAJOR(devt); disk->first_minor = MINOR(devt); disk_alloc_events(disk); if (disk->flags & GENHD_FL_HIDDEN) { /* * Don't let hidden disks show up in /proc/partitions, * and don't bother scanning for partitions either. */ disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; disk->flags |= GENHD_FL_NO_PART_SCAN; } else { struct backing_dev_info *bdi = disk->queue->backing_dev_info; struct device *dev = disk_to_dev(disk); int ret; /* Register BDI before referencing it from bdev */ dev->devt = devt; ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); WARN_ON(ret); bdi_set_owner(bdi, dev); blk_register_region(disk_devt(disk), disk->minors, NULL, exact_match, exact_lock, disk); } register_disk(parent, disk, groups); if (register_queue) blk_register_queue(disk); /* * Take an extra ref on queue which will be put on disk_release() * so that it sticks around as long as @disk is there. */ WARN_ON_ONCE(!blk_get_queue(disk->queue)); disk_add_events(disk); blk_integrity_add(disk); } void device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups) { __device_add_disk(parent, disk, groups, true); } EXPORT_SYMBOL(device_add_disk); void device_add_disk_no_queue_reg(struct device *parent, struct gendisk *disk) { __device_add_disk(parent, disk, NULL, false); } EXPORT_SYMBOL(device_add_disk_no_queue_reg); static void invalidate_partition(struct gendisk *disk, int partno) { struct block_device *bdev; bdev = bdget_disk(disk, partno); if (!bdev) return; fsync_bdev(bdev); __invalidate_device(bdev, true); /* * Unhash the bdev inode for this device so that it gets evicted as soon * as last inode reference is dropped. */ remove_inode_hash(bdev->bd_inode); bdput(bdev); } /** * del_gendisk - remove the gendisk * @disk: the struct gendisk to remove * * Removes the gendisk and all its associated resources. This deletes the * partitions associated with the gendisk, and unregisters the associated * request_queue. * * This is the counter to the respective __device_add_disk() call. * * The final removal of the struct gendisk happens when its refcount reaches 0 * with put_disk(), which should be called after del_gendisk(), if * __device_add_disk() was used. * * Drivers exist which depend on the release of the gendisk to be synchronous, * it should not be deferred. * * Context: can sleep */ void del_gendisk(struct gendisk *disk) { struct disk_part_iter piter; struct hd_struct *part; might_sleep(); blk_integrity_del(disk); disk_del_events(disk); /* * Block lookups of the disk until all bdevs are unhashed and the * disk is marked as dead (GENHD_FL_UP cleared). */ down_write(&disk->lookup_sem); /* invalidate stuff */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE); while ((part = disk_part_iter_next(&piter))) { invalidate_partition(disk, part->partno); delete_partition(part); } disk_part_iter_exit(&piter); invalidate_partition(disk, 0); set_capacity(disk, 0); disk->flags &= ~GENHD_FL_UP; up_write(&disk->lookup_sem); if (!(disk->flags & GENHD_FL_HIDDEN)) sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); if (disk->queue) { /* * Unregister bdi before releasing device numbers (as they can * get reused and we'd get clashes in sysfs). */ if (!(disk->flags & GENHD_FL_HIDDEN)) bdi_unregister(disk->queue->backing_dev_info); blk_unregister_queue(disk); } else { WARN_ON(1); } if (!(disk->flags & GENHD_FL_HIDDEN)) blk_unregister_region(disk_devt(disk), disk->minors); /* * Remove gendisk pointer from idr so that it cannot be looked up * while RCU period before freeing gendisk is running to prevent * use-after-free issues. Note that the device number stays * "in-use" until we really free the gendisk. */ blk_invalidate_devt(disk_devt(disk)); kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); part_stat_set_all(&disk->part0, 0); disk->part0.stamp = 0; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); device_del(disk_to_dev(disk)); } EXPORT_SYMBOL(del_gendisk); /* sysfs access to bad-blocks list. */ static ssize_t disk_badblocks_show(struct device *dev, struct device_attribute *attr, char *page) { struct gendisk *disk = dev_to_disk(dev); if (!disk->bb) return sprintf(page, "\n"); return badblocks_show(disk->bb, page, 0); } static ssize_t disk_badblocks_store(struct device *dev, struct device_attribute *attr, const char *page, size_t len) { struct gendisk *disk = dev_to_disk(dev); if (!disk->bb) return -ENXIO; return badblocks_store(disk->bb, page, len, 0); } /** * get_gendisk - get partitioning information for a given device * @devt: device to get partitioning information for * @partno: returned partition index * * This function gets the structure containing partitioning * information for the given device @devt. * * Context: can sleep */ struct gendisk *get_gendisk(dev_t devt, int *partno) { struct gendisk *disk = NULL; might_sleep(); if (MAJOR(devt) != BLOCK_EXT_MAJOR) { struct kobject *kobj; kobj = kobj_lookup(bdev_map, devt, partno); if (kobj) disk = dev_to_disk(kobj_to_dev(kobj)); } else { struct hd_struct *part; spin_lock_bh(&ext_devt_lock); part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt))); if (part && get_disk_and_module(part_to_disk(part))) { *partno = part->partno; disk = part_to_disk(part); } spin_unlock_bh(&ext_devt_lock); } if (!disk) return NULL; /* * Synchronize with del_gendisk() to not return disk that is being * destroyed. */ down_read(&disk->lookup_sem); if (unlikely((disk->flags & GENHD_FL_HIDDEN) || !(disk->flags & GENHD_FL_UP))) { up_read(&disk->lookup_sem); put_disk_and_module(disk); disk = NULL; } else { up_read(&disk->lookup_sem); } return disk; } /** * bdget_disk - do bdget() by gendisk and partition number * @disk: gendisk of interest * @partno: partition number * * Find partition @partno from @disk, do bdget() on it. * * CONTEXT: * Don't care. * * RETURNS: * Resulting block_device on success, NULL on failure. */ struct block_device *bdget_disk(struct gendisk *disk, int partno) { struct hd_struct *part; struct block_device *bdev = NULL; part = disk_get_part(disk, partno); if (part) bdev = bdget_part(part); disk_put_part(part); return bdev; } EXPORT_SYMBOL(bdget_disk); /* * print a full list of all partitions - intended for places where the root * filesystem can't be mounted and thus to give the victim some idea of what * went wrong */ void __init printk_all_partitions(void) { struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); struct disk_part_iter piter; struct hd_struct *part; char name_buf[BDEVNAME_SIZE]; char devt_buf[BDEVT_SIZE]; /* * Don't show empty devices or things that have been * suppressed */ if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)) continue; /* * Note, unlike /proc/partitions, I am showing the * numbers in hex - the same format as the root= * option takes. */ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) { bool is_part0 = part == &disk->part0; printk("%s%s %10llu %s %s", is_part0 ? "" : " ", bdevt_str(part_devt(part), devt_buf), (unsigned long long)part_nr_sects_read(part) >> 1 , disk_name(disk, part->partno, name_buf), part->info ? part->info->uuid : ""); if (is_part0) { if (dev->parent && dev->parent->driver) printk(" driver: %s\n", dev->parent->driver->name); else printk(" (driver?)\n"); } else printk("\n"); } disk_part_iter_exit(&piter); } class_dev_iter_exit(&iter); } #ifdef CONFIG_PROC_FS /* iterator */ static void *disk_seqf_start(struct seq_file *seqf, loff_t *pos) { loff_t skip = *pos; struct class_dev_iter *iter; struct device *dev; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return ERR_PTR(-ENOMEM); seqf->private = iter; class_dev_iter_init(iter, &block_class, NULL, &disk_type); do { dev = class_dev_iter_next(iter); if (!dev) return NULL; } while (skip--); return dev_to_disk(dev); } static void *disk_seqf_next(struct seq_file *seqf, void *v, loff_t *pos) { struct device *dev; (*pos)++; dev = class_dev_iter_next(seqf->private); if (dev) return dev_to_disk(dev); return NULL; } static void disk_seqf_stop(struct seq_file *seqf, void *v) { struct class_dev_iter *iter = seqf->private; /* stop is called even after start failed :-( */ if (iter) { class_dev_iter_exit(iter); kfree(iter); seqf->private = NULL; } } static void *show_partition_start(struct seq_file *seqf, loff_t *pos) { void *p; p = disk_seqf_start(seqf, pos); if (!IS_ERR_OR_NULL(p) && !*pos) seq_puts(seqf, "major minor #blocks name\n\n"); return p; } static int show_partition(struct seq_file *seqf, void *v) { struct gendisk *sgp = v; struct disk_part_iter piter; struct hd_struct *part; char buf[BDEVNAME_SIZE]; /* Don't show non-partitionable removeable devices or empty devices */ if (!get_capacity(sgp) || (!disk_max_parts(sgp) && (sgp->flags & GENHD_FL_REMOVABLE))) return 0; if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) return 0; /* show the full disk and all non-0 size partitions of it */ disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0); while ((part = disk_part_iter_next(&piter))) seq_printf(seqf, "%4d %7d %10llu %s\n", MAJOR(part_devt(part)), MINOR(part_devt(part)), (unsigned long long)part_nr_sects_read(part) >> 1, disk_name(sgp, part->partno, buf)); disk_part_iter_exit(&piter); return 0; } static const struct seq_operations partitions_op = { .start = show_partition_start, .next = disk_seqf_next, .stop = disk_seqf_stop, .show = show_partition }; #endif static struct kobject *base_probe(dev_t devt, int *partno, void *data) { if (request_module("block-major-%d-%d", MAJOR(devt), MINOR(devt)) > 0) /* Make old-style 2.4 aliases work */ request_module("block-major-%d", MAJOR(devt)); return NULL; } static int __init genhd_device_init(void) { int error; block_class.dev_kobj = sysfs_dev_block_kobj; error = class_register(&block_class); if (unlikely(error)) return error; bdev_map = kobj_map_init(base_probe, &block_class_lock); blk_dev_init(); register_blkdev(BLOCK_EXT_MAJOR, "blkext"); /* create top-level block dir */ if (!sysfs_deprecated) block_depr = kobject_create_and_add("block", NULL); return 0; } subsys_initcall(genhd_device_init); static ssize_t disk_range_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", disk->minors); } static ssize_t disk_ext_range_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", disk_max_parts(disk)); } static ssize_t disk_removable_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0)); } static ssize_t disk_hidden_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", (disk->flags & GENHD_FL_HIDDEN ? 1 : 0)); } static ssize_t disk_ro_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0); } ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); return sprintf(buf, "%llu\n", (unsigned long long)part_nr_sects_read(p)); } ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); struct request_queue *q = part_to_disk(p)->queue; struct disk_stats stat; unsigned int inflight; part_stat_read_all(p, &stat); if (queue_is_mq(q)) inflight = blk_mq_in_flight(q, p); else inflight = part_in_flight(p); return sprintf(buf, "%8lu %8lu %8llu %8u " "%8lu %8lu %8llu %8u " "%8u %8u %8u " "%8lu %8lu %8llu %8u " "%8lu %8u" "\n", stat.ios[STAT_READ], stat.merges[STAT_READ], (unsigned long long)stat.sectors[STAT_READ], (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC), stat.ios[STAT_WRITE], stat.merges[STAT_WRITE], (unsigned long long)stat.sectors[STAT_WRITE], (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC), inflight, jiffies_to_msecs(stat.io_ticks), (unsigned int)div_u64(stat.nsecs[STAT_READ] + stat.nsecs[STAT_WRITE] + stat.nsecs[STAT_DISCARD] + stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC), stat.ios[STAT_DISCARD], stat.merges[STAT_DISCARD], (unsigned long long)stat.sectors[STAT_DISCARD], (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC), stat.ios[STAT_FLUSH], (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC)); } ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); struct request_queue *q = part_to_disk(p)->queue; unsigned int inflight[2]; if (queue_is_mq(q)) blk_mq_in_flight_rw(q, p, inflight); else part_in_flight_rw(p, inflight); return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]); } static ssize_t disk_capability_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%x\n", disk->flags); } static ssize_t disk_alignment_offset_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue)); } static ssize_t disk_discard_alignment_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue)); } static DEVICE_ATTR(range, 0444, disk_range_show, NULL); static DEVICE_ATTR(ext_range, 0444, disk_ext_range_show, NULL); static DEVICE_ATTR(removable, 0444, disk_removable_show, NULL); static DEVICE_ATTR(hidden, 0444, disk_hidden_show, NULL); static DEVICE_ATTR(ro, 0444, disk_ro_show, NULL); static DEVICE_ATTR(size, 0444, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, 0444, disk_alignment_offset_show, NULL); static DEVICE_ATTR(discard_alignment, 0444, disk_discard_alignment_show, NULL); static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL); static DEVICE_ATTR(stat, 0444, part_stat_show, NULL); static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL); static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store); #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct hd_struct *p = dev_to_part(dev); return sprintf(buf, "%d\n", p->make_it_fail); } ssize_t part_fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct hd_struct *p = dev_to_part(dev); int i; if (count > 0 && sscanf(buf, "%d", &i) > 0) p->make_it_fail = (i == 0) ? 0 : 1; return count; } static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, 0644, part_fail_show, part_fail_store); #endif /* CONFIG_FAIL_MAKE_REQUEST */ #ifdef CONFIG_FAIL_IO_TIMEOUT static struct device_attribute dev_attr_fail_timeout = __ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store); #endif static struct attribute *disk_attrs[] = { &dev_attr_range.attr, &dev_attr_ext_range.attr, &dev_attr_removable.attr, &dev_attr_hidden.attr, &dev_attr_ro.attr, &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_discard_alignment.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, &dev_attr_badblocks.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif #ifdef CONFIG_FAIL_IO_TIMEOUT &dev_attr_fail_timeout.attr, #endif NULL }; static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n) { struct device *dev = container_of(kobj, typeof(*dev), kobj); struct gendisk *disk = dev_to_disk(dev); if (a == &dev_attr_badblocks.attr && !disk->bb) return 0; return a->mode; } static struct attribute_group disk_attr_group = { .attrs = disk_attrs, .is_visible = disk_visible, }; static const struct attribute_group *disk_attr_groups[] = { &disk_attr_group, NULL }; /** * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way * @disk: disk to replace part_tbl for * @new_ptbl: new part_tbl to install * * Replace disk->part_tbl with @new_ptbl in RCU-safe way. The * original ptbl is freed using RCU callback. * * LOCKING: * Matching bd_mutex locked or the caller is the only user of @disk. */ static void disk_replace_part_tbl(struct gendisk *disk, struct disk_part_tbl *new_ptbl) { struct disk_part_tbl *old_ptbl = rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(disk->part_tbl, new_ptbl); if (old_ptbl) { rcu_assign_pointer(old_ptbl->last_lookup, NULL); kfree_rcu(old_ptbl, rcu_head); } } /** * disk_expand_part_tbl - expand disk->part_tbl * @disk: disk to expand part_tbl for * @partno: expand such that this partno can fit in * * Expand disk->part_tbl such that @partno can fit in. disk->part_tbl * uses RCU to allow unlocked dereferencing for stats and other stuff. * * LOCKING: * Matching bd_mutex locked or the caller is the only user of @disk. * Might sleep. * * RETURNS: * 0 on success, -errno on failure. */ int disk_expand_part_tbl(struct gendisk *disk, int partno) { struct disk_part_tbl *old_ptbl = rcu_dereference_protected(disk->part_tbl, 1); struct disk_part_tbl *new_ptbl; int len = old_ptbl ? old_ptbl->len : 0; int i, target; /* * check for int overflow, since we can get here from blkpg_ioctl() * with a user passed 'partno'. */ target = partno + 1; if (target < 0) return -EINVAL; /* disk_max_parts() is zero during initialization, ignore if so */ if (disk_max_parts(disk) && target > disk_max_parts(disk)) return -EINVAL; if (target <= len) return 0; new_ptbl = kzalloc_node(struct_size(new_ptbl, part, target), GFP_KERNEL, disk->node_id); if (!new_ptbl) return -ENOMEM; new_ptbl->len = target; for (i = 0; i < len; i++) rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]); disk_replace_part_tbl(disk, new_ptbl); return 0; } /** * disk_release - releases all allocated resources of the gendisk * @dev: the device representing this disk * * This function releases all allocated resources of the gendisk. * * The struct gendisk refcount is incremented with get_gendisk() or * get_disk_and_module(), and its refcount is decremented with * put_disk_and_module() or put_disk(). Once the refcount reaches 0 this * function is called. * * Drivers which used __device_add_disk() have a gendisk with a request_queue * assigned. Since the request_queue sits on top of the gendisk for these * drivers we also call blk_put_queue() for them, and we expect the * request_queue refcount to reach 0 at this point, and so the request_queue * will also be freed prior to the disk. * * Context: can sleep */ static void disk_release(struct device *dev) { struct gendisk *disk = dev_to_disk(dev); might_sleep(); blk_free_devt(dev->devt); disk_release_events(disk); kfree(disk->random); disk_replace_part_tbl(disk, NULL); hd_free_part(&disk->part0); if (disk->queue) blk_put_queue(disk->queue); kfree(disk); } struct class block_class = { .name = "block", }; static char *block_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { struct gendisk *disk = dev_to_disk(dev); if (disk->fops->devnode) return disk->fops->devnode(disk, mode); return NULL; } const struct device_type disk_type = { .name = "disk", .groups = disk_attr_groups, .release = disk_release, .devnode = block_devnode, }; #ifdef CONFIG_PROC_FS /* * aggregate disk stat collector. Uses the same stats that the sysfs * entries do, above, but makes them available through one seq_file. * * The output looks suspiciously like /proc/partitions with a bunch of * extra fields. */ static int diskstats_show(struct seq_file *seqf, void *v) { struct gendisk *gp = v; struct disk_part_iter piter; struct hd_struct *hd; char buf[BDEVNAME_SIZE]; unsigned int inflight; struct disk_stats stat; /* if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next) seq_puts(seqf, "major minor name" " rio rmerge rsect ruse wio wmerge " "wsect wuse running use aveq" "\n\n"); */ disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0); while ((hd = disk_part_iter_next(&piter))) { part_stat_read_all(hd, &stat); if (queue_is_mq(gp->queue)) inflight = blk_mq_in_flight(gp->queue, hd); else inflight = part_in_flight(hd); seq_printf(seqf, "%4d %7d %s " "%lu %lu %lu %u " "%lu %lu %lu %u " "%u %u %u " "%lu %lu %lu %u " "%lu %u" "\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), stat.ios[STAT_READ], stat.merges[STAT_READ], stat.sectors[STAT_READ], (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC), stat.ios[STAT_WRITE], stat.merges[STAT_WRITE], stat.sectors[STAT_WRITE], (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC), inflight, jiffies_to_msecs(stat.io_ticks), (unsigned int)div_u64(stat.nsecs[STAT_READ] + stat.nsecs[STAT_WRITE] + stat.nsecs[STAT_DISCARD] + stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC), stat.ios[STAT_DISCARD], stat.merges[STAT_DISCARD], stat.sectors[STAT_DISCARD], (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC), stat.ios[STAT_FLUSH], (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC) ); } disk_part_iter_exit(&piter); return 0; } static const struct seq_operations diskstats_op = { .start = disk_seqf_start, .next = disk_seqf_next, .stop = disk_seqf_stop, .show = diskstats_show }; static int __init proc_genhd_init(void) { proc_create_seq("diskstats", 0, NULL, &diskstats_op); proc_create_seq("partitions", 0, NULL, &partitions_op); return 0; } module_init(proc_genhd_init); #endif /* CONFIG_PROC_FS */ dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); struct class_dev_iter iter; struct device *dev; class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); struct hd_struct *part; if (strcmp(dev_name(dev), name)) continue; if (partno < disk->minors) { /* We need to return the right devno, even * if the partition doesn't exist yet. */ devt = MKDEV(MAJOR(dev->devt), MINOR(dev->devt) + partno); break; } part = disk_get_part(disk, partno); if (part) { devt = part_devt(part); disk_put_part(part); break; } disk_put_part(part); } class_dev_iter_exit(&iter); return devt; } struct gendisk *__alloc_disk_node(int minors, int node_id) { struct gendisk *disk; struct disk_part_tbl *ptbl; if (minors > DISK_MAX_PARTS) { printk(KERN_ERR "block: can't allocate more than %d partitions\n", DISK_MAX_PARTS); minors = DISK_MAX_PARTS; } disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) return NULL; disk->part0.dkstats = alloc_percpu(struct disk_stats); if (!disk->part0.dkstats) goto out_free_disk; init_rwsem(&disk->lookup_sem); disk->node_id = node_id; if (disk_expand_part_tbl(disk, 0)) { free_percpu(disk->part0.dkstats); goto out_free_disk; } ptbl = rcu_dereference_protected(disk->part_tbl, 1); rcu_assign_pointer(ptbl->part[0], &disk->part0); /* * set_capacity() and get_capacity() currently don't use * seqcounter to read/update the part0->nr_sects. Still init * the counter as we can read the sectors in IO submission * patch using seqence counters. * * TODO: Ideally set_capacity() and get_capacity() should be * converted to make use of bd_mutex and sequence counters. */ hd_sects_seq_init(&disk->part0); if (hd_ref_init(&disk->part0)) goto out_free_part0; disk->minors = minors; rand_initialize_disk(disk); disk_to_dev(disk)->class = &block_class; disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); return disk; out_free_part0: hd_free_part(&disk->part0); out_free_disk: kfree(disk); return NULL; } EXPORT_SYMBOL(__alloc_disk_node); /** * get_disk_and_module - increments the gendisk and gendisk fops module refcount * @disk: the struct gendisk to increment the refcount for * * This increments the refcount for the struct gendisk, and the gendisk's * fops module owner. * * Context: Any context. */ struct kobject *get_disk_and_module(struct gendisk *disk) { struct module *owner; struct kobject *kobj; if (!disk->fops) return NULL; owner = disk->fops->owner; if (owner && !try_module_get(owner)) return NULL; kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj); if (kobj == NULL) { module_put(owner); return NULL; } return kobj; } EXPORT_SYMBOL(get_disk_and_module); /** * put_disk - decrements the gendisk refcount * @disk: the struct gendisk to decrement the refcount for * * This decrements the refcount for the struct gendisk. When this reaches 0 * we'll have disk_release() called. * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void put_disk(struct gendisk *disk) { if (disk) kobject_put(&disk_to_dev(disk)->kobj); } EXPORT_SYMBOL(put_disk); /** * put_disk_and_module - decrements the module and gendisk refcount * @disk: the struct gendisk to decrement the refcount for * * This is a counterpart of get_disk_and_module() and thus also of * get_gendisk(). * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void put_disk_and_module(struct gendisk *disk) { if (disk) { struct module *owner = disk->fops->owner; put_disk(disk); module_put(owner); } } EXPORT_SYMBOL(put_disk_and_module); static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; char *envp[] = { event, NULL }; if (!ro) event[8] = '0'; kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp); } void set_device_ro(struct block_device *bdev, int flag) { bdev->bd_part->policy = flag; } EXPORT_SYMBOL(set_device_ro); void set_disk_ro(struct gendisk *disk, int flag) { struct disk_part_iter piter; struct hd_struct *part; if (disk->part0.policy != flag) { set_disk_ro_uevent(disk, flag); disk->part0.policy = flag; } disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY); while ((part = disk_part_iter_next(&piter))) part->policy = flag; disk_part_iter_exit(&piter); } EXPORT_SYMBOL(set_disk_ro); int bdev_read_only(struct block_device *bdev) { if (!bdev) return 0; return bdev->bd_part->policy; } EXPORT_SYMBOL(bdev_read_only); /* * Disk events - monitor disk events like media change and eject request. */ struct disk_events { struct list_head node; /* all disk_event's */ struct gendisk *disk; /* the associated disk */ spinlock_t lock; struct mutex block_mutex; /* protects blocking */ int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ long poll_msecs; /* interval, -1 for default */ struct delayed_work dwork; }; static const char *disk_events_strs[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", }; static char *disk_uevents[] = { [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", }; /* list of all disk_events */ static DEFINE_MUTEX(disk_events_mutex); static LIST_HEAD(disk_events); /* disable in-kernel polling by default */ static unsigned long disk_events_dfl_poll_msecs; static unsigned long disk_events_poll_jiffies(struct gendisk *disk) { struct disk_events *ev = disk->ev; long intv_msecs = 0; /* * If device-specific poll interval is set, always use it. If * the default is being used, poll if the POLL flag is set. */ if (ev->poll_msecs >= 0) intv_msecs = ev->poll_msecs; else if (disk->event_flags & DISK_EVENT_FLAG_POLL) intv_msecs = disk_events_dfl_poll_msecs; return msecs_to_jiffies(intv_msecs); } /** * disk_block_events - block and flush disk event checking * @disk: disk to block events for * * On return from this function, it is guaranteed that event checking * isn't in progress and won't happen until unblocked by * disk_unblock_events(). Events blocking is counted and the actual * unblocking happens after the matching number of unblocks are done. * * Note that this intentionally does not block event checking from * disk_clear_events(). * * CONTEXT: * Might sleep. */ void disk_block_events(struct gendisk *disk) { struct disk_events *ev = disk->ev; unsigned long flags; bool cancel; if (!ev) return; /* * Outer mutex ensures that the first blocker completes canceling * the event work before further blockers are allowed to finish. */ mutex_lock(&ev->block_mutex); spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); if (cancel) cancel_delayed_work_sync(&disk->ev->dwork); mutex_unlock(&ev->block_mutex); } static void __disk_unblock_events(struct gendisk *disk, bool check_now) { struct disk_events *ev = disk->ev; unsigned long intv; unsigned long flags; spin_lock_irqsave(&ev->lock, flags); if (WARN_ON_ONCE(ev->block <= 0)) goto out_unlock; if (--ev->block) goto out_unlock; intv = disk_events_poll_jiffies(disk); if (check_now) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); else if (intv) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, intv); out_unlock: spin_unlock_irqrestore(&ev->lock, flags); } /** * disk_unblock_events - unblock disk event checking * @disk: disk to unblock events for * * Undo disk_block_events(). When the block count reaches zero, it * starts events polling if configured. * * CONTEXT: * Don't care. Safe to call from irq context. */ void disk_unblock_events(struct gendisk *disk) { if (disk->ev) __disk_unblock_events(disk, false); } /** * disk_flush_events - schedule immediate event checking and flushing * @disk: disk to check and flush events for * @mask: events to flush * * Schedule immediate event checking on @disk if not blocked. Events in * @mask are scheduled to be cleared from the driver. Note that this * doesn't clear the events from @disk->ev. * * CONTEXT: * If @mask is non-zero must be called with bdev->bd_mutex held. */ void disk_flush_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; if (!ev) return; spin_lock_irq(&ev->lock); ev->clearing |= mask; if (!ev->block) mod_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, 0); spin_unlock_irq(&ev->lock); } /** * disk_clear_events - synchronously check, clear and return pending events * @disk: disk to fetch and clear events from * @mask: mask of events to be fetched and cleared * * Disk events are synchronously checked and pending events in @mask * are cleared and returned. This ignores the block count. * * CONTEXT: * Might sleep. */ static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) { struct disk_events *ev = disk->ev; unsigned int pending; unsigned int clearing = mask; if (!ev) return 0; disk_block_events(disk); /* * store the union of mask and ev->clearing on the stack so that the * race with disk_flush_events does not cause ambiguity (ev->clearing * can still be modified even if events are blocked). */ spin_lock_irq(&ev->lock); clearing |= ev->clearing; ev->clearing = 0; spin_unlock_irq(&ev->lock); disk_check_events(ev, &clearing); /* * if ev->clearing is not 0, the disk_flush_events got called in the * middle of this function, so we want to run the workfn without delay. */ __disk_unblock_events(disk, ev->clearing ? true : false); /* then, fetch and clear pending events */ spin_lock_irq(&ev->lock); pending = ev->pending & mask; ev->pending &= ~mask; spin_unlock_irq(&ev->lock); WARN_ON_ONCE(clearing & mask); return pending; } /** * bdev_check_media_change - check if a removable media has been changed * @bdev: block device to check * * Check whether a removable media has been changed, and attempt to free all * dentries and inodes and invalidates all block device page cache entries in * that case. * * Returns %true if the block device changed, or %false if not. */ bool bdev_check_media_change(struct block_device *bdev) { unsigned int events; events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST); if (!(events & DISK_EVENT_MEDIA_CHANGE)) return false; if (__invalidate_device(bdev, true)) pr_warn("VFS: busy inodes on changed media %s\n", bdev->bd_disk->disk_name); set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); return true; } EXPORT_SYMBOL(bdev_check_media_change); /* * Separate this part out so that a different pointer for clearing_ptr can be * passed in for disk_clear_events. */ static void disk_events_workfn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct disk_events *ev = container_of(dwork, struct disk_events, dwork); disk_check_events(ev, &ev->clearing); } static void disk_check_events(struct disk_events *ev, unsigned int *clearing_ptr) { struct gendisk *disk = ev->disk; char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; unsigned int clearing = *clearing_ptr; unsigned int events; unsigned long intv; int nr_events = 0, i; /* check events */ events = disk->fops->check_events(disk, clearing); /* accumulate pending events and schedule next poll if necessary */ spin_lock_irq(&ev->lock); events &= ~ev->pending; ev->pending |= events; *clearing_ptr &= ~clearing; intv = disk_events_poll_jiffies(disk); if (!ev->block && intv) queue_delayed_work(system_freezable_power_efficient_wq, &ev->dwork, intv); spin_unlock_irq(&ev->lock); /* * Tell userland about new events. Only the events listed in * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT * is set. Otherwise, events are processed internally but never * get reported to userland. */ for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) if ((events & disk->events & (1 << i)) && (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) envp[nr_events++] = disk_uevents[i]; if (nr_events) kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); } /* * A disk events enabled device has the following sysfs nodes under * its /sys/block/X/ directory. * * events : list of all supported events * events_async : list of events which can be detected w/o polling * (always empty, only for backwards compatibility) * events_poll_msecs : polling interval, 0: disable, -1: system default */ static ssize_t __disk_events_show(unsigned int events, char *buf) { const char *delim = ""; ssize_t pos = 0; int i; for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) if (events & (1 << i)) { pos += sprintf(buf + pos, "%s%s", delim, disk_events_strs[i]); delim = " "; } if (pos) pos += sprintf(buf + pos, "\n"); return pos; } static ssize_t disk_events_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) return 0; return __disk_events_show(disk->events, buf); } static ssize_t disk_events_async_show(struct device *dev, struct device_attribute *attr, char *buf) { return 0; } static ssize_t disk_events_poll_msecs_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); if (!disk->ev) return sprintf(buf, "-1\n"); return sprintf(buf, "%ld\n", disk->ev->poll_msecs); } static ssize_t disk_events_poll_msecs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct gendisk *disk = dev_to_disk(dev); long intv; if (!count || !sscanf(buf, "%ld", &intv)) return -EINVAL; if (intv < 0 && intv != -1) return -EINVAL; if (!disk->ev) return -ENODEV; disk_block_events(disk); disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); return count; } static const DEVICE_ATTR(events, 0444, disk_events_show, NULL); static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); static const DEVICE_ATTR(events_poll_msecs, 0644, disk_events_poll_msecs_show, disk_events_poll_msecs_store); static const struct attribute *disk_events_attrs[] = { &dev_attr_events.attr, &dev_attr_events_async.attr, &dev_attr_events_poll_msecs.attr, NULL, }; /* * The default polling interval can be specified by the kernel * parameter block.events_dfl_poll_msecs which defaults to 0 * (disable). This can also be modified runtime by writing to * /sys/module/block/parameters/events_dfl_poll_msecs. */ static int disk_events_set_dfl_poll_msecs(const char *val, const struct kernel_param *kp) { struct disk_events *ev; int ret; ret = param_set_ulong(val, kp); if (ret < 0) return ret; mutex_lock(&disk_events_mutex); list_for_each_entry(ev, &disk_events, node) disk_flush_events(ev->disk, 0); mutex_unlock(&disk_events_mutex); return 0; } static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { .set = disk_events_set_dfl_poll_msecs, .get = param_get_ulong, }; #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "block." module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, &disk_events_dfl_poll_msecs, 0644); /* * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. */ static void disk_alloc_events(struct gendisk *disk) { struct disk_events *ev; if (!disk->fops->check_events || !disk->events) return; ev = kzalloc(sizeof(*ev), GFP_KERNEL); if (!ev) { pr_warn("%s: failed to initialize events\n", disk->disk_name); return; } INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); mutex_init(&ev->block_mutex); ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); disk->ev = ev; } static void disk_add_events(struct gendisk *disk) { /* FIXME: error handling */ if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) pr_warn("%s: failed to create sysfs files for events\n", disk->disk_name); if (!disk->ev) return; mutex_lock(&disk_events_mutex); list_add_tail(&disk->ev->node, &disk_events); mutex_unlock(&disk_events_mutex); /* * Block count is initialized to 1 and the following initial * unblock kicks it into action. */ __disk_unblock_events(disk, true); } static void disk_del_events(struct gendisk *disk) { if (disk->ev) { disk_block_events(disk); mutex_lock(&disk_events_mutex); list_del_init(&disk->ev->node); mutex_unlock(&disk_events_mutex); } sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs); } static void disk_release_events(struct gendisk *disk) { /* the block count should be 1 from disk_del_events() */ WARN_ON_ONCE(disk->ev && disk->ev->block != 1); kfree(disk->ev); } |
| 156 155 156 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 | // SPDX-License-Identifier: GPL-2.0 /* * Devices PM QoS constraints management * * Copyright (C) 2011 Texas Instruments, Inc. * * This module exposes the interface to kernel space for specifying * per-device PM QoS dependencies. It provides infrastructure for registration * of: * * Dependents on a QoS value : register requests * Watchers of QoS value : get notified when target QoS value changes * * This QoS design is best effort based. Dependents register their QoS needs. * Watchers register to keep track of the current QoS needs of the system. * Watchers can register a per-device notification callback using the * dev_pm_qos_*_notifier API. The notification chain data is stored in the * per-device constraint data struct. * * Note about the per-device constraint data struct allocation: * . The per-device constraints data struct ptr is stored into the device * dev_pm_info. * . To minimize the data usage by the per-device constraints, the data struct * is only allocated at the first call to dev_pm_qos_add_request. * . The data is later free'd when the device is removed from the system. * . A global mutex protects the constraints users from the data being * allocated and free'd. */ #include <linux/pm_qos.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/err.h> #include <trace/events/power.h> #include "power.h" static DEFINE_MUTEX(dev_pm_qos_mtx); static DEFINE_MUTEX(dev_pm_qos_sysfs_mtx); /** * __dev_pm_qos_flags - Check PM QoS flags for a given device. * @dev: Device to check the PM QoS flags for. * @mask: Flags to check against. * * This routine must be called with dev->power.lock held. */ enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask) { struct dev_pm_qos *qos = dev->power.qos; struct pm_qos_flags *pqf; s32 val; lockdep_assert_held(&dev->power.lock); if (IS_ERR_OR_NULL(qos)) return PM_QOS_FLAGS_UNDEFINED; pqf = &qos->flags; if (list_empty(&pqf->list)) return PM_QOS_FLAGS_UNDEFINED; val = pqf->effective_flags & mask; if (val) return (val == mask) ? PM_QOS_FLAGS_ALL : PM_QOS_FLAGS_SOME; return PM_QOS_FLAGS_NONE; } /** * dev_pm_qos_flags - Check PM QoS flags for a given device (locked). * @dev: Device to check the PM QoS flags for. * @mask: Flags to check against. */ enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask) { unsigned long irqflags; enum pm_qos_flags_status ret; spin_lock_irqsave(&dev->power.lock, irqflags); ret = __dev_pm_qos_flags(dev, mask); spin_unlock_irqrestore(&dev->power.lock, irqflags); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_flags); /** * __dev_pm_qos_resume_latency - Get resume latency constraint for a given device. * @dev: Device to get the PM QoS constraint value for. * * This routine must be called with dev->power.lock held. */ s32 __dev_pm_qos_resume_latency(struct device *dev) { lockdep_assert_held(&dev->power.lock); return dev_pm_qos_raw_resume_latency(dev); } /** * dev_pm_qos_read_value - Get PM QoS constraint for a given device (locked). * @dev: Device to get the PM QoS constraint value for. * @type: QoS request type. */ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type) { struct dev_pm_qos *qos = dev->power.qos; unsigned long flags; s32 ret; spin_lock_irqsave(&dev->power.lock, flags); switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT : pm_qos_read_value(&qos->resume_latency); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE : freq_qos_read_value(&qos->freq, FREQ_QOS_MIN); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE : freq_qos_read_value(&qos->freq, FREQ_QOS_MAX); break; default: WARN_ON(1); ret = 0; } spin_unlock_irqrestore(&dev->power.lock, flags); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_read_value); /** * apply_constraint - Add/modify/remove device PM QoS request. * @req: Constraint request to apply * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. * * Internal function to update the constraints list using the PM QoS core * code and if needed call the per-device callbacks. */ static int apply_constraint(struct dev_pm_qos_request *req, enum pm_qos_req_action action, s32 value) { struct dev_pm_qos *qos = req->dev->power.qos; int ret; switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: if (WARN_ON(action != PM_QOS_REMOVE_REQ && value < 0)) value = 0; ret = pm_qos_update_target(&qos->resume_latency, &req->data.pnode, action, value); break; case DEV_PM_QOS_LATENCY_TOLERANCE: ret = pm_qos_update_target(&qos->latency_tolerance, &req->data.pnode, action, value); if (ret) { value = pm_qos_read_value(&qos->latency_tolerance); req->dev->power.set_latency_tolerance(req->dev, value); } break; case DEV_PM_QOS_MIN_FREQUENCY: case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_apply(&req->data.freq, action, value); break; case DEV_PM_QOS_FLAGS: ret = pm_qos_update_flags(&qos->flags, &req->data.flr, action, value); break; default: ret = -EINVAL; } return ret; } /* * dev_pm_qos_constraints_allocate * @dev: device to allocate data for * * Called at the first call to add_request, for constraint data allocation * Must be called with the dev_pm_qos_mtx mutex held */ static int dev_pm_qos_constraints_allocate(struct device *dev) { struct dev_pm_qos *qos; struct pm_qos_constraints *c; struct blocking_notifier_head *n; qos = kzalloc(sizeof(*qos), GFP_KERNEL); if (!qos) return -ENOMEM; n = kzalloc(3 * sizeof(*n), GFP_KERNEL); if (!n) { kfree(qos); return -ENOMEM; } c = &qos->resume_latency; plist_head_init(&c->list); c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE; c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE; c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; c->type = PM_QOS_MIN; c->notifiers = n; BLOCKING_INIT_NOTIFIER_HEAD(n); c = &qos->latency_tolerance; plist_head_init(&c->list); c->target_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE; c->default_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE; c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; c->type = PM_QOS_MIN; freq_constraints_init(&qos->freq); INIT_LIST_HEAD(&qos->flags.list); spin_lock_irq(&dev->power.lock); dev->power.qos = qos; spin_unlock_irq(&dev->power.lock); return 0; } static void __dev_pm_qos_hide_latency_limit(struct device *dev); static void __dev_pm_qos_hide_flags(struct device *dev); /** * dev_pm_qos_constraints_destroy * @dev: target device * * Called from the device PM subsystem on device removal under device_pm_lock(). */ void dev_pm_qos_constraints_destroy(struct device *dev) { struct dev_pm_qos *qos; struct dev_pm_qos_request *req, *tmp; struct pm_qos_constraints *c; struct pm_qos_flags *f; mutex_lock(&dev_pm_qos_sysfs_mtx); /* * If the device's PM QoS resume latency limit or PM QoS flags have been * exposed to user space, they have to be hidden at this point. */ pm_qos_sysfs_remove_resume_latency(dev); pm_qos_sysfs_remove_flags(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_latency_limit(dev); __dev_pm_qos_hide_flags(dev); qos = dev->power.qos; if (!qos) goto out; /* Flush the constraints lists for the device. */ c = &qos->resume_latency; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { /* * Update constraints list and call the notification * callbacks if needed */ apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->latency_tolerance; plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->freq.min_freq; plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } c = &qos->freq.max_freq; plist_for_each_entry_safe(req, tmp, &c->list, data.freq.pnode) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } f = &qos->flags; list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) { apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); } spin_lock_irq(&dev->power.lock); dev->power.qos = ERR_PTR(-ENODEV); spin_unlock_irq(&dev->power.lock); kfree(qos->resume_latency.notifiers); kfree(qos); out: mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); } static bool dev_pm_qos_invalid_req_type(struct device *dev, enum dev_pm_qos_req_type type) { return type == DEV_PM_QOS_LATENCY_TOLERANCE && !dev->power.set_latency_tolerance; } static int __dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { int ret = 0; if (!dev || !req || dev_pm_qos_invalid_req_type(dev, type)) return -EINVAL; if (WARN(dev_pm_qos_request_active(req), "%s() called for already added request\n", __func__)) return -EINVAL; if (IS_ERR(dev->power.qos)) ret = -ENODEV; else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); trace_dev_pm_qos_add_request(dev_name(dev), type, value); if (ret) return ret; req->dev = dev; req->type = type; if (req->type == DEV_PM_QOS_MIN_FREQUENCY) ret = freq_qos_add_request(&dev->power.qos->freq, &req->data.freq, FREQ_QOS_MIN, value); else if (req->type == DEV_PM_QOS_MAX_FREQUENCY) ret = freq_qos_add_request(&dev->power.qos->freq, &req->data.freq, FREQ_QOS_MAX, value); else ret = apply_constraint(req, PM_QOS_ADD_REQ, value); return ret; } /** * dev_pm_qos_add_request - inserts new qos request into the list * @dev: target device for the constraint * @req: pointer to a preallocated handle * @type: type of the request * @value: defines the qos request * * This function inserts a new entry in the device constraints list of * requested qos performance characteristics. It recomputes the aggregate * QoS expectations of parameters and initializes the dev_pm_qos_request * handle. Caller needs to save this handle for later use in updates and * removal. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENOMEM if there's not enough memory * to allocate for data structures, -ENODEV if the device has just been removed * from the system. * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_add_request(dev, req, type, value); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_request); /** * __dev_pm_qos_update_request - Modify an existing device PM QoS request. * @req : PM QoS request to modify. * @new_value: New value to request. */ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { s32 curr_value; int ret = 0; if (!req) /*guard against callers passing in null */ return -EINVAL; if (WARN(!dev_pm_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; switch(req->type) { case DEV_PM_QOS_RESUME_LATENCY: case DEV_PM_QOS_LATENCY_TOLERANCE: curr_value = req->data.pnode.prio; break; case DEV_PM_QOS_MIN_FREQUENCY: case DEV_PM_QOS_MAX_FREQUENCY: curr_value = req->data.freq.pnode.prio; break; case DEV_PM_QOS_FLAGS: curr_value = req->data.flr.flags; break; default: return -EINVAL; } trace_dev_pm_qos_update_request(dev_name(req->dev), req->type, new_value); if (curr_value != new_value) ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value); return ret; } /** * dev_pm_qos_update_request - modifies an existing qos request * @req : handle to list element holding a dev_pm_qos request to use * @new_value: defines the qos request * * Updates an existing dev PM qos request along with updating the * target value. * * Attempts are made to make this code callable on hot code paths. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENODEV if the device has been * removed from the system * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_update_request(req, new_value); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_update_request); static int __dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { int ret; if (!req) /*guard against callers passing in null */ return -EINVAL; if (WARN(!dev_pm_qos_request_active(req), "%s() called for unknown object\n", __func__)) return -EINVAL; if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; trace_dev_pm_qos_remove_request(dev_name(req->dev), req->type, PM_QOS_DEFAULT_VALUE); ret = apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); return ret; } /** * dev_pm_qos_remove_request - modifies an existing qos request * @req: handle to request list element * * Will remove pm qos request from the list of constraints and * recompute the current target value. Call this on slow code paths. * * Returns 1 if the aggregated constraint value has changed, * 0 if the aggregated constraint value has not changed, * -EINVAL in case of wrong parameters, -ENODEV if the device has been * removed from the system * * Callers should ensure that the target device is not RPM_SUSPENDED before * using this function for requests of type DEV_PM_QOS_FLAGS. */ int dev_pm_qos_remove_request(struct dev_pm_qos_request *req) { int ret; mutex_lock(&dev_pm_qos_mtx); ret = __dev_pm_qos_remove_request(req); mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_request); /** * dev_pm_qos_add_notifier - sets notification entry for changes to target value * of per-device PM QoS constraints * * @dev: target device for the constraint * @notifier: notifier block managed by caller. * @type: request type. * * Will register the notifier into a notification chain that gets called * upon changes to the target value for the device. * * If the device's constraints object doesn't exist when this routine is called, * it will be created (or error code will be returned if that fails). */ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { int ret = 0; mutex_lock(&dev_pm_qos_mtx); if (IS_ERR(dev->power.qos)) ret = -ENODEV; else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); if (ret) goto unlock; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers, notifier); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = freq_qos_add_notifier(&dev->power.qos->freq, FREQ_QOS_MIN, notifier); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_add_notifier(&dev->power.qos->freq, FREQ_QOS_MAX, notifier); break; default: WARN_ON(1); ret = -EINVAL; } unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_notifier); /** * dev_pm_qos_remove_notifier - deletes notification for changes to target value * of per-device PM QoS constraints * * @dev: target device for the constraint * @notifier: notifier block to be removed. * @type: request type. * * Will remove the notifier from the notification chain that gets called * upon changes to the target value. */ int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier, enum dev_pm_qos_req_type type) { int ret = 0; mutex_lock(&dev_pm_qos_mtx); /* Silently return if the constraints object is not present. */ if (IS_ERR_OR_NULL(dev->power.qos)) goto unlock; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers, notifier); break; case DEV_PM_QOS_MIN_FREQUENCY: ret = freq_qos_remove_notifier(&dev->power.qos->freq, FREQ_QOS_MIN, notifier); break; case DEV_PM_QOS_MAX_FREQUENCY: ret = freq_qos_remove_notifier(&dev->power.qos->freq, FREQ_QOS_MAX, notifier); break; default: WARN_ON(1); ret = -EINVAL; } unlock: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_remove_notifier); /** * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor. * @dev: Device whose ancestor to add the request for. * @req: Pointer to the preallocated handle. * @type: Type of the request. * @value: Constraint latency value. */ int dev_pm_qos_add_ancestor_request(struct device *dev, struct dev_pm_qos_request *req, enum dev_pm_qos_req_type type, s32 value) { struct device *ancestor = dev->parent; int ret = -ENODEV; switch (type) { case DEV_PM_QOS_RESUME_LATENCY: while (ancestor && !ancestor->power.ignore_children) ancestor = ancestor->parent; break; case DEV_PM_QOS_LATENCY_TOLERANCE: while (ancestor && !ancestor->power.set_latency_tolerance) ancestor = ancestor->parent; break; default: ancestor = NULL; } if (ancestor) ret = dev_pm_qos_add_request(ancestor, req, type, value); if (ret < 0) req->dev = NULL; return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_add_ancestor_request); static void __dev_pm_qos_drop_user_request(struct device *dev, enum dev_pm_qos_req_type type) { struct dev_pm_qos_request *req = NULL; switch(type) { case DEV_PM_QOS_RESUME_LATENCY: req = dev->power.qos->resume_latency_req; dev->power.qos->resume_latency_req = NULL; break; case DEV_PM_QOS_LATENCY_TOLERANCE: req = dev->power.qos->latency_tolerance_req; dev->power.qos->latency_tolerance_req = NULL; break; case DEV_PM_QOS_FLAGS: req = dev->power.qos->flags_req; dev->power.qos->flags_req = NULL; break; default: WARN_ON(1); return; } __dev_pm_qos_remove_request(req); kfree(req); } static void dev_pm_qos_drop_user_request(struct device *dev, enum dev_pm_qos_req_type type) { mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_drop_user_request(dev, type); mutex_unlock(&dev_pm_qos_mtx); } /** * dev_pm_qos_expose_latency_limit - Expose PM QoS latency limit to user space. * @dev: Device whose PM QoS latency limit is to be exposed to user space. * @value: Initial value of the latency limit. */ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value) { struct dev_pm_qos_request *req; int ret; if (!device_is_registered(dev) || value < 0) return -EINVAL; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_RESUME_LATENCY, value); if (ret < 0) { kfree(req); return ret; } mutex_lock(&dev_pm_qos_sysfs_mtx); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos)) ret = -ENODEV; else if (dev->power.qos->resume_latency_req) ret = -EEXIST; if (ret < 0) { __dev_pm_qos_remove_request(req); kfree(req); mutex_unlock(&dev_pm_qos_mtx); goto out; } dev->power.qos->resume_latency_req = req; mutex_unlock(&dev_pm_qos_mtx); ret = pm_qos_sysfs_add_resume_latency(dev); if (ret) dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY); out: mutex_unlock(&dev_pm_qos_sysfs_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit); static void __dev_pm_qos_hide_latency_limit(struct device *dev) { if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->resume_latency_req) __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY); } /** * dev_pm_qos_hide_latency_limit - Hide PM QoS latency limit from user space. * @dev: Device whose PM QoS latency limit is to be hidden from user space. */ void dev_pm_qos_hide_latency_limit(struct device *dev) { mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_resume_latency(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_latency_limit(dev); mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_limit); /** * dev_pm_qos_expose_flags - Expose PM QoS flags of a device to user space. * @dev: Device whose PM QoS flags are to be exposed to user space. * @val: Initial values of the flags. */ int dev_pm_qos_expose_flags(struct device *dev, s32 val) { struct dev_pm_qos_request *req; int ret; if (!device_is_registered(dev)) return -EINVAL; req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_FLAGS, val); if (ret < 0) { kfree(req); return ret; } pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_sysfs_mtx); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos)) ret = -ENODEV; else if (dev->power.qos->flags_req) ret = -EEXIST; if (ret < 0) { __dev_pm_qos_remove_request(req); kfree(req); mutex_unlock(&dev_pm_qos_mtx); goto out; } dev->power.qos->flags_req = req; mutex_unlock(&dev_pm_qos_mtx); ret = pm_qos_sysfs_add_flags(dev); if (ret) dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS); out: mutex_unlock(&dev_pm_qos_sysfs_mtx); pm_runtime_put(dev); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_flags); static void __dev_pm_qos_hide_flags(struct device *dev) { if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->flags_req) __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_FLAGS); } /** * dev_pm_qos_hide_flags - Hide PM QoS flags of a device from user space. * @dev: Device whose PM QoS flags are to be hidden from user space. */ void dev_pm_qos_hide_flags(struct device *dev) { pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_flags(dev); mutex_lock(&dev_pm_qos_mtx); __dev_pm_qos_hide_flags(dev); mutex_unlock(&dev_pm_qos_mtx); mutex_unlock(&dev_pm_qos_sysfs_mtx); pm_runtime_put(dev); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_flags); /** * dev_pm_qos_update_flags - Update PM QoS flags request owned by user space. * @dev: Device to update the PM QoS flags request for. * @mask: Flags to set/clear. * @set: Whether to set or clear the flags (true means set). */ int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set) { s32 value; int ret; pm_runtime_get_sync(dev); mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->flags_req) { ret = -EINVAL; goto out; } value = dev_pm_qos_requested_flags(dev); if (set) value |= mask; else value &= ~mask; ret = __dev_pm_qos_update_request(dev->power.qos->flags_req, value); out: mutex_unlock(&dev_pm_qos_mtx); pm_runtime_put(dev); return ret; } /** * dev_pm_qos_get_user_latency_tolerance - Get user space latency tolerance. * @dev: Device to obtain the user space latency tolerance for. */ s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev) { s32 ret; mutex_lock(&dev_pm_qos_mtx); ret = IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->latency_tolerance_req ? PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT : dev->power.qos->latency_tolerance_req->data.pnode.prio; mutex_unlock(&dev_pm_qos_mtx); return ret; } /** * dev_pm_qos_update_user_latency_tolerance - Update user space latency tolerance. * @dev: Device to update the user space latency tolerance for. * @val: New user space latency tolerance for @dev (negative values disable). */ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val) { int ret; mutex_lock(&dev_pm_qos_mtx); if (IS_ERR_OR_NULL(dev->power.qos) || !dev->power.qos->latency_tolerance_req) { struct dev_pm_qos_request *req; if (val < 0) { if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT) ret = 0; else ret = -EINVAL; goto out; } req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) { ret = -ENOMEM; goto out; } ret = __dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY_TOLERANCE, val); if (ret < 0) { kfree(req); goto out; } dev->power.qos->latency_tolerance_req = req; } else { if (val < 0) { __dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY_TOLERANCE); ret = 0; } else { ret = __dev_pm_qos_update_request(dev->power.qos->latency_tolerance_req, val); } } out: mutex_unlock(&dev_pm_qos_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance); /** * dev_pm_qos_expose_latency_tolerance - Expose latency tolerance to userspace * @dev: Device whose latency tolerance to expose */ int dev_pm_qos_expose_latency_tolerance(struct device *dev) { int ret; if (!dev->power.set_latency_tolerance) return -EINVAL; mutex_lock(&dev_pm_qos_sysfs_mtx); ret = pm_qos_sysfs_add_latency_tolerance(dev); mutex_unlock(&dev_pm_qos_sysfs_mtx); return ret; } EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_tolerance); /** * dev_pm_qos_hide_latency_tolerance - Hide latency tolerance from userspace * @dev: Device whose latency tolerance to hide */ void dev_pm_qos_hide_latency_tolerance(struct device *dev) { mutex_lock(&dev_pm_qos_sysfs_mtx); pm_qos_sysfs_remove_latency_tolerance(dev); mutex_unlock(&dev_pm_qos_sysfs_mtx); /* Remove the request from user space now */ pm_runtime_get_sync(dev); dev_pm_qos_update_user_latency_tolerance(dev, PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT); pm_runtime_put(dev); } EXPORT_SYMBOL_GPL(dev_pm_qos_hide_latency_tolerance); |
| 9 2 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 | /* SPDX-License-Identifier: GPL-2.0-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 router. * * Version: @(#)route.h 1.0.4 05/27/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Fixes: * Alan Cox : Reformatted. Added ip_rt_local() * Alan Cox : Support for TCP parameters. * Alexey Kuznetsov: Major changes for new routing code. * Mike McLagan : Routing by source * Robert Olsson : Added rt_cache statistics */ #ifndef _ROUTE_H #define _ROUTE_H #include <net/dst.h> #include <net/inetpeer.h> #include <net/flow.h> #include <net/inet_sock.h> #include <net/ip_fib.h> #include <net/arp.h> #include <net/ndisc.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> #include <linux/route.h> #include <linux/ip.h> #include <linux/cache.h> #include <linux/security.h> /* IPv4 datagram length is stored into 16bit field (tot_len) */ #define IP_MAX_MTU 0xFFFFU #define RTO_ONLINK 0x01 #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) struct fib_nh; struct fib_info; struct uncached_list; struct rtable { struct dst_entry dst; int rt_genid; unsigned int rt_flags; __u16 rt_type; __u8 rt_is_input; __u8 rt_uses_gateway; int rt_iif; u8 rt_gw_family; /* Info on neighbour */ union { __be32 rt_gw4; struct in6_addr rt_gw6; }; /* Miscellaneous cached information */ u32 rt_mtu_locked:1, rt_pmtu:31; struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; static inline bool rt_is_input_route(const struct rtable *rt) { return rt->rt_is_input != 0; } static inline bool rt_is_output_route(const struct rtable *rt) { return rt->rt_is_input == 0; } static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr) { if (rt->rt_gw_family == AF_INET) return rt->rt_gw4; return daddr; } struct ip_rt_acct { __u32 o_bytes; __u32 o_packets; __u32 i_bytes; __u32 i_packets; }; struct rt_cache_stat { unsigned int in_slow_tot; unsigned int in_slow_mc; unsigned int in_no_route; unsigned int in_brd; unsigned int in_martian_dst; unsigned int in_martian_src; unsigned int out_slow_tot; unsigned int out_slow_mc; }; extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; int ip_rt_init(void); void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp, const struct sk_buff *skb); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp, struct fib_result *res, const struct sk_buff *skb); static inline struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp) { return ip_route_output_key_hash(net, flp, NULL); } struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); struct rtable *ip_route_output_tunnel(struct sk_buff *skb, struct net_device *dev, struct net *net, __be32 *saddr, const struct ip_tunnel_info *info, u8 protocol, bool use_cache); struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); static inline struct rtable *ip_route_output_key(struct net *net, struct flowi4 *flp) { return ip_route_output_flow(net, flp, NULL); } static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, __be32 saddr, u8 tos, int oif) { struct flowi4 fl4 = { .flowi4_oif = oif, .flowi4_tos = tos, .daddr = daddr, .saddr = saddr, }; return ip_route_output_key(net, &fl4); } static inline struct rtable *ip_route_output_ports(struct net *net, struct flowi4 *fl4, struct sock *sk, __be32 daddr, __be32 saddr, __be16 dport, __be16 sport, __u8 proto, __u8 tos, int oif) { flowi4_init_output(fl4, oif, sk ? sk->sk_mark : 0, tos, RT_SCOPE_UNIVERSE, proto, sk ? inet_sk_flowi_flags(sk) : 0, daddr, saddr, dport, sport, sock_net_uid(net, sk)); if (sk) security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 *fl4, __be32 daddr, __be32 saddr, __be32 gre_key, __u8 tos, int oif) { memset(fl4, 0, sizeof(*fl4)); fl4->flowi4_oif = oif; fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; fl4->flowi4_proto = IPPROTO_GRE; fl4->fl4_gre_key = gre_key; return ip_route_output_key(net, fl4); } int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, struct fib_result *res); int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, const struct sk_buff *hint); static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin) { int err; rcu_read_lock(); err = ip_route_input_noref(skb, dst, src, tos, devin); if (!err) { skb_dst_force(skb); if (!skb_dst(skb)) err = -EINVAL; } rcu_read_unlock(); return err; } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol); void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk); void ip_rt_send_redirect(struct sk_buff *skb); unsigned int inet_addr_type(struct net *net, __be32 addr); unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr); unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr); void ip_rt_multicast_event(struct in_device *); int ip_rt_ioctl(struct net *, unsigned int cmd, struct rtentry *rt); void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool nopolicy, bool noxfrm); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt); struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *); void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric); void rt_add_uncached_list(struct rtable *rt); void rt_del_uncached_list(struct rtable *rt); int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags); static inline void ip_rt_put(struct rtable *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rtable */ BUILD_BUG_ON(offsetof(struct rtable, dst) != 0); dst_release(&rt->dst); } #define IPTOS_RT_MASK (IPTOS_TOS_MASK & ~3) extern const __u8 ip_tos2prio[16]; static inline char rt_tos2priority(u8 tos) { return ip_tos2prio[IPTOS_TOS(tos)>>1]; } /* ip_route_connect() and ip_route_newports() work in tandem whilst * binding a socket for a new outgoing connection. * * In order to use IPSEC properly, we must, in the end, have a * route that was looked up using all available keys including source * and destination ports. * * However, if a source port needs to be allocated (the user specified * a wildcard source port) we need to obtain addressing information * in order to perform that allocation. * * So ip_route_connect() looks up a route using wildcarded source and * destination ports in the key, simply so that we can get a pair of * addresses to use for port allocation. * * Later, once the ports are allocated, ip_route_newports() will make * another route lookup if needed to make sure we catch any IPSEC * rules keyed on the port information. * * The callers allocate the flow key on their stack, and must pass in * the same flowi4 object to both the ip_route_connect() and the * ip_route_newports() calls. */ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src, u32 tos, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { __u8 flow_flags = 0; if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, protocol, flow_flags, dst, src, dport, sport, sk->sk_uid); } static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, __be32 src, u32 tos, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; ip_route_connect_init(fl4, dst, src, tos, oif, protocol, sport, dport, sk); if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; ip_rt_put(rt); flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable *rt, __be16 orig_sport, __be16 orig_dport, __be16 sport, __be16 dport, struct sock *sk) { if (sport != orig_sport || dport != orig_dport) { fl4->fl4_dport = dport; fl4->fl4_sport = sport; ip_rt_put(rt); flowi4_update_output(fl4, sk->sk_bound_dev_if, RT_CONN_FLAGS(sk), fl4->daddr, fl4->saddr); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(sock_net(sk), fl4, sk); } return rt; } static inline int inet_iif(const struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); if (rt && rt->rt_iif) return rt->rt_iif; return skb->skb_iif; } static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); struct net *net = dev_net(dst->dev); if (hoplimit == 0) hoplimit = net->ipv4.sysctl_ip_default_ttl; return hoplimit; } static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, __be32 daddr) { struct neighbour *neigh; neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &daddr, dev, false); return neigh; } static inline struct neighbour *ip_neigh_for_gw(struct rtable *rt, struct sk_buff *skb, bool *is_v6gw) { struct net_device *dev = rt->dst.dev; struct neighbour *neigh; if (likely(rt->rt_gw_family == AF_INET)) { neigh = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &rt->rt_gw6); *is_v6gw = true; } else { neigh = ip_neigh_gw4(dev, ip_hdr(skb)->daddr); } return neigh; } #endif /* _ROUTE_H */ |
| 5498 5494 5492 5497 5 5 5 5493 5494 5499 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.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); } /** * 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. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *parent; unsigned long flags; /* nothing to do for root */ if (!cgroup_parent(cgrp)) return; /* * 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 (cgroup_rstat_cpu(cgrp, cpu)->updated_next) return; raw_spin_lock_irqsave(cpu_lock, flags); /* put @cgrp and all ancestors on the corresponding updated lists */ for (parent = cgroup_parent(cgrp); parent; cgrp = parent, parent = cgroup_parent(cgrp)) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; } raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree * @pos: current position * @root: root of the tree to traversal * @cpu: target cpu * * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, if a child is visited, its parent is * guaranteed to be visited afterwards. */ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; if (pos == root) return NULL; /* * We're gonna walk down to the first leaf and visit/remove it. We * can pick whatever unvisited node as the starting point. */ if (!pos) pos = root; else pos = cgroup_parent(pos); /* walk down to the first leaf */ while (true) { rstatc = cgroup_rstat_cpu(pos, cpu); if (rstatc->updated_children == pos) break; pos = rstatc->updated_children; } /* * Unlink @pos from the tree. As the updated_children list is * singly linked, we have to walk it to find the removal point. * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ if (rstatc->updated_next) { struct cgroup *parent = cgroup_parent(pos); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); struct cgroup_rstat_cpu *nrstatc; struct cgroup **nextp; nextp = &prstatc->updated_children; while (true) { nrstatc = cgroup_rstat_cpu(*nextp, cpu); if (*nextp == pos) break; WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; rstatc->updated_next = NULL; return pos; } /* only happens for @root */ return NULL; } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; raw_spin_lock(cpu_lock); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(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(); } raw_spin_unlock(cpu_lock); /* if @may_sleep, play nice and yield if necessary */ if (may_sleep && (need_resched() || spin_needbreak(&cgroup_rstat_lock))) { spin_unlock_irq(&cgroup_rstat_lock); if (!cond_resched()) cpu_relax(); spin_lock_irq(&cgroup_rstat_lock); } } } /** * 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. */ void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); spin_unlock_irq(&cgroup_rstat_lock); } /** * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() * @cgrp: target cgroup * * This function can be called from any context. */ void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) { unsigned long flags; spin_lock_irqsave(&cgroup_rstat_lock, flags); cgroup_rstat_flush_locked(cgrp, false); spin_unlock_irqrestore(&cgroup_rstat_lock, flags); } /** * cgroup_rstat_flush_begin - 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(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() */ void cgroup_rstat_flush_release(void) __releases(&cgroup_rstat_lock) { spin_unlock_irq(&cgroup_rstat_lock); } 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)); BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp)); } /* * 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; } 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; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_base_stat cur, delta; unsigned seq; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); cur.cputime = rstatc->bstat.cputime; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate percpu delta to global */ delta = cur; cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); /* propagate global delta to parent */ if (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); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); u64_stats_update_begin(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc) { u64_stats_update_end(&rstatc->bsync); 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; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc); } /* * 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 task_cputime *cputime) { int i; cputime->stime = 0; cputime->utime = 0; cputime->sum_exec_runtime = 0; 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]; } } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; struct task_cputime cputime; 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); cgroup_rstat_flush_release(); } else { root_cgroup_cputime(&cputime); usage = cputime.sum_exec_runtime; utime = cputime.utime; stime = cputime.stime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); } |
| 8 7 3 7 7 8 8 6 8 6 7 7 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * arch/x86_64/lib/csum-partial.c * * This file contains network checksum routines that are better done * in an architecture-specific manner due to speed. */ #include <linux/compiler.h> #include <linux/export.h> #include <asm/checksum.h> static inline unsigned short from32to16(unsigned a) { unsigned short b = a >> 16; asm("addw %w2,%w0\n\t" "adcw $0,%w0\n" : "=r" (b) : "0" (b), "r" (a)); return b; } /* * Do a 64-bit checksum on an arbitrary memory area. * Returns a 32bit checksum. * * This isn't as time critical as it used to be because many NICs * do hardware checksumming these days. * * Things tried and found to not make it faster: * Manual Prefetching * Unrolling to an 128 bytes inner loop. * Using interleaving with more registers to break the carry chains. */ static unsigned do_csum(const unsigned char *buff, unsigned len) { unsigned odd, count; unsigned long result = 0; if (unlikely(len == 0)) return result; odd = 1 & (unsigned long) buff; if (unlikely(odd)) { result = *buff << 8; len--; buff++; } count = len >> 1; /* nr of 16-bit words.. */ if (count) { if (2 & (unsigned long) buff) { result += *(unsigned short *)buff; count--; len -= 2; buff += 2; } count >>= 1; /* nr of 32-bit words.. */ if (count) { unsigned long zero; unsigned count64; if (4 & (unsigned long) buff) { result += *(unsigned int *) buff; count--; len -= 4; buff += 4; } count >>= 1; /* nr of 64-bit words.. */ /* main loop using 64byte blocks */ zero = 0; count64 = count >> 3; while (count64) { asm("addq 0*8(%[src]),%[res]\n\t" "adcq 1*8(%[src]),%[res]\n\t" "adcq 2*8(%[src]),%[res]\n\t" "adcq 3*8(%[src]),%[res]\n\t" "adcq 4*8(%[src]),%[res]\n\t" "adcq 5*8(%[src]),%[res]\n\t" "adcq 6*8(%[src]),%[res]\n\t" "adcq 7*8(%[src]),%[res]\n\t" "adcq %[zero],%[res]" : [res] "=r" (result) : [src] "r" (buff), [zero] "r" (zero), "[res]" (result)); buff += 64; count64--; } /* last up to 7 8byte blocks */ count %= 8; while (count) { asm("addq %1,%0\n\t" "adcq %2,%0\n" : "=r" (result) : "m" (*(unsigned long *)buff), "r" (zero), "0" (result)); --count; buff += 8; } result = add32_with_carry(result>>32, result&0xffffffff); if (len & 4) { result += *(unsigned int *) buff; buff += 4; } } if (len & 2) { result += *(unsigned short *) buff; buff += 2; } } if (len & 1) result += *buff; result = add32_with_carry(result>>32, result & 0xffffffff); if (unlikely(odd)) { result = from32to16(result); result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); } return result; } /* * computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) * * returns a 32-bit number suitable for feeding into itself * or csum_tcpudp_magic * * this function must be called with even lengths, except * for the last fragment, which may be odd * * it's best to have buff aligned on a 64-bit boundary */ __wsum csum_partial(const void *buff, int len, __wsum sum) { return (__force __wsum)add32_with_carry(do_csum(buff, len), (__force u32)sum); } EXPORT_SYMBOL(csum_partial); /* * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c */ __sum16 ip_compute_csum(const void *buff, int len) { return csum_fold(csum_partial(buff,len,0)); } EXPORT_SYMBOL(ip_compute_csum); |
| 1622 140 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/atomic.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; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { atomic_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && atomic_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) atomic_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ /* * generic net pointers */ #ifndef __NET_GENERIC_H__ #define __NET_GENERIC_H__ #include <linux/bug.h> #include <linux/rcupdate.h> /* * Generic net pointers are to be used by modules to put some private * stuff on the struct net without explicit struct net modification * * The rules are simple: * 1. set pernet_operations->id. After register_pernet_device you * will have the id of your private pointer. * 2. set pernet_operations->size to have the code allocate and free * a private structure pointed to from struct net. * 3. do not change this pointer while the net is alive; * 4. do not try to have any private reference on the net_generic object. * * After accomplishing all of the above, the private pointer can be * accessed with the net_generic() call. */ struct net_generic { union { struct { unsigned int len; struct rcu_head rcu; } s; void *ptr[0]; }; }; static inline void *net_generic(const struct net *net, unsigned int id) { struct net_generic *ng; void *ptr; rcu_read_lock(); ng = rcu_dereference(net->gen); ptr = ng->ptr[id]; rcu_read_unlock(); return ptr; } #endif |
| 53 53 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; if (!tsk->ptrace || (current != tsk->parent) || ((get_dumpable(mm) != SUID_DUMP_USER) && !ptracer_capable(tsk, mm->user_ns))) { mmput(mm); return 0; } ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) { child->jobctl |= JOBCTL_STOP_PENDING; /* * This is only possible if this thread was cloned by the * traced task running in the stopped group, set the signal * for the future reports. * FIXME: we should change ptrace_init_task() to handle this * case. */ if (!(child->jobctl & JOBCTL_STOP_SIGMASK)) child->jobctl |= SIGSTOP; } /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* Ensure that nothing can wake it up, even SIGKILL */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->state = __TASK_TRACED; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { if (task->state != __TASK_TRACED) return; WARN_ON(!task->ptrace || task->parent != current); /* * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. * Recheck state under the lock to close this race. */ spin_lock_irq(&task->sighand->siglock); if (task->state == __TASK_TRACED) { if (__fatal_signal_pending(task)) wake_up_state(task, __TASK_TRACED); else task->state = TASK_TRACED; } spin_unlock_irq(&task->sighand->siglock); } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { WARN_ON(child->state == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state) { if (!wait_task_inactive(child, __TASK_TRACED)) { /* * This can only happen if may_ptrace_stop() fails and * ptrace_stop() changes ->state back to TASK_RUNNING, * so we should not worry about leaking __TASK_TRACED. */ WARN_ON(child->state == __TASK_TRACED); ret = -ESRCH; } } return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int check_ptrace_options(unsigned long data) { if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || current->ptrace & PT_SUSPEND_SECCOMP) return -EPERM; } return 0; } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; retval = -EIO; if (seize) { if (addr != 0) goto out; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) goto out; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); retval = -EPERM; if (unlikely(task->flags & PF_KTHREAD)) goto out; if (same_thread_group(task, current)) goto out; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ retval = -ERESTARTNOINTR; if (mutex_lock_interruptible(&task->signal->cred_guard_mutex)) goto out; task_lock(task); retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); task_unlock(task); if (retval) goto unlock_creds; write_lock_irq(&tasklist_lock); retval = -EPERM; if (unlikely(task->exit_state)) goto unlock_tasklist; if (task->ptrace) goto unlock_tasklist; if (seize) flags |= PT_SEIZED; task->ptrace = flags; ptrace_link(task, current); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); spin_lock(&task->sighand->siglock); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) signal_wake_up_state(task, __TASK_STOPPED); spin_unlock(&task->sighand->siglock); retval = 0; unlock_tasklist: write_unlock_irq(&tasklist_lock); unlock_creds: mutex_unlock(&task->signal->cred_guard_mutex); out: if (!retval) { /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); proc_ptrace_connector(task, PTRACE_ATTACH); } return retval; } /** * ptrace_traceme -- helper for PTRACE_TRACEME * * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ static int ptrace_traceme(void) { int ret = -EPERM; write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { ret = security_ptrace_traceme(current->parent); /* * Check PF_EXITING to ensure ->real_parent has not passed * exit_ptrace(). Otherwise we don't report the error but * pretend ->real_parent untraces us right after return. */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); return ret; } /* * Called with irqs disabled, returns true if childs should reap themselves. */ static int ignoring_children(struct sighand_struct *sigh) { int ret; spin_lock(&sigh->siglock); ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); spin_unlock(&sigh->siglock); return ret; } /* * Called with tasklist_lock held for writing. * Unlink a traced task, and clean it up if it was a traced zombie. * Return true if it needs to be reaped with release_task(). * (We can't call release_task() here because we already hold tasklist_lock.) * * If it's a zombie, our attachedness prevented normal parent notification * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * * If it's our own child, there is no notification to do. But if our normal * children self-reap, then this child was prevented by ptrace and we must * reap it now, in that case we must also wake up sub-threads sleeping in * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { bool dead; __ptrace_unlink(p); if (p->exit_state != EXIT_ZOMBIE) return false; dead = !thread_group_leader(p); if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); else if (ignoring_children(tracer->sighand)) { __wake_up_parent(p, tracer); dead = true; } } /* Mark it as in the process of being reaped. */ if (dead) p->exit_state = EXIT_DEAD; return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); write_lock_irq(&tasklist_lock); /* * We rely on ptrace_freeze_traced(). It can't be killed and * untraced by another thread, it can't be a zombie. */ WARN_ON(!child->ptrace || child->exit_state); /* * tasklist_lock avoids the race with wait_task_stopped(), see * the comment in ptrace_resume(). */ child->exit_code = data; __ptrace_detach(current, child); write_unlock_irq(&tasklist_lock); proc_ptrace_connector(child, PTRACE_DETACH); return 0; } /* * Detach all tasks we were using ptrace on. Called with tasklist held * for writing. */ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) { struct task_struct *p, *n; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); } } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; return -EIO; } if (copy_to_user(dst, buf, retval)) return -EFAULT; copied += retval; src += retval; dst += retval; len -= retval; } return copied; } int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; return -EIO; } copied += retval; src += retval; dst += retval; len -= retval; } return copied; } static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; int ret; ret = check_ptrace_options(data); if (ret) return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); flags |= (data << PT_OPT_FLAG_SHIFT); child->ptrace = flags; return 0; } static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(info, child->last_siginfo); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(child->last_siginfo, info); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_peek_siginfo(struct task_struct *child, unsigned long addr, unsigned long data) { struct ptrace_peeksiginfo_args arg; struct sigpending *pending; struct sigqueue *q; int ret, i; ret = copy_from_user(&arg, (void __user *) addr, sizeof(struct ptrace_peeksiginfo_args)); if (ret) return -EFAULT; if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) return -EINVAL; /* unknown flags */ if (arg.nr < 0) return -EINVAL; /* Ensure arg.off fits in an unsigned long */ if (arg.off > ULONG_MAX) return 0; if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else pending = &child->pending; for (i = 0; i < arg.nr; ) { kernel_siginfo_t info; unsigned long off = arg.off + i; bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info)) { ret = -EFAULT; break; } } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; if (copy_siginfo_to_user(uinfo, &info)) { ret = -EFAULT; break; } } data += sizeof(siginfo_t); i++; if (signal_pending(current)) break; cond_resched(); } if (i > 0) return i; return ret; } #ifdef PTRACE_SINGLESTEP #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) #else #define is_singlestep(request) 0 #endif #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) #else #define is_singleblock(request) 0 #endif #ifdef PTRACE_SYSEMU #define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) #else #define is_sysemu_singlestep(request) 0 #endif static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { bool need_siglock; if (!valid_signal(data)) return -EIO; if (request == PTRACE_SYSCALL) set_tsk_thread_flag(child, TIF_SYSCALL_TRACE); else clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) set_tsk_thread_flag(child, TIF_SYSCALL_EMU); else clear_tsk_thread_flag(child, TIF_SYSCALL_EMU); #endif if (is_singleblock(request)) { if (unlikely(!arch_has_block_step())) return -EIO; user_enable_block_step(child); } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { if (unlikely(!arch_has_single_step())) return -EIO; user_enable_single_step(child); } else { user_disable_single_step(child); } /* * Change ->exit_code and ->state under siglock to avoid the race * with wait_task_stopped() in between; a non-zero ->exit_code will * wrongly look like another report from tracee. * * Note that we need siglock even if ->exit_code == data and/or this * status was not reported yet, the new status must not be cleared by * wait_task_stopped() after resume. * * If data == 0 we do not care if wait_task_stopped() reports the old * status and clears the code too; this can't race with the tracee, it * takes siglock after resume. */ need_siglock = data && !thread_group_empty(current); if (need_siglock) spin_lock_irq(&child->sighand->siglock); child->exit_code = data; wake_up_state(child, __TASK_TRACED); if (need_siglock) spin_unlock_irq(&child->sighand->siglock); return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static const struct user_regset * find_regset(const struct user_regset_view *view, unsigned int type) { const struct user_regset *regset; int n; for (n = 0; n < view->n; ++n) { regset = view->regsets + n; if (regset->core_note_type == type) return regset; } return NULL; } static int ptrace_regset(struct task_struct *task, int req, unsigned int type, struct iovec *kiov) { const struct user_regset_view *view = task_user_regset_view(task); const struct user_regset *regset = find_regset(view, type); int regset_no; if (!regset || (kiov->iov_len % regset->size) != 0) return -EINVAL; regset_no = regset - view->regsets; kiov->iov_len = min(kiov->iov_len, (__kernel_size_t) (regset->n * regset->size)); if (req == PTRACE_GETREGSET) return copy_regset_to_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); else return copy_regset_from_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); } /* * This is declared in linux/regset.h and defined in machine-dependent * code. We put the export here, near the primary machine-neutral use, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); static unsigned long ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { unsigned long args[ARRAY_SIZE(info->entry.args)]; int i; info->op = PTRACE_SYSCALL_INFO_ENTRY; info->entry.nr = syscall_get_nr(child, regs); syscall_get_arguments(child, regs, args); for (i = 0; i < ARRAY_SIZE(args); i++) info->entry.args[i] = args[i]; /* args is the last field in struct ptrace_syscall_info.entry */ return offsetofend(struct ptrace_syscall_info, entry.args); } static unsigned long ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { /* * As struct ptrace_syscall_info.entry is currently a subset * of struct ptrace_syscall_info.seccomp, it makes sense to * initialize that subset using ptrace_get_syscall_info_entry(). * This can be reconsidered in the future if these structures * diverge significantly enough. */ ptrace_get_syscall_info_entry(child, regs, info); info->op = PTRACE_SYSCALL_INFO_SECCOMP; info->seccomp.ret_data = child->ptrace_message; /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } static unsigned long ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { info->op = PTRACE_SYSCALL_INFO_EXIT; info->exit.rval = syscall_get_error(child, regs); info->exit.is_error = !!info->exit.rval; if (!info->exit.is_error) info->exit.rval = syscall_get_return_value(child, regs); /* is_error is the last field in struct ptrace_syscall_info.exit */ return offsetofend(struct ptrace_syscall_info, exit.is_error); } static int ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, void __user *datavp) { struct pt_regs *regs = task_pt_regs(child); struct ptrace_syscall_info info = { .op = PTRACE_SYSCALL_INFO_NONE, .arch = syscall_get_arch(child), .instruction_pointer = instruction_pointer(regs), .stack_pointer = user_stack_pointer(regs), }; unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); unsigned long write_size; /* * This does not need lock_task_sighand() to access * child->last_siginfo because ptrace_freeze_traced() * called earlier by ptrace_check_attach() ensures that * the tracee cannot go away and clear its last_siginfo. */ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { case SIGTRAP | 0x80: switch (child->ptrace_message) { case PTRACE_EVENTMSG_SYSCALL_ENTRY: actual_size = ptrace_get_syscall_info_entry(child, regs, &info); break; case PTRACE_EVENTMSG_SYSCALL_EXIT: actual_size = ptrace_get_syscall_info_exit(child, regs, &info); break; } break; case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info); break; } write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: return generic_ptrace_peekdata(child, addr, data); case PTRACE_POKETEXT: case PTRACE_POKEDATA: return generic_ptrace_pokedata(child, addr, data); #ifdef PTRACE_OLDSETOPTIONS case PTRACE_OLDSETOPTIONS: #endif case PTRACE_SETOPTIONS: ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: ret = put_user(child->ptrace_message, datalp); break; case PTRACE_PEEKSIGINFO: ret = ptrace_peek_siginfo(child, addr, data); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user(&siginfo, datavp); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; case PTRACE_GETSIGMASK: { sigset_t *mask; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (test_tsk_restore_sigmask(child)) mask = &child->saved_sigmask; else mask = &child->blocked; if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; } case PTRACE_SETSIGMASK: { sigset_t new_set; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { ret = -EFAULT; break; } sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); /* * Every thread does recalc_sigpending() after resume, so * retarget_shared_pending() and recalc_sigpending() are not * called here. */ spin_lock_irq(&child->sighand->siglock); child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); clear_tsk_restore_sigmask(child); ret = 0; break; } case PTRACE_INTERRUPT: /* * Stop tracee without any side-effect on signal or job * control. At least one trap is guaranteed to happen * after this request. If @child is already trapped, the * current trap is not disturbed and another trap will * happen after the current trap is ended with PTRACE_CONT. * * The actual trap might not be PTRACE_EVENT_STOP trap but * the pending condition is cleared regardless. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; /* * INTERRUPT doesn't disturb existing trap sans one * exception. If ptracer issued LISTEN for the current * STOP, this INTERRUPT should clear LISTEN and re-trap * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; break; case PTRACE_LISTEN: /* * Listen for events. Tracee must be in STOP. It's not * resumed per-se but is not considered to be in TRACED by * wait(2) or ptrace(2). If an async event (e.g. group * stop state change) happens, tracee will enter STOP trap * again. Alternatively, ptracer can issue INTERRUPT to * finish listening and re-trap tracee into STOP. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; si = child->last_siginfo; if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { child->jobctl |= JOBCTL_LISTENING; /* * If NOTIFY is set, it means event happened between * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); break; case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { struct mm_struct *mm = get_task_mm(child); unsigned long tmp = 0; ret = -ESRCH; if (!mm) break; switch (addr) { case PTRACE_GETFDPIC_EXEC: tmp = mm->context.exec_fdpic_loadmap; break; case PTRACE_GETFDPIC_INTERP: tmp = mm->context.interp_fdpic_loadmap; break; default: break; } mmput(mm); ret = put_user(tmp, datalp); break; } #endif #ifdef PTRACE_SINGLESTEP case PTRACE_SINGLESTEP: #endif #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif #ifdef PTRACE_SYSEMU case PTRACE_SYSEMU: case PTRACE_SYSEMU_SINGLESTEP: #endif case PTRACE_SYSCALL: case PTRACE_CONT: return ptrace_resume(child, request, data); case PTRACE_KILL: send_sig_info(SIGKILL, SEND_SIG_NOINFO, child); return 0; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct iovec __user *uiov = datavp; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || __get_user(kiov.iov_len, &uiov->iov_len)) return -EFAULT; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; #endif case PTRACE_SECCOMP_GET_FILTER: ret = seccomp_get_filter(child, addr, datavp); break; case PTRACE_SECCOMP_GET_METADATA: ret = seccomp_get_metadata(child, addr, datavp); break; default: break; } return ret; } #ifndef arch_ptrace_attach #define arch_ptrace_attach(child) do { } while (0) #endif SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, unsigned long, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); if (!ret) arch_ptrace_attach(current); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); /* * Some architectures need to do book-keeping after * a ptrace attach. */ if (!ret) arch_ptrace_attach(child); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); out: return ret; } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data) { unsigned long tmp; int copied; copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); } int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data) { int copied; copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } #if defined CONFIG_COMPAT int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; kernel_siginfo_t siginfo; int ret; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else ret = put_user(word, datap); break; case PTRACE_POKETEXT: case PTRACE_POKEDATA: ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; case PTRACE_GETEVENTMSG: ret = put_user((compat_ulong_t) child->ptrace_message, datap); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user32( (struct compat_siginfo __user *) datap, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user32( &siginfo, (struct compat_siginfo __user *) datap); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct compat_iovec __user *uiov = (struct compat_iovec __user *) datap; compat_uptr_t ptr; compat_size_t len; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || __get_user(len, &uiov->iov_len)) return -EFAULT; kiov.iov_base = compat_ptr(ptr); kiov.iov_len = len; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } #endif default: ret = ptrace_request(child, request, addr, data); } return ret; } COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); /* * Some architectures need to do book-keeping after * a ptrace attach. */ if (!ret) arch_ptrace_attach(child); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); } out_put_task_struct: put_task_struct(child); out: return ret; } #endif /* CONFIG_COMPAT */ |
| 528 526 | 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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_SORT_EXTABLE #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ #endif /* !ARCH_HAS_SORT_EXTABLE */ #ifndef ARCH_HAS_SEARCH_EXTABLE static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM net #if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NET_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/tracepoint.h> TRACE_EVENT(net_dev_start_xmit, TP_PROTO(const struct sk_buff *skb, const struct net_device *dev), TP_ARGS(skb, dev), TP_STRUCT__entry( __string( name, dev->name ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( int, network_offset ) __field( bool, transport_offset_valid) __field( int, transport_offset) __field( u8, tx_flags ) __field( u16, gso_size ) __field( u16, gso_segs ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name, dev->name); __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->network_offset = skb_network_offset(skb); __entry->transport_offset_valid = skb_transport_header_was_set(skb); __entry->transport_offset = skb_transport_offset(skb); __entry->tx_flags = skb_shinfo(skb)->tx_flags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_segs = skb_shinfo(skb)->gso_segs; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, __entry->data_len, __entry->network_offset, __entry->transport_offset_valid, __entry->transport_offset, __entry->tx_flags, __entry->gso_size, __entry->gso_segs, __entry->gso_type) ); TRACE_EVENT(net_dev_xmit, TP_PROTO(struct sk_buff *skb, int rc, struct net_device *dev, unsigned int skb_len), TP_ARGS(skb, rc, dev, skb_len), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __field( int, rc ) __string( name, dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb_len; __entry->rc = rc; __assign_str(name, dev->name); ), TP_printk("dev=%s skbaddr=%p len=%u rc=%d", __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) ); TRACE_EVENT(net_dev_xmit_timeout, TP_PROTO(struct net_device *dev, int queue_index), TP_ARGS(dev, queue_index), TP_STRUCT__entry( __string( name, dev->name ) __string( driver, netdev_drivername(dev)) __field( int, queue_index ) ), TP_fast_assign( __assign_str(name, dev->name); __assign_str(driver, netdev_drivername(dev)); __entry->queue_index = queue_index; ), TP_printk("dev=%s driver=%s queue=%d", __get_str(name), __get_str(driver), __entry->queue_index) ); DECLARE_EVENT_CLASS(net_dev_template, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __field( void *, skbaddr ) __field( unsigned int, len ) __string( name, skb->dev->name ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb->len; __assign_str(name, skb->dev->name); ), TP_printk("dev=%s skbaddr=%p len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) DEFINE_EVENT(net_dev_template, net_dev_queue, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_receive_skb, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_template, netif_rx, TP_PROTO(struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb), TP_STRUCT__entry( __string( name, skb->dev->name ) __field( unsigned int, napi_id ) __field( u16, queue_mapping ) __field( const void *, skbaddr ) __field( bool, vlan_tagged ) __field( u16, vlan_proto ) __field( u16, vlan_tci ) __field( u16, protocol ) __field( u8, ip_summed ) __field( u32, hash ) __field( bool, l4_hash ) __field( unsigned int, len ) __field( unsigned int, data_len ) __field( unsigned int, truesize ) __field( bool, mac_header_valid) __field( int, mac_header ) __field( unsigned char, nr_frags ) __field( u16, gso_size ) __field( u16, gso_type ) ), TP_fast_assign( __assign_str(name, skb->dev->name); #ifdef CONFIG_NET_RX_BUSY_POLL __entry->napi_id = skb->napi_id; #else __entry->napi_id = 0; #endif __entry->queue_mapping = skb->queue_mapping; __entry->skbaddr = skb; __entry->vlan_tagged = skb_vlan_tag_present(skb); __entry->vlan_proto = ntohs(skb->vlan_proto); __entry->vlan_tci = skb_vlan_tag_get(skb); __entry->protocol = ntohs(skb->protocol); __entry->ip_summed = skb->ip_summed; __entry->hash = skb->hash; __entry->l4_hash = skb->l4_hash; __entry->len = skb->len; __entry->data_len = skb->data_len; __entry->truesize = skb->truesize; __entry->mac_header_valid = skb_mac_header_was_set(skb); __entry->mac_header = skb_mac_header(skb) - skb->data; __entry->nr_frags = skb_shinfo(skb)->nr_frags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_type = skb_shinfo(skb)->gso_type; ), TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->hash, __entry->l4_hash, __entry->len, __entry->data_len, __entry->truesize, __entry->mac_header_valid, __entry->mac_header, __entry->nr_frags, __entry->gso_size, __entry->gso_type) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_receive_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_ni_entry, TP_PROTO(const struct sk_buff *skb), TP_ARGS(skb) ); DECLARE_EVENT_CLASS(net_dev_rx_exit_template, TP_PROTO(int ret), TP_ARGS(ret), TP_STRUCT__entry( __field(int, ret) ), TP_fast_assign( __entry->ret = ret; ), TP_printk("ret=%d", __entry->ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_frags_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, napi_gro_receive_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_rx_ni_exit, TP_PROTO(int ret), TP_ARGS(ret) ); DEFINE_EVENT(net_dev_rx_exit_template, netif_receive_skb_list_exit, TP_PROTO(int ret), TP_ARGS(ret) ); #endif /* _TRACE_NET_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
open /syzkaller/managers/ci2-android-5-10-perf/kernel/security/selinux/flask.h: no such file or directory
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM namei #if !defined(_TRACE_INODEPATH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_INODEPATH_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> TRACE_EVENT(inodepath, TP_PROTO(struct inode *inode, char *path), TP_ARGS(inode, path), TP_STRUCT__entry( /* dev_t and ino_t are arch dependent bit width * so just use 64-bit */ __field(unsigned long, ino) __field(unsigned long, dev) __string(path, path) ), TP_fast_assign( __entry->ino = inode->i_ino; __entry->dev = inode->i_sb->s_dev; __assign_str(path, path); ), TP_printk("dev %d:%d ino=%lu path=%s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __get_str(path)) ); #endif /* _TRACE_INODEPATH_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 38 31 1 1 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 | // SPDX-License-Identifier: GPL-2.0-only /* * Support Intel/AMD RAPL energy consumption counters * Copyright (C) 2013 Google, Inc., Stephane Eranian * * Intel RAPL interface is specified in the IA-32 Manual Vol3b * section 14.7.1 (September 2013) * * AMD RAPL interface for Fam17h is described in the public PPR: * https://bugzilla.kernel.org/show_bug.cgi?id=206537 * * RAPL provides more controls than just reporting energy consumption * however here we only expose the 3 energy consumption free running * counters (pp0, pkg, dram). * * Each of those counters increments in a power unit defined by the * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules * but it can vary. * * Counter to rapl events mappings: * * pp0 counter: consumption of all physical cores (power plane 0) * event: rapl_energy_cores * perf code: 0x1 * * pkg counter: consumption of the whole processor package * event: rapl_energy_pkg * perf code: 0x2 * * dram counter: consumption of the dram domain (servers only) * event: rapl_energy_dram * perf code: 0x3 * * gpu counter: consumption of the builtin-gpu domain (client only) * event: rapl_energy_gpu * perf code: 0x4 * * psys counter: consumption of the builtin-psys domain (client only) * event: rapl_energy_psys * perf code: 0x5 * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * * The events only support system-wide mode counting. There is no * sampling support because it does not make sense and is not * supported by the RAPL hardware. * * Because we want to avoid floating-point operations in the kernel, * the events are all reported in fixed point arithmetic (32.32). * Tools must adjust the counts to convert them to Watts using * the duration of the measurement. Tools may use a function such as * ldexp(raw_count, -32); */ #define pr_fmt(fmt) "RAPL PMU: " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/nospec.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "perf_event.h" #include "probe.h" MODULE_LICENSE("GPL"); /* * RAPL energy status counters */ enum perf_rapl_events { PERF_RAPL_PP0 = 0, /* all cores */ PERF_RAPL_PKG, /* entire package */ PERF_RAPL_RAM, /* DRAM */ PERF_RAPL_PP1, /* gpu */ PERF_RAPL_PSYS, /* psys */ PERF_RAPL_MAX, NR_RAPL_DOMAINS = PERF_RAPL_MAX, }; static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", "pp1-gpu", "psys", }; /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ static struct perf_pmu_events_attr event_attr_##v = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = str, \ }; struct rapl_pmu { raw_spinlock_t lock; int n_active; int cpu; struct list_head active_list; struct pmu *pmu; ktime_t timer_interval; struct hrtimer hrtimer; }; struct rapl_pmus { struct pmu pmu; unsigned int maxdie; struct rapl_pmu *pmus[]; }; enum rapl_unit_quirk { RAPL_UNIT_QUIRK_NONE, RAPL_UNIT_QUIRK_INTEL_HSW, RAPL_UNIT_QUIRK_INTEL_SPR, }; struct rapl_model { struct perf_msr *rapl_msrs; unsigned long events; unsigned int msr_power_unit; enum rapl_unit_quirk unit_quirk; }; /* 1/2^hw_unit Joule */ static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; static struct rapl_pmus *rapl_pmus; static cpumask_t rapl_cpu_mask; static unsigned int rapl_cntr_mask; static u64 rapl_timer_ms; static struct perf_msr *rapl_msrs; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { unsigned int dieid = topology_logical_die_id(cpu); /* * The unsigned check also catches the '-1' return value for non * existent mappings in the topology map. */ return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; rdmsrl(event->hw.event_base, raw); return raw; } static inline u64 rapl_scale(u64 v, int cfg) { if (cfg > NR_RAPL_DOMAINS) { pr_warn("Invalid domain %d, failed to scale data\n", cfg); return v; } /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ return v << (32 - rapl_hw_unit[cfg - 1]); } static u64 rapl_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; u64 prev_raw_count, new_raw_count; s64 delta, sdelta; int shift = RAPL_CNTR_WIDTH; again: prev_raw_count = local64_read(&hwc->prev_count); rdmsrl(event->hw.event_base, new_raw_count); if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) { cpu_relax(); goto again; } /* * Now we have the new raw value and have updated the prev * timestamp already. We can now calculate the elapsed delta * (event-)time and add that to the generic event. * * Careful, not all hw sign-extends above the physical width * of the count. */ delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; sdelta = rapl_scale(delta, event->hw.config); local64_add(sdelta, &event->count); return new_raw_count; } static void rapl_start_hrtimer(struct rapl_pmu *pmu) { hrtimer_start(&pmu->hrtimer, pmu->timer_interval, HRTIMER_MODE_REL_PINNED); } static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; if (!pmu->n_active) return HRTIMER_NORESTART; raw_spin_lock_irqsave(&pmu->lock, flags); list_for_each_entry(event, &pmu->active_list, active_entry) rapl_event_update(event); raw_spin_unlock_irqrestore(&pmu->lock, flags); hrtimer_forward_now(hrtimer, pmu->timer_interval); return HRTIMER_RESTART; } static void rapl_hrtimer_init(struct rapl_pmu *pmu) { struct hrtimer *hr = &pmu->hrtimer; hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hr->function = rapl_hrtimer_handle; } static void __rapl_pmu_event_start(struct rapl_pmu *pmu, struct perf_event *event) { if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) return; event->hw.state = 0; list_add_tail(&event->active_entry, &pmu->active_list); local64_set(&event->hw.prev_count, rapl_read_counter(event)); pmu->n_active++; if (pmu->n_active == 1) rapl_start_hrtimer(pmu); } static void rapl_pmu_event_start(struct perf_event *event, int mode) { struct rapl_pmu *pmu = event->pmu_private; unsigned long flags; raw_spin_lock_irqsave(&pmu->lock, flags); __rapl_pmu_event_start(pmu, event); raw_spin_unlock_irqrestore(&pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; raw_spin_lock_irqsave(&pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { WARN_ON_ONCE(pmu->n_active <= 0); pmu->n_active--; if (pmu->n_active == 0) hrtimer_cancel(&pmu->hrtimer); list_del(&event->active_entry); WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } /* check if update of sw counter is necessary */ if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { /* * Drain the remaining delta count out of a event * that we are disabling: */ rapl_event_update(event); hwc->state |= PERF_HES_UPTODATE; } raw_spin_unlock_irqrestore(&pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; raw_spin_lock_irqsave(&pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) __rapl_pmu_event_start(pmu, event); raw_spin_unlock_irqrestore(&pmu->lock, flags); return 0; } static void rapl_pmu_event_del(struct perf_event *event, int flags) { rapl_pmu_event_stop(event, PERF_EF_UPDATE); } static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; int bit, ret = 0; struct rapl_pmu *pmu; /* only look at RAPL events */ if (event->attr.type != rapl_pmus->pmu.type) return -ENOENT; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) return -EINVAL; if (event->cpu < 0) return -EINVAL; event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; if (!cfg || cfg >= NR_RAPL_DOMAINS + 1) return -EINVAL; cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1); bit = cfg - 1; /* check event supported */ if (!(rapl_cntr_mask & (1 << bit))) return -EINVAL; /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; /* must be done before validate_group */ pmu = cpu_to_rapl_pmu(event->cpu); if (!pmu) return -EINVAL; event->cpu = pmu->cpu; event->pmu_private = pmu; event->hw.event_base = rapl_msrs[bit].msr; event->hw.config = cfg; event->hw.idx = bit; return ret; } static void rapl_pmu_event_read(struct perf_event *event) { rapl_event_update(event); } static ssize_t rapl_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask); } static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL); static struct attribute *rapl_pmu_attrs[] = { &dev_attr_cpumask.attr, NULL, }; static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR */ RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); /* * There are no default events, but we need to create * "events" group (with empty attrs) before updating * it with detected events. */ static struct attribute *attrs_empty[] = { NULL, }; static struct attribute_group rapl_pmu_events_group = { .name = "events", .attrs = attrs_empty, }; PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, }; static struct attribute_group rapl_pmu_format_group = { .name = "format", .attrs = rapl_formats_attr, }; static const struct attribute_group *rapl_attr_groups[] = { &rapl_pmu_attr_group, &rapl_pmu_format_group, &rapl_pmu_events_group, NULL, }; static struct attribute *rapl_events_cores[] = { EVENT_PTR(rapl_cores), EVENT_PTR(rapl_cores_unit), EVENT_PTR(rapl_cores_scale), NULL, }; static umode_t rapl_not_visible(struct kobject *kobj, struct attribute *attr, int i) { return 0; } static struct attribute_group rapl_events_cores_group = { .name = "events", .attrs = rapl_events_cores, .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_pkg[] = { EVENT_PTR(rapl_pkg), EVENT_PTR(rapl_pkg_unit), EVENT_PTR(rapl_pkg_scale), NULL, }; static struct attribute_group rapl_events_pkg_group = { .name = "events", .attrs = rapl_events_pkg, .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_ram[] = { EVENT_PTR(rapl_ram), EVENT_PTR(rapl_ram_unit), EVENT_PTR(rapl_ram_scale), NULL, }; static struct attribute_group rapl_events_ram_group = { .name = "events", .attrs = rapl_events_ram, .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_gpu[] = { EVENT_PTR(rapl_gpu), EVENT_PTR(rapl_gpu_unit), EVENT_PTR(rapl_gpu_scale), NULL, }; static struct attribute_group rapl_events_gpu_group = { .name = "events", .attrs = rapl_events_gpu, .is_visible = rapl_not_visible, }; static struct attribute *rapl_events_psys[] = { EVENT_PTR(rapl_psys), EVENT_PTR(rapl_psys_unit), EVENT_PTR(rapl_psys_scale), NULL, }; static struct attribute_group rapl_events_psys_group = { .name = "events", .attrs = rapl_events_psys, .is_visible = rapl_not_visible, }; static bool test_msr(int idx, void *data) { return test_bit(idx, (unsigned long *) data); } static struct perf_msr intel_rapl_msrs[] = { [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr }, [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr }, [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr }, [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr }, [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr }, }; /* * Force to PERF_RAPL_MAX size due to: * - perf_msr_probe(PERF_RAPL_MAX) * - want to use same event codes across both architectures */ static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = { [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr }, }; static int rapl_cpu_offline(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; /* Check if exiting cpu is used for collecting rapl events */ if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask)) return 0; pmu->cpu = -1; /* Find a new cpu to collect rapl events */ target = cpumask_any_but(topology_die_cpumask(cpu), cpu); /* Migrate rapl events to the new target */ if (target < nr_cpu_ids) { cpumask_set_cpu(target, &rapl_cpu_mask); pmu->cpu = target; perf_pmu_migrate_context(pmu->pmu, cpu, target); } return 0; } static int rapl_cpu_online(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; if (!pmu) { pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -ENOMEM; raw_spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); pmu->pmu = &rapl_pmus->pmu; pmu->timer_interval = ms_to_ktime(rapl_timer_ms); rapl_hrtimer_init(pmu); rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu; } /* * Check if there is an online cpu in the package which collects rapl * events already. */ target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu)); if (target < nr_cpu_ids) return 0; cpumask_set_cpu(cpu, &rapl_cpu_mask); pmu->cpu = cpu; return 0; } static int rapl_check_hw_unit(struct rapl_model *rm) { u64 msr_rapl_power_unit_bits; int i; /* protect rdmsrl() to handle virtualization */ if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits)) return -1; for (i = 0; i < NR_RAPL_DOMAINS; i++) rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; switch (rm->unit_quirk) { /* * DRAM domain on HSW server and KNL has fixed energy unit which can be * different than the unit from power unit MSR. See * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 * of 2. Datasheet, September 2014, Reference Number: 330784-001 " */ case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_hw_unit[PERF_RAPL_RAM] = 16; break; /* * SPR shares the same DRAM domain energy unit as HSW, plus it * also has a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: rapl_hw_unit[PERF_RAPL_RAM] = 16; rapl_hw_unit[PERF_RAPL_PSYS] = 0; break; default: break; } /* * Calculate the timer rate: * Use reference of 200W for scaling the timeout to avoid counter * overflows. 200W = 200 Joules/sec * Divide interval by 2 to avoid lockstep (2 * 100) * if hw unit is 32, then we use 2 ms 1/200/2 */ rapl_timer_ms = 2; if (rapl_hw_unit[0] < 32) { rapl_timer_ms = (1000 / (2 * 100)); rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1)); } return 0; } static void __init rapl_advertise(void) { int i; pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", hweight32(rapl_cntr_mask), rapl_timer_ms); for (i = 0; i < NR_RAPL_DOMAINS; i++) { if (rapl_cntr_mask & (1 << i)) { pr_info("hw unit of domain %s 2^-%d Joules\n", rapl_domain_names[i], rapl_hw_unit[i]); } } } static void cleanup_rapl_pmus(void) { int i; for (i = 0; i < rapl_pmus->maxdie; i++) kfree(rapl_pmus->pmus[i]); kfree(rapl_pmus); } static const struct attribute_group *rapl_attr_update[] = { &rapl_events_cores_group, &rapl_events_pkg_group, &rapl_events_ram_group, &rapl_events_gpu_group, &rapl_events_psys_group, NULL, }; static int __init init_rapl_pmus(void) { int maxdie = topology_max_packages() * topology_max_die_per_package(); size_t size; size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *); rapl_pmus = kzalloc(size, GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; rapl_pmus->maxdie = maxdie; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; rapl_pmus->pmu.event_init = rapl_pmu_event_init; rapl_pmus->pmu.add = rapl_pmu_event_add; rapl_pmus->pmu.del = rapl_pmu_event_del; rapl_pmus->pmu.start = rapl_pmu_event_start; rapl_pmus->pmu.stop = rapl_pmu_event_stop; rapl_pmus->pmu.read = rapl_pmu_event_read; rapl_pmus->pmu.module = THIS_MODULE; rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; return 0; } static struct rapl_model model_snb = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_snbep = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsw = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsx = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_knl = { .events = BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_skl = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1) | BIT(PERF_RAPL_PSYS), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_spr = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PSYS), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_amd_fam17h = { .events = BIT(PERF_RAPL_PKG), .msr_power_unit = MSR_AMD_RAPL_POWER_UNIT, .rapl_msrs = amd_rapl_msrs, }; static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE, &model_snb), X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X, &model_snbep), X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE, &model_snb), X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X, &model_snbep), X86_MATCH_INTEL_FAM6_MODEL(HASWELL, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &model_knl), X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &model_knl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS, &model_hsw), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h), X86_MATCH_VENDOR_FAM(HYGON, 0x18, &model_amd_fam17h), X86_MATCH_VENDOR_FAM(AMD, 0x19, &model_amd_fam17h), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); static int __init rapl_pmu_init(void) { const struct x86_cpu_id *id; struct rapl_model *rm; int ret; id = x86_match_cpu(rapl_model_match); if (!id) return -ENODEV; rm = (struct rapl_model *) id->driver_data; rapl_msrs = rm->rapl_msrs; rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX, false, (void *) &rm->events); ret = rapl_check_hw_unit(rm); if (ret) return ret; ret = init_rapl_pmus(); if (ret) return ret; /* * Install callbacks. Core will call them for each online cpu. */ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) goto out; ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); if (ret) goto out1; rapl_advertise(); return 0; out1: cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(); return ret; } module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE); perf_pmu_unregister(&rapl_pmus->pmu); cleanup_rapl_pmus(); } module_exit(intel_rapl_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> #include "internal.h" /* * /proc/thread_self: */ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; /* * Not currently supported. Once we can inherit all of struct pid, * we can allow this. */ if (current->flags & PF_IO_WORKER) return ERR_PTR(-EOPNOTSUPP); if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%u/task/%u", tgid, pid); set_delayed_call(done, kfree_link, name); return name; } static const struct inode_operations proc_thread_self_inode_operations = { .get_link = proc_thread_self_get_link, }; static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *thread_self; int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); if (thread_self) { struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); ret = 0; } else { dput(thread_self); } } inode_unlock(root_inode); if (ret) pr_err("proc_fill_super: can't allocate /proc/thread-self\n"); else fs_info->proc_thread_self = thread_self; return ret; } void __init proc_thread_self_init(void) { proc_alloc_inum(&thread_self_inum); } |
| 59 1083 59 1120 3 3 3 3 3 1083 2224 2222 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel thread helper functions. * Copyright (C) 2004 IBM Corporation, Rusty Russell. * Copyright (C) 2009 Red Hat, Inc. * * Creation is done via kthreadd, so that we get a clean environment * even if we're invoked from userspace (think modprobe, hotplug cpu, * etc.). */ #include <uapi/linux/sched/types.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/kthread.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/unistd.h> #include <linux/file.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/numa.h> #include <linux/sched/isolation.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ int (*threadfn)(void *data); void *data; int node; /* Result passed back to kthread_create() from kthreadd. */ struct task_struct *result; struct completion *done; struct list_head list; }; struct kthread { unsigned long flags; unsigned int cpu; int (*threadfn)(void *); void *data; mm_segment_t oldfs; struct completion parked; struct completion exited; #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif }; enum KTHREAD_BITS { KTHREAD_IS_PER_CPU = 0, KTHREAD_SHOULD_STOP, KTHREAD_SHOULD_PARK, }; static inline void set_kthread_struct(void *kthread) { /* * We abuse ->set_child_tid to avoid the new member and because it * can't be wrongly copied by copy_process(). We also rely on fact * that the caller can't exec, so PF_KTHREAD can't be cleared. */ current->set_child_tid = (__force void __user *)kthread; } static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); return (__force void *)k->set_child_tid; } /* * Variant of to_kthread() that doesn't assume @p is a kthread. * * Per construction; when: * * (p->flags & PF_KTHREAD) && p->set_child_tid * * the task is both a kthread and struct kthread is persistent. However * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and * begin_new_exec()). */ static inline struct kthread *__to_kthread(struct task_struct *p) { void *kthread = (__force void *)p->set_child_tid; if (kthread && !(p->flags & PF_KTHREAD)) kthread = NULL; return kthread; } void free_kthread_struct(struct task_struct *k) { struct kthread *kthread; /* * Can be NULL if this kthread was created by kernel_thread() * or if kmalloc() in kthread() failed. */ kthread = to_kthread(k); #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread && kthread->blkcg_css); #endif kfree(kthread); } /** * kthread_should_stop - should this kthread return now? * * When someone calls kthread_stop() on your kthread, it will be woken * and this will return true. You should then return, and your return * value will be passed through to kthread_stop(). */ bool kthread_should_stop(void) { return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); } EXPORT_SYMBOL(kthread_should_stop); bool __kthread_should_park(struct task_struct *k) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags); } EXPORT_SYMBOL_GPL(__kthread_should_park); /** * kthread_should_park - should this kthread park now? * * When someone calls kthread_park() on your kthread, it will be woken * and this will return true. You should then do the necessary * cleanup and call kthread_parkme() * * Similar to kthread_should_stop(), but this keeps the thread alive * and in a park position. kthread_unpark() "restarts" the thread and * calls the thread function again. */ bool kthread_should_park(void) { return __kthread_should_park(current); } EXPORT_SYMBOL_GPL(kthread_should_park); /** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen * * kthread_should_stop() for freezable kthreads, which will enter * refrigerator if necessary. This function is safe from kthread_stop() / * freezer deadlock and freezable kthreads should use this function instead * of calling try_to_freeze() directly. */ bool kthread_freezable_should_stop(bool *was_frozen) { bool frozen = false; might_sleep(); if (unlikely(freezing(current))) frozen = __refrigerator(true); if (was_frozen) *was_frozen = frozen; return kthread_should_stop(); } EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); /** * kthread_func - return the function specified on kthread creation * @task: kthread task in question * * Returns NULL if the task is not a kthread. */ void *kthread_func(struct task_struct *task) { struct kthread *kthread = __to_kthread(task); if (kthread) return kthread->threadfn; return NULL; } EXPORT_SYMBOL_GPL(kthread_func); /** * kthread_data - return data value specified on kthread creation * @task: kthread task in question * * Return the data value specified when kthread @task was created. * The caller is responsible for ensuring the validity of @task when * calling this function. */ void *kthread_data(struct task_struct *task) { return to_kthread(task)->data; } EXPORT_SYMBOL_GPL(kthread_data); /** * kthread_probe_data - speculative version of kthread_data() * @task: possible kthread task in question * * @task could be a kthread task. Return the data value specified when it * was created if accessible. If @task isn't a kthread task or its data is * inaccessible for any reason, %NULL is returned. This function requires * that @task itself is safe to dereference. */ void *kthread_probe_data(struct task_struct *task) { struct kthread *kthread = __to_kthread(task); void *data = NULL; if (kthread) copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); return data; } static void __kthread_parkme(struct kthread *self) { for (;;) { /* * TASK_PARKED is a special state; we must serialize against * possible pending wakeups to avoid store-store collisions on * task->state. * * Such a collision might possibly result in the task state * changin from TASK_PARKED and us failing the * wait_task_inactive() in kthread_park(). */ set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; /* * Thread is going to call schedule(), do not preempt it, * or the caller of kthread_park() may spend more time in * wait_task_inactive(). */ preempt_disable(); complete(&self->parked); schedule_preempt_disabled(); preempt_enable(); } __set_current_state(TASK_RUNNING); } void kthread_parkme(void) { __kthread_parkme(to_kthread(current)); } EXPORT_SYMBOL_GPL(kthread_parkme); static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; void *data = create->data; struct completion *done; struct kthread *self; int ret; self = kzalloc(sizeof(*self), GFP_KERNEL); set_kthread_struct(self); /* If user was SIGKILLed, I release the structure. */ done = xchg(&create->done, NULL); if (!done) { kfree(create); do_exit(-EINTR); } if (!self) { create->result = ERR_PTR(-ENOMEM); complete(done); do_exit(-ENOMEM); } self->threadfn = threadfn; self->data = data; init_completion(&self->exited); init_completion(&self->parked); current->vfork_done = &self->exited; /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; /* * Thread is going to call schedule(), do not preempt it, * or the creator may spend more time in wait_task_inactive(). */ preempt_disable(); complete(done); schedule_preempt_disabled(); preempt_enable(); ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } do_exit(ret); } /* called from do_fork() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA if (tsk == kthreadd_task) return tsk->pref_node_fork; #endif return NUMA_NO_NODE; } static void create_kthread(struct kthread_create_info *create) { int pid; #ifdef CONFIG_NUMA current->pref_node_fork = create->node; #endif /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { /* If user was SIGKILLed, I release the structure. */ struct completion *done = xchg(&create->done, NULL); if (!done) { kfree(create); return; } create->result = ERR_PTR(pid); complete(done); } } static __printf(4, 0) struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], va_list args) { DECLARE_COMPLETION_ONSTACK(done); struct task_struct *task; struct kthread_create_info *create = kmalloc(sizeof(*create), GFP_KERNEL); if (!create) return ERR_PTR(-ENOMEM); create->threadfn = threadfn; create->data = data; create->node = node; create->done = &done; spin_lock(&kthread_create_lock); list_add_tail(&create->list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); /* * Wait for completion in killable state, for I might be chosen by * the OOM killer while kthreadd is trying to allocate memory for * new kernel thread. */ if (unlikely(wait_for_completion_killable(&done))) { /* * If I was SIGKILLed before kthreadd (or new kernel thread) * calls complete(), leave the cleanup of this structure to * that thread. */ if (xchg(&create->done, NULL)) return ERR_PTR(-EINTR); /* * kthreadd (or new kernel thread) will call complete() * shortly. */ wait_for_completion(&done); } task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; char name[TASK_COMM_LEN]; /* * task is already visible to other tasks, so updating * COMM must be protected. */ vsnprintf(name, sizeof(name), namefmt, args); set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. */ sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); set_cpus_allowed_ptr(task, housekeeping_cpumask(HK_FLAG_KTHREAD)); } kfree(create); return task; } /** * kthread_create_on_node - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @node: task and thread structures for the thread are allocated on this node * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(). The new thread has SCHED_NORMAL policy and * is affine to all CPUs. * * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], ...) { struct task_struct *task; va_list args; va_start(args, namefmt); task = __kthread_create_on_node(threadfn, data, node, namefmt, args); va_end(args); return task; } EXPORT_SYMBOL(kthread_create_on_node); static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state) { unsigned long flags; if (!wait_task_inactive(p, state)) { WARN_ON(1); return; } /* It's safe because the task is inactive. */ raw_spin_lock_irqsave(&p->pi_lock, flags); do_set_cpus_allowed(p, mask); p->flags |= PF_NO_SETAFFINITY; raw_spin_unlock_irqrestore(&p->pi_lock, flags); } static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state) { __kthread_bind_mask(p, cpumask_of(cpu), state); } void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) { __kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL_GPL(kthread_bind_mask); /** * kthread_bind - bind a just-created kthread to a cpu. * @p: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *p, unsigned int cpu) { __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(kthread_bind); /** * kthread_create_on_cpu - Create a cpu bound kthread * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @cpu: The cpu on which the thread should be bound, * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Description: This helper function creates and names a kernel thread */ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, const char *namefmt) { struct task_struct *p; p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, cpu); if (IS_ERR(p)) return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ to_kthread(p)->cpu = cpu; return p; } void kthread_set_per_cpu(struct task_struct *k, int cpu) { struct kthread *kthread = to_kthread(k); if (!kthread) return; WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); if (cpu < 0) { clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); return; } kthread->cpu = cpu; set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } bool kthread_is_per_cpu(struct task_struct *p) { struct kthread *kthread = __to_kthread(p); if (!kthread) return false; return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return false, wakes it, and * waits for it to return. If the thread is marked percpu then its * bound to the cpu again. */ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_kthread(k); /* * Newly created kthread was parked when the CPU was offline. * The binding was lost and we need to set it again. */ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); /** * kthread_park - park a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return true, wakes it, and * waits for it to return. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will park without * calling threadfn(). * * Returns 0 if the thread is parked, -ENOSYS if the thread exited. * If called by the kthread itself just the park bit is set. */ int kthread_park(struct task_struct *k) { struct kthread *kthread = to_kthread(k); if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) return -EBUSY; set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); /* * Wait for __kthread_parkme() to complete(), this means we * _will_ have TASK_PARKED and are about to call schedule(). */ wait_for_completion(&kthread->parked); /* * Now wait for that schedule() to complete and the task to * get scheduled out. */ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; } EXPORT_SYMBOL_GPL(kthread_park); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * * If threadfn() may call do_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { struct kthread *kthread; int ret; trace_sched_kthread_stop(k); get_task_struct(k); kthread = to_kthread(k); set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); kthread_unpark(k); wake_up_process(k); wait_for_completion(&kthread->exited); ret = k->exit_code; put_task_struct(k); trace_sched_kthread_stop_ret(ret); return ret; } EXPORT_SYMBOL(kthread_stop); int kthreadd(void *unused) { struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; cgroup_init_kthreadd(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (list_empty(&kthread_create_list)) schedule(); __set_current_state(TASK_RUNNING); spin_lock(&kthread_create_lock); while (!list_empty(&kthread_create_list)) { struct kthread_create_info *create; create = list_entry(kthread_create_list.next, struct kthread_create_info, list); list_del_init(&create->list); spin_unlock(&kthread_create_lock); create_kthread(create); spin_lock(&kthread_create_lock); } spin_unlock(&kthread_create_lock); } return 0; } void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) { memset(worker, 0, sizeof(struct kthread_worker)); raw_spin_lock_init(&worker->lock); lockdep_set_class_and_name(&worker->lock, key, name); INIT_LIST_HEAD(&worker->work_list); INIT_LIST_HEAD(&worker->delayed_work_list); } EXPORT_SYMBOL_GPL(__kthread_init_worker); /** * kthread_worker_fn - kthread function to process kthread_worker * @worker_ptr: pointer to initialized kthread_worker * * This function implements the main cycle of kthread worker. It processes * work_list until it is stopped with kthread_stop(). It sleeps when the queue * is empty. * * The works are not allowed to keep any locks, disable preemption or interrupts * when they finish. There is defined a safe point for freezing when one work * finishes and before a new one is started. * * Also the works must not be handled by more than one worker at the same time, * see also kthread_queue_work(). */ int kthread_worker_fn(void *worker_ptr) { struct kthread_worker *worker = worker_ptr; struct kthread_work *work; /* * FIXME: Update the check and remove the assignment when all kthread * worker users are created using kthread_create_worker*() functions. */ WARN_ON(worker->task && worker->task != current); worker->task = current; if (worker->flags & KTW_FREEZABLE) set_freezable(); repeat: set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&worker->lock); worker->task = NULL; raw_spin_unlock_irq(&worker->lock); return 0; } work = NULL; raw_spin_lock_irq(&worker->lock); if (!list_empty(&worker->work_list)) { work = list_first_entry(&worker->work_list, struct kthread_work, node); list_del_init(&work->node); } worker->current_work = work; raw_spin_unlock_irq(&worker->lock); if (work) { __set_current_state(TASK_RUNNING); work->func(work); } else if (!freezing(current)) schedule(); try_to_freeze(); cond_resched(); goto repeat; } EXPORT_SYMBOL_GPL(kthread_worker_fn); static __printf(3, 0) struct kthread_worker * __kthread_create_worker(int cpu, unsigned int flags, const char namefmt[], va_list args) { struct kthread_worker *worker; struct task_struct *task; int node = NUMA_NO_NODE; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) return ERR_PTR(-ENOMEM); kthread_init_worker(worker); if (cpu >= 0) node = cpu_to_node(cpu); task = __kthread_create_on_node(kthread_worker_fn, worker, node, namefmt, args); if (IS_ERR(task)) goto fail_task; if (cpu >= 0) kthread_bind(task, cpu); worker->flags = flags; worker->task = task; wake_up_process(task); return worker; fail_task: kfree(worker); return ERR_CAST(task); } /** * kthread_create_worker - create a kthread worker * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the kthread worker (task). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the worker was SIGKILLed. */ struct kthread_worker * kthread_create_worker(unsigned int flags, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); worker = __kthread_create_worker(-1, flags, namefmt, args); va_end(args); return worker; } EXPORT_SYMBOL(kthread_create_worker); /** * kthread_create_worker_on_cpu - create a kthread worker and bind it * to a given CPU and the associated NUMA node. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the kthread worker (task). * * Use a valid CPU number if you want to bind the kthread worker * to the given CPU and the associated NUMA node. * * A good practice is to add the cpu number also into the worker name. * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the worker was SIGKILLed. */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); worker = __kthread_create_worker(cpu, flags, namefmt, args); va_end(args); return worker; } EXPORT_SYMBOL(kthread_create_worker_on_cpu); /* * Returns true when the work could not be queued at the moment. * It happens when it is already pending in a worker list * or when it is being cancelled. */ static inline bool queuing_blocked(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); return !list_empty(&work->node) || work->canceling; } static void kthread_insert_work_sanity_check(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); WARN_ON_ONCE(!list_empty(&work->node)); /* Do not use a work with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker && work->worker != worker); } /* insert @work before @pos in @worker */ static void kthread_insert_work(struct kthread_worker *worker, struct kthread_work *work, struct list_head *pos) { kthread_insert_work_sanity_check(worker, work); list_add_tail(&work->node, pos); work->worker = worker; if (!worker->current_work && likely(worker->task)) wake_up_process(worker->task); } /** * kthread_queue_work - queue a kthread_work * @worker: target kthread_worker * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task * must have been created with kthread_worker_create(). Returns %true * if @work was successfully queued, %false if it was already pending. * * Reinitialize the work if it needs to be used by another worker. * For example, when the worker was stopped and started again. */ bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work) { bool ret = false; unsigned long flags; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { kthread_insert_work(worker, work, &worker->work_list); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_work); /** * kthread_delayed_work_timer_fn - callback that queues the associated kthread * delayed work when the timer expires. * @t: pointer to the expired timer * * The format of the function is defined by struct timer_list. * It should have been called from irqsafe timer with irq already off. */ void kthread_delayed_work_timer_fn(struct timer_list *t) { struct kthread_delayed_work *dwork = from_timer(dwork, t, timer); struct kthread_work *work = &dwork->work; struct kthread_worker *worker = work->worker; unsigned long flags; /* * This might happen when a pending work is reinitialized. * It means that it is used a wrong way. */ if (WARN_ON_ONCE(!worker)) return; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); if (!work->canceling) kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); static void __kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; /* * With CFI, timer->function can point to a jump table entry in a module, * which fails the comparison. Disable the warning if CFI and modules are * both enabled. */ if (!IS_ENABLED(CONFIG_CFI_CLANG) || !IS_ENABLED(CONFIG_MODULES)) WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { kthread_insert_work(worker, work, &worker->work_list); return; } /* Be paranoid and try to detect possible races already now. */ kthread_insert_work_sanity_check(worker, work); list_add(&work->node, &worker->delayed_work_list); work->worker = worker; timer->expires = jiffies + delay; add_timer(timer); } /** * kthread_queue_delayed_work - queue the associated kthread work * after a delay. * @worker: target kthread_worker * @dwork: kthread_delayed_work to queue * @delay: number of jiffies to wait before queuing * * If the work has not been pending it starts a timer that will queue * the work after the given @delay. If @delay is zero, it queues the * work immediately. * * Return: %false if the @work has already been pending. It means that * either the timer was running or the work was queued. It returns %true * otherwise. */ bool kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; bool ret = false; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { __kthread_queue_delayed_work(worker, dwork, delay); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); struct kthread_flush_work { struct kthread_work work; struct completion done; }; static void kthread_flush_work_fn(struct kthread_work *work) { struct kthread_flush_work *fwork = container_of(work, struct kthread_flush_work, work); complete(&fwork->done); } /** * kthread_flush_work - flush a kthread_work * @work: work to flush * * If @work is queued or executing, wait for it to finish execution. */ void kthread_flush_work(struct kthread_work *work) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; struct kthread_worker *worker; bool noop = false; worker = work->worker; if (!worker) return; raw_spin_lock_irq(&worker->lock); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (!list_empty(&work->node)) kthread_insert_work(worker, &fwork.work, work->node.next); else if (worker->current_work == work) kthread_insert_work(worker, &fwork.work, worker->work_list.next); else noop = true; raw_spin_unlock_irq(&worker->lock); if (!noop) wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_work); /* * Make sure that the timer is neither set nor running and could * not manipulate the work list_head any longer. * * The function is called under worker->lock. The lock is temporary * released but the timer can't be set again in the meantime. */ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, unsigned long *flags) { struct kthread_delayed_work *dwork = container_of(work, struct kthread_delayed_work, work); struct kthread_worker *worker = work->worker; /* * del_timer_sync() must be called to make sure that the timer * callback is not running. The lock must be temporary released * to avoid a deadlock with the callback. In the meantime, * any queuing is blocked by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, *flags); del_timer_sync(&dwork->timer); raw_spin_lock_irqsave(&worker->lock, *flags); work->canceling--; } /* * This function removes the work from the worker queue. * * It is called under worker->lock. The caller must make sure that * the timer used by delayed work is not running, e.g. by calling * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. * * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ static bool __kthread_cancel_work(struct kthread_work *work) { /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. */ if (!list_empty(&work->node)) { list_del_init(&work->node); return true; } return false; } /** * kthread_mod_delayed_work - modify delay of or queue a kthread delayed work * @worker: kthread worker to use * @dwork: kthread delayed work to queue * @delay: number of jiffies to wait before queuing * * If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is zero, * @work is guaranteed to be queued immediately. * * Return: %false if @dwork was idle and queued, %true otherwise. * * A special case is when the work is being canceled in parallel. * It might be caused either by the real kthread_cancel_delayed_work_sync() * or yet another kthread_mod_delayed_work() call. We let the other command * win and return %true here. The return value can be used for reference * counting and the number of queued works stays the same. Anyway, the caller * is supposed to synchronize these operations a reasonable way. * * This function is safe to call from any context including IRQ handler. * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() * for details. */ bool kthread_mod_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; int ret; raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ if (!work->worker) { ret = false; goto fast_queue; } /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); /* * Temporary cancel the work but do not fight with another command * that is canceling the work as well. * * It is a bit tricky because of possible races with another * mod_delayed_work() and cancel_delayed_work() callers. * * The timer must be canceled first because worker->lock is released * when doing so. But the work can be removed from the queue (list) * only when it can be queued again so that the return value can * be used for reference counting. */ kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) { /* The number of works in the queue does not change. */ ret = true; goto out; } ret = __kthread_cancel_work(work); /* * Canceling could run in parallel from kthread_cancel_delayed_work_sync * and change work's canceling count as the spinlock is released and regain * in __kthread_cancel_work so we need to check the count again. Otherwise, * we might incorrectly queue the dwork and further cause * cancel_delayed_work_sync thread waiting for flush dwork endlessly. */ if (work->canceling) { ret = false; goto out; } fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) { struct kthread_worker *worker = work->worker; unsigned long flags; int ret = false; if (!worker) goto out; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (is_dwork) kthread_cancel_delayed_work_timer(work, &flags); ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; /* * The work is in progress and we need to wait with the lock released. * In the meantime, block any queuing by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, flags); kthread_flush_work(work); raw_spin_lock_irqsave(&worker->lock, flags); work->canceling--; out_fast: raw_spin_unlock_irqrestore(&worker->lock, flags); out: return ret; } /** * kthread_cancel_work_sync - cancel a kthread work and wait for it to finish * @work: the kthread work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself. On return from this * function, @work is guaranteed to be not pending or executing on any CPU. * * kthread_cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use kthread_cancel_delayed_work_sync() instead. * * The caller must ensure that the worker on which @work was last * queued can't be destroyed before this function returns. * * Return: %true if @work was pending, %false otherwise. */ bool kthread_cancel_work_sync(struct kthread_work *work) { return __kthread_cancel_work_sync(work, false); } EXPORT_SYMBOL_GPL(kthread_cancel_work_sync); /** * kthread_cancel_delayed_work_sync - cancel a kthread delayed work and * wait for it to finish. * @dwork: the kthread delayed work to cancel * * This is kthread_cancel_work_sync() for delayed works. * * Return: %true if @dwork was pending, %false otherwise. */ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork) { return __kthread_cancel_work_sync(&dwork->work, true); } EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync); /** * kthread_flush_worker - flush all current works on a kthread_worker * @worker: worker to flush * * Wait until all currently executing or pending works on @worker are * finished. */ void kthread_flush_worker(struct kthread_worker *worker) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; kthread_queue_work(worker, &fwork.work); wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_worker); /** * kthread_destroy_worker - destroy a kthread worker * @worker: worker to be destroyed * * Flush and destroy @worker. The simple flush is enough because the kthread * worker API is used only in trivial scenarios. There are no multi-step state * machines needed. */ void kthread_destroy_worker(struct kthread_worker *worker) { struct task_struct *task; task = worker->task; if (WARN_ON(!task)) return; kthread_flush_worker(worker); kthread_stop(task); WARN_ON(!list_empty(&worker->work_list)); kfree(worker); } EXPORT_SYMBOL(kthread_destroy_worker); /** * kthread_use_mm - make the calling kthread operate on an address space * @mm: address space to operate on */ void kthread_use_mm(struct mm_struct *mm) { struct mm_struct *active_mm; struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); task_lock(tsk); /* Hold off tlb flush IPIs while switching mm's */ local_irq_disable(); active_mm = tsk->active_mm; if (active_mm != mm) { mmgrab(mm); tsk->active_mm = mm; } tsk->mm = mm; switch_mm_irqs_off(active_mm, mm, tsk); local_irq_enable(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); #endif if (active_mm != mm) mmdrop(active_mm); to_kthread(tsk)->oldfs = force_uaccess_begin(); } EXPORT_SYMBOL_GPL(kthread_use_mm); /** * kthread_unuse_mm - reverse the effect of kthread_use_mm() * @mm: address space to operate on */ void kthread_unuse_mm(struct mm_struct *mm) { struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(!tsk->mm); force_uaccess_end(to_kthread(tsk)->oldfs); task_lock(tsk); sync_mm_rss(mm); local_irq_disable(); tsk->mm = NULL; /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); local_irq_enable(); task_unlock(tsk); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); #ifdef CONFIG_BLK_CGROUP /** * kthread_associate_blkcg - associate blkcg to current kthread * @css: the cgroup info * * Current thread must be a kthread. The thread is running jobs on behalf of * other threads. In some cases, we expect the jobs attach cgroup info of * original threads instead of that of current thread. This function stores * original thread's cgroup info in current kthread context for later * retrieval. */ void kthread_associate_blkcg(struct cgroup_subsys_state *css) { struct kthread *kthread; if (!(current->flags & PF_KTHREAD)) return; kthread = to_kthread(current); if (!kthread) return; if (kthread->blkcg_css) { css_put(kthread->blkcg_css); kthread->blkcg_css = NULL; } if (css) { css_get(css); kthread->blkcg_css = css; } } EXPORT_SYMBOL(kthread_associate_blkcg); /** * kthread_blkcg - get associated blkcg css of current kthread * * Current thread must be a kthread. */ struct cgroup_subsys_state *kthread_blkcg(void) { struct kthread *kthread; if (current->flags & PF_KTHREAD) { kthread = to_kthread(current); if (kthread) return kthread->blkcg_css; } return NULL; } EXPORT_SYMBOL(kthread_blkcg); #endif |
| 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* * This file implement the Wireless Extensions proc API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ /* * The /proc/net/wireless file is a human readable user-space interface * exporting various wireless specific statistics from the wireless devices. * This is the most popular part of the Wireless Extensions ;-) * * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). * The content of the file is basically the content of "struct iw_statistics". */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/wireless.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/iw_handler.h> #include <net/wext.h> static void wireless_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); static struct iw_statistics nullstats = {}; /* show device if it's wireless regardless of current stats */ if (!stats) { #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) stats = &nullstats; #endif #ifdef CONFIG_CFG80211 if (dev->ieee80211_ptr) stats = &nullstats; #endif } if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " "%6d %6d %6d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & IW_QUAL_QUAL_UPDATED ? '.' : ' ', ((__s32) stats->qual.level) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_LEVEL_UPDATED ? '.' : ' ', ((__s32) stats->qual.noise) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_NOISE_UPDATED ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); if (stats != &nullstats) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } /* ---------------------------------------------------------------- */ /* * Print info for /proc/net/wireless (print all entries) */ static int wireless_dev_seq_show(struct seq_file *seq, void *v) { might_sleep(); if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" " face | tus | link level noise | nwid " "crypt frag retry misc | beacon | %d\n", WIRELESS_EXT); else wireless_seq_printf_stats(seq, v); return 0; } static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; rtnl_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; for_each_netdev(net, dev) if (off++ == *pos) return dev; return NULL; } static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); ++*pos; return v == SEQ_START_TOKEN ? first_net_device(net) : next_net_device(v); } static void wireless_dev_seq_stop(struct seq_file *seq, void *v) { rtnl_unlock(); } static const struct seq_operations wireless_seq_ops = { .start = wireless_dev_seq_start, .next = wireless_dev_seq_next, .stop = wireless_dev_seq_stop, .show = wireless_dev_seq_show, }; int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_create_net("wireless", 0444, net->proc_net, &wireless_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } void __net_exit wext_proc_exit(struct net *net) { remove_proc_entry("wireless", net->proc_net); } |
| 898 898 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include <crypto/internal/blake2s.h> #include <crypto/internal/simd.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sizes.h> #include <asm/cpufeature.h> #include <asm/fpu/api.h> #include <asm/processor.h> #include <asm/simd.h> asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state, const u8 *block, const size_t nblocks, const u32 inc); asmlinkage void blake2s_compress_avx512(struct blake2s_state *state, const u8 *block, const size_t nblocks, const u32 inc); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3); static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512); void blake2s_compress(struct blake2s_state *state, const u8 *block, size_t nblocks, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { blake2s_compress_generic(state, block, nblocks, inc); return; } do { const size_t blocks = min_t(size_t, nblocks, SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&blake2s_use_avx512)) blake2s_compress_avx512(state, block, blocks, inc); else blake2s_compress_ssse3(state, block, blocks, inc); kernel_fpu_end(); nblocks -= blocks; block += blocks * BLAKE2S_BLOCK_SIZE; } while (nblocks); } EXPORT_SYMBOL(blake2s_compress); static int __init blake2s_mod_init(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) static_branch_enable(&blake2s_use_ssse3); if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) && boot_cpu_has(X86_FEATURE_AVX512VL) && cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL)) static_branch_enable(&blake2s_use_avx512); return 0; } module_init(blake2s_mod_init); MODULE_LICENSE("GPL v2"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Hash algorithms. * * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_INTERNAL_HASH_H #define _CRYPTO_INTERNAL_HASH_H #include <crypto/algapi.h> #include <crypto/hash.h> struct ahash_request; struct scatterlist; struct crypto_hash_walk { char *data; unsigned int offset; unsigned int alignmask; struct page *pg; unsigned int entrylen; unsigned int total; struct scatterlist *sg; unsigned int flags; }; struct ahash_instance { void (*free)(struct ahash_instance *inst); union { struct { char head[offsetof(struct ahash_alg, halg.base)]; struct crypto_instance base; } s; struct ahash_alg alg; }; }; struct shash_instance { void (*free)(struct shash_instance *inst); union { struct { char head[offsetof(struct shash_alg, base)]; struct crypto_instance base; } s; struct shash_alg alg; }; }; struct crypto_ahash_spawn { struct crypto_spawn base; }; struct crypto_shash_spawn { struct crypto_spawn base; }; int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err); int crypto_hash_walk_first(struct ahash_request *req, struct crypto_hash_walk *walk); static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) { return !(walk->entrylen | walk->total); } int crypto_register_ahash(struct ahash_alg *alg); void crypto_unregister_ahash(struct ahash_alg *alg); int crypto_register_ahashes(struct ahash_alg *algs, int count); void crypto_unregister_ahashes(struct ahash_alg *algs, int count); int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst); bool crypto_shash_alg_has_setkey(struct shash_alg *alg); static inline bool crypto_shash_alg_needs_key(struct shash_alg *alg) { return crypto_shash_alg_has_setkey(alg) && !(alg->base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY); } bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg); int crypto_grab_ahash(struct crypto_ahash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_ahash(struct crypto_ahash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct hash_alg_common *crypto_spawn_ahash_alg( struct crypto_ahash_spawn *spawn) { return __crypto_hash_alg_common(spawn->base.alg); } int crypto_register_shash(struct shash_alg *alg); void crypto_unregister_shash(struct shash_alg *alg); int crypto_register_shashes(struct shash_alg *algs, int count); void crypto_unregister_shashes(struct shash_alg *algs, int count); int shash_register_instance(struct crypto_template *tmpl, struct shash_instance *inst); void shash_free_singlespawn_instance(struct shash_instance *inst); int crypto_grab_shash(struct crypto_shash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); static inline void crypto_drop_shash(struct crypto_shash_spawn *spawn) { crypto_drop_spawn(&spawn->base); } static inline struct shash_alg *crypto_spawn_shash_alg( struct crypto_shash_spawn *spawn) { return __crypto_shash_alg(spawn->base.alg); } int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc); int crypto_init_shash_ops_async(struct crypto_tfm *tfm); static inline void *crypto_ahash_ctx(struct crypto_ahash *tfm) { return crypto_tfm_ctx(crypto_ahash_tfm(tfm)); } static inline struct ahash_alg *__crypto_ahash_alg(struct crypto_alg *alg) { return container_of(__crypto_hash_alg_common(alg), struct ahash_alg, halg); } static inline void crypto_ahash_set_reqsize(struct crypto_ahash *tfm, unsigned int reqsize) { tfm->reqsize = reqsize; } static inline struct crypto_instance *ahash_crypto_instance( struct ahash_instance *inst) { return &inst->s.base; } static inline struct ahash_instance *ahash_instance( struct crypto_instance *inst) { return container_of(inst, struct ahash_instance, s.base); } static inline struct ahash_instance *ahash_alg_instance( struct crypto_ahash *ahash) { return ahash_instance(crypto_tfm_alg_instance(&ahash->base)); } static inline void *ahash_instance_ctx(struct ahash_instance *inst) { return crypto_instance_ctx(ahash_crypto_instance(inst)); } static inline void ahash_request_complete(struct ahash_request *req, int err) { req->base.complete(&req->base, err); } static inline u32 ahash_request_flags(struct ahash_request *req) { return req->base.flags; } static inline struct crypto_ahash *crypto_spawn_ahash( struct crypto_ahash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline int ahash_enqueue_request(struct crypto_queue *queue, struct ahash_request *request) { return crypto_enqueue_request(queue, &request->base); } static inline struct ahash_request *ahash_dequeue_request( struct crypto_queue *queue) { return ahash_request_cast(crypto_dequeue_request(queue)); } static inline void *crypto_shash_ctx(struct crypto_shash *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline struct crypto_instance *shash_crypto_instance( struct shash_instance *inst) { return &inst->s.base; } static inline struct shash_instance *shash_instance( struct crypto_instance *inst) { return container_of(inst, struct shash_instance, s.base); } static inline struct shash_instance *shash_alg_instance( struct crypto_shash *shash) { return shash_instance(crypto_tfm_alg_instance(&shash->base)); } static inline void *shash_instance_ctx(struct shash_instance *inst) { return crypto_instance_ctx(shash_crypto_instance(inst)); } static inline struct crypto_shash *crypto_spawn_shash( struct crypto_shash_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } static inline void *crypto_shash_ctx_aligned(struct crypto_shash *tfm) { return crypto_tfm_ctx_aligned(&tfm->base); } static inline struct crypto_shash *__crypto_shash_cast(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_shash, base); } #endif /* _CRYPTO_INTERNAL_HASH_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Access kernel or user memory without faulting. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/uaccess.h> bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return true; } #ifdef HAVE_GET_KERNEL_NOFAULT #define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __get_kernel_nofault(dst, src, type, err_label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } long copy_from_kernel_nofault(void *dst, const void *src, size_t size) { if (!copy_from_kernel_nofault_allowed(src, size)) return -ERANGE; pagefault_disable(); copy_from_kernel_nofault_loop(dst, src, size, u64, Efault); copy_from_kernel_nofault_loop(dst, src, size, u32, Efault); copy_from_kernel_nofault_loop(dst, src, size, u16, Efault); copy_from_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); #define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __put_kernel_nofault(dst, src, type, err_label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } long copy_to_kernel_nofault(void *dst, const void *src, size_t size) { pagefault_disable(); copy_to_kernel_nofault_loop(dst, src, size, u64, Efault); copy_to_kernel_nofault_loop(dst, src, size, u32, Efault); copy_to_kernel_nofault_loop(dst, src, size, u16, Efault); copy_to_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) { const void *src = unsafe_addr; if (unlikely(count <= 0)) return 0; if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) return -ERANGE; pagefault_disable(); do { __get_kernel_nofault(dst, src, u8, Efault); dst++; src++; } while (dst[-1] && src - unsafe_addr < count); pagefault_enable(); dst[-1] = '\0'; return src - unsafe_addr; Efault: pagefault_enable(); dst[-1] = '\0'; return -EFAULT; } #else /* HAVE_GET_KERNEL_NOFAULT */ /** * copy_from_kernel_nofault(): safely attempt to read from kernel-space * @dst: pointer to the buffer that shall take the data * @src: address to read from * @size: size of the data chunk * * Safely read from kernel address @src to the buffer at @dst. If a kernel * fault happens, handle that and return -EFAULT. If @src is not a valid kernel * address, return -ERANGE. * * We ensure that the copy_from_user is executed in atomic context so that * do_page_fault() doesn't attempt to take mmap_lock. This makes * copy_from_kernel_nofault() suitable for use within regions where the caller * already holds mmap_lock, or other locks which nest inside mmap_lock. */ long copy_from_kernel_nofault(void *dst, const void *src, size_t size) { long ret; mm_segment_t old_fs = get_fs(); if (!copy_from_kernel_nofault_allowed(src, size)) return -ERANGE; set_fs(KERNEL_DS); pagefault_disable(); ret = __copy_from_user_inatomic(dst, (__force const void __user *)src, size); pagefault_enable(); set_fs(old_fs); if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); /** * copy_to_kernel_nofault(): safely attempt to write to a location * @dst: address to write to * @src: pointer to the data that shall be written * @size: size of the data chunk * * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_to_kernel_nofault(void *dst, const void *src, size_t size) { long ret; mm_segment_t old_fs = get_fs(); set_fs(KERNEL_DS); pagefault_disable(); ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); pagefault_enable(); set_fs(old_fs); if (ret) return -EFAULT; return 0; } /** * strncpy_from_kernel_nofault: - Copy a NUL terminated string from unsafe * address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @unsafe_addr: Unsafe address. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from unsafe address to kernel buffer. * * On success, returns the length of the string INCLUDING the trailing NUL. * * If access fails, returns -EFAULT (some data may have been copied and the * trailing NUL added). If @unsafe_addr is not a valid kernel address, return * -ERANGE. * * If @count is smaller than the length of the string, copies @count-1 bytes, * sets the last byte of @dst buffer to NUL and returns @count. */ long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) { mm_segment_t old_fs = get_fs(); const void *src = unsafe_addr; long ret; if (unlikely(count <= 0)) return 0; if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) return -ERANGE; set_fs(KERNEL_DS); pagefault_disable(); do { ret = __get_user(*dst++, (const char __user __force *)src++); } while (dst[-1] && ret == 0 && src - unsafe_addr < count); dst[-1] = '\0'; pagefault_enable(); set_fs(old_fs); return ret ? -EFAULT : src - unsafe_addr; } #endif /* HAVE_GET_KERNEL_NOFAULT */ /** * copy_from_user_nofault(): safely attempt to read from a user-space location * @dst: pointer to the buffer that shall take the data * @src: address to read from. This must be a user address. * @size: size of the data chunk * * Safely read from user address @src to the buffer at @dst. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_from_user_nofault(void *dst, const void __user *src, size_t size) { long ret = -EFAULT; mm_segment_t old_fs = force_uaccess_begin(); if (access_ok(src, size)) { pagefault_disable(); ret = __copy_from_user_inatomic(dst, src, size); pagefault_enable(); } force_uaccess_end(old_fs); if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_from_user_nofault); /** * copy_to_user_nofault(): safely attempt to write to a user-space location * @dst: address to write to * @src: pointer to the data that shall be written * @size: size of the data chunk * * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_to_user_nofault(void __user *dst, const void *src, size_t size) { long ret = -EFAULT; mm_segment_t old_fs = force_uaccess_begin(); if (access_ok(dst, size)) { pagefault_disable(); ret = __copy_to_user_inatomic(dst, src, size); pagefault_enable(); } force_uaccess_end(old_fs); if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_to_user_nofault); /** * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user * address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @unsafe_addr: Unsafe user address. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from unsafe user address to kernel buffer. * * On success, returns the length of the string INCLUDING the trailing NUL. * * If access fails, returns -EFAULT (some data may have been copied * and the trailing NUL added). * * If @count is smaller than the length of the string, copies @count-1 bytes, * sets the last byte of @dst buffer to NUL and returns @count. */ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count) { mm_segment_t old_fs; long ret; if (unlikely(count <= 0)) return 0; old_fs = force_uaccess_begin(); pagefault_disable(); ret = strncpy_from_user(dst, unsafe_addr, count); pagefault_enable(); force_uaccess_end(old_fs); if (ret >= count) { ret = count; dst[ret - 1] = '\0'; } else if (ret > 0) { ret++; } return ret; } /** * strnlen_user_nofault: - Get the size of a user string INCLUDING final NUL. * @unsafe_addr: The string to measure. * @count: Maximum count (including NUL) * * Get the size of a NUL-terminated string in user space without pagefault. * * Returns the size of the string INCLUDING the terminating NUL. * * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * Unlike strnlen_user, this can be used from IRQ handler etc. because * it disables pagefaults. */ long strnlen_user_nofault(const void __user *unsafe_addr, long count) { mm_segment_t old_fs; int ret; old_fs = force_uaccess_begin(); pagefault_disable(); ret = strnlen_user(unsafe_addr, count); pagefault_enable(); force_uaccess_end(old_fs); return ret; } |
| 160 160 160 1081 1082 960 960 1096 1096 1096 160 160 160 1082 1082 960 1096 1096 1096 160 1080 1080 155 156 1087 956 156 156 956 956 956 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net-sysfs.c - network device class and attributes * * Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/sched/isolation.h> #include <linux/nsproxy.h> #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/pm_runtime.h> #include <linux/of.h> #include <linux/of_net.h> #include <linux/cpu.h> #include "net-sysfs.h" #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; static inline int dev_isalive(const struct net_device *dev) { return dev->reg_state <= NETREG_REGISTERED; } /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); read_unlock(&dev_base_lock); return ret; } /* generate a show function for simple field */ #define NETDEVICE_SHOW(field, format_string) \ static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ return sprintf(buf, format_string, dev->field); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ return netdev_show(dev, attr, buf, format_##field); \ } \ #define NETDEVICE_SHOW_RO(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RO(field) #define NETDEVICE_SHOW_RW(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) goto err; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } rtnl_unlock(); err: return ret; } NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); static ssize_t iflink_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); return sprintf(buf, fmt_dec, dev_get_iflink(ndev)); } static DEVICE_ATTR_RO(iflink); static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { return sprintf(buf, fmt_dec, dev->name_assign_type); } static ssize_t name_assign_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; if (ndev->name_assign_type != NET_NAME_UNKNOWN) ret = netdev_show(dev, attr, buf, format_name_assign_type); return ret; } static DEVICE_ATTR_RO(name_assign_type); /* use same locking rules as GIFHWADDR ioctl's */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; read_lock(&dev_base_lock); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); read_unlock(&dev_base_lock); return ret; } static DEVICE_ATTR_RO(address); static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); if (dev_isalive(ndev)) return sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); return -EINVAL; } static DEVICE_ATTR_RO(broadcast); static int change_carrier(struct net_device *dev, unsigned long new_carrier) { if (!netif_running(dev)) return -EINVAL; return dev_change_carrier(dev, (bool)new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_carrier; this helps returning early * without hitting the trylock/restart in netdev_store. */ if (!netdev->netdev_ops->ndo_change_carrier) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_carrier); } static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_carrier_ok(netdev)); return -EINVAL; } static DEVICE_ATTR_RW(carrier); static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev) && netif_device_present(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) ret = sprintf(buf, fmt_dec, cmd.base.speed); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(speed); static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) { const char *duplex; switch (cmd.base.duplex) { case DUPLEX_HALF: duplex = "half"; break; case DUPLEX_FULL: duplex = "full"; break; default: duplex = "unknown"; break; } ret = sprintf(buf, "%s\n", duplex); } } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(duplex); static ssize_t testing_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_testing(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(testing); static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sprintf(buf, fmt_dec, !!netif_dormant(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(dormant); static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", "lowerlayerdown", "testing", "dormant", "up" }; static ssize_t operstate_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; read_lock(&dev_base_lock); operstate = netdev->operstate; if (!netif_running(netdev)) operstate = IF_OPER_DOWN; read_unlock(&dev_base_lock); if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sprintf(buf, "%s\n", operstates[operstate]); } static DEVICE_ATTR_RO(operstate); static ssize_t carrier_changes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_up_count) + atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_changes); static ssize_t carrier_up_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_up_count)); } static DEVICE_ATTR_RO(carrier_up_count); static ssize_t carrier_down_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sprintf(buf, fmt_dec, atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_down_count); /* read-write attributes */ static int change_mtu(struct net_device *dev, unsigned long new_mtu) { return dev_set_mtu(dev, (int)new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_mtu); } NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *dev, unsigned long new_flags) { return dev_change_flags(dev, (unsigned int)new_flags, NULL); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_flags); } NETDEVICE_SHOW_RW(flags, fmt_hex); static ssize_t tx_queue_len_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, dev_change_tx_queue_len); } NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { WRITE_ONCE(dev->gro_flush_timeout, val); return 0; } static ssize_t gro_flush_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { WRITE_ONCE(dev->napi_defer_hard_irqs, val); return 0; } static ssize_t napi_defer_hard_irqs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; ssize_t ret = 0; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = dev_set_alias(netdev, buf, count); if (ret < 0) goto err; ret = len; netdev_state_change(netdev); } err: rtnl_unlock(); return ret; } static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); char tmp[IFALIASZ]; ssize_t ret = 0; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) ret = sprintf(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); static int change_group(struct net_device *dev, unsigned long new_group) { dev_set_group(dev, (int)new_group); return 0; } static ssize_t group_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_group); } NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, 0644, group_show, group_store); static int change_proto_down(struct net_device *dev, unsigned long proto_down) { return dev_change_proto_down(dev, (bool)proto_down); } static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_proto_down; this helps returning * early without hitting the trylock/restart in netdev_store. */ if (!netdev->netdev_ops->ndo_change_proto_down) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The check is also done in dev_get_phys_port_id; this helps returning * early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid; ret = dev_get_phys_port_id(netdev, &ppid); if (!ret) ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_id); static ssize_t phys_port_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->netdev_ops->ndo_get_devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { char name[IFNAMSIZ]; ret = dev_get_phys_port_name(netdev, name, sizeof(name)); if (!ret) ret = sprintf(buf, "%s\n", name); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_name); static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->netdev_ops->ndo_get_devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid = { }; ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_switch_id); static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_name_assign_type.attr, &dev_attr_addr_assign_type.attr, &dev_attr_addr_len.attr, &dev_attr_link_mode.attr, &dev_attr_address.attr, &dev_attr_broadcast.attr, &dev_attr_speed.attr, &dev_attr_duplex.attr, &dev_attr_dormant.attr, &dev_attr_testing.attr, &dev_attr_operstate.attr, &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, &dev_attr_carrier.attr, &dev_attr_mtu.attr, &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ static ssize_t netstat_show(const struct device *d, struct device_attribute *attr, char *buf, unsigned long offset) { struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; WARN_ON(offset > sizeof(struct rtnl_link_stats64) || offset % sizeof(u64) != 0); read_lock(&dev_base_lock); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } read_unlock(&dev_base_lock); return ret; } /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); NETSTAT_ENTRY(rx_bytes); NETSTAT_ENTRY(tx_bytes); NETSTAT_ENTRY(rx_errors); NETSTAT_ENTRY(tx_errors); NETSTAT_ENTRY(rx_dropped); NETSTAT_ENTRY(tx_dropped); NETSTAT_ENTRY(multicast); NETSTAT_ENTRY(collisions); NETSTAT_ENTRY(rx_length_errors); NETSTAT_ENTRY(rx_over_errors); NETSTAT_ENTRY(rx_crc_errors); NETSTAT_ENTRY(rx_frame_errors); NETSTAT_ENTRY(rx_fifo_errors); NETSTAT_ENTRY(rx_missed_errors); NETSTAT_ENTRY(tx_aborted_errors); NETSTAT_ENTRY(tx_carrier_errors); NETSTAT_ENTRY(tx_fifo_errors); NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] __ro_after_init = { &dev_attr_rx_packets.attr, &dev_attr_tx_packets.attr, &dev_attr_rx_bytes.attr, &dev_attr_tx_bytes.attr, &dev_attr_rx_errors.attr, &dev_attr_tx_errors.attr, &dev_attr_rx_dropped.attr, &dev_attr_tx_dropped.attr, &dev_attr_multicast.attr, &dev_attr_collisions.attr, &dev_attr_rx_length_errors.attr, &dev_attr_rx_over_errors.attr, &dev_attr_rx_crc_errors.attr, &dev_attr_rx_frame_errors.attr, &dev_attr_rx_fifo_errors.attr, &dev_attr_rx_missed_errors.attr, &dev_attr_tx_aborted_errors.attr, &dev_attr_tx_carrier_errors.attr, &dev_attr_tx_fifo_errors.attr, &dev_attr_tx_heartbeat_errors.attr, &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, &dev_attr_rx_nohandler.attr, NULL }; static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; #if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) static struct attribute *wireless_attrs[] = { NULL }; static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; #endif #else /* CONFIG_SYSFS */ #define net_class_groups NULL #endif /* CONFIG_SYSFS */ #ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) \ container_of(_attr, struct rx_queue_attribute, attr) #define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops rx_queue_sysfs_ops = { .show = rx_queue_attr_show, .store = rx_queue_attr_store, }; #ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) { struct rps_map *map; cpumask_var_t mask; int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rcu_read_lock(); map = rcu_dereference(queue->rps_map); if (map) for (i = 0; i < map->len; i++) cpumask_set_cpu(map->cpus[i], mask); len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, const char *buf, size_t len) { struct rps_map *old_map, *map; cpumask_var_t mask; int err, cpu, i, hk_flags; static DEFINE_MUTEX(rps_map_mutex); if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } if (!cpumask_empty(mask)) { hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; cpumask_and(mask, mask, housekeeping_cpumask(hk_flags)); if (cpumask_empty(mask)) { free_cpumask_var(mask); return -EINVAL; } } map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) { free_cpumask_var(mask); return -ENOMEM; } i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) map->cpus[i++] = cpu; if (i) { map->len = i; } else { kfree(map); map = NULL; } mutex_lock(&rps_map_mutex); old_map = rcu_dereference_protected(queue->rps_map, mutex_is_locked(&rps_map_mutex)); rcu_assign_pointer(queue->rps_map, map); if (map) static_branch_inc(&rps_needed); if (old_map) static_branch_dec(&rps_needed); mutex_unlock(&rps_map_mutex); if (old_map) kfree_rcu(old_map, rcu); free_cpumask_var(mask); return len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, char *buf) { struct rps_dev_flow_table *flow_table; unsigned long val = 0; rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) val = (unsigned long)flow_table->mask + 1; rcu_read_unlock(); return sprintf(buf, "%lu\n", val); } static void rps_dev_flow_table_release(struct rcu_head *rcu) { struct rps_dev_flow_table *table = container_of(rcu, struct rps_dev_flow_table, rcu); vfree(table); } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, const char *buf, size_t len) { unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; static DEFINE_SPINLOCK(rps_dev_flow_lock); int rc; if (!capable(CAP_NET_ADMIN)) return -EPERM; rc = kstrtoul(buf, 0, &count); if (rc < 0) return rc; if (count) { mask = count - 1; /* mask = roundup_pow_of_two(count) - 1; * without overflows... */ while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), * and on 32bit arches, must check * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) return -EINVAL; #else if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } #endif table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); if (!table) return -ENOMEM; table->mask = mask; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; } else { table = NULL; } spin_lock(&rps_dev_flow_lock); old_table = rcu_dereference_protected(queue->rps_flow_table, lockdep_is_held(&rps_dev_flow_lock)); rcu_assign_pointer(queue->rps_flow_table, table); spin_unlock(&rps_dev_flow_lock); if (old_table) call_rcu(&old_table->rcu, rps_dev_flow_table_release); return len; } static struct rx_queue_attribute rps_cpus_attribute __ro_after_init = __ATTR(rps_cpus, 0644, show_rps_map, store_rps_map); static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute __ro_after_init = __ATTR(rps_flow_cnt, 0644, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); #endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] __ro_after_init = { #ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, #endif NULL }; ATTRIBUTE_GROUPS(rx_queue_default); static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); #ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); kfree_rcu(map, rcu); } flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } #endif memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } static const void *rx_queue_namespace(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->ns_type) ns = dev->class->namespace(dev); return ns; } static void rx_queue_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = rx_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static struct kobj_type rx_queue_ktype __ro_after_init = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_groups = rx_queue_default_groups, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; static int rx_queue_add_kobject(struct net_device *dev, int index) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ dev_hold(queue->dev); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err; } kobject_uevent(kobj, KOBJ_ADD); return error; err: kobject_put(kobj); return error; } static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (dev->sysfs_rx_queue_group) error = sysfs_group_change_owner( kobj, dev->sysfs_rx_queue_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; if (!refcount_read(&dev_net(dev)->count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); kobject_put(kobj); } return error; #else return 0; #endif } static int net_rx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = 0; i < num; i++) { error = rx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif } #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ struct netdev_queue_attribute { struct attribute attr; ssize_t (*show)(struct netdev_queue *queue, char *buf); ssize_t (*store)(struct netdev_queue *queue, const char *buf, size_t len); }; #define to_netdev_queue_attr(_attr) \ container_of(_attr, struct netdev_queue_attribute, attr) #define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) static ssize_t netdev_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { .show = netdev_queue_attr_show, .store = netdev_queue_attr_store, }; static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) { unsigned long trans_timeout; spin_lock_irq(&queue->_xmit_lock); trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; unsigned int i; i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; } static ssize_t traffic_class_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int index; int tc; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); /* If queue belongs to subordinate dev use its TC mapping */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; /* We can report the traffic class one of two ways: * Subordinate device traffic classes are reported with the traffic * class first, and then the subordinate class so for example TC0 on * subordinate device 2 will be reported as "0-2". If the queue * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ return dev->num_tc < 0 ? sprintf(buf, "%d%d\n", tc, dev->num_tc) : sprintf(buf, "%d\n", tc); } #ifdef CONFIG_XPS static ssize_t tx_maxrate_show(struct netdev_queue *queue, char *buf) { return sprintf(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; int err, index = get_netdev_queue_index(queue); u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the trylock/restart below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; if (!rtnl_trylock()) return restart_syscall(); err = -EOPNOTSUPP; if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); rtnl_unlock(); if (!err) { queue->tx_maxrate = rate; return len; } return err; } static struct netdev_queue_attribute queue_tx_maxrate __ro_after_init = __ATTR_RW(tx_maxrate); #endif static struct netdev_queue_attribute queue_trans_timeout __ro_after_init = __ATTR_RO(tx_timeout); static struct netdev_queue_attribute queue_traffic_class __ro_after_init = __ATTR_RO(traffic_class); #ifdef CONFIG_BQL /* * Byte queue limits sysfs structures and functions. */ static ssize_t bql_show(char *buf, unsigned int value) { return sprintf(buf, "%u\n", value); } static ssize_t bql_set(const char *buf, const size_t count, unsigned int *pvalue) { unsigned int value; int err; if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) { value = DQL_MAX_LIMIT; } else { err = kstrtouint(buf, 10, &value); if (err < 0) return err; if (value > DQL_MAX_LIMIT) return -EINVAL; } *pvalue = value; return count; } static ssize_t bql_show_hold_time(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sprintf(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } static ssize_t bql_set_hold_time(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; dql->slack_hold_time = msecs_to_jiffies(value); return len; } static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed); } static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, 0444, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ } \ \ static struct netdev_queue_attribute bql_ ## NAME ## _attribute __ro_after_init \ = __ATTR(NAME, 0644, \ bql_show_ ## NAME, bql_set_ ## NAME) BQL_ATTR(limit, limit); BQL_ATTR(limit_max, max_limit); BQL_ATTR(limit_min, min_limit); static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_attribute.attr, &bql_limit_max_attribute.attr, &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, NULL }; static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) { int cpu, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; struct xps_dev_maps *dev_maps; cpumask_var_t mask; unsigned long index; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; if (num_tc < 0) { ret = -EINVAL; goto err_rtnl_unlock; } /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) { ret = -EINVAL; goto err_rtnl_unlock; } } if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { ret = -ENOMEM; goto err_rtnl_unlock; } rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_cpus_map); if (dev_maps) { for_each_possible_cpu(cpu) { int i, tci = cpu * num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; for (i = map->len; i--;) { if (map->queues[i] == index) { cpumask_set_cpu(cpu, mask); break; } } } } rcu_read_unlock(); rtnl_unlock(); len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; err_rtnl_unlock: rtnl_unlock(); return ret; } static ssize_t xps_cpus_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned long index; cpumask_var_t mask; int err; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } if (!rtnl_trylock()) { free_cpumask_var(mask); return restart_syscall(); } err = netif_set_xps_queue(dev, mask, index); rtnl_unlock(); free_cpumask_var(mask); return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { int j, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; struct xps_dev_maps *dev_maps; unsigned long *mask, index; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); if (dev->num_tc) { num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); if (tc < 0) { ret = -EINVAL; goto err_rtnl_unlock; } } mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); if (!mask) { ret = -ENOMEM; goto err_rtnl_unlock; } rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_rxqs_map); if (!dev_maps) goto out_no_maps; for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues), j < dev->num_rx_queues;) { int i, tci = j * num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; for (i = map->len; i--;) { if (map->queues[i] == index) { set_bit(j, mask); break; } } } out_no_maps: rcu_read_unlock(); rtnl_unlock(); len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; err_rtnl_unlock: rtnl_unlock(); return ret; } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; struct net *net = dev_net(dev); unsigned long *mask, index; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); if (!mask) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, mask, dev->num_rx_queues); if (err) { bitmap_free(mask); return err; } if (!rtnl_trylock()) { bitmap_free(mask); return restart_syscall(); } cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, true); cpus_read_unlock(); rtnl_unlock(); bitmap_free(mask); return err ? : len; } static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init = __ATTR_RW(xps_rxqs); #endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_trans_timeout.attr, &queue_traffic_class.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, &xps_rxqs_attribute.attr, &queue_tx_maxrate.attr, #endif NULL }; ATTRIBUTE_GROUPS(netdev_queue_default); static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } static const void *netdev_queue_namespace(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->ns_type) ns = dev->class->namespace(dev); return ns; } static void netdev_queue_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = netdev_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static struct kobj_type netdev_queue_ktype __ro_after_init = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_groups = netdev_queue_default_groups, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; static int netdev_queue_add_kobject(struct net_device *dev, int index) { struct netdev_queue *queue = dev->_tx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ dev_hold(queue->dev); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); if (error) goto err; #endif kobject_uevent(kobj, KOBJ_ADD); return 0; err: kobject_put(kobj); return error; } static int tx_queue_change_owner(struct net_device *ndev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_queue *queue = ndev->_tx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; #ifdef CONFIG_BQL error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); #endif return error; } #endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; for (i = old_num; i < new_num; i++) { error = netdev_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; if (!refcount_read(&dev_net(dev)->count)) queue->kobj.uevent_suppress = 1; #ifdef CONFIG_BQL sysfs_remove_group(&queue->kobj, &dql_group); #endif kobject_put(&queue->kobj); } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int net_tx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; for (i = 0; i < num; i++) { error = tx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS dev->queues_kset = kset_create_and_add("queues", NULL, &dev->dev.kobj); if (!dev->queues_kset) return -ENOMEM; real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; error = net_rx_queue_update_kobjects(dev, 0, real_rx); if (error) goto error; rxq = real_rx; error = netdev_queue_update_kobjects(dev, 0, real_tx); if (error) goto error; txq = real_tx; return 0; error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif return error; } static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) { int error = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS if (ndev->queues_kset) { error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); if (error) return error; } real_rx = ndev->real_num_rx_queues; #endif real_tx = ndev->real_num_tx_queues; error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); if (error) return error; error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); if (error) return error; return 0; } static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif } static bool net_current_may_mount(void) { struct net *net = current->nsproxy->net_ns; return ns_capable(net->user_ns, CAP_SYS_ADMIN); } static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) refcount_inc(&ns->passive); #endif return ns; } static const void *net_initial_ns(void) { return &init_net; } static const void *net_netlink_ns(struct sock *sk) { return sock_net(sk); } const struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { struct net_device *dev = to_net_dev(d); int retval; /* pass interface to uevent. */ retval = add_uevent_var(env, "INTERFACE=%s", dev->name); if (retval) goto exit; /* pass ifindex to uevent. * ifindex is useful as it won't change (interface name may change) * and is what RtNetlink uses natively. */ retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); exit: return retval; } /* * netdev_release -- destroy and free a dead device. * Called when last reference to device kobject is gone. */ static void netdev_release(struct device *d) { struct net_device *dev = to_net_dev(d); BUG_ON(dev->reg_state != NETREG_RELEASED); /* no need to wait for rcu grace period: * device is dead and about to be freed. */ kfree(rcu_access_pointer(dev->ifalias)); netdev_freemem(dev); } static const void *net_namespace(struct device *d) { struct net_device *dev = to_net_dev(d); return dev_net(dev); } static void net_get_ownership(struct device *d, kuid_t *uid, kgid_t *gid) { struct net_device *dev = to_net_dev(d); const struct net *net = dev_net(dev); net_ns_get_ownership(net, uid, gid); } static struct class net_class __ro_after_init = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, .dev_uevent = netdev_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, .get_ownership = net_get_ownership, }; #ifdef CONFIG_OF_NET static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { if (dev->of_node == data) return 1; } return 0; } /* * of_find_net_device_by_node - lookup the net device for the device node * @np: OF device node * * Looks up the net_device structure corresponding with the device node. * If successful, returns a pointer to the net_device with the embedded * struct device refcount incremented by one, or NULL on failure. The * refcount must be dropped when done with the net_device. */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; dev = class_find_device(&net_class, NULL, np, of_dev_node_match); if (!dev) return NULL; return to_net_dev(dev); } EXPORT_SYMBOL(of_find_net_device_by_node); #endif /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; if (!refcount_read(&dev_net(ndev)->count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); remove_queue_kobjects(ndev); pm_runtime_set_memalloc_noio(dev, false); device_del(dev); } /* Create sysfs entries for network device. */ int netdev_register_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; device_initialize(dev); dev->class = &net_class; dev->platform_data = ndev; dev->groups = groups; dev_set_name(dev, "%s", ndev->name); #ifdef CONFIG_SYSFS /* Allow for a device specific group */ if (*groups) groups++; *groups++ = &netstat_group; #if IS_ENABLED(CONFIG_WIRELESS_EXT) || IS_ENABLED(CONFIG_CFG80211) if (ndev->ieee80211_ptr) *groups++ = &wireless_group; #if IS_ENABLED(CONFIG_WIRELESS_EXT) else if (ndev->wireless_handlers) *groups++ = &wireless_group; #endif #endif #endif /* CONFIG_SYSFS */ error = device_add(dev); if (error) return error; error = register_queue_kobjects(ndev); if (error) { device_del(dev); return error; } pm_runtime_set_memalloc_noio(dev, true); return error; } /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); net_ns_get_ownership(net_new, &new_uid, &new_gid); /* The network namespace was changed but the owning user namespace is * identical so there's no need to change the owner of sysfs entries. */ if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) return 0; error = device_change_owner(dev, new_uid, new_gid); if (error) return error; error = queue_change_owner(ndev, new_uid, new_gid); if (error) return error; return 0; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns) { class_remove_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_remove_file_ns); int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); } |
| 93 339 6 6111 15 18 51 4915 673 612 145 140 874 26 19 2119 1301 2651 3094 193 289 100 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <linux/kernel.h> /* * Simple doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); list->prev = list; } #ifdef CONFIG_DEBUG_LIST extern bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next); extern bool __list_del_entry_valid(struct list_head *entry); #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); entry->prev = entry; smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return (next == head) && (next == head->prev); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && (head->next != entry && head != entry)) return; if (entry == head) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two 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 list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two 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 list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two 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 list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two 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 list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; pos != (head); pos = pos->next) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; pos != (head); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; pos != (head); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ pos != (head); \ pos = n, n = pos->prev) /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ (&pos->member == (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behing - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) #endif |
| 147 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H #include <linux/bug.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/once.h> #include <uapi/linux/random.h> struct notifier_block; void add_device_randomness(const void *buf, unsigned int len); void add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) { add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); } #else static inline void add_latent_entropy(void) { } #endif void get_random_bytes(void *buf, int len); int __must_check get_random_bytes_arch(void *buf, int len); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned int get_random_int(void) { return get_random_u32(); } static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 return get_random_u64(); #else return get_random_u32(); #endif } /* * On 64-bit architectures, protect against non-terminated C string overflows * by zeroing out the first byte of the canary; this leaves 56 bits of entropy. */ #ifdef CONFIG_64BIT # ifdef __LITTLE_ENDIAN # define CANARY_MASK 0xffffffffffffff00UL # else /* big endian, 64 bits: */ # define CANARY_MASK 0x00ffffffffffffffUL # endif #else /* 32 bits: */ # define CANARY_MASK 0xffffffffUL #endif static inline unsigned long get_random_canary(void) { return get_random_long() & CANARY_MASK; } int __init random_init(const char *command_line); bool rng_is_initialized(void); int wait_for_random_bytes(void); int register_random_ready_notifier(struct notifier_block *nb); int unregister_random_ready_notifier(struct notifier_block *nb); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ static inline int get_random_bytes_wait(void *buf, size_t nbytes) { int ret = wait_for_random_bytes(); get_random_bytes(buf, nbytes); return ret; } #define declare_get_random_var_wait(name, ret_type) \ static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ *out = get_random_ ## name(); \ return 0; \ } declare_get_random_var_wait(u32, u32) declare_get_random_var_wait(u64, u32) declare_get_random_var_wait(int, unsigned int) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var /* * This is designed to be standalone for just prandom * users, but for now we include it from <linux/random.h> * for legacy reasons. */ #include <linux/prandom.h> #ifdef CONFIG_ARCH_RANDOM # include <asm/archrandom.h> #else static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; } static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; } static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return false; } static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return false; } #endif /* * Called from the boot CPU during startup; not valid to call once * secondary CPUs are up and preemption is possible. */ #ifndef arch_get_random_seed_long_early static inline bool __init arch_get_random_seed_long_early(unsigned long *v) { WARN_ON(system_state != SYSTEM_BOOTING); return arch_get_random_seed_long(v); } #endif #ifndef arch_get_random_long_early static inline bool __init arch_get_random_long_early(unsigned long *v) { WARN_ON(system_state != SYSTEM_BOOTING); return arch_get_random_long(v); } #endif #ifdef CONFIG_SMP int random_prepare_cpu(unsigned int cpu); int random_online_cpu(unsigned int cpu); #endif #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif /* * Android KABI fixups * Added back the following structure and calls to preserve the ABI for * out-of-tree drivers that were using them. */ struct random_ready_callback { struct list_head list; void (*func)(struct random_ready_callback *rdy); struct module *owner; }; extern int add_random_ready_callback(struct random_ready_callback *rdy); extern void del_random_ready_callback(struct random_ready_callback *rdy); #endif /* _LINUX_RANDOM_H */ |
| 956 956 955 956 956 156 156 156 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 | // SPDX-License-Identifier: GPL-2.0 /* sysfs entries for device PM */ #include <linux/device.h> #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeup.h> #include <linux/atomic.h> #include <linux/jiffies.h> #include "power.h" /* * control - Report/change current runtime PM setting of the device * * Runtime power management of a device can be blocked with the help of * this attribute. All devices have one of the following two values for * the power/control file: * * + "auto\n" to allow the device to be power managed at run time; * + "on\n" to prevent the device from being power managed at run time; * * The default for all devices is "auto", which means that devices may be * subject to automatic power management, depending on their drivers. * Changing this attribute to "on" prevents the driver from power managing * the device at run time. Doing that while the device is suspended causes * it to be woken up. * * wakeup - Report/change current wakeup option for device * * Some devices support "wakeup" events, which are hardware signals * used to activate devices from suspended or low power states. Such * devices have one of three values for the sysfs power/wakeup file: * * + "enabled\n" to issue the events; * + "disabled\n" not to do so; or * + "\n" for temporary or permanent inability to issue wakeup. * * (For example, unconfigured USB devices can't issue wakeups.) * * Familiar examples of devices that can issue wakeup events include * keyboards and mice (both PS2 and USB styles), power buttons, modems, * "Wake-On-LAN" Ethernet links, GPIO lines, and more. Some events * will wake the entire system from a suspend state; others may just * wake up the device (if the system as a whole is already active). * Some wakeup events use normal IRQ lines; other use special out * of band signaling. * * It is the responsibility of device drivers to enable (or disable) * wakeup signaling as part of changing device power states, respecting * the policy choices provided through the driver model. * * Devices may not be able to generate wakeup events from all power * states. Also, the events may be ignored in some configurations; * for example, they might need help from other devices that aren't * active, or which may have wakeup disabled. Some drivers rely on * wakeup events internally (unless they are disabled), keeping * their hardware in low power modes whenever they're unused. This * saves runtime power, without requiring system-wide sleep states. * * async - Report/change current async suspend setting for the device * * Asynchronous suspend and resume of the device during system-wide power * state transitions can be enabled by writing "enabled" to this file. * Analogously, if "disabled" is written to this file, the device will be * suspended and resumed synchronously. * * All devices have one of the following two values for power/async: * * + "enabled\n" to permit the asynchronous suspend/resume of the device; * + "disabled\n" to forbid it; * * NOTE: It generally is unsafe to permit the asynchronous suspend/resume * of a device unless it is certain that all of the PM dependencies of the * device are known to the PM core. However, for some devices this * attribute is set to "enabled" by bus type code or device drivers and in * that cases it should be safe to leave the default value. * * autosuspend_delay_ms - Report/change a device's autosuspend_delay value * * Some drivers don't want to carry out a runtime suspend as soon as a * device becomes idle; they want it always to remain idle for some period * of time before suspending it. This period is the autosuspend_delay * value (expressed in milliseconds) and it can be controlled by the user. * If the value is negative then the device will never be runtime * suspended. * * NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay * value are used only if the driver calls pm_runtime_use_autosuspend(). * * wakeup_count - Report the number of wakeup events related to the device */ const char power_group_name[] = "power"; EXPORT_SYMBOL_GPL(power_group_name); static const char ctrl_auto[] = "auto"; static const char ctrl_on[] = "on"; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", dev->power.runtime_auto ? ctrl_auto : ctrl_on); } static ssize_t control_store(struct device * dev, struct device_attribute *attr, const char * buf, size_t n) { device_lock(dev); if (sysfs_streq(buf, ctrl_auto)) pm_runtime_allow(dev); else if (sysfs_streq(buf, ctrl_on)) pm_runtime_forbid(dev); else n = -EINVAL; device_unlock(dev); return n; } static DEVICE_ATTR_RW(control); static ssize_t runtime_active_time_show(struct device *dev, struct device_attribute *attr, char *buf) { u64 tmp = pm_runtime_active_time(dev); do_div(tmp, NSEC_PER_MSEC); return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_active_time); static ssize_t runtime_suspended_time_show(struct device *dev, struct device_attribute *attr, char *buf) { u64 tmp = pm_runtime_suspended_time(dev); do_div(tmp, NSEC_PER_MSEC); return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_suspended_time); static ssize_t runtime_status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; if (dev->power.runtime_error) { output = "error"; } else if (dev->power.disable_depth) { output = "unsupported"; } else { switch (dev->power.runtime_status) { case RPM_SUSPENDED: output = "suspended"; break; case RPM_SUSPENDING: output = "suspending"; break; case RPM_RESUMING: output = "resuming"; break; case RPM_ACTIVE: output = "active"; break; default: return -EIO; } } return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_status); static ssize_t autosuspend_delay_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { if (!dev->power.use_autosuspend) return -EIO; return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay); } static ssize_t autosuspend_delay_ms_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { long delay; if (!dev->power.use_autosuspend) return -EIO; if (kstrtol(buf, 10, &delay) != 0 || delay != (int) delay) return -EINVAL; device_lock(dev); pm_runtime_set_autosuspend_delay(dev, delay); device_unlock(dev); return n; } static DEVICE_ATTR_RW(autosuspend_delay_ms); static ssize_t pm_qos_resume_latency_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_requested_resume_latency(dev); if (value == 0) return sysfs_emit(buf, "n/a\n"); if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) value = 0; return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_resume_latency_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (!kstrtos32(buf, 0, &value)) { /* * Prevent users from writing negative or "no constraint" values * directly. */ if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) return -EINVAL; if (value == 0) value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } else if (sysfs_streq(buf, "n/a")) { value = 0; } else { return -EINVAL; } ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_resume_latency_us); static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_get_user_latency_tolerance(dev); if (value < 0) return sysfs_emit(buf, "%s\n", "auto"); if (value == PM_QOS_LATENCY_ANY) return sysfs_emit(buf, "%s\n", "any"); return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (kstrtos32(buf, 0, &value) == 0) { /* Users can't write negative values directly */ if (value < 0) return -EINVAL; } else { if (sysfs_streq(buf, "auto")) value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (sysfs_streq(buf, "any")) value = PM_QOS_LATENCY_ANY; else return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_latency_tolerance_us); static ssize_t pm_qos_no_power_off_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) & PM_QOS_FLAG_NO_POWER_OFF)); } static ssize_t pm_qos_no_power_off_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { int ret; if (kstrtoint(buf, 0, &ret)) return -EINVAL; if (ret != 0 && ret != 1) return -EINVAL; ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_NO_POWER_OFF, ret); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_no_power_off); #ifdef CONFIG_PM_SLEEP static const char _enabled[] = "enabled"; static const char _disabled[] = "disabled"; static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", device_can_wakeup(dev) ? (device_may_wakeup(dev) ? _enabled : _disabled) : ""); } static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { if (!device_can_wakeup(dev)) return -EINVAL; if (sysfs_streq(buf, _enabled)) device_set_wakeup_enable(dev, 1); else if (sysfs_streq(buf, _disabled)) device_set_wakeup_enable(dev, 0); else return -EINVAL; return n; } static DEVICE_ATTR_RW(wakeup); static ssize_t wakeup_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->wakeup_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_count); static ssize_t wakeup_active_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->active_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_active_count); static ssize_t wakeup_abort_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->wakeup_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_abort_count); static ssize_t wakeup_expire_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->expire_count; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lu\n", count); } static DEVICE_ATTR_RO(wakeup_expire_count); static ssize_t wakeup_active_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int active; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { active = dev->power.wakeup->active; enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%u\n", active); } static DEVICE_ATTR_RO(wakeup_active); static ssize_t wakeup_total_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->total_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_total_time_ms); static ssize_t wakeup_max_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->max_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_max_time_ms); static ssize_t wakeup_last_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->last_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { if (dev->power.wakeup && dev->power.wakeup->dev) return device_change_owner(dev->power.wakeup->dev, kuid, kgid); return 0; } static DEVICE_ATTR_RO(wakeup_last_time_ms); #ifdef CONFIG_PM_AUTOSLEEP static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->prevent_sleep_time); enabled = true; } spin_unlock_irq(&dev->power.lock); if (!enabled) return sysfs_emit(buf, "\n"); return sysfs_emit(buf, "%lld\n", msec); } static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); #endif /* CONFIG_PM_AUTOSLEEP */ #else /* CONFIG_PM_SLEEP */ static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { return 0; } #endif #ifdef CONFIG_PM_ADVANCED_DEBUG static ssize_t runtime_usage_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count)); } static DEVICE_ATTR_RO(runtime_usage); static ssize_t runtime_active_kids_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", dev->power.ignore_children ? 0 : atomic_read(&dev->power.child_count)); } static DEVICE_ATTR_RO(runtime_active_kids); static ssize_t runtime_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; if (dev->power.disable_depth && !dev->power.runtime_auto) output = "disabled & forbidden"; else if (dev->power.disable_depth) output = "disabled"; else if (!dev->power.runtime_auto) output = "forbidden"; else output = "enabled"; return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_enabled); #ifdef CONFIG_PM_SLEEP static ssize_t async_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", device_async_suspend_enabled(dev) ? _enabled : _disabled); } static ssize_t async_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { if (sysfs_streq(buf, _enabled)) device_enable_async_suspend(dev); else if (sysfs_streq(buf, _disabled)) device_disable_async_suspend(dev); else return -EINVAL; return n; } static DEVICE_ATTR_RW(async); #endif /* CONFIG_PM_SLEEP */ #endif /* CONFIG_PM_ADVANCED_DEBUG */ static struct attribute *power_attrs[] = { #ifdef CONFIG_PM_ADVANCED_DEBUG #ifdef CONFIG_PM_SLEEP &dev_attr_async.attr, #endif &dev_attr_runtime_status.attr, &dev_attr_runtime_usage.attr, &dev_attr_runtime_active_kids.attr, &dev_attr_runtime_enabled.attr, #endif /* CONFIG_PM_ADVANCED_DEBUG */ NULL, }; static const struct attribute_group pm_attr_group = { .name = power_group_name, .attrs = power_attrs, }; static struct attribute *wakeup_attrs[] = { #ifdef CONFIG_PM_SLEEP &dev_attr_wakeup.attr, &dev_attr_wakeup_count.attr, &dev_attr_wakeup_active_count.attr, &dev_attr_wakeup_abort_count.attr, &dev_attr_wakeup_expire_count.attr, &dev_attr_wakeup_active.attr, &dev_attr_wakeup_total_time_ms.attr, &dev_attr_wakeup_max_time_ms.attr, &dev_attr_wakeup_last_time_ms.attr, #ifdef CONFIG_PM_AUTOSLEEP &dev_attr_wakeup_prevent_sleep_time_ms.attr, #endif #endif NULL, }; static const struct attribute_group pm_wakeup_attr_group = { .name = power_group_name, .attrs = wakeup_attrs, }; static struct attribute *runtime_attrs[] = { #ifndef CONFIG_PM_ADVANCED_DEBUG &dev_attr_runtime_status.attr, #endif &dev_attr_control.attr, &dev_attr_runtime_suspended_time.attr, &dev_attr_runtime_active_time.attr, &dev_attr_autosuspend_delay_ms.attr, NULL, }; static const struct attribute_group pm_runtime_attr_group = { .name = power_group_name, .attrs = runtime_attrs, }; static struct attribute *pm_qos_resume_latency_attrs[] = { &dev_attr_pm_qos_resume_latency_us.attr, NULL, }; static const struct attribute_group pm_qos_resume_latency_attr_group = { .name = power_group_name, .attrs = pm_qos_resume_latency_attrs, }; static struct attribute *pm_qos_latency_tolerance_attrs[] = { &dev_attr_pm_qos_latency_tolerance_us.attr, NULL, }; static const struct attribute_group pm_qos_latency_tolerance_attr_group = { .name = power_group_name, .attrs = pm_qos_latency_tolerance_attrs, }; static struct attribute *pm_qos_flags_attrs[] = { &dev_attr_pm_qos_no_power_off.attr, NULL, }; static const struct attribute_group pm_qos_flags_attr_group = { .name = power_group_name, .attrs = pm_qos_flags_attrs, }; int dpm_sysfs_add(struct device *dev) { int rc; /* No need to create PM sysfs if explicitly disabled. */ if (device_pm_not_required(dev)) return 0; rc = sysfs_create_group(&dev->kobj, &pm_attr_group); if (rc) return rc; if (!pm_runtime_has_no_callbacks(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group); if (rc) goto err_out; } if (device_can_wakeup(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); if (rc) goto err_runtime; } if (dev->power.set_latency_tolerance) { rc = sysfs_merge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); if (rc) goto err_wakeup; } rc = pm_wakeup_source_sysfs_add(dev); if (rc) goto err_latency; return 0; err_latency: sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); err_wakeup: sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); err_runtime: sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); err_out: sysfs_remove_group(&dev->kobj, &pm_attr_group); return rc; } int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { int rc; if (device_pm_not_required(dev)) return 0; rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid); if (rc) return rc; if (!pm_runtime_has_no_callbacks(dev)) { rc = sysfs_group_change_owner( &dev->kobj, &pm_runtime_attr_group, kuid, kgid); if (rc) return rc; } if (device_can_wakeup(dev)) { rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group, kuid, kgid); if (rc) return rc; rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid); if (rc) return rc; } if (dev->power.set_latency_tolerance) { rc = sysfs_group_change_owner( &dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid, kgid); if (rc) return rc; } return 0; } int wakeup_sysfs_add(struct device *dev) { int ret = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); if (!ret) kobject_uevent(&dev->kobj, KOBJ_CHANGE); return ret; } void wakeup_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); kobject_uevent(&dev->kobj, KOBJ_CHANGE); } int pm_qos_sysfs_add_resume_latency(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_resume_latency_attr_group); } void pm_qos_sysfs_remove_resume_latency(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_resume_latency_attr_group); } int pm_qos_sysfs_add_flags(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_flags_attr_group); } void pm_qos_sysfs_remove_flags(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group); } int pm_qos_sysfs_add_latency_tolerance(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); } void pm_qos_sysfs_remove_latency_tolerance(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); } void rpm_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); } void dpm_sysfs_remove(struct device *dev) { if (device_pm_not_required(dev)) return; sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); dev_pm_qos_constraints_destroy(dev); rpm_sysfs_remove(dev); sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); sysfs_remove_group(&dev->kobj, &pm_attr_group); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Routines to manage notifier chains for passing status changes to any * interested routines. We need this instead of hard coded call lists so * that modules can poke their nose into the innards. The network devices * needed them so here they are for the rest of you. * * Alan Cox <Alan.Cox@linux.org> */ #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include <linux/errno.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/srcu.h> /* * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. * Blocking notifier chains: Chain callbacks run in process context. * Callouts are allowed to block. * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. * SRCU notifier chains: A variant of blocking notifier chains, with * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, * but blocking_notifier_chain_register() and srcu_notifier_chain_register() * must be called from a process context. Ditto for the corresponding * _unregister() routines. * * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), * and srcu_notifier_chain_unregister() _must not_ be called from within * the call chain. * * SRCU notifier chains are an alternative form of blocking notifier chains. * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for * protection of the chain links. This means there is _very_ low overhead * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very * often but notifier_blocks will seldom be removed. */ struct notifier_block; typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); struct notifier_block { notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; struct notifier_block __rcu *head; }; struct raw_notifier_head { struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_struct srcu; struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ init_rwsem(&(name)->rwsem); \ (name)->head = NULL; \ } while (0) #define RAW_INIT_NOTIFIER_HEAD(name) do { \ (name)->head = NULL; \ } while (0) /* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ .srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ ATOMIC_NOTIFIER_INIT(name) #define BLOCKING_NOTIFIER_HEAD(name) \ struct blocking_notifier_head name = \ BLOCKING_NOTIFIER_INIT(name) #define RAW_NOTIFIER_HEAD(name) \ struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) #else #define _SRCU_NOTIFIER_HEAD(name, mod) \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name) #endif #define SRCU_NOTIFIER_HEAD(name) \ _SRCU_NOTIFIER_HEAD(name, /* not static */) #define SRCU_NOTIFIER_HEAD_STATIC(name) \ _SRCU_NOTIFIER_HEAD(name, static) #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); extern int atomic_notifier_call_chain_robust(struct atomic_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ #define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ #define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK) /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err); return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ static inline int notifier_to_errno(int ret) { ret &= ~NOTIFY_STOP_MASK; return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0; } /* * Declared notifiers so far. I can imagine quite a few more chains * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ /* reboot notifiers are defined in include/linux/reboot.h. */ /* Hibernation and suspend events are defined in include/linux/suspend.h. */ /* Virtual Terminal events are defined in include/linux/vt.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and * KBD_KEYSYM. */ #define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ #define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ #define KBD_UNICODE 0x0003 /* Keyboard unicode */ #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ extern struct blocking_notifier_head reboot_notifier_list; #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ |
| 18 18 18 17 18 18 18 835 2 833 820 4 827 828 828 823 824 824 822 1 824 823 828 819 9 20 20 19 2 2 2 2 3 819 819 1086 1088 819 819 819 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 | // SPDX-License-Identifier: GPL-2.0-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. * * PF_INET protocol family socket 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> * * Changes (see also sock.c) * * piggy, * Karl Knutson : Socket protocol table * A.N.Kuznetsov : Socket death error in accept(). * John Richardson : Fix non blocking error in connect() * so sockets that fail to connect * don't return -EINPROGRESS. * Alan Cox : Asynchronous I/O support * Alan Cox : Keep correct socket pointer on sock * structures * when accept() ed * Alan Cox : Semantics of SO_LINGER aren't state * moved to close when you look carefully. * With this fixed and the accept bug fixed * some RPC stuff seems happier. * Niibe Yutaka : 4.4BSD style write async I/O * Alan Cox, * Tony Gale : Fixed reuse semantics. * Alan Cox : bind() shouldn't abort existing but dead * sockets. Stops FTP netin:.. I hope. * Alan Cox : bind() works correctly for RAW sockets. * Note that FreeBSD at least was broken * in this respect so be careful with * compatibility tests... * Alan Cox : routing cache support * Alan Cox : memzero the socket structure for * compactness. * Matt Day : nonblock connect error handler * Alan Cox : Allow large numbers of pending sockets * (eg for big web sites), but only if * specifically application requested. * Alan Cox : New buffering throughout IP. Used * dumbly. * Alan Cox : New buffering now used smartly. * Alan Cox : BSD rather than common sense * interpretation of listen. * Germano Caronni : Assorted small races. * Alan Cox : sendmsg/recvmsg basic support. * Alan Cox : Only sendmsg/recvmsg now supported. * Alan Cox : Locked down bind (see security list). * Alan Cox : Loosened bind a little. * Mike McLagan : ADD/DEL DLCI Ioctls * Willy Konynenberg : Transparent proxying support. * David S. Miller : New socket lookup architecture. * Some other random speedups. * Cyrus Durgin : Cleaned up file for kmod hacks. * Andi Kleen : Fix inet_stream_connect TCP race. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <net/checksum.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #include <net/l3mdev.h> #include <net/compat.h> #include <trace/events/sock.h> /* The inetsw table contains everything that inet_create needs to * build a new socket. */ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); /* New destruction routine */ void inet_sock_destruct(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); if (sk->sk_rx_skb_cache) { __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive inet socket %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(sk->sk_rx_dst); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET * socket object. Mostly it punts to the subprotocols of IP to do * the work. */ /* * Automatically bind an unbound socket. */ static int inet_autobind(struct sock *sk) { struct inet_sock *inet; /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; } /* * Move a socket into listening state. */ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; int err, tcp_fastopen; lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; old_state = sk->sk_state; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) goto out; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. * Also fastopen backlog may already been set via the option * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk, backlog); if (err) goto out; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } err = 0; out: release_sock(sk); return err; } EXPORT_SYMBOL(inet_listen); /* * Create an inet socket. */ static int inet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-2-proto-132-type-1 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-2-proto-132 * (net-pf-PF_INET-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOBUFS; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; inet->nodefrag = 0; if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; inet->inet_id = 0; sock_init_data(sock, sk); sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; inet->uc_ttl = -1; inet->mc_loop = 1; inet->mc_ttl = 1; inet->mc_all = 1; inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; sk_refcnt_debug_inc(sk); if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); if (err) { sk_common_release(sk); goto out; } } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) { sk_common_release(sk); goto out; } } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) { sk_common_release(sk); goto out; } } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; } /* * The peer socket should always be NULL (or else). When we call this * function we are destroying the object and from then on nobody * should refer to it. */ int inet_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { long timeout; if (!sk->sk_kern_sock) BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); /* If linger is set, we don't return until the close * is complete. Otherwise we return immediately. The * actually closing is done the same either way. * * If the close is due to the process exiting, we never * linger.. */ timeout = 0; if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) timeout = sk->sk_lingertime; sk->sk_prot->close(sk, timeout); sock->sk = NULL; } return 0; } EXPORT_SYMBOL(inet_release); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { return sk->sk_prot->bind(sk, uaddr, addr_len); } if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr); if (err) return err; return __inet_bind(sk, uaddr, addr_len, BIND_WITH_LOCK); } EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; u32 tb_id = RT_TABLE_LOCAL; int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) * only if s_addr is INADDR_ANY. */ err = -EAFNOSUPPORT; if (addr->sin_family != AF_UNSPEC || addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; } tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since * allowing applications to make a non-local bind solves * several problems with systems using dynamic addressing. * (ie. your servers still start up even if your ISDN link * is temporarily down) */ err = -EADDRNOTAVAIL; if (!inet_can_nonlocal_bind(net, inet) && addr->sin_addr.s_addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; snum = ntohs(addr->sin_port); err = -EPERM; if (snum && inet_is_local_unbindable_port(net, snum)) goto out; err = -EACCES; if (snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one * used by hash lookups, and saddr is used for transmit. * * In the BSD API these are the same except where it * would be illegal to use them (multicast/broadcast) in * which case the sending device address is used. */ if (flags & BIND_WITH_LOCK) lock_sock(sk); /* Check these errors (active socket, double bind). */ err = -EINVAL; if (sk->sk_state != TCP_CLOSE || inet->inet_num) goto out_release_sock; inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { if (sk->sk_prot->get_port(sk, snum)) { inet->inet_saddr = inet->inet_rcv_saddr = 0; err = -EADDRINUSE; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; goto out_release_sock; } } } if (inet->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); inet->inet_daddr = 0; inet->inet_dport = 0; sk_dst_reset(sk); err = 0; out_release_sock: if (flags & BIND_WITH_LOCK) release_sock(sk); out: return err; } int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; int err; if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) return sk->sk_prot->disconnect(sk, flags); if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); if (err) return err; } if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. * Connect() does not allow to get error notifications * without closing the socket. */ while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); if (signal_pending(current) || !timeo) break; } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; return timeo; } /* * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg) { struct sock *sk = sock->sk; int err; long timeo; /* * uaddr can be NULL and addr_len can be 0 if: * sk is a TCP fastopen active socket and * TCP_FASTOPEN_CONNECT sockopt is set and * we already have a valid cookie for this socket. * In this case, user can call write() after connect(). * write() will invoke tcp_sendmsg_fastopen() which calls * __inet_stream_connect(). */ if (uaddr) { if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; } } switch (sock->state) { default: err = -EINVAL; goto out; case SS_CONNECTED: err = -EISCONN; goto out; case SS_CONNECTING: if (inet_sk(sk)->defer_connect) err = is_sendmsg ? -EINPROGRESS : -EISCONN; else err = -EALREADY; /* Fall out of switch with err, set for this state */ break; case SS_UNCONNECTED: err = -EISCONN; if (sk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); if (err) goto out; } err = sk->sk_prot->connect(sk, uaddr, addr_len); if (err < 0) goto out; sock->state = SS_CONNECTING; if (!err && inet_sk(sk)->defer_connect) goto out; /* Just entered SS_CONNECTING state; the only * difference is that return value in non-blocking * case is EINPROGRESS, rather than EALREADY. */ err = -EINPROGRESS; break; } timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) goto out; err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; } /* Connection was closed by RST, timeout, ICMP error * or another process disconnected us. */ if (sk->sk_state == TCP_CLOSE) goto sock_error; /* sk->sk_err may be not zero now, if RECVERR was ordered by user * and error was received after socket entered established state. * Hence, it is handled normally after connect() return successfully. */ sock->state = SS_CONNECTED; err = 0; out: return err; sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; } EXPORT_SYMBOL(__inet_stream_connect); int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { int err; lock_sock(sock->sk); err = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); release_sock(sock->sk); return err; } EXPORT_SYMBOL(inet_stream_connect); /* * Accept a pending connection. The TCP layer now gives BSD semantics. */ int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk1 = sock->sk; int err = -EINVAL; struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern); if (!sk2) goto do_err; lock_sock(sk2); sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_CLOSE_WAIT | TCPF_CLOSE))); sock_graft(sk2, newsock); newsock->state = SS_CONNECTED; err = 0; release_sock(sk2); do_err: return err; } EXPORT_SYMBOL(inet_accept); /* * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); sin->sin_family = AF_INET; if (peer) { if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) return -ENOTCONN; sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; } if (cgroup_bpf_enabled) BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, peer ? BPF_CGROUP_INET4_GETPEERNAME : BPF_CGROUP_INET4_GETSOCKNAME, NULL); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sizeof(*sin); } EXPORT_SYMBOL(inet_getname); int inet_send_prepare(struct sock *sk) { sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; return 0; } EXPORT_SYMBOL_GPL(inet_send_prepare); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg, sk, msg, size); } EXPORT_SYMBOL(inet_sendmsg); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; if (sk->sk_prot->sendpage) return sk->sk_prot->sendpage(sk, page, offset, size, flags); return sock_no_sendpage(sock, page, offset, size, flags); } EXPORT_SYMBOL(inet_sendpage); INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *, size_t, int, int, int *)); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; if (likely(!(flags & MSG_ERRQUEUE))) sock_rps_record_flow(sk); err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; /* This should really check to make sure * the socket is a TCP socket. (WHY AC...) */ how++; /* maps 0->1 has the advantage of making bit 1 rcvs and 1->2 bit 2 snds. 2->3 */ if ((how & ~SHUTDOWN_MASK) || !how) /* MAXINT->0 */ return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTING) { if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE)) sock->state = SS_DISCONNECTING; else sock->state = SS_CONNECTED; } switch (sk->sk_state) { case TCP_CLOSE: err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: sk->sk_shutdown |= how; if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; /* Remaining two branches are temporary solution for missing * close() in multithreaded environment. It is _not_ a good idea, * but we have no choice until close() is repaired at VFS level. */ case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; break; } /* Wake up anyone sleeping in poll. */ sk->sk_state_change(sk); release_sock(sk); return err; } EXPORT_SYMBOL(inet_shutdown); /* * ioctl() calls you can issue on an INET socket. Most of these are * device configuration and stuff and very rarely used. Some ioctls * pass on to the socket itself. * * NOTE: I like the idea of a module for the config stuff. ie ifconfig * loads the devconfigure module does its configuring and unloads it. * There's a good 20K of config code hanging around the kernel. */ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; int err = 0; struct net *net = sock_net(sk); void __user *p = (void __user *)arg; struct ifreq ifr; struct rtentry rt; switch (cmd) { case SIOCADDRT: case SIOCDELRT: if (copy_from_user(&rt, p, sizeof(struct rtentry))) return -EFAULT; err = ip_rt_ioctl(net, cmd, &rt); break; case SIOCRTMSG: err = -EINVAL; break; case SIOCDARP: case SIOCGARP: case SIOCSARP: err = arp_ioctl(net, cmd, (void __user *)arg); break; case SIOCGIFADDR: case SIOCGIFBRDADDR: case SIOCGIFNETMASK: case SIOCGIFDSTADDR: case SIOCGIFPFLAGS: if (copy_from_user(&ifr, p, sizeof(struct ifreq))) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); if (!err && copy_to_user(p, &ifr, sizeof(struct ifreq))) err = -EFAULT; break; case SIOCSIFADDR: case SIOCSIFBRDADDR: case SIOCSIFNETMASK: case SIOCSIFDSTADDR: case SIOCSIFPFLAGS: case SIOCSIFFLAGS: if (copy_from_user(&ifr, p, sizeof(struct ifreq))) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); break; default: if (sk->sk_prot->ioctl) err = sk->sk_prot->ioctl(sk, cmd, arg); else err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(inet_ioctl); #ifdef CONFIG_COMPAT static int inet_compat_routing_ioctl(struct sock *sk, unsigned int cmd, struct compat_rtentry __user *ur) { compat_uptr_t rtdev; struct rtentry rt; if (copy_from_user(&rt.rt_dst, &ur->rt_dst, 3 * sizeof(struct sockaddr)) || get_user(rt.rt_flags, &ur->rt_flags) || get_user(rt.rt_metric, &ur->rt_metric) || get_user(rt.rt_mtu, &ur->rt_mtu) || get_user(rt.rt_window, &ur->rt_window) || get_user(rt.rt_irtt, &ur->rt_irtt) || get_user(rtdev, &ur->rt_dev)) return -EFAULT; rt.rt_dev = compat_ptr(rtdev); return ip_rt_ioctl(sock_net(sk), cmd, &rt); } static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; switch (cmd) { case SIOCADDRT: case SIOCDELRT: return inet_compat_routing_ioctl(sk, cmd, argp); default: if (!sk->sk_prot->compat_ioctl) return -ENOIOCTLCMD; return sk->sk_prot->compat_ioctl(sk, cmd, arg); } } #endif /* CONFIG_COMPAT */ const struct proto_ops inet_stream_ops = { .family = PF_INET, .flags = PROTO_CMSG_DATA_ONLY, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, .poll = tcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif .set_rcvlowat = tcp_set_rcvlowat, }; EXPORT_SYMBOL(inet_stream_ops); const struct proto_ops inet_dgram_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = udp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_dgram_ops); /* * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without * udp_poll */ static const struct proto_ops inet_sockraw_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; static const struct net_proto_family inet_family_ops = { .family = PF_INET, .create = inet_create, .owner = THIS_MODULE, }; /* Upon startup we insert all the elements in inetsw_array[] into * the linked list inetsw. */ static struct inet_protosw inetsw_array[] = { { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, } }; #define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array) void inet_register_protosw(struct inet_protosw *p) { struct list_head *lh; struct inet_protosw *answer; int protocol = p->protocol; struct list_head *last_perm; spin_lock_bh(&inetsw_lock); if (p->type >= SOCK_MAX) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ last_perm = &inetsw[p->type]; list_for_each(lh, &inetsw[p->type]) { answer = list_entry(lh, struct inet_protosw, list); /* Check only the non-wild match. */ if ((INET_PROTOSW_PERMANENT & answer->flags) == 0) break; if (protocol == answer->protocol) goto out_permanent; last_perm = lh; } /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with * a wild-card protocol. But it is allowed to override any existing * non-permanent entry. This means that when we remove this entry, the * system automatically returns to the old behavior. */ list_add_rcu(&p->list, last_perm); out: spin_unlock_bh(&inetsw_lock); return; out_permanent: pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } EXPORT_SYMBOL(inet_register_protosw); void inet_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw_lock); list_del_rcu(&p->list); spin_unlock_bh(&inetsw_lock); synchronize_net(); } } EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; __be32 new_saddr; struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* Query new route. */ fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, daddr, 0, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, sk->sk_protocol, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); sk_setup_caps(sk, &rt->dst); new_saddr = fl4->saddr; if (new_saddr == old_saddr) return 0; if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; /* * XXX The only one ugly spot where we need to * XXX really change the sockets identity after * XXX it has entered the hashes. -DaveM * * Besides that, it does not check for connection * uniqueness. Wait for troubles. */ return __sk_prot_rehash(sk); } int inet_sk_rebuild_header(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0); __be32 daddr; struct ip_options_rcu *inet_opt; struct flowi4 *fl4; int err; /* Route is OK, nothing to do. */ if (rt) return 0; /* Reroute. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; rcu_read_unlock(); fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; sk_setup_caps(sk, &rt->dst); } else { err = PTR_ERR(rt); /* Routing failed... */ sk->sk_route_caps = 0; /* * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) sk->sk_err_soft = -err; } return err; } EXPORT_SYMBOL(inet_sk_rebuild_header); void inet_sk_set_state(struct sock *sk, int state) { trace_inet_sock_set_state(sk, sk->sk_state, state); sk->sk_state = state; } EXPORT_SYMBOL(inet_sk_set_state); void inet_sk_state_store(struct sock *sk, int newstate) { trace_inet_sock_set_state(sk, sk->sk_state, newstate); smp_store_release(&sk->sk_state, newstate); } struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; struct iphdr *iph; int proto, tot_len; int nhoff; int ihl; int id; skb_reset_network_header(skb); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) goto out; iph = ip_hdr(skb); ihl = iph->ihl * 4; if (ihl < sizeof(*iph)) goto out; id = ntohs(iph->id); proto = iph->protocol; /* Warning: after this point, iph might be no longer valid */ if (unlikely(!pskb_may_pull(skb, ihl))) goto out; __skb_pull(skb, ihl); encap = SKB_GSO_CB(skb)->encap_level > 0; if (encap) features &= skb->dev->hw_enc_features; SKB_GSO_CB(skb)->encap_level += ihl; skb_reset_transport_header(skb); segs = ERR_PTR(-EPROTONOSUPPORT); if (!skb->encapsulation || encap) { udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); if (udpfrag) { iph->frag_off = htons(offset >> 3); if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; tot_len = skb->len - nhoff; } else if (skb_is_gso(skb)) { if (!fixedid) { iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; } if (gso_partial) tot_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)iph; else tot_len = skb->len - nhoff; } else { if (!fixedid) iph->id = htons(id++); tot_len = skb->len - nhoff; } iph->tot_len = htons(tot_len); ip_send_check(iph); if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; skb_reset_mac_len(skb); } while ((skb = skb->next)); out: return segs; } EXPORT_SYMBOL(inet_gso_segment); static struct sk_buff *ipip_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4)) return ERR_PTR(-EINVAL); return inet_gso_segment(skb, features); } struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; const struct iphdr *iph; struct sk_buff *p; unsigned int hlen; unsigned int off; unsigned int id; int flush = 1; int proto; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); iph = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, hlen)) { iph = skb_gro_header_slow(skb, hlen, off); if (unlikely(!iph)) goto out; } proto = iph->protocol; rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out_unlock; if (*(u8 *)iph != 0x45) goto out_unlock; if (ip_is_fragment(iph)) goto out_unlock; if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out_unlock; id = ntohl(*(__be32 *)&iph->id); flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; list_for_each_entry(p, head, list) { struct iphdr *iph2; u16 flush_id; if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = (struct iphdr *)(p->data + off); /* The above works because, with the exception of the top * (inner most) layer, we only aggregate pkts with the same * hdr length so all the hdrs we'll need to verify will start * at the same offset. */ if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } /* All fields must match except length and checksum. */ NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); NAPI_GRO_CB(p)->flush |= flush; /* We need to store of the IP ID check to be included later * when we can verify that this packet does in fact belong * to a given flow. */ flush_id = (u16)(id - ntohs(iph2->id)); /* This bit of code makes it much easier for us to identify * the cases where we are doing atomic vs non-atomic IP ID * checks. Specifically an atomic check can return IP ID * values 0 - 0xFFFF, while a non-atomic check can only * return 0 or 0xFFFF. */ if (!NAPI_GRO_CB(p)->is_atomic || !(iph->frag_off & htons(IP_DF))) { flush_id ^= NAPI_GRO_CB(p)->count; flush_id = flush_id ? 0xFFFF : 0; } /* If the previous IP ID value was based on an atomic * datagram we can overwrite the value and ignore it. */ if (NAPI_GRO_CB(skb)->is_atomic) NAPI_GRO_CB(p)->flush_id = flush_id; else NAPI_GRO_CB(p)->flush_id |= flush_id; } NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF)); NAPI_GRO_CB(skb)->flush |= flush; skb_set_network_header(skb, off); /* The above will be needed by the transport layer if there is one * immediately following this IP hdr. */ /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 */ skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); pp = indirect_call_gro_receive(tcp4_gro_receive, udp4_gro_receive, ops->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(inet_gro_receive); static struct sk_buff *ipip_gro_receive(struct list_head *head, struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return inet_gro_receive(head, skb); } #define SECONDS_PER_DAY 86400 /* inet_current_timestamp - Return IP network timestamp * * Return milliseconds since midnight in network byte order. */ __be32 inet_current_timestamp(void) { u32 secs; u32 msecs; struct timespec64 ts; ktime_get_real_ts64(&ts); /* Get secs since midnight. */ (void)div_u64_rem(ts.tv_sec, SECONDS_PER_DAY, &secs); /* Convert to msecs. */ msecs = secs * MSEC_PER_SEC; /* Convert nsec to msec. */ msecs += (u32)ts.tv_nsec / NSEC_PER_MSEC; /* Convert to network byte order. */ return htonl(msecs); } EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { if (sk->sk_family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; } int inet_gro_complete(struct sk_buff *skb, int nhoff) { __be16 newlen = htons(skb->len - nhoff); struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; if (skb->encapsulation) { skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); } csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; rcu_read_lock(); ops = rcu_dereference(inet_offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out_unlock; /* Only need to add sizeof(*iph) to get to the next hdr below * because any hdr with option will have been flushed in * inet_gro_receive(). */ err = INDIRECT_CALL_2(ops->callbacks.gro_complete, tcp4_gro_complete, udp4_gro_complete, skb, nhoff + sizeof(*iph)); out_unlock: rcu_read_unlock(); return err; } EXPORT_SYMBOL(inet_gro_complete); static int ipip_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return inet_gro_complete(skb, nhoff); } int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) { struct socket *sock; int rc = sock_create_kern(net, family, type, protocol, &sock); if (rc == 0) { *sk = sock->sk; (*sk)->sk_allocation = GFP_ATOMIC; /* * Unhash it so that IP input processing does not even see it, * we do not wish this socket to see incoming packets. */ (*sk)->sk_prot->unhash(*sk); } return rc; } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt) { return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt); } EXPORT_SYMBOL_GPL(snmp_get_cpu_field); unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; int i; for_each_possible_cpu(i) res += snmp_get_cpu_field(mib, i, offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, size_t syncp_offset) { void *bhptr; struct u64_stats_sync *syncp; u64 v; unsigned int start; bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { start = u64_stats_fetch_begin_irq(syncp); v = *(((u64 *)bhptr) + offt); } while (u64_stats_fetch_retry_irq(syncp, start)); return v; } EXPORT_SYMBOL_GPL(snmp_get_cpu_field64); u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; for_each_possible_cpu(cpu) { res += snmp_get_cpu_field64(mib, cpu, offt, syncp_offset); } return res; } EXPORT_SYMBOL_GPL(snmp_fold_field64); #endif #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, .netns_ok = 1, }; #endif /* thinking of making this const? Don't. * early_demux can change based on sysctl. */ static struct net_protocol tcp_protocol = { .early_demux = tcp_v4_early_demux, .early_demux_handler = tcp_v4_early_demux, .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .netns_ok = 1, .icmp_strict_tag_validation = 1, }; /* thinking of making this const? Don't. * early_demux can change based on sysctl. */ static struct net_protocol udp_protocol = { .early_demux = udp_v4_early_demux, .early_demux_handler = udp_v4_early_demux, .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, .netns_ok = 1, }; static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, .no_policy = 1, .netns_ok = 1, }; static __net_init int ipv4_mib_init_net(struct net *net) { int i; net->mib.tcp_statistics = alloc_percpu(struct tcp_mib); if (!net->mib.tcp_statistics) goto err_tcp_mib; net->mib.ip_statistics = alloc_percpu(struct ipstats_mib); if (!net->mib.ip_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet_stats; af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i); u64_stats_init(&af_inet_stats->syncp); } net->mib.net_statistics = alloc_percpu(struct linux_mib); if (!net->mib.net_statistics) goto err_net_mib; net->mib.udp_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udp_statistics) goto err_udp_mib; net->mib.udplite_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udplite_statistics) goto err_udplite_mib; net->mib.icmp_statistics = alloc_percpu(struct icmp_mib); if (!net->mib.icmp_statistics) goto err_icmp_mib; net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), GFP_KERNEL); if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); return 0; err_icmpmsg_mib: free_percpu(net->mib.icmp_statistics); err_icmp_mib: free_percpu(net->mib.udplite_statistics); err_udplite_mib: free_percpu(net->mib.udp_statistics); err_udp_mib: free_percpu(net->mib.net_statistics); err_net_mib: free_percpu(net->mib.ip_statistics); err_ip_mib: free_percpu(net->mib.tcp_statistics); err_tcp_mib: return -ENOMEM; } static __net_exit void ipv4_mib_exit_net(struct net *net) { kfree(net->mib.icmpmsg_statistics); free_percpu(net->mib.icmp_statistics); free_percpu(net->mib.udplite_statistics); free_percpu(net->mib.udp_statistics); free_percpu(net->mib.net_statistics); free_percpu(net->mib.ip_statistics); free_percpu(net->mib.tcp_statistics); #ifdef CONFIG_MPTCP /* allocated on demand, see mptcp_init_sock() */ free_percpu(net->mib.mptcp_statistics); #endif } static __net_initdata struct pernet_operations ipv4_mib_ops = { .init = ipv4_mib_init_net, .exit = ipv4_mib_exit_net, }; static int __init init_ipv4_mibs(void) { return register_pernet_subsys(&ipv4_mib_ops); } static __net_init int inet_init_net(struct net *net) { /* * Set defaults for local port range */ seqlock_init(&net->ipv4.ip_local_ports.lock); net->ipv4.ip_local_ports.range[0] = 32768; net->ipv4.ip_local_ports.range[1] = 60999; seqlock_init(&net->ipv4.ping_group_range.lock); /* * Sane defaults - nobody may create ping sockets. * Boot scripts should set this to distro-specific group. */ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); /* Default values for sysctl-controlled parameters. * We set them here, in case sysctl is not compiled. */ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; net->ipv4.sysctl_ip_fwd_update_priority = 1; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; net->ipv4.sysctl_tcp_early_demux = 1; net->ipv4.sysctl_nexthop_compat_mode = 1; #ifdef CONFIG_SYSCTL net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif /* Some igmp sysctl, whose values are always used */ net->ipv4.sysctl_igmp_max_memberships = 20; net->ipv4.sysctl_igmp_max_msf = 10; /* IGMP reports for link-local multicast groups are enabled by default */ net->ipv4.sysctl_igmp_llm_reports = 1; net->ipv4.sysctl_igmp_qrv = 2; return 0; } static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, }; static int __init init_inet_pernet_ops(void) { return register_pernet_subsys(&af_inet_ops); } static int ipv4_proc_init(void); /* * IP protocol layer initialiser */ static struct packet_offload ip_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .callbacks = { .gso_segment = inet_gso_segment, .gro_receive = inet_gro_receive, .gro_complete = inet_gro_complete, }, }; static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = ipip_gso_segment, .gro_receive = ipip_gro_receive, .gro_complete = ipip_gro_complete, }, }; static int __init ipip_offload_init(void) { return inet_add_offload(&ipip_offload, IPPROTO_IPIP); } static int __init ipv4_offload_init(void) { /* * Add offloads */ if (udpv4_offload_init() < 0) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (tcpv4_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); dev_add_offload(&ip_packet_offload); return 0; } fs_initcall(ipv4_offload_init); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, .list_func = ip_list_rcv, }; static int __init inet_init(void) { struct inet_protosw *q; struct list_head *r; int rc; sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); rc = proto_register(&tcp_prot, 1); if (rc) goto out; rc = proto_register(&udp_prot, 1); if (rc) goto out_unregister_tcp_proto; rc = proto_register(&raw_prot, 1); if (rc) goto out_unregister_udp_proto; rc = proto_register(&ping_prot, 1); if (rc) goto out_unregister_raw_proto; /* * Tell SOCKET that we are alive... */ (void)sock_register(&inet_family_ops); #ifdef CONFIG_SYSCTL ip_static_sysctl_init(); #endif /* * Add all the base protocols. */ if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) pr_crit("%s: Cannot add IGMP protocol\n", __func__); #endif /* Register the socket-side information for inet_create. */ for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q) inet_register_protosw(q); /* * Set the ARP module up */ arp_init(); /* * Set the IP module up */ ip_init(); /* Initialise per-cpu ipv4 mibs */ if (init_ipv4_mibs()) panic("%s: Cannot init ipv4 mibs\n", __func__); /* Setup TCP slab cache for open requests. */ tcp_init(); /* Setup UDP memory threshold */ udp_init(); /* Add UDP-Lite (RFC 3828) */ udplite4_register(); raw_init(); ping_init(); /* * Set the ICMP layer up */ if (icmp_init() < 0) panic("Failed to create the ICMP control socket.\n"); /* * Initialise the multicast router */ #if defined(CONFIG_IP_MROUTE) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif if (init_inet_pernet_ops()) pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); ipv4_proc_init(); ipfrag_init(); dev_add_pack(&ip_packet_type); ip_tunnel_core_init(); rc = 0; out: return rc; out_unregister_raw_proto: proto_unregister(&raw_prot); out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); goto out; } fs_initcall(inet_init); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS static int __init ipv4_proc_init(void) { int rc = 0; if (raw_proc_init()) goto out_raw; if (tcp4_proc_init()) goto out_tcp; if (udp4_proc_init()) goto out_udp; if (ping_proc_init()) goto out_ping; if (ip_misc_proc_init()) goto out_misc; out: return rc; out_misc: ping_proc_exit(); out_ping: udp4_proc_exit(); out_udp: tcp4_proc_exit(); out_tcp: raw_proc_exit(); out_raw: rc = -ENOMEM; goto out; } #else /* CONFIG_PROC_FS */ static int __init ipv4_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ |
| 1763 1141 1761 708 1140 1142 1142 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> static struct vfsmount *anon_inode_mnt __read_mostly; static struct inode *anon_inode_inode; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *anon_inode_make_secure_inode( const char *name, const struct inode *context_inode) { struct inode *inode; const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; error = security_inode_init_security_anon(inode, &qname, context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool secure) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (secure) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool secure) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, secure); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_getfd_secure - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. This allows the inode to have its * own security context and for a LSM to reject creation of the inode. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. */ int anon_inode_getfd_secure(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_getfd_secure); static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); return 0; } fs_initcall(anon_inode_init); |
| 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* Connection tracking via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org> * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org> * (C) 2003 by Patrick Mchardy <kaber@trash.net> * (C) 2005-2012 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial connection tracking via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/rculist.h> #include <linux/rculist_nulls.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/security.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/netlink.h> #include <linux/spinlock.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/siphash.h> #include <linux/netfilter.h> #include <net/netlink.h> #include <net/sock.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_conntrack_synproxy.h> #if IS_ENABLED(CONFIG_NF_NAT) #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #endif #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include "nf_internals.h" MODULE_LICENSE("GPL"); static int ctnetlink_dump_tuples_proto(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_PROTO); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTO_NUM, tuple->dst.protonum)) goto nla_put_failure; if (likely(l4proto->tuple_to_nlattr)) ret = l4proto->tuple_to_nlattr(skb, tuple); nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ipv4_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) || nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip)) return -EMSGSIZE; return 0; } static int ipv6_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) || nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6)) return -EMSGSIZE; return 0; } static int ctnetlink_dump_tuples_ip(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { int ret = 0; struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, CTA_TUPLE_IP); if (!nest_parms) goto nla_put_failure; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_tuple_to_nlattr(skb, tuple); break; case NFPROTO_IPV6: ret = ipv6_tuple_to_nlattr(skb, tuple); break; } nla_nest_end(skb, nest_parms); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_tuples(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { const struct nf_conntrack_l4proto *l4proto; int ret; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); } rcu_read_unlock(); return ret; } static int ctnetlink_dump_zone_id(struct sk_buff *skb, int attrtype, const struct nf_conntrack_zone *zone, int dir) { if (zone->id == NF_CT_DEFAULT_ZONE_ID || zone->dir != dir) return 0; if (nla_put_be16(skb, attrtype, htons(zone->id))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_status(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_STATUS, htonl(ct->status))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct) { long timeout = nf_ct_expires(ct) / HZ; if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *nest_proto; int ret; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (!l4proto->to_nlattr) return 0; nest_proto = nla_nest_start(skb, CTA_PROTOINFO); if (!nest_proto) goto nla_put_failure; ret = l4proto->to_nlattr(skb, nest_proto, ct); nla_nest_end(skb, nest_proto); return ret; nla_put_failure: return -1; } static int ctnetlink_dump_helpinfo(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_helper; const struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_helper *helper; if (!help) return 0; rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; nest_helper = nla_nest_start(skb, CTA_HELP); if (!nest_helper) goto nla_put_failure; if (nla_put_string(skb, CTA_HELP_NAME, helper->name)) goto nla_put_failure; if (helper->to_nlattr) helper->to_nlattr(skb, ct); nla_nest_end(skb, nest_helper); out: rcu_read_unlock(); return 0; nla_put_failure: rcu_read_unlock(); return -1; } static int dump_counters(struct sk_buff *skb, struct nf_conn_acct *acct, enum ip_conntrack_dir dir, int type) { enum ctattr_type attr = dir ? CTA_COUNTERS_REPLY: CTA_COUNTERS_ORIG; struct nf_conn_counter *counter = acct->counter; struct nlattr *nest_count; u64 pkts, bytes; if (type == IPCTNL_MSG_CT_GET_CTRZERO) { pkts = atomic64_xchg(&counter[dir].packets, 0); bytes = atomic64_xchg(&counter[dir].bytes, 0); } else { pkts = atomic64_read(&counter[dir].packets); bytes = atomic64_read(&counter[dir].bytes); } nest_count = nla_nest_start(skb, attr); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_COUNTERS_PACKETS, cpu_to_be64(pkts), CTA_COUNTERS_PAD) || nla_put_be64(skb, CTA_COUNTERS_BYTES, cpu_to_be64(bytes), CTA_COUNTERS_PAD)) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_acct(struct sk_buff *skb, const struct nf_conn *ct, int type) { struct nf_conn_acct *acct = nf_conn_acct_find(ct); if (!acct) return 0; if (dump_counters(skb, acct, IP_CT_DIR_ORIGINAL, type) < 0) return -1; if (dump_counters(skb, acct, IP_CT_DIR_REPLY, type) < 0) return -1; return 0; } static int ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_count; const struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (!tstamp) return 0; nest_count = nla_nest_start(skb, CTA_TIMESTAMP); if (!nest_count) goto nla_put_failure; if (nla_put_be64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start), CTA_TIMESTAMP_PAD) || (tstamp->stop != 0 && nla_put_be64(skb, CTA_TIMESTAMP_STOP, cpu_to_be64(tstamp->stop), CTA_TIMESTAMP_PAD))) goto nla_put_failure; nla_nest_end(skb, nest_count); return 0; nla_put_failure: return -1; } #ifdef CONFIG_NF_CONNTRACK_MARK static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) goto nla_put_failure; return 0; nla_put_failure: return -1; } #else #define ctnetlink_dump_mark(a, b) (0) #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_secctx; int len, ret; char *secctx; ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) return 0; ret = -1; nest_secctx = nla_nest_start(skb, CTA_SECCTX); if (!nest_secctx) goto nla_put_failure; if (nla_put_string(skb, CTA_SECCTX_NAME, secctx)) goto nla_put_failure; nla_nest_end(skb, nest_secctx); ret = 0; nla_put_failure: security_release_secctx(secctx, len); return ret; } #else #define ctnetlink_dump_secctx(a, b) (0) #endif #ifdef CONFIG_NF_CONNTRACK_LABELS static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); if (!labels) return 0; return nla_total_size(sizeof(labels->bits)); } static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); unsigned int i; if (!labels) return 0; i = 0; do { if (labels->bits[i] != 0) return nla_put(skb, CTA_LABELS, sizeof(labels->bits), labels->bits); i++; } while (i < ARRAY_SIZE(labels->bits)); return 0; } #else #define ctnetlink_dump_labels(a, b) (0) #define ctnetlink_label_size(a) (0) #endif #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) static int ctnetlink_dump_master(struct sk_buff *skb, const struct nf_conn *ct) { struct nlattr *nest_parms; if (!(ct->status & IPS_EXPECTED)) return 0; nest_parms = nla_nest_start(skb, CTA_TUPLE_MASTER); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, master_tuple(ct)) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int dump_ct_seq_adj(struct sk_buff *skb, const struct nf_ct_seqadj *seq, int type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SEQADJ_CORRECTION_POS, htonl(seq->correction_pos)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_BEFORE, htonl(seq->offset_before)) || nla_put_be32(skb, CTA_SEQADJ_OFFSET_AFTER, htonl(seq->offset_after))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_ct_seq_adj(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); struct nf_ct_seqadj *seq; if (!(ct->status & IPS_SEQ_ADJUST) || !seqadj) return 0; spin_lock_bh(&ct->lock); seq = &seqadj->seq[IP_CT_DIR_ORIGINAL]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_ORIG) == -1) goto err; seq = &seqadj->seq[IP_CT_DIR_REPLY]; if (dump_ct_seq_adj(skb, seq, CTA_SEQ_ADJ_REPLY) == -1) goto err; spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return -1; } static int ctnetlink_dump_ct_synproxy(struct sk_buff *skb, struct nf_conn *ct) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *nest_parms; if (!synproxy) return 0; nest_parms = nla_nest_start(skb, CTA_SYNPROXY); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_SYNPROXY_ISN, htonl(synproxy->isn)) || nla_put_be32(skb, CTA_SYNPROXY_ITS, htonl(synproxy->its)) || nla_put_be32(skb, CTA_SYNPROXY_TSOFF, htonl(synproxy->tsoff))) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct) { __be32 id = (__force __be32)nf_ct_get_id(ct); if (nla_put_be32(skb, CTA_ID, id)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { if (nla_put_be32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use)))) goto nla_put_failure; return 0; nla_put_failure: return -1; } /* all these functions access ct->ext. Caller must either hold a reference * on ct or prevent its deletion by holding either the bucket spinlock or * pcpu dying list lock. */ static int ctnetlink_dump_extinfo(struct sk_buff *skb, struct nf_conn *ct, u32 type) { if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_ct_seq_adj(skb, ct) < 0 || ctnetlink_dump_ct_synproxy(skb, ct) < 0) return -1; return 0; } static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0) return -1; if (!test_bit(IPS_OFFLOAD_BIT, &ct->status) && (ctnetlink_dump_timeout(skb, ct) < 0 || ctnetlink_dump_protoinfo(skb, ct) < 0)) return -1; return 0; } static int ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct, bool extinfo, unsigned int flags) { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; unsigned int event; if (portid) flags |= NLM_F_MULTI; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = nf_ct_l3num(ct); nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_info(skb, ct) < 0) goto nla_put_failure; if (extinfo && ctnetlink_dump_extinfo(skb, ct, type) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static const struct nla_policy cta_ip_nla_policy[CTA_IP_MAX + 1] = { [CTA_IP_V4_SRC] = { .type = NLA_U32 }, [CTA_IP_V4_DST] = { .type = NLA_U32 }, [CTA_IP_V6_SRC] = { .len = sizeof(__be32) * 4 }, [CTA_IP_V6_DST] = { .len = sizeof(__be32) * 4 }, }; #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS) static size_t ctnetlink_proto_size(const struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; size_t len, len4 = 0; len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); len += l4proto->nlattr_size; if (l4proto->nlattr_tuple_size) { len4 = l4proto->nlattr_tuple_size(); len4 *= 3u; /* ORIG, REPLY, MASTER */ } return len + len4; } #endif static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) { if (!nf_ct_ext_exist(ct, NF_CT_EXT_ACCT)) return 0; return 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */ + 2 * nla_total_size_64bit(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */ ; } static inline int ctnetlink_secctx_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_SECMARK int len, ret; ret = security_secid_to_secctx(ct->secmark, NULL, &len); if (ret) return 0; return nla_total_size(0) /* CTA_SECCTX */ + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */ #else return 0; #endif } static inline size_t ctnetlink_timestamp_size(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) return 0; return nla_total_size(0) + 2 * nla_total_size_64bit(sizeof(uint64_t)); #else return 0; #endif } #ifdef CONFIG_NF_CONNTRACK_EVENTS static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) { return NLMSG_ALIGN(sizeof(struct nfgenmsg)) + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + ctnetlink_acct_size(ct) + ctnetlink_timestamp_size(ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) ; } static int ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) { const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; struct nf_conn *ct = item->ct; struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; int err; if (events & (1 << IPCT_DESTROY)) { type = IPCTNL_MSG_CT_DELETE; group = NFNLGRP_CONNTRACK_DESTROY; } else if (events & ((1 << IPCT_NEW) | (1 << IPCT_RELATED))) { type = IPCTNL_MSG_CT_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_NEW; } else if (events) { type = IPCTNL_MSG_CT_NEW; group = NFNLGRP_CONNTRACK_UPDATE; } else return 0; net = nf_ct_net(ct); if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type); nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = nf_ct_l3num(ct); nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_acct(skb, ct, type) < 0 || ctnetlink_dump_timestamp(skb, ct) < 0) goto nla_put_failure; } else { if (ctnetlink_dump_timeout(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_PROTOINFO) && ctnetlink_dump_protoinfo(skb, ct) < 0) goto nla_put_failure; if ((events & (1 << IPCT_HELPER) || nfct_help(ct)) && ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if ((events & (1 << IPCT_SECMARK) || ct->secmark) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (events & (1 << IPCT_LABEL) && ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SEQADJ) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (events & (1 << IPCT_SYNPROXY) && ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; } #ifdef CONFIG_NF_CONNTRACK_MARK if ((events & (1 << IPCT_MARK) || ct->mark) && ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: if (nfnetlink_set_err(net, 0, group, -ENOBUFS) > 0) return -ENOBUFS; return 0; } #endif /* CONFIG_NF_CONNTRACK_EVENTS */ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } struct ctnetlink_filter { u8 family; u_int32_t orig_flags; u_int32_t reply_flags; struct nf_conntrack_tuple orig; struct nf_conntrack_tuple reply; struct nf_conntrack_zone zone; struct { u_int32_t val; u_int32_t mask; } mark; }; static const struct nla_policy cta_filter_nla_policy[CTA_FILTER_MAX + 1] = { [CTA_FILTER_ORIG_FLAGS] = { .type = NLA_U32 }, [CTA_FILTER_REPLY_FLAGS] = { .type = NLA_U32 }, }; static int ctnetlink_parse_filter(const struct nlattr *attr, struct ctnetlink_filter *filter) { struct nlattr *tb[CTA_FILTER_MAX + 1]; int ret = 0; ret = nla_parse_nested(tb, CTA_FILTER_MAX, attr, cta_filter_nla_policy, NULL); if (ret) return ret; if (tb[CTA_FILTER_ORIG_FLAGS]) { filter->orig_flags = nla_get_u32(tb[CTA_FILTER_ORIG_FLAGS]); if (filter->orig_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } if (tb[CTA_FILTER_REPLY_FLAGS]) { filter->reply_flags = nla_get_u32(tb[CTA_FILTER_REPLY_FLAGS]); if (filter->reply_flags & ~CTA_FILTER_F_ALL) return -EOPNOTSUPP; } return 0; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone); static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags); static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { struct ctnetlink_filter *filter; int err; #ifndef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK] || cda[CTA_MARK_MASK]) return ERR_PTR(-EOPNOTSUPP); #endif filter = kzalloc(sizeof(*filter), GFP_KERNEL); if (filter == NULL) return ERR_PTR(-ENOMEM); filter->family = family; #ifdef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK]) { filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); if (cda[CTA_MARK_MASK]) filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); else filter->mark.mask = 0xffffffff; } else if (cda[CTA_MARK_MASK]) { err = -EINVAL; goto err_filter; } #endif if (!cda[CTA_FILTER]) return filter; err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone); if (err < 0) goto err_filter; err = ctnetlink_parse_filter(cda[CTA_FILTER], filter); if (err < 0) goto err_filter; if (filter->orig_flags) { if (!cda[CTA_TUPLE_ORIG]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->orig, CTA_TUPLE_ORIG, filter->family, &filter->zone, filter->orig_flags); if (err < 0) goto err_filter; } if (filter->reply_flags) { if (!cda[CTA_TUPLE_REPLY]) { err = -EINVAL; goto err_filter; } err = ctnetlink_parse_tuple_filter(cda, &filter->reply, CTA_TUPLE_REPLY, filter->family, &filter->zone, filter->reply_flags); if (err < 0) goto err_filter; } return filter; err_filter: kfree(filter); return ERR_PTR(err); } static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda) { return family || cda[CTA_MARK] || cda[CTA_FILTER]; } static int ctnetlink_start(struct netlink_callback *cb) { const struct nlattr * const *cda = cb->data; struct ctnetlink_filter *filter = NULL; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u8 family = nfmsg->nfgen_family; if (ctnetlink_needs_filter(family, cda)) { filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } cb->data = filter; return 0; } static int ctnetlink_filter_match_tuple(struct nf_conntrack_tuple *filter_tuple, struct nf_conntrack_tuple *ct_tuple, u_int32_t flags, int family) { switch (family) { case NFPROTO_IPV4: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && filter_tuple->src.u3.ip != ct_tuple->src.u3.ip) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && filter_tuple->dst.u3.ip != ct_tuple->dst.u3.ip) return 0; break; case NFPROTO_IPV6: if ((flags & CTA_FILTER_FLAG(CTA_IP_SRC)) && !ipv6_addr_cmp(&filter_tuple->src.u3.in6, &ct_tuple->src.u3.in6)) return 0; if ((flags & CTA_FILTER_FLAG(CTA_IP_DST)) && !ipv6_addr_cmp(&filter_tuple->dst.u3.in6, &ct_tuple->dst.u3.in6)) return 0; break; } if ((flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) && filter_tuple->dst.protonum != ct_tuple->dst.protonum) return 0; switch (ct_tuple->dst.protonum) { case IPPROTO_TCP: case IPPROTO_UDP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_SRC_PORT)) && filter_tuple->src.u.tcp.port != ct_tuple->src.u.tcp.port) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_DST_PORT)) && filter_tuple->dst.u.tcp.port != ct_tuple->dst.u.tcp.port) return 0; break; case IPPROTO_ICMP: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; case IPPROTO_ICMPV6: if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_TYPE)) && filter_tuple->dst.u.icmp.type != ct_tuple->dst.u.icmp.type) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_CODE)) && filter_tuple->dst.u.icmp.code != ct_tuple->dst.u.icmp.code) return 0; if ((flags & CTA_FILTER_FLAG(CTA_PROTO_ICMPV6_ID)) && filter_tuple->src.u.icmp.id != ct_tuple->src.u.icmp.id) return 0; break; } return 1; } static int ctnetlink_filter_match(struct nf_conn *ct, void *data) { struct ctnetlink_filter *filter = data; struct nf_conntrack_tuple *tuple; if (filter == NULL) goto out; /* Match entries of a given L3 protocol number. * If it is not specified, ie. l3proto == 0, * then match everything. */ if (filter->family && nf_ct_l3num(ct) != filter->family) goto ignore_entry; if (filter->orig_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL); if (!ctnetlink_filter_match_tuple(&filter->orig, tuple, filter->orig_flags, filter->family)) goto ignore_entry; } if (filter->reply_flags) { tuple = nf_ct_tuple(ct, IP_CT_DIR_REPLY); if (!ctnetlink_filter_match_tuple(&filter->reply, tuple, filter->reply_flags, filter->family)) goto ignore_entry; } #ifdef CONFIG_NF_CONNTRACK_MARK if ((ct->mark & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif out: return 1; ignore_entry: return 0; } static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; int res, i; spinlock_t *lockp; last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); for (; cb->args[0] < nf_conntrack_htable_size; cb->args[0]++) { restart: while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } lockp = &nf_conntrack_locks[cb->args[0] % CONNTRACK_LOCKS]; nf_conntrack_lock(lockp); if (cb->args[0] >= nf_conntrack_htable_size) { spin_unlock(lockp); goto out; } hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[cb->args[0]], hnnode) { if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) continue; ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { if (i < ARRAY_SIZE(nf_ct_evict) && atomic_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; continue; } if (!net_eq(net, nf_ct_net(ct))) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } if (!ctnetlink_filter_match(ct, cb->data)) continue; res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { nf_conntrack_get(&ct->ct_general); cb->args[1] = (unsigned long)ct; spin_unlock(lockp); goto out; } } spin_unlock(lockp); if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: local_bh_enable(); if (last) { /* nf ct hash resize happened, now clear the leftover. */ if ((struct nf_conn *)cb->args[1] == last) cb->args[1] = 0; nf_ct_put(last); } while (i) { i--; if (nf_ct_should_gc(nf_ct_evict[i])) nf_ct_kill(nf_ct_evict[i]); nf_ct_put(nf_ct_evict[i]); } return skb->len; } static int ipv4_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V4_SRC]) return -EINVAL; t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V4_DST]) return -EINVAL; t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]); } return 0; } static int ipv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_IP_V6_SRC]) return -EINVAL; t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]); } if (flags & CTA_FILTER_FLAG(CTA_IP_DST)) { if (!tb[CTA_IP_V6_DST]) return -EINVAL; t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]); } return 0; } static int ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { struct nlattr *tb[CTA_IP_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_IP_MAX, attr, NULL, NULL); if (ret < 0) return ret; ret = nla_validate_nested_deprecated(attr, CTA_IP_MAX, cta_ip_nla_policy, NULL); if (ret) return ret; switch (tuple->src.l3num) { case NFPROTO_IPV4: ret = ipv4_nlattr_to_tuple(tb, tuple, flags); break; case NFPROTO_IPV6: ret = ipv6_nlattr_to_tuple(tb, tuple, flags); break; } return ret; } static const struct nla_policy proto_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_NUM] = { .type = NLA_U8 }, }; static int ctnetlink_parse_tuple_proto(struct nlattr *attr, struct nf_conntrack_tuple *tuple, u_int32_t flags) { const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTO_MAX+1]; int ret = 0; ret = nla_parse_nested_deprecated(tb, CTA_PROTO_MAX, attr, proto_nla_policy, NULL); if (ret < 0) return ret; if (!(flags & CTA_FILTER_FLAG(CTA_PROTO_NUM))) return 0; if (!tb[CTA_PROTO_NUM]) return -EINVAL; tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); l4proto = nf_ct_l4proto_find(tuple->dst.protonum); if (likely(l4proto->nlattr_to_tuple)) { ret = nla_validate_nested_deprecated(attr, CTA_PROTO_MAX, l4proto->nla_policy, NULL); if (ret == 0) ret = l4proto->nlattr_to_tuple(tb, tuple, flags); } rcu_read_unlock(); return ret; } static int ctnetlink_parse_zone(const struct nlattr *attr, struct nf_conntrack_zone *zone) { nf_ct_zone_init(zone, NF_CT_DEFAULT_ZONE_ID, NF_CT_DEFAULT_ZONE_DIR, 0); #ifdef CONFIG_NF_CONNTRACK_ZONES if (attr) zone->id = ntohs(nla_get_be16(attr)); #else if (attr) return -EOPNOTSUPP; #endif return 0; } static int ctnetlink_parse_tuple_zone(struct nlattr *attr, enum ctattr_type type, struct nf_conntrack_zone *zone) { int ret; if (zone->id != NF_CT_DEFAULT_ZONE_ID) return -EINVAL; ret = ctnetlink_parse_zone(attr, zone); if (ret < 0) return ret; if (type == CTA_TUPLE_REPLY) zone->dir = NF_CT_ZONE_DIR_REPL; else zone->dir = NF_CT_ZONE_DIR_ORIG; return 0; } static const struct nla_policy tuple_nla_policy[CTA_TUPLE_MAX+1] = { [CTA_TUPLE_IP] = { .type = NLA_NESTED }, [CTA_TUPLE_PROTO] = { .type = NLA_NESTED }, [CTA_TUPLE_ZONE] = { .type = NLA_U16 }, }; #define CTA_FILTER_F_ALL_CTA_PROTO \ (CTA_FILTER_F_CTA_PROTO_SRC_PORT | \ CTA_FILTER_F_CTA_PROTO_DST_PORT | \ CTA_FILTER_F_CTA_PROTO_ICMP_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMP_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMP_ID | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_TYPE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_CODE | \ CTA_FILTER_F_CTA_PROTO_ICMPV6_ID) static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone, u_int32_t flags) { struct nlattr *tb[CTA_TUPLE_MAX+1]; int err; memset(tuple, 0, sizeof(*tuple)); err = nla_parse_nested_deprecated(tb, CTA_TUPLE_MAX, cda[type], tuple_nla_policy, NULL); if (err < 0) return err; if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) return -EOPNOTSUPP; tuple->src.l3num = l3num; if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || flags & CTA_FILTER_FLAG(CTA_IP_SRC)) { if (!tb[CTA_TUPLE_IP]) return -EINVAL; err = ctnetlink_parse_tuple_ip(tb[CTA_TUPLE_IP], tuple, flags); if (err < 0) return err; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_NUM)) { if (!tb[CTA_TUPLE_PROTO]) return -EINVAL; err = ctnetlink_parse_tuple_proto(tb[CTA_TUPLE_PROTO], tuple, flags); if (err < 0) return err; } else if (flags & CTA_FILTER_FLAG(ALL_CTA_PROTO)) { /* Can't manage proto flags without a protonum */ return -EINVAL; } if ((flags & CTA_FILTER_FLAG(CTA_TUPLE_ZONE)) && tb[CTA_TUPLE_ZONE]) { if (!zone) return -EINVAL; err = ctnetlink_parse_tuple_zone(tb[CTA_TUPLE_ZONE], type, zone); if (err < 0) return err; } /* orig and expect tuples get DIR_ORIGINAL */ if (type == CTA_TUPLE_REPLY) tuple->dst.dir = IP_CT_DIR_REPLY; else tuple->dst.dir = IP_CT_DIR_ORIGINAL; return 0; } static int ctnetlink_parse_tuple(const struct nlattr * const cda[], struct nf_conntrack_tuple *tuple, u32 type, u_int8_t l3num, struct nf_conntrack_zone *zone) { return ctnetlink_parse_tuple_filter(cda, tuple, type, l3num, zone, CTA_FILTER_FLAG(ALL)); } static const struct nla_policy help_nla_policy[CTA_HELP_MAX+1] = { [CTA_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, }; static int ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, struct nlattr **helpinfo) { int err; struct nlattr *tb[CTA_HELP_MAX+1]; err = nla_parse_nested_deprecated(tb, CTA_HELP_MAX, attr, help_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_HELP_NAME]) return -EINVAL; *helper_name = nla_data(tb[CTA_HELP_NAME]); if (tb[CTA_HELP_INFO]) *helpinfo = tb[CTA_HELP_INFO]; return 0; } static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, [CTA_STATUS] = { .type = NLA_U32 }, [CTA_PROTOINFO] = { .type = NLA_NESTED }, [CTA_HELP] = { .type = NLA_NESTED }, [CTA_NAT_SRC] = { .type = NLA_NESTED }, [CTA_TIMEOUT] = { .type = NLA_U32 }, [CTA_MARK] = { .type = NLA_U32 }, [CTA_ID] = { .type = NLA_U32 }, [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_ORIG] = { .type = NLA_NESTED }, [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, [CTA_LABELS] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_LABELS_MASK] = { .type = NLA_BINARY, .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) return 0; return ctnetlink_filter_match(ct, data); } static int ctnetlink_flush_conntrack(struct net *net, const struct nlattr * const cda[], u32 portid, int report, u8 family) { struct ctnetlink_filter *filter = NULL; if (ctnetlink_needs_filter(family, cda)) { if (cda[CTA_FILTER]) return -EOPNOTSUPP; filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); } nf_ct_iterate_cleanup_net(net, ctnetlink_flush_iterate, filter, portid, report); kfree(filter); return 0; } static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conn *ct; struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_conntrack_zone zone; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, nfmsg->nfgen_family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, nfmsg->nfgen_family, &zone); else { u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC; return ctnetlink_flush_conntrack(net, cda, NETLINK_CB(skb).portid, nlmsg_report(nlh), u3); } if (err < 0) return err; h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) { nf_ct_put(ct); return -EBUSY; } if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]); if (id != (__force __be32)nf_ct_get_id(ct)) { nf_ct_put(ct); return -ENOENT; } } nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_put(ct); return 0; } static int ctnetlink_get_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conn *ct; struct sk_buff *skb2 = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = ctnetlink_start, .dump = ctnetlink_dump_table, .done = ctnetlink_done, .data = (void *)cda, }; return netlink_dump_start(ctnl, skb, nlh, &c); } err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, u3, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3, &zone); else return -EINVAL; if (err < 0) return err; h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { nf_ct_put(ct); return -ENOMEM; } err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); if (err <= 0) goto free; err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; return 0; free: kfree_skb(skb2); out: /* this avoids a loop in nfnetlink. */ return err == -EAGAIN ? -ENOBUFS : err; } static int ctnetlink_done_list(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); return 0; } static int ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying) { struct nf_conn *ct, *last; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; int res; int cpu; struct hlist_nulls_head *list; struct net *net = sock_net(skb->sk); if (cb->args[2]) return 0; last = (struct nf_conn *)cb->args[1]; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { struct ct_pcpu *pcpu; if (!cpu_possible(cpu)) continue; pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu); spin_lock_bh(&pcpu->lock); list = dying ? &pcpu->dying : &pcpu->unconfirmed; restart: hlist_nulls_for_each_entry(h, n, list, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (l3proto && nf_ct_l3num(ct) != l3proto) continue; if (cb->args[1]) { if (ct != last) continue; cb->args[1] = 0; } /* We can't dump extension info for the unconfirmed * list because unconfirmed conntracks can have * ct->ext reallocated (and thus freed). * * In the dying list case ct->ext can't be free'd * until after we drop pcpu->lock. */ res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, dying ? true : false, 0); if (res < 0) { if (!atomic_inc_not_zero(&ct->ct_general.use)) continue; cb->args[0] = cpu; cb->args[1] = (unsigned long)ct; spin_unlock_bh(&pcpu->lock); goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } spin_unlock_bh(&pcpu->lock); } cb->args[2] = 1; out: if (last) nf_ct_put(last); return skb->len; } static int ctnetlink_dump_dying(struct sk_buff *skb, struct netlink_callback *cb) { return ctnetlink_dump_list(skb, cb, true); } static int ctnetlink_get_ct_dying(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_dying, .done = ctnetlink_done_list, }; return netlink_dump_start(ctnl, skb, nlh, &c); } return -EOPNOTSUPP; } static int ctnetlink_dump_unconfirmed(struct sk_buff *skb, struct netlink_callback *cb) { return ctnetlink_dump_list(skb, cb, false); } static int ctnetlink_get_ct_unconfirmed(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_dump_unconfirmed, .done = ctnetlink_done_list, }; return netlink_dump_start(ctnl, skb, nlh, &c); } return -EOPNOTSUPP; } #if IS_ENABLED(CONFIG_NF_NAT) static int ctnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) __must_hold(RCU) { struct nf_nat_hook *nat_hook; int err; nat_hook = rcu_dereference(nf_nat_hook); if (!nat_hook) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat") < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); if (nat_hook) return -EAGAIN; #endif return -EOPNOTSUPP; } err = nat_hook->parse_nat_setup(ct, manip, attr); if (err == -EAGAIN) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(NFNL_SUBSYS_CTNETLINK); if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); return -EOPNOTSUPP; } nfnl_lock(NFNL_SUBSYS_CTNETLINK); rcu_read_lock(); #else err = -EOPNOTSUPP; #endif } return err; } #endif static void __ctnetlink_change_status(struct nf_conn *ct, unsigned long on, unsigned long off) { unsigned int bit; /* Ignore these unchangable bits */ on &= ~IPS_UNCHANGEABLE_MASK; off &= ~IPS_UNCHANGEABLE_MASK; for (bit = 0; bit < __IPS_MAX_BIT; bit++) { if (on & (1 << bit)) set_bit(bit, &ct->status); else if (off & (1 << bit)) clear_bit(bit, &ct->status); } } static int ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned long d; unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); d = ct->status ^ status; if (d & (IPS_EXPECTED|IPS_CONFIRMED|IPS_DYING)) /* unchangeable */ return -EBUSY; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; __ctnetlink_change_status(ct, status, 0); return 0; } static int ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #if IS_ENABLED(CONFIG_NF_NAT) int ret; if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, cda[CTA_NAT_DST]); if (ret < 0) return ret; return ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, cda[CTA_NAT_SRC]); #else if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) return 0; return -EOPNOTSUPP; #endif } static int ctnetlink_change_helper(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conntrack_helper *helper; struct nf_conn_help *help = nfct_help(ct); char *helpname = NULL; struct nlattr *helpinfo = NULL; int err; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) return err; /* don't change helper of sibling connections */ if (ct->master) { /* If we try to change the helper to the same thing twice, * treat the second attempt as a no-op instead of returning * an error. */ err = -EBUSY; if (help) { rcu_read_lock(); helper = rcu_dereference(help->helper); if (helper && !strcmp(helper->name, helpname)) err = 0; rcu_read_unlock(); } return err; } if (!strcmp(helpname, "")) { if (help && help->helper) { /* we had a helper before ... */ nf_ct_remove_expectations(ct); RCU_INIT_POINTER(help->helper, NULL); } return 0; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); return -EOPNOTSUPP; } if (help) { if (help->helper == helper) { /* update private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); err = 0; } else err = -EBUSY; } else { /* we cannot set a helper for an existing conntrack */ err = -EOPNOTSUPP; } rcu_read_unlock(); return err; } static int ctnetlink_change_timeout(struct nf_conn *ct, const struct nlattr * const cda[]) { u64 timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; if (timeout > INT_MAX) timeout = INT_MAX; WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; return 0; } #if defined(CONFIG_NF_CONNTRACK_MARK) static void ctnetlink_change_mark(struct nf_conn *ct, const struct nlattr * const cda[]) { u32 mark, newmark, mask = 0; if (cda[CTA_MARK_MASK]) mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); newmark = (ct->mark & mask) ^ mark; if (newmark != ct->mark) ct->mark = newmark; } #endif static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = { [CTA_PROTOINFO_TCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_DCCP] = { .type = NLA_NESTED }, [CTA_PROTOINFO_SCTP] = { .type = NLA_NESTED }, }; static int ctnetlink_change_protoinfo(struct nf_conn *ct, const struct nlattr * const cda[]) { const struct nlattr *attr = cda[CTA_PROTOINFO]; const struct nf_conntrack_l4proto *l4proto; struct nlattr *tb[CTA_PROTOINFO_MAX+1]; int err = 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_MAX, attr, protoinfo_policy, NULL); if (err < 0) return err; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->from_nlattr) err = l4proto->from_nlattr(tb, ct); return err; } static const struct nla_policy seqadj_policy[CTA_SEQADJ_MAX+1] = { [CTA_SEQADJ_CORRECTION_POS] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_BEFORE] = { .type = NLA_U32 }, [CTA_SEQADJ_OFFSET_AFTER] = { .type = NLA_U32 }, }; static int change_seq_adj(struct nf_ct_seqadj *seq, const struct nlattr * const attr) { int err; struct nlattr *cda[CTA_SEQADJ_MAX+1]; err = nla_parse_nested_deprecated(cda, CTA_SEQADJ_MAX, attr, seqadj_policy, NULL); if (err < 0) return err; if (!cda[CTA_SEQADJ_CORRECTION_POS]) return -EINVAL; seq->correction_pos = ntohl(nla_get_be32(cda[CTA_SEQADJ_CORRECTION_POS])); if (!cda[CTA_SEQADJ_OFFSET_BEFORE]) return -EINVAL; seq->offset_before = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_BEFORE])); if (!cda[CTA_SEQADJ_OFFSET_AFTER]) return -EINVAL; seq->offset_after = ntohl(nla_get_be32(cda[CTA_SEQADJ_OFFSET_AFTER])); return 0; } static int ctnetlink_change_seq_adj(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_seqadj *seqadj = nfct_seqadj(ct); int ret = 0; if (!seqadj) return 0; spin_lock_bh(&ct->lock); if (cda[CTA_SEQ_ADJ_ORIG]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_ORIGINAL], cda[CTA_SEQ_ADJ_ORIG]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } if (cda[CTA_SEQ_ADJ_REPLY]) { ret = change_seq_adj(&seqadj->seq[IP_CT_DIR_REPLY], cda[CTA_SEQ_ADJ_REPLY]); if (ret < 0) goto err; set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); } spin_unlock_bh(&ct->lock); return 0; err: spin_unlock_bh(&ct->lock); return ret; } static const struct nla_policy synproxy_policy[CTA_SYNPROXY_MAX + 1] = { [CTA_SYNPROXY_ISN] = { .type = NLA_U32 }, [CTA_SYNPROXY_ITS] = { .type = NLA_U32 }, [CTA_SYNPROXY_TSOFF] = { .type = NLA_U32 }, }; static int ctnetlink_change_synproxy(struct nf_conn *ct, const struct nlattr * const cda[]) { struct nf_conn_synproxy *synproxy = nfct_synproxy(ct); struct nlattr *tb[CTA_SYNPROXY_MAX + 1]; int err; if (!synproxy) return 0; err = nla_parse_nested_deprecated(tb, CTA_SYNPROXY_MAX, cda[CTA_SYNPROXY], synproxy_policy, NULL); if (err < 0) return err; if (!tb[CTA_SYNPROXY_ISN] || !tb[CTA_SYNPROXY_ITS] || !tb[CTA_SYNPROXY_TSOFF]) return -EINVAL; synproxy->isn = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ISN])); synproxy->its = ntohl(nla_get_be32(tb[CTA_SYNPROXY_ITS])); synproxy->tsoff = ntohl(nla_get_be32(tb[CTA_SYNPROXY_TSOFF])); return 0; } static int ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_CONNTRACK_LABELS size_t len = nla_len(cda[CTA_LABELS]); const void *mask = cda[CTA_LABELS_MASK]; if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ return -EINVAL; if (mask) { if (nla_len(cda[CTA_LABELS_MASK]) == 0 || nla_len(cda[CTA_LABELS_MASK]) != len) return -EINVAL; mask = nla_data(cda[CTA_LABELS_MASK]); } len /= sizeof(u32); return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); #else return -EOPNOTSUPP; #endif } static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { int err; /* only allow NAT changes and master assignation for new conntracks */ if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST] || cda[CTA_TUPLE_MASTER]) return -EOPNOTSUPP; if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) return err; } if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) return err; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } return 0; } static struct nf_conn * ctnetlink_create_conntrack(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], struct nf_conntrack_tuple *otuple, struct nf_conntrack_tuple *rtuple, u8 u3) { struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; struct nf_conn_tstamp *tstamp; u64 timeout; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) return ERR_PTR(-ENOMEM); if (!cda[CTA_TIMEOUT]) goto err1; timeout = (u64)ntohl(nla_get_be32(cda[CTA_TIMEOUT])) * HZ; if (timeout > INT_MAX) timeout = INT_MAX; ct->timeout = (u32)timeout + nfct_time_stamp; rcu_read_lock(); if (cda[CTA_HELP]) { char *helpname = NULL; struct nlattr *helpinfo = NULL; err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo); if (err < 0) goto err2; helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err1; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err2; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err1; } else { struct nf_conn_help *help; help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help == NULL) { err = -ENOMEM; goto err2; } /* set private helper data if allowed. */ if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); /* disable helper auto-assignment for this entry */ ct->status |= IPS_HELPER; RCU_INIT_POINTER(help->helper, helper); } } else { /* try an implicit helper assignation */ err = __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC); if (err < 0) goto err2; } err = ctnetlink_setup_nat(ct, cda); if (err < 0) goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); nf_ct_labels_ext_add(ct); nfct_seqadj_ext_add(ct); nfct_synproxy_ext_add(ct); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SEQ_ADJ_ORIG] || cda[CTA_SEQ_ADJ_REPLY]) { err = ctnetlink_change_seq_adj(ct, cda); if (err < 0) goto err2; } memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) goto err2; } if (cda[CTA_SYNPROXY]) { err = ctnetlink_change_synproxy(ct, cda); if (err < 0) goto err2; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ctnetlink_change_mark(ct, cda); #endif /* setup master conntrack: this is a confirmed expectation */ if (cda[CTA_TUPLE_MASTER]) { struct nf_conntrack_tuple master; struct nf_conntrack_tuple_hash *master_h; struct nf_conn *master_ct; err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3, NULL); if (err < 0) goto err2; master_h = nf_conntrack_find_get(net, zone, &master); if (master_h == NULL) { err = -ENOENT; goto err2; } master_ct = nf_ct_tuplehash_to_ctrack(master_h); __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } tstamp = nf_conn_tstamp_find(ct); if (tstamp) tstamp->start = ktime_get_real_ns(); err = nf_conntrack_hash_check_insert(ct); if (err < 0) goto err2; rcu_read_unlock(); return ct; err2: rcu_read_unlock(); err1: nf_conntrack_free(ct); return ERR_PTR(err); } static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) return err; if (cda[CTA_TUPLE_ORIG]) { err = ctnetlink_parse_tuple(cda, &otuple, CTA_TUPLE_ORIG, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_REPLY]) { err = ctnetlink_parse_tuple(cda, &rtuple, CTA_TUPLE_REPLY, u3, &zone); if (err < 0) return err; } if (cda[CTA_TUPLE_ORIG]) h = nf_conntrack_find_get(net, &zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) h = nf_conntrack_find_get(net, &zone, &rtuple); if (h == NULL) { err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { enum ip_conntrack_events events; if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; if (otuple.dst.protonum != rtuple.dst.protonum) return -EINVAL; ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); if (IS_ERR(ct)) return PTR_ERR(ct); err = 0; if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = 1 << IPCT_RELATED; else events = 1 << IPCT_NEW; if (cda[CTA_LABELS] && ctnetlink_attach_labels(ct, cda) == 0) events |= (1 << IPCT_LABEL); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY) | events, ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_put(ct); } return err; } /* implicit 'else' */ err = -EEXIST; ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { err = ctnetlink_change_conntrack(ct, cda); if (err == 0) { nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | (1 << IPCT_LABEL) | (1 << IPCT_PROTOINFO) | (1 << IPCT_SEQADJ) | (1 << IPCT_MARK) | (1 << IPCT_SYNPROXY), ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } } nf_ct_put(ct); return err; } static int ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS_CPU); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = AF_UNSPEC; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(cpu); if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) || nla_put_be32(skb, CTA_STATS_INSERT_FAILED, htonl(st->insert_failed)) || nla_put_be32(skb, CTA_STATS_DROP, htonl(st->drop)) || nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) || nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) || nla_put_be32(skb, CTA_STATS_SEARCH_RESTART, htonl(st->search_restart)) || nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE, htonl(st->clash_resolve))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_ct_stat_cpu_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_ct_cpu(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_ct_stat_cpu_dump, }; return netlink_dump_start(ctnl, skb, nlh, &c); } return 0; } static int ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks = atomic_read(&net->ct.count); event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = AF_UNSPEC; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_stat_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct sk_buff *skb2; int err; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) return -ENOMEM; err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) goto free; err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; return 0; free: kfree_skb(skb2); out: /* this avoids a loop in nfnetlink. */ return err == -EAGAIN ? -ENOBUFS : err; } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { [CTA_EXPECT_MASTER] = { .type = NLA_NESTED }, [CTA_EXPECT_TUPLE] = { .type = NLA_NESTED }, [CTA_EXPECT_MASK] = { .type = NLA_NESTED }, [CTA_EXPECT_TIMEOUT] = { .type = NLA_U32 }, [CTA_EXPECT_ID] = { .type = NLA_U32 }, [CTA_EXPECT_HELP_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN - 1 }, [CTA_EXPECT_ZONE] = { .type = NLA_U16 }, [CTA_EXPECT_FLAGS] = { .type = NLA_U32 }, [CTA_EXPECT_CLASS] = { .type = NLA_U32 }, [CTA_EXPECT_NAT] = { .type = NLA_NESTED }, [CTA_EXPECT_FN] = { .type = NLA_NUL_STRING }, }; static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT static size_t ctnetlink_glue_build_size(const struct nf_conn *ct) { return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */ + ctnetlink_secctx_size(ct) #if IS_ENABLED(CONFIG_NF_NAT) + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */ #endif #ifdef CONFIG_NF_CONNTRACK_MARK + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif #ifdef CONFIG_NF_CONNTRACK_ZONES + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE|CTA_TUPLE_ZONE */ #endif + ctnetlink_proto_size(ct) ; } static struct nf_conn *ctnetlink_glue_get_ct(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) { return nf_ct_get(skb, ctinfo); } static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_ORIG) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0) goto nla_put_failure; if (ctnetlink_dump_zone_id(skb, CTA_TUPLE_ZONE, zone, NF_CT_ZONE_DIR_REPL) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (ctnetlink_dump_zone_id(skb, CTA_ZONE, zone, NF_CT_DEFAULT_ZONE_DIR) < 0) goto nla_put_failure; if (ctnetlink_dump_id(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_status(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_timeout(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_protoinfo(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_helpinfo(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_SECMARK if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif if (ct->master && ctnetlink_dump_master(skb, ct) < 0) goto nla_put_failure; if ((ct->status & IPS_SEQ_ADJUST) && ctnetlink_dump_ct_seq_adj(skb, ct) < 0) goto nla_put_failure; if (ctnetlink_dump_ct_synproxy(skb, ct) < 0) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u_int16_t ct_attr, u_int16_t ct_info_attr) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, ct_attr); if (!nest_parms) goto nla_put_failure; if (__ctnetlink_glue_build(skb, ct) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); if (nla_put_be32(skb, ct_info_attr, htonl(ctinfo))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static int ctnetlink_update_status(struct nf_conn *ct, const struct nlattr * const cda[]) { unsigned int status = ntohl(nla_get_be32(cda[CTA_STATUS])); unsigned long d = ct->status ^ status; if (d & IPS_SEEN_REPLY && !(status & IPS_SEEN_REPLY)) /* SEEN_REPLY bit can only be set */ return -EBUSY; if (d & IPS_ASSURED && !(status & IPS_ASSURED)) /* ASSURED bit can only be set */ return -EBUSY; /* This check is less strict than ctnetlink_change_status() * because callers often flip IPS_EXPECTED bits when sending * an NFQA_CT attribute to the kernel. So ignore the * unchangeable bits but do not error out. Also user programs * are allowed to clear the bits that they are allowed to change. */ __ctnetlink_change_status(ct, status, ~status); return 0; } static int ctnetlink_glue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) { int err; if (cda[CTA_TIMEOUT]) { err = ctnetlink_change_timeout(ct, cda); if (err < 0) return err; } if (cda[CTA_STATUS]) { err = ctnetlink_update_status(ct, cda); if (err < 0) return err; } if (cda[CTA_HELP]) { err = ctnetlink_change_helper(ct, cda); if (err < 0) return err; } if (cda[CTA_LABELS]) { err = ctnetlink_attach_labels(ct, cda); if (err < 0) return err; } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) { ctnetlink_change_mark(ct, cda); } #endif return 0; } static int ctnetlink_glue_parse(const struct nlattr *attr, struct nf_conn *ct) { struct nlattr *cda[CTA_MAX+1]; int ret; ret = nla_parse_nested_deprecated(cda, CTA_MAX, attr, ct_nla_policy, NULL); if (ret < 0) return ret; return ctnetlink_glue_parse_ct((const struct nlattr **)cda, ct); } static int ctnetlink_glue_exp_parse(const struct nlattr * const *cda, const struct nf_conn *ct, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { int err; err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE, nf_ct_l3num(ct), NULL); if (err < 0) return err; return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK, nf_ct_l3num(ct), NULL); } static int ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, u32 portid, u32 report) { struct nlattr *cda[CTA_EXPECT_MAX+1]; struct nf_conntrack_tuple tuple, mask; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; int err; err = nla_parse_nested_deprecated(cda, CTA_EXPECT_MAX, attr, exp_nla_policy, NULL); if (err < 0) return err; err = ctnetlink_glue_exp_parse((const struct nlattr * const *)cda, ct, &tuple, &mask); if (err < 0) return err; if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), nf_ct_protonum(ct)); if (helper == NULL) return -EOPNOTSUPP; } exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int diff) { if (!(ct->status & IPS_NAT_MASK)) return; nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff); } static struct nfnl_ct_hook ctnetlink_glue_hook = { .get_ct = ctnetlink_glue_get_ct, .build_size = ctnetlink_glue_build_size, .build = ctnetlink_glue_build, .parse = ctnetlink_glue_parse, .attach_expect = ctnetlink_glue_attach_expect, .seq_adjust = ctnetlink_glue_seqadj, }; #endif /* CONFIG_NETFILTER_NETLINK_GLUE_CT */ /*********************************************************************** * EXPECT ***********************************************************************/ static int ctnetlink_exp_dump_tuple(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, u32 type) { struct nlattr *nest_parms; nest_parms = nla_nest_start(skb, type); if (!nest_parms) goto nla_put_failure; if (ctnetlink_dump_tuples(skb, tuple) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static int ctnetlink_exp_dump_mask(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple_mask *mask) { const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple m; struct nlattr *nest_parms; int ret; memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK); if (!nest_parms) goto nla_put_failure; rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); } rcu_read_unlock(); if (unlikely(ret < 0)) goto nla_put_failure; nla_nest_end(skb, nest_parms); return 0; nla_put_failure: return -1; } static const union nf_inet_addr any_addr; static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { static __read_mostly siphash_key_t exp_id_seed; unsigned long a, b, c, d; net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); a = (unsigned long)exp; b = (unsigned long)exp->helper; c = (unsigned long)exp->master; d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed); #ifdef CONFIG_64BIT return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed); #else return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed); #endif } static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *nest_parms; struct nf_conntrack_tuple nat_tuple = {}; #endif struct nf_ct_helper_expectfn *expfn; if (timeout < 0) timeout = 0; if (ctnetlink_exp_dump_tuple(skb, &exp->tuple, CTA_EXPECT_TUPLE) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_mask(skb, &exp->tuple, &exp->mask) < 0) goto nla_put_failure; if (ctnetlink_exp_dump_tuple(skb, &master->tuplehash[IP_CT_DIR_ORIGINAL].tuple, CTA_EXPECT_MASTER) < 0) goto nla_put_failure; #if IS_ENABLED(CONFIG_NF_NAT) if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT); if (!nest_parms) goto nla_put_failure; if (nla_put_be32(skb, CTA_EXPECT_NAT_DIR, htonl(exp->dir))) goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; if (ctnetlink_exp_dump_tuple(skb, &nat_tuple, CTA_EXPECT_NAT_TUPLE) < 0) goto nla_put_failure; nla_nest_end(skb, nest_parms); } #endif if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) || nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) || nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) || nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class))) goto nla_put_failure; help = nfct_help(master); if (help) { struct nf_conntrack_helper *helper; helper = rcu_dereference(help->helper); if (helper && nla_put_string(skb, CTA_EXPECT_HELP_NAME, helper->name)) goto nla_put_failure; } expfn = nf_ct_helper_expectfn_find_by_symbol(exp->expectfn); if (expfn != NULL && nla_put_string(skb, CTA_EXPECT_FN, expfn->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = exp->tuple.src.l3num; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static int ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) { struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct sk_buff *skb; unsigned int type, group; int flags = 0; if (events & (1 << IPEXP_DESTROY)) { type = IPCTNL_MSG_EXP_DELETE; group = NFNLGRP_CONNTRACK_EXP_DESTROY; } else if (events & (1 << IPEXP_NEW)) { type = IPCTNL_MSG_EXP_NEW; flags = NLM_F_CREATE|NLM_F_EXCL; group = NFNLGRP_CONNTRACK_EXP_NEW; } else return 0; if (!item->report && !nfnetlink_has_listeners(net, group)) return 0; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (skb == NULL) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type); nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = exp->tuple.src.l3num; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = 0; if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); nlmsg_failure: kfree_skb(skb); errout: nfnetlink_set_err(net, 0, 0, -ENOBUFS); return 0; } #endif static int ctnetlink_exp_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); return 0; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (!net_eq(nf_ct_net(exp->master), net)) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } } out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; if (cb->args[0]) return 0; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { if (exp != last) continue; cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { if (!refcount_inc_not_zero(&exp->use)) continue; cb->args[1] = (unsigned long)exp; goto out; } } if (cb->args[1]) { cb->args[1] = 0; goto restart; } cb->args[0] = 1; out: rcu_read_unlock(); if (last) nf_ct_expect_put(last); return skb->len; } static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { int err; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; h = nf_conntrack_find_get(net, &zone, &tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); /* No expectation linked to this connection tracking. */ if (!nfct_help(ct)) { nf_ct_put(ct); return 0; } c.data = ct; err = netlink_dump_start(ctnl, skb, nlh, &c); nf_ct_put(ct); return err; } static int ctnetlink_get_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct sk_buff *skb2; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; if (nlh->nlmsg_flags & NLM_F_DUMP) { if (cda[CTA_EXPECT_MASTER]) return ctnetlink_dump_exp_ct(net, ctnl, skb, nlh, cda, extack); else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, .done = ctnetlink_exp_done, }; return netlink_dump_start(ctnl, skb, nlh, &c); } } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; if (cda[CTA_EXPECT_TUPLE]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); else if (cda[CTA_EXPECT_MASTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, u3, NULL); else return -EINVAL; if (err < 0) return err; exp = nf_ct_expect_find_get(net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } } err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { nf_ct_expect_put(exp); goto out; } rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) goto free; err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; return 0; free: kfree_skb(skb2); out: /* this avoids a loop in nfnetlink. */ return err == -EAGAIN ? -ENOBUFS : err; } static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) { const struct nf_conn_help *m_help; const char *name = data; m_help = nfct_help(exp->master); return strcmp(m_help->helper->name, name) == 0; } static bool expect_iter_all(struct nf_conntrack_expect *exp, void *data) { return true; } static int ctnetlink_del_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; if (cda[CTA_EXPECT_TUPLE]) { /* delete a single expect by tuple */ err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; /* bump usage count to 2 */ exp = nf_ct_expect_find_get(net, &zone, &tuple); if (!exp) return -ENOENT; if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); if (ntohl(id) != (u32)(unsigned long)exp) { nf_ct_expect_put(exp); return -ENOENT; } } /* after list removal, usage count == 1 */ spin_lock_bh(&nf_conntrack_expect_lock); if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } spin_unlock_bh(&nf_conntrack_expect_lock); /* have to put what we 'get' above. * after this line usage count == 0 */ nf_ct_expect_put(exp); } else if (cda[CTA_EXPECT_HELP_NAME]) { char *name = nla_data(cda[CTA_EXPECT_HELP_NAME]); nf_ct_expect_iterate_net(net, expect_iter_name, name, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } else { /* This basically means we have to flush everything*/ nf_ct_expect_iterate_net(net, expect_iter_all, NULL, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } return 0; } static int ctnetlink_change_expect(struct nf_conntrack_expect *x, const struct nlattr * const cda[]) { if (cda[CTA_EXPECT_TIMEOUT]) { if (!del_timer(&x->timeout)) return -ETIME; x->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; add_timer(&x->timeout); } return 0; } static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; static int ctnetlink_parse_expect_nat(const struct nlattr *attr, struct nf_conntrack_expect *exp, u_int8_t u3) { #if IS_ENABLED(CONFIG_NF_NAT) struct nlattr *tb[CTA_EXPECT_NAT_MAX+1]; struct nf_conntrack_tuple nat_tuple = {}; int err; err = nla_parse_nested_deprecated(tb, CTA_EXPECT_NAT_MAX, attr, exp_nat_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_EXPECT_NAT_DIR] || !tb[CTA_EXPECT_NAT_TUPLE]) return -EINVAL; err = ctnetlink_parse_tuple((const struct nlattr * const *)tb, &nat_tuple, CTA_EXPECT_NAT_TUPLE, u3, NULL); if (err < 0) return err; exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); return 0; #else return -EOPNOTSUPP; #endif } static struct nf_conntrack_expect * ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct, struct nf_conntrack_helper *helper, struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *mask) { u_int32_t class = 0; struct nf_conntrack_expect *exp; struct nf_conn_help *help; int err; help = nfct_help(ct); if (!help) return ERR_PTR(-EOPNOTSUPP); if (cda[CTA_EXPECT_CLASS] && helper) { class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS])); if (class > helper->expect_class_max) return ERR_PTR(-EINVAL); } exp = nf_ct_expect_alloc(ct); if (!exp) return ERR_PTR(-ENOMEM); if (cda[CTA_EXPECT_FLAGS]) { exp->flags = ntohl(nla_get_be32(cda[CTA_EXPECT_FLAGS])); exp->flags &= ~NF_CT_EXPECT_USERSPACE; } else { exp->flags = 0; } if (cda[CTA_EXPECT_FN]) { const char *name = nla_data(cda[CTA_EXPECT_FN]); struct nf_ct_helper_expectfn *expfn; expfn = nf_ct_helper_expectfn_find_by_name(name); if (expfn == NULL) { err = -EINVAL; goto err_out; } exp->expectfn = expfn->expectfn; } else exp->expectfn = NULL; exp->class = class; exp->master = ct; exp->helper = helper; exp->tuple = *tuple; exp->mask.src.u3 = mask->src.u3; exp->mask.src.u.all = mask->src.u.all; if (cda[CTA_EXPECT_NAT]) { err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT], exp, nf_ct_l3num(ct)); if (err < 0) goto err_out; } return exp; err_out: nf_ct_expect_put(exp); return ERR_PTR(err); } static int ctnetlink_create_expect(struct net *net, const struct nf_conntrack_zone *zone, const struct nlattr * const cda[], u_int8_t u3, u32 portid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; struct nf_conntrack_helper *helper = NULL; struct nf_conntrack_expect *exp; struct nf_conn *ct; int err; /* caller guarantees that those three CTA_EXPECT_* exist */ err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3, NULL); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3, NULL); if (err < 0) return err; /* Look for master conntrack of this expectation */ h = nf_conntrack_find_get(net, zone, &master_tuple); if (!h) return -ENOENT; ct = nf_ct_tuplehash_to_ctrack(h); rcu_read_lock(); if (cda[CTA_EXPECT_HELP_NAME]) { const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { err = -EOPNOTSUPP; goto err_ct; } rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, u3, nf_ct_protonum(ct)); if (helper) { err = -EAGAIN; goto err_rcu; } rcu_read_unlock(); #endif err = -EOPNOTSUPP; goto err_ct; } } exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto err_rcu; } err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); err_ct: nf_ct_put(ct); return err; } static int ctnetlink_new_expect(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int8_t u3 = nfmsg->nfgen_family; struct nf_conntrack_zone zone; int err; if (!cda[CTA_EXPECT_TUPLE] || !cda[CTA_EXPECT_MASK] || !cda[CTA_EXPECT_MASTER]) return -EINVAL; err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); if (err < 0) return err; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3, NULL); if (err < 0) return err; spin_lock_bh(&nf_conntrack_expect_lock); exp = __nf_ct_expect_find(net, &zone, &tuple); if (!exp) { spin_unlock_bh(&nf_conntrack_expect_lock); err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(net, &zone, cda, u3, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } return err; } err = -EEXIST; if (!(nlh->nlmsg_flags & NLM_F_EXCL)) err = ctnetlink_change_expect(exp, cda); spin_unlock_bh(&nf_conntrack_expect_lock); return err; } static int ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_EXP_GET_STATS_CPU); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; nfmsg = nlmsg_data(nlh); nfmsg->nfgen_family = AF_UNSPEC; nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(cpu); if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nla_put_failure: nlmsg_failure: nlmsg_cancel(skb, nlh); return -1; } static int ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) { int cpu; struct net *net = sock_net(skb->sk); if (cb->args[0] == nr_cpu_ids) return 0; for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) { const struct ip_conntrack_stat *st; if (!cpu_possible(cpu)) continue; st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; } cb->args[0] = cpu; return skb->len; } static int ctnetlink_stat_exp_cpu(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[], struct netlink_ext_ack *extack) { if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = ctnetlink_exp_stat_cpu_dump, }; return netlink_dump_start(ctnl, skb, nlh, &c); } return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS static struct nf_ct_event_notifier ctnl_notifier = { .fcn = ctnetlink_conntrack_event, }; static struct nf_exp_event_notifier ctnl_notifier_exp = { .fcn = ctnetlink_expect_event, }; #endif static const struct nfnl_callback ctnl_cb[IPCTNL_MSG_MAX] = { [IPCTNL_MSG_CT_NEW] = { .call = ctnetlink_new_conntrack, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET] = { .call = ctnetlink_get_conntrack, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_DELETE] = { .call = ctnetlink_del_conntrack, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_CTRZERO] = { .call = ctnetlink_get_conntrack, .attr_count = CTA_MAX, .policy = ct_nla_policy }, [IPCTNL_MSG_CT_GET_STATS_CPU] = { .call = ctnetlink_stat_ct_cpu }, [IPCTNL_MSG_CT_GET_STATS] = { .call = ctnetlink_stat_ct }, [IPCTNL_MSG_CT_GET_DYING] = { .call = ctnetlink_get_ct_dying }, [IPCTNL_MSG_CT_GET_UNCONFIRMED] = { .call = ctnetlink_get_ct_unconfirmed }, }; static const struct nfnl_callback ctnl_exp_cb[IPCTNL_MSG_EXP_MAX] = { [IPCTNL_MSG_EXP_GET] = { .call = ctnetlink_get_expect, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_NEW] = { .call = ctnetlink_new_expect, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_DELETE] = { .call = ctnetlink_del_expect, .attr_count = CTA_EXPECT_MAX, .policy = exp_nla_policy }, [IPCTNL_MSG_EXP_GET_STATS_CPU] = { .call = ctnetlink_stat_exp_cpu }, }; static const struct nfnetlink_subsystem ctnl_subsys = { .name = "conntrack", .subsys_id = NFNL_SUBSYS_CTNETLINK, .cb_count = IPCTNL_MSG_MAX, .cb = ctnl_cb, }; static const struct nfnetlink_subsystem ctnl_exp_subsys = { .name = "conntrack_expect", .subsys_id = NFNL_SUBSYS_CTNETLINK_EXP, .cb_count = IPCTNL_MSG_EXP_MAX, .cb = ctnl_exp_cb, }; MODULE_ALIAS("ip_conntrack_netlink"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP); static int __net_init ctnetlink_net_init(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS int ret; ret = nf_conntrack_register_notifier(net, &ctnl_notifier); if (ret < 0) { pr_err("ctnetlink_init: cannot register notifier.\n"); goto err_out; } ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp); if (ret < 0) { pr_err("ctnetlink_init: cannot expect register notifier.\n"); goto err_unreg_notifier; } #endif return 0; #ifdef CONFIG_NF_CONNTRACK_EVENTS err_unreg_notifier: nf_conntrack_unregister_notifier(net, &ctnl_notifier); err_out: return ret; #endif } static void ctnetlink_net_exit(struct net *net) { #ifdef CONFIG_NF_CONNTRACK_EVENTS nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp); nf_conntrack_unregister_notifier(net, &ctnl_notifier); #endif } static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); /* wait for other cpus until they are done with ctnl_notifiers */ synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { .init = ctnetlink_net_init, .exit_batch = ctnetlink_net_exit_batch, }; static int __init ctnetlink_init(void) { int ret; ret = nfnetlink_subsys_register(&ctnl_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register with nfnetlink.\n"); goto err_out; } ret = nfnetlink_subsys_register(&ctnl_exp_subsys); if (ret < 0) { pr_err("ctnetlink_init: cannot register exp with nfnetlink.\n"); goto err_unreg_subsys; } ret = register_pernet_subsys(&ctnetlink_net_ops); if (ret < 0) { pr_err("ctnetlink_init: cannot register pernet operations\n"); goto err_unreg_exp_subsys; } #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT /* setup interaction between nf_queue and nf_conntrack_netlink. */ RCU_INIT_POINTER(nfnl_ct_hook, &ctnetlink_glue_hook); #endif return 0; err_unreg_exp_subsys: nfnetlink_subsys_unregister(&ctnl_exp_subsys); err_unreg_subsys: nfnetlink_subsys_unregister(&ctnl_subsys); err_out: return ret; } static void __exit ctnetlink_exit(void) { unregister_pernet_subsys(&ctnetlink_net_ops); nfnetlink_subsys_unregister(&ctnl_exp_subsys); nfnetlink_subsys_unregister(&ctnl_subsys); #ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT RCU_INIT_POINTER(nfnl_ct_hook, NULL); #endif synchronize_rcu(); } module_init(ctnetlink_init); module_exit(ctnetlink_exit); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/root.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc root directory handling functions */ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/stat.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/pid_namespace.h> #include <linux/fs_parser.h> #include <linux/cred.h> #include <linux/magic.h> #include <linux/slab.h> #include "internal.h" struct proc_fs_context { struct pid_namespace *pid_ns; unsigned int mask; enum proc_hidepid hidepid; int gid; enum proc_pidonly pidonly; }; enum proc_param { Opt_gid, Opt_hidepid, Opt_subset, }; static const struct fs_parameter_spec proc_fs_parameters[] = { fsparam_u32("gid", Opt_gid), fsparam_string("hidepid", Opt_hidepid), fsparam_string("subset", Opt_subset), {} }; static inline int valid_hidepid(unsigned int value) { return (value == HIDEPID_OFF || value == HIDEPID_NO_ACCESS || value == HIDEPID_INVISIBLE || value == HIDEPID_NOT_PTRACEABLE); } static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid); struct fs_parse_result result; int base = (unsigned long)hidepid_u32_spec.data; if (param->type != fs_value_is_string) return invalf(fc, "proc: unexpected type of hidepid value\n"); if (!kstrtouint(param->string, base, &result.uint_32)) { if (!valid_hidepid(result.uint_32)) return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); ctx->hidepid = result.uint_32; return 0; } if (!strcmp(param->string, "off")) ctx->hidepid = HIDEPID_OFF; else if (!strcmp(param->string, "noaccess")) ctx->hidepid = HIDEPID_NO_ACCESS; else if (!strcmp(param->string, "invisible")) ctx->hidepid = HIDEPID_INVISIBLE; else if (!strcmp(param->string, "ptraceable")) ctx->hidepid = HIDEPID_NOT_PTRACEABLE; else return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string); return 0; } static int proc_parse_subset_param(struct fs_context *fc, char *value) { struct proc_fs_context *ctx = fc->fs_private; while (value) { char *ptr = strchr(value, ','); if (ptr != NULL) *ptr++ = '\0'; if (*value != '\0') { if (!strcmp(value, "pid")) { ctx->pidonly = PROC_PIDONLY_ON; } else { return invalf(fc, "proc: unsupported subset option - %s\n", value); } } value = ptr; } return 0; } static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct proc_fs_context *ctx = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, proc_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_gid: ctx->gid = result.uint_32; break; case Opt_hidepid: if (proc_parse_hidepid_param(fc, param)) return -EINVAL; break; case Opt_subset: if (proc_parse_subset_param(fc, param->string) < 0) return -EINVAL; break; default: return -EINVAL; } ctx->mask |= 1 << opt; return 0; } static void proc_apply_options(struct proc_fs_info *fs_info, struct fs_context *fc, struct user_namespace *user_ns) { struct proc_fs_context *ctx = fc->fs_private; if (ctx->mask & (1 << Opt_gid)) fs_info->pid_gid = make_kgid(user_ns, ctx->gid); if (ctx->mask & (1 << Opt_hidepid)) fs_info->hide_pid = ctx->hidepid; if (ctx->mask & (1 << Opt_subset)) fs_info->pidonly = ctx->pidonly; } static int proc_fill_super(struct super_block *s, struct fs_context *fc) { struct proc_fs_context *ctx = fc->fs_private; struct inode *root_inode; struct proc_fs_info *fs_info; int ret; fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL); if (!fs_info) return -ENOMEM; fs_info->pid_ns = get_pid_ns(ctx->pid_ns); proc_apply_options(fs_info, fc, current_user_ns()); /* User space would break if executables or devices appear on proc */ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV; s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = PROC_SUPER_MAGIC; s->s_op = &proc_sops; s->s_time_gran = 1; s->s_fs_info = fs_info; /* * procfs isn't actually a stacking filesystem; however, there is * too much magic going on inside it to permit stacking things on * top of it */ s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; /* procfs dentries and inodes don't require IO to create */ s->s_shrink.seeks = 0; pde_get(&proc_root); root_inode = proc_get_inode(s, &proc_root); if (!root_inode) { pr_err("proc_fill_super: get root inode failed\n"); return -ENOMEM; } s->s_root = d_make_root(root_inode); if (!s->s_root) { pr_err("proc_fill_super: allocate dentry failed\n"); return -ENOMEM; } ret = proc_setup_self(s); if (ret) { return ret; } return proc_setup_thread_self(s); } static int proc_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct proc_fs_info *fs_info = proc_sb_info(sb); sync_filesystem(sb); proc_apply_options(fs_info, fc, current_user_ns()); return 0; } static int proc_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, proc_fill_super); } static void proc_fs_context_free(struct fs_context *fc) { struct proc_fs_context *ctx = fc->fs_private; put_pid_ns(ctx->pid_ns); kfree(ctx); } static const struct fs_context_operations proc_fs_context_ops = { .free = proc_fs_context_free, .parse_param = proc_parse_param, .get_tree = proc_get_tree, .reconfigure = proc_reconfigure, }; static int proc_init_fs_context(struct fs_context *fc) { struct proc_fs_context *ctx; ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->pid_ns = get_pid_ns(task_active_pid_ns(current)); put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->pid_ns->user_ns); fc->fs_private = ctx; fc->ops = &proc_fs_context_ops; return 0; } static void proc_kill_sb(struct super_block *sb) { struct proc_fs_info *fs_info = proc_sb_info(sb); if (!fs_info) { kill_anon_super(sb); return; } dput(fs_info->proc_self); dput(fs_info->proc_thread_self); kill_anon_super(sb); put_pid_ns(fs_info->pid_ns); kfree(fs_info); } static struct file_system_type proc_fs_type = { .name = "proc", .init_fs_context = proc_init_fs_context, .parameters = proc_fs_parameters, .kill_sb = proc_kill_sb, .fs_flags = FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM, }; void __init proc_root_init(void) { proc_init_kmemcache(); set_proc_pid_nlink(); proc_self_init(); proc_thread_self_init(); proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */ #if defined(CONFIG_SUN_OPENPROMFS) || defined(CONFIG_SUN_OPENPROMFS_MODULE) /* just give it a mountpoint */ proc_create_mount_point("openprom"); #endif proc_tty_init(); proc_mkdir("bus", NULL); proc_sys_init(); register_filesystem(&proc_fs_type); } static int proc_root_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { generic_fillattr(d_inode(path->dentry), stat); stat->nlink = proc_root.nlink + nr_processes(); return 0; } static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); } static int proc_root_readdir(struct file *file, struct dir_context *ctx) { if (ctx->pos < FIRST_PROCESS_ENTRY) { int error = proc_readdir(file, ctx); if (unlikely(error <= 0)) return error; ctx->pos = FIRST_PROCESS_ENTRY; } return proc_pid_readdir(file, ctx); } /* * The root /proc directory is special, as it has the * <pid> directories. Thus we don't use the generic * directory handling functions for that.. */ static const struct file_operations proc_root_operations = { .read = generic_read_dir, .iterate_shared = proc_root_readdir, .llseek = generic_file_llseek, }; /* * proc root can do almost nothing.. */ static const struct inode_operations proc_root_inode_operations = { .lookup = proc_root_lookup, .getattr = proc_root_getattr, }; /* * This is the root "inode" in the /proc tree.. */ struct proc_dir_entry proc_root = { .low_ino = PROC_ROOT_INO, .namelen = 5, .mode = S_IFDIR | S_IRUGO | S_IXUGO, .nlink = 2, .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_dir_ops = &proc_root_operations, .parent = &proc_root, .subdir = RB_ROOT, .name = "/proc", }; |
| 3991 3989 208 210 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | // SPDX-License-Identifier: GPL-2.0-only /* * Lock-less NULL terminated single linked list * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/llist.h> /** * llist_add_batch - add several linked entries in batch * @new_first: first entry in batch to be added * @new_last: last entry in batch to be added * @head: the head for your lock-less list * * Return whether list is empty before adding. */ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head) { struct llist_node *first; do { new_last->next = first = READ_ONCE(head->first); } while (cmpxchg(&head->first, first, new_first) != first); return !first; } EXPORT_SYMBOL_GPL(llist_add_batch); /** * llist_del_first - delete the first entry of lock-less list * @head: the head for your lock-less list * * If list is empty, return NULL, otherwise, return the first entry * deleted, this is the newest added one. * * Only one llist_del_first user can be used simultaneously with * multiple llist_add users without lock. Because otherwise * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, * llist_add) sequence in another user may change @head->first->next, * but keep @head->first. If multiple consumers are needed, please * use llist_del_all or use lock between consumers. */ struct llist_node *llist_del_first(struct llist_head *head) { struct llist_node *entry, *old_entry, *next; entry = smp_load_acquire(&head->first); for (;;) { if (entry == NULL) return NULL; old_entry = entry; next = READ_ONCE(entry->next); entry = cmpxchg(&head->first, old_entry, next); if (entry == old_entry) break; } return entry; } EXPORT_SYMBOL_GPL(llist_del_first); /** * llist_reverse_order - reverse order of a llist chain * @head: first item of the list to be reversed * * Reverse the order of a chain of llist entries and return the * new first entry. */ struct llist_node *llist_reverse_order(struct llist_node *head) { struct llist_node *new_head = NULL; while (head) { struct llist_node *tmp = head; head = head->next; tmp->next = new_head; new_head = tmp; } return new_head; } EXPORT_SYMBOL_GPL(llist_reverse_order); |
| 33 48 50 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/bitops.h> #include <asm/word-at-a-time.h> /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the * address space maximum. * * Return 0 for exceptions (which includes hitting the address * space maximum), or 'count+1' if hitting the user-supplied * maximum count. * * NOTE! We can sometimes overshoot the user-supplied maximum * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; unsigned long c; /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align; unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { unsigned long data; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); /* We already handled 'unsigned long' bytes. Did we do it all ? */ if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, return the marker for "too long". */ if (res >= count) return count+1; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ efault: return 0; } /** * strnlen_user: - Get the size of a user string INCLUDING final NUL. * @str: The string to measure. * @count: Maximum count (including NUL character) * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * NOTE! You should basically never use this function. There is * almost never any valid case for using the length of a user space * string, since the string can be changed at any time by other * threads. Use "strncpy_from_user()" instead to get a stable copy * of the string. */ long strnlen_user(const char __user *str, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(str); 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(str, max)) { retval = do_strnlen_user(str, count, max); user_read_access_end(); return retval; } } return 0; } EXPORT_SYMBOL(strnlen_user); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This file provides wrappers with sanitizer instrumentation for non-atomic * bit operations. * * To use this functionality, an arch's bitops.h file needs to define each of * the below bit operations with an arch_ prefix (e.g. arch_set_bit(), * arch___set_bit(), etc.). */ #ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H #include <linux/instrumented.h> /** * __set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * * Unlike set_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static inline void __set_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); } /** * __clear_bit - Clears a bit in memory * @nr: the bit to clear * @addr: the address to start counting from * * Unlike clear_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static inline void __clear_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); } /** * __change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * * Unlike change_bit(), this function is non-atomic. If it is called on the same * region of memory concurrently, the effect may be that only one operation * succeeds. */ static inline void __change_bit(long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); } static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* * We treat non-atomic read-write bitops a little more special. * Given the operations here only modify a single bit, assuming * non-atomicity of the writer is sufficient may be reasonable * for certain usage (and follows the permissible nature of the * assume-plain-writes-atomic rule): * 1. report read-modify-write races -> check read; * 2. do not report races with marked readers, but do report * races with unmarked readers -> check "atomic" write. */ kcsan_check_read(addr + BIT_WORD(nr), sizeof(long)); /* * Use generic write instrumentation, in case other sanitizers * or tools are enabled alongside KCSAN. */ instrument_write(addr + BIT_WORD(nr), sizeof(long)); } else { instrument_read_write(addr + BIT_WORD(nr), sizeof(long)); } } /** * __test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } /** * __test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } /** * __test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } /** * test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static inline bool test_bit(long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ |
| 177 4 5 3 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SOCK_DIAG_H__ #define __SOCK_DIAG_H__ #include <linux/netlink.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> struct sk_buff; struct nlmsghdr; struct sock; struct sock_diag_handler { __u8 family; int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh); int (*get_info)(struct sk_buff *skb, struct sock *sk); int (*destroy)(struct sk_buff *skb, struct nlmsghdr *nlh); }; int sock_diag_register(const struct sock_diag_handler *h); void sock_diag_unregister(const struct sock_diag_handler *h); void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)); u64 __sock_gen_cookie(struct sock *sk); static inline u64 sock_gen_cookie(struct sock *sk) { u64 cookie; preempt_disable(); cookie = __sock_gen_cookie(sk); preempt_enable(); return cookie; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attr); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype); static inline enum sknetlink_groups sock_diag_destroy_group(const struct sock *sk) { switch (sk->sk_family) { case AF_INET: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET_UDP_DESTROY; default: return SKNLGRP_NONE; } case AF_INET6: if (sk->sk_type == SOCK_RAW) return SKNLGRP_NONE; switch (sk->sk_protocol) { case IPPROTO_TCP: return SKNLGRP_INET6_TCP_DESTROY; case IPPROTO_UDP: return SKNLGRP_INET6_UDP_DESTROY; default: return SKNLGRP_NONE; } default: return SKNLGRP_NONE; } } static inline bool sock_diag_has_destroy_listeners(const struct sock *sk) { const struct net *n = sock_net(sk); const enum sknetlink_groups group = sock_diag_destroy_group(sk); return group != SKNLGRP_NONE && n->diag_nlsk && netlink_has_listeners(n->diag_nlsk, group); } void sock_diag_broadcast_destroy(struct sock *sk); int sock_diag_destroy(struct sock *sk, int err); #endif |
| 109 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_NULLS_H #define _LINUX_RCULIST_NULLS_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list_nulls.h> #include <linux/rcupdate.h> /** * hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_nulls_add_head_rcu() or * hlist_nulls_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_nulls_for_each_entry_rcu(). */ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * hlist_nulls_first_rcu - returns the first element of the hash list. * @head: the head of the list. */ #define hlist_nulls_first_rcu(head) \ (*((struct hlist_nulls_node __rcu __force **)&(head)->first)) /** * hlist_nulls_next_rcu - returns the element of the list after @node. * @node: element of the list. */ #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_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_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry(). */ static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_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_nulls, * 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_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_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_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_nulls_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_nulls, * 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_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_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_nulls_add_tail_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; !is_a_nulls(i); i = i->next) last = i; if (last) { n->next = last->next; n->pprev = &last->next; rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_nulls_add_head_rcu(n, h); } } /* after that hlist_nulls_del will work */ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) { n->pprev = &n->next; n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); } /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. * * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] * [1] Documentation/core-api/atomic_ops.rst around line 114 * [2] Documentation/RCU/rculist_nulls.rst around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) /** * hlist_nulls_for_each_entry_safe - * iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. */ #define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif |
| 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/udp.h> #include <linux/seq_file.h> #include <linux/skbuff.h> #include <linux/ipv6.h> #include <net/ip6_checksum.h> #include <net/checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_log.h> #include <net/netfilter/ipv4/nf_conntrack_ipv4.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> static const unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_UNREPLIED] = 30*HZ, [UDP_CT_REPLIED] = 120*HZ, }; static unsigned int *udp_get_timeouts(struct net *net) { return nf_udp_pernet(net)->timeouts; } static void udp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state->net, state->pf, IPPROTO_UDP, "%s", msg); } static bool udp_error(struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { unsigned int udplen = skb->len - dataoff; const struct udphdr *hdr; struct udphdr _hdr; /* Header is too small? */ hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (!hdr) { udp_error_log(skb, state, "short packet"); return true; } /* Truncated/malformed packets */ if (ntohs(hdr->len) > udplen || ntohs(hdr->len) < sizeof(*hdr)) { udp_error_log(skb, state, "truncated/malformed packet"); return true; } /* Packet with no checksum */ if (!hdr->check) return false; /* Checksum invalid? Ignore. * We skip checking packets on the outgoing path * because the checksum is assumed to be correct. * FIXME: Source route IP option packets --RR */ if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && nf_checksum(skb, state->hook, dataoff, IPPROTO_UDP, state->pf)) { udp_error_log(skb, state, "bad checksum"); return true; } return false; } /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { unsigned int *timeouts; if (udp_error(skb, dataoff, state)) return -NF_ACCEPT; timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = udp_get_timeouts(nf_ct_net(ct)); if (!nf_ct_is_confirmed(ct)) ct->proto.udp.stream_ts = 2 * HZ + jiffies; /* If we've seen traffic both ways, this is some kind of UDP * stream. Set Assured. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { unsigned long extra = timeouts[UDP_CT_UNREPLIED]; bool stream = false; /* Still active after two seconds? Extend timeout. */ if (time_after(jiffies, ct->proto.udp.stream_ts)) { extra = timeouts[UDP_CT_REPLIED]; stream = true; } nf_ct_refresh_acct(ct, ctinfo, skb, extra); /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ if (unlikely((ct->status & IPS_NAT_CLASH))) return NF_ACCEPT; /* Also, more likely to be important, and not a probe */ if (stream && !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } #ifdef CONFIG_NF_CT_PROTO_UDPLITE static void udplite_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state->net, state->pf, IPPROTO_UDPLITE, "%s", msg); } static bool udplite_error(struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { unsigned int udplen = skb->len - dataoff; const struct udphdr *hdr; struct udphdr _hdr; unsigned int cscov; /* Header is too small? */ hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (!hdr) { udplite_error_log(skb, state, "short packet"); return true; } cscov = ntohs(hdr->len); if (cscov == 0) { cscov = udplen; } else if (cscov < sizeof(*hdr) || cscov > udplen) { udplite_error_log(skb, state, "invalid checksum coverage"); return true; } /* UDPLITE mandates checksums */ if (!hdr->check) { udplite_error_log(skb, state, "checksum missing"); return true; } /* Checksum invalid? Ignore. */ if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && nf_checksum_partial(skb, state->hook, dataoff, cscov, IPPROTO_UDP, state->pf)) { udplite_error_log(skb, state, "bad checksum"); return true; } return false; } /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udplite_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { unsigned int *timeouts; if (udplite_error(skb, dataoff, state)) return -NF_ACCEPT; timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = udp_get_timeouts(nf_ct_net(ct)); /* If we've seen traffic both ways, this is some kind of UDP stream. Extend timeout. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_REPLIED]); if (unlikely((ct->status & IPS_NAT_CLASH))) return NF_ACCEPT; /* Also, more likely to be important, and not a probe */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; struct nf_udp_net *un = nf_udp_pernet(net); if (!timeouts) timeouts = un->timeouts; /* set default timeouts for UDP. */ timeouts[UDP_CT_UNREPLIED] = un->timeouts[UDP_CT_UNREPLIED]; timeouts[UDP_CT_REPLIED] = un->timeouts[UDP_CT_REPLIED]; if (tb[CTA_TIMEOUT_UDP_UNREPLIED]) { timeouts[UDP_CT_UNREPLIED] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDP_UNREPLIED])) * HZ; } if (tb[CTA_TIMEOUT_UDP_REPLIED]) { timeouts[UDP_CT_REPLIED] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_UDP_REPLIED])) * HZ; } return 0; } static int udp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; if (nla_put_be32(skb, CTA_TIMEOUT_UDP_UNREPLIED, htonl(timeouts[UDP_CT_UNREPLIED] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_UDP_REPLIED, htonl(timeouts[UDP_CT_REPLIED] / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_udp_init_net(struct net *net) { struct nf_udp_net *un = nf_udp_pernet(net); int i; for (i = 0; i < UDP_CT_MAX; i++) un->timeouts[i] = udp_timeouts[i]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = { .l4proto = IPPROTO_UDP, .allow_clash = true, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_UDP_MAX, .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; #ifdef CONFIG_NF_CT_PROTO_UDPLITE const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite = { .l4proto = IPPROTO_UDPLITE, .allow_clash = true, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_UDP_MAX, .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; #endif |
| 233 23 2 1 2 23 18 1 14 13 23 23 23 23 13 1 14 14 20 20 20 2 18 18 12 8 23 23 220 220 7 220 220 1119 1119 1119 1119 903 903 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * User-space Probes (UProbes) * * Copyright (C) IBM Corporation, 2008-2012 * Authors: * Srikar Dronamraju * Jim Keniston * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> #include <linux/highmem.h> #include <linux/pagemap.h> /* read_mapping_page */ #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ #include <linux/mmu_notifier.h> /* set_pte_at_notify */ #include <linux/swap.h> /* try_to_free_swap */ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ #include "../../mm/internal.h" /* munlock_vma_page */ #include <linux/percpu-rwsem.h> #include <linux/task_work.h> #include <linux/shmem_fs.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE static struct rb_root uprobes_tree = RB_ROOT; /* * allows us to skip the uprobe_mmap if there are no uprobe events active * at this time. Probably a fine grained per inode count is better? */ #define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree) static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 /* serialize uprobe->pending_list */ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; #define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) DEFINE_STATIC_PERCPU_RWSEM(dup_mmap_sem); /* Have a copy of original instruction */ #define UPROBE_COPY_INSN 0 struct uprobe { struct rb_node rb_node; /* node in the rb tree */ refcount_t ref; struct rw_semaphore register_rwsem; struct rw_semaphore consumer_rwsem; struct list_head pending_list; struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ loff_t offset; loff_t ref_ctr_offset; unsigned long flags; /* * The generic code assumes that it has two members of unknown type * owned by the arch-specific code: * * insn - copy_insn() saves the original instruction here for * arch_uprobe_analyze_insn(). * * ixol - potentially modified instruction to execute out of * line, copied to xol_area by xol_get_insn_slot(). */ struct arch_uprobe arch; }; struct delayed_uprobe { struct list_head list; struct uprobe *uprobe; struct mm_struct *mm; }; static DEFINE_MUTEX(delayed_uprobe_lock); static LIST_HEAD(delayed_uprobe_list); /* * Execute out of line area: anonymous executable mapping installed * by the probed task to execute the copy of the original instruction * mangled by set_swbp(). * * On a breakpoint hit, thread contests for a slot. It frees the * slot after singlestep. Currently a fixed number of slots are * allocated. */ struct xol_area { wait_queue_head_t wq; /* if all slots are busy */ atomic_t slot_count; /* number of in-use slots */ unsigned long *bitmap; /* 0 = free slot */ struct vm_special_mapping xol_mapping; struct page *pages[2]; /* * We keep the vma's vm_start rather than a pointer to the vma * itself. The probed process or a naughty kernel module could make * the vma go away, and we must handle that reasonably gracefully. */ unsigned long vaddr; /* Page(s) of instruction slots */ }; /* * valid_vma: Verify if the specified vma is an executable vma * Relax restrictions while unregistering: vm_flags might have * changed after breakpoint was inserted. * - is_register: indicates if we are in register context. * - Return 1 if the specified virtual address is in an * executable vma. */ static bool valid_vma(struct vm_area_struct *vma, bool is_register) { vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE; if (is_register) flags |= VM_WRITE; return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC; } static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset) { return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT); } static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr) { return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start); } /** * __replace_page - replace page in vma by new page. * based on replace_page in mm/ksm.c * * @vma: vma that holds the pte pointing to page * @addr: address the old @page is mapped at * @old_page: the page we are replacing by new_page * @new_page: the modified page we replace page by * * If @new_page is NULL, only unmap @old_page. * * Returns 0 on success, negative error code otherwise. */ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, struct page *old_page, struct page *new_page) { struct mm_struct *mm = vma->vm_mm; struct page_vma_mapped_walk pvmw = { .page = compound_head(old_page), .vma = vma, .address = addr, }; int err; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, addr + PAGE_SIZE); if (new_page) { err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); if (err) return err; } /* For try_to_free_swap() and munlock_vma_page() below */ lock_page(old_page); mmu_notifier_invalidate_range_start(&range); err = -EAGAIN; if (!page_vma_mapped_walk(&pvmw)) goto unlock; VM_BUG_ON_PAGE(addr != pvmw.address, old_page); if (new_page) { get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ dec_mm_counter(mm, MM_ANONPAGES); if (!PageAnon(old_page)) { dec_mm_counter(mm, mm_counter_file(old_page)); inc_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(*pvmw.pte)); ptep_clear_flush_notify(vma, addr, pvmw.pte); if (new_page) set_pte_at_notify(mm, addr, pvmw.pte, mk_pte(new_page, vma->vm_page_prot)); page_remove_rmap(old_page, false); if (!page_mapped(old_page)) try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); err = 0; unlock: mmu_notifier_invalidate_range_end(&range); unlock_page(old_page); return err; } /** * is_swbp_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_swbp_insn * Returns true if @insn is a breakpoint instruction. */ bool __weak is_swbp_insn(uprobe_opcode_t *insn) { return *insn == UPROBE_SWBP_INSN; } /** * is_trap_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_trap_insn * Returns true if @insn is a breakpoint instruction. * * This function is needed for the case where an architecture has multiple * trap instructions (like powerpc). */ bool __weak is_trap_insn(uprobe_opcode_t *insn) { return is_swbp_insn(insn); } static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len) { void *kaddr = kmap_atomic(page); memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len); kunmap_atomic(kaddr); } static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len) { void *kaddr = kmap_atomic(page); memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len); kunmap_atomic(kaddr); } static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode) { uprobe_opcode_t old_opcode; bool is_swbp; /* * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here. * We do not check if it is any other 'trap variant' which could * be conditional trap instruction such as the one powerpc supports. * * The logic is that we do not care if the underlying instruction * is a trap variant; uprobes always wins over any other (gdb) * breakpoint. */ copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE); is_swbp = is_swbp_insn(&old_opcode); if (is_swbp_insn(new_opcode)) { if (is_swbp) /* register: already installed? */ return 0; } else { if (!is_swbp) /* unregister: was it changed by us? */ return 0; } return 1; } static struct delayed_uprobe * delayed_uprobe_check(struct uprobe *uprobe, struct mm_struct *mm) { struct delayed_uprobe *du; list_for_each_entry(du, &delayed_uprobe_list, list) if (du->uprobe == uprobe && du->mm == mm) return du; return NULL; } static int delayed_uprobe_add(struct uprobe *uprobe, struct mm_struct *mm) { struct delayed_uprobe *du; if (delayed_uprobe_check(uprobe, mm)) return 0; du = kzalloc(sizeof(*du), GFP_KERNEL); if (!du) return -ENOMEM; du->uprobe = uprobe; du->mm = mm; list_add(&du->list, &delayed_uprobe_list); return 0; } static void delayed_uprobe_delete(struct delayed_uprobe *du) { if (WARN_ON(!du)) return; list_del(&du->list); kfree(du); } static void delayed_uprobe_remove(struct uprobe *uprobe, struct mm_struct *mm) { struct list_head *pos, *q; struct delayed_uprobe *du; if (!uprobe && !mm) return; list_for_each_safe(pos, q, &delayed_uprobe_list) { du = list_entry(pos, struct delayed_uprobe, list); if (uprobe && du->uprobe != uprobe) continue; if (mm && du->mm != mm) continue; delayed_uprobe_delete(du); } } static bool valid_ref_ctr_vma(struct uprobe *uprobe, struct vm_area_struct *vma) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->ref_ctr_offset); return uprobe->ref_ctr_offset && vma->vm_file && file_inode(vma->vm_file) == uprobe->inode && (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && vma->vm_start <= vaddr && vma->vm_end > vaddr; } static struct vm_area_struct * find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm) { struct vm_area_struct *tmp; for (tmp = mm->mmap; tmp; tmp = tmp->vm_next) if (valid_ref_ctr_vma(uprobe, tmp)) return tmp; return NULL; } static int __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d) { void *kaddr; struct page *page; struct vm_area_struct *vma; int ret; short *ptr; if (!vaddr || !d) return -EINVAL; ret = get_user_pages_remote(mm, vaddr, 1, FOLL_WRITE, &page, &vma, NULL); if (unlikely(ret <= 0)) { /* * We are asking for 1 page. If get_user_pages_remote() fails, * it may return 0, in that case we have to return error. */ return ret == 0 ? -EBUSY : ret; } kaddr = kmap_atomic(page); ptr = kaddr + (vaddr & ~PAGE_MASK); if (unlikely(*ptr + d < 0)) { pr_warn("ref_ctr going negative. vaddr: 0x%lx, " "curr val: %d, delta: %d\n", vaddr, *ptr, d); ret = -EINVAL; goto out; } *ptr += d; ret = 0; out: kunmap_atomic(kaddr); put_page(page); return ret; } static void update_ref_ctr_warn(struct uprobe *uprobe, struct mm_struct *mm, short d) { pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) uprobe->ref_ctr_offset, mm); } static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, short d) { struct vm_area_struct *rc_vma; unsigned long rc_vaddr; int ret = 0; rc_vma = find_ref_ctr_vma(uprobe, mm); if (rc_vma) { rc_vaddr = offset_to_vaddr(rc_vma, uprobe->ref_ctr_offset); ret = __update_ref_ctr(mm, rc_vaddr, d); if (ret) update_ref_ctr_warn(uprobe, mm, d); if (d > 0) return ret; } mutex_lock(&delayed_uprobe_lock); if (d > 0) ret = delayed_uprobe_add(uprobe, mm); else delayed_uprobe_remove(uprobe, mm); mutex_unlock(&delayed_uprobe_lock); return ret; } /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for * the architecture. If an arch has variable length instruction and the * breakpoint instruction is not of the smallest length instruction * supported by that architecture then we need to modify is_trap_at_addr and * uprobe_write_opcode accordingly. This would never be a problem for archs * that have fixed length instructions. * * uprobe_write_opcode - write the opcode at a given virtual address. * @mm: the probed process address space. * @vaddr: the virtual address to store the opcode. * @opcode: opcode to be written at @vaddr. * * Called with mm->mmap_lock held for write. * Return 0 (success) or a negative errno. */ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { struct uprobe *uprobe; struct page *old_page, *new_page; struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; bool orig_page_huge = false; unsigned int gup_flags = FOLL_FORCE; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); retry: if (is_register) gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ ret = get_user_pages_remote(mm, vaddr, 1, gup_flags, &old_page, &vma, NULL); if (ret <= 0) return ret; ret = verify_opcode(old_page, vaddr, &opcode); if (ret <= 0) goto put_old; if (WARN(!is_register && PageCompound(old_page), "uprobe unregister should never work on compound page\n")) { ret = -EINVAL; goto put_old; } /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); if (ret) goto put_old; ref_ctr_updated = 1; } ret = 0; if (!is_register && !PageAnon(old_page)) goto put_old; ret = anon_vma_prepare(vma); if (ret) goto put_old; ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) goto put_old; __SetPageUptodate(new_page); copy_highpage(new_page, old_page); copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); if (!is_register) { struct page *orig_page; pgoff_t index; VM_BUG_ON_PAGE(!PageAnon(old_page), old_page); index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT; orig_page = find_get_page(vma->vm_file->f_inode->i_mapping, index); if (orig_page) { if (PageUptodate(orig_page) && pages_identical(new_page, orig_page)) { /* let go new_page */ put_page(new_page); new_page = NULL; if (PageCompound(orig_page)) orig_page_huge = true; } put_page(orig_page); } } ret = __replace_page(vma, vaddr, old_page, new_page); if (new_page) put_page(new_page); put_old: put_page(old_page); if (unlikely(ret == -EAGAIN)) goto retry; /* Revert back reference counter if instruction update failed. */ if (ret && is_register && ref_ctr_updated) update_ref_ctr(uprobe, mm, -1); /* try collapse pmd for compound page */ if (!ret && orig_page_huge) collapse_pte_mapped_thp(mm, vaddr); return ret; } /** * set_swbp - store breakpoint at a given address. * @auprobe: arch specific probepoint information. * @mm: the probed process address space. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, store the breakpoint instruction at @vaddr. * Return 0 (success) or a negative errno. */ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); } /** * set_orig_insn - Restore the original instruction. * @mm: the probed process address space. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ int __weak set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { return uprobe_write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn); } static struct uprobe *get_uprobe(struct uprobe *uprobe) { refcount_inc(&uprobe->ref); return uprobe; } static void put_uprobe(struct uprobe *uprobe) { if (refcount_dec_and_test(&uprobe->ref)) { /* * If application munmap(exec_vma) before uprobe_unregister() * gets called, we don't get a chance to remove uprobe from * delayed_uprobe_list from remove_breakpoint(). Do it here. */ mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(uprobe, NULL); mutex_unlock(&delayed_uprobe_lock); kfree(uprobe); } } static int match_uprobe(struct uprobe *l, struct uprobe *r) { if (l->inode < r->inode) return -1; if (l->inode > r->inode) return 1; if (l->offset < r->offset) return -1; if (l->offset > r->offset) return 1; return 0; } static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) { struct uprobe u = { .inode = inode, .offset = offset }; struct rb_node *n = uprobes_tree.rb_node; struct uprobe *uprobe; int match; while (n) { uprobe = rb_entry(n, struct uprobe, rb_node); match = match_uprobe(&u, uprobe); if (!match) return get_uprobe(uprobe); if (match < 0) n = n->rb_left; else n = n->rb_right; } return NULL; } /* * Find a uprobe corresponding to a given inode:offset * Acquires uprobes_treelock */ static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; spin_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); spin_unlock(&uprobes_treelock); return uprobe; } static struct uprobe *__insert_uprobe(struct uprobe *uprobe) { struct rb_node **p = &uprobes_tree.rb_node; struct rb_node *parent = NULL; struct uprobe *u; int match; while (*p) { parent = *p; u = rb_entry(parent, struct uprobe, rb_node); match = match_uprobe(uprobe, u); if (!match) return get_uprobe(u); if (match < 0) p = &parent->rb_left; else p = &parent->rb_right; } u = NULL; rb_link_node(&uprobe->rb_node, parent, p); rb_insert_color(&uprobe->rb_node, &uprobes_tree); /* get access + creation ref */ refcount_set(&uprobe->ref, 2); return u; } /* * Acquire uprobes_treelock. * Matching uprobe already exists in rbtree; * increment (access refcount) and return the matching uprobe. * * No matching uprobe; insert the uprobe in rb_tree; * get a double refcount (access + creation) and return NULL. */ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { struct uprobe *u; spin_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); spin_unlock(&uprobes_treelock); return u; } static void ref_ctr_mismatch_warn(struct uprobe *cur_uprobe, struct uprobe *uprobe) { pr_warn("ref_ctr_offset mismatch. inode: 0x%lx offset: 0x%llx " "ref_ctr_offset(old): 0x%llx ref_ctr_offset(new): 0x%llx\n", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) cur_uprobe->ref_ctr_offset, (unsigned long long) uprobe->ref_ctr_offset); } static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, loff_t ref_ctr_offset) { struct uprobe *uprobe, *cur_uprobe; uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); if (!uprobe) return NULL; uprobe->inode = inode; uprobe->offset = offset; uprobe->ref_ctr_offset = ref_ctr_offset; init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); /* a uprobe exists for this inode:offset combination */ if (cur_uprobe) { if (cur_uprobe->ref_ctr_offset != uprobe->ref_ctr_offset) { ref_ctr_mismatch_warn(cur_uprobe, uprobe); put_uprobe(cur_uprobe); kfree(uprobe); return ERR_PTR(-EINVAL); } kfree(uprobe); uprobe = cur_uprobe; } return uprobe; } static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) { down_write(&uprobe->consumer_rwsem); uc->next = uprobe->consumers; uprobe->consumers = uc; up_write(&uprobe->consumer_rwsem); } /* * For uprobe @uprobe, delete the consumer @uc. * Return true if the @uc is deleted successfully * or return false. */ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) { struct uprobe_consumer **con; bool ret = false; down_write(&uprobe->consumer_rwsem); for (con = &uprobe->consumers; *con; con = &(*con)->next) { if (*con == uc) { *con = uc->next; ret = true; break; } } up_write(&uprobe->consumer_rwsem); return ret; } static int __copy_insn(struct address_space *mapping, struct file *filp, void *insn, int nbytes, loff_t offset) { struct page *page; /* * Ensure that the page that has the original instruction is populated * and in page-cache. If ->readpage == NULL it must be shmem_mapping(), * see uprobe_register(). */ if (mapping->a_ops->readpage) page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp); else page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); copy_from_page(page, offset, insn, nbytes); put_page(page); return 0; } static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping = uprobe->inode->i_mapping; loff_t offs = uprobe->offset; void *insn = &uprobe->arch.insn; int size = sizeof(uprobe->arch.insn); int len, err = -EIO; /* Copy only available bytes, -EIO if nothing was read */ do { if (offs >= i_size_read(uprobe->inode)) break; len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK)); err = __copy_insn(mapping, filp, insn, len, offs); if (err) break; insn += len; offs += len; size -= len; } while (size); return err; } static int prepare_uprobe(struct uprobe *uprobe, struct file *file, struct mm_struct *mm, unsigned long vaddr) { int ret = 0; if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) return ret; /* TODO: move this into _register, until then we abuse this sem. */ down_write(&uprobe->consumer_rwsem); if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) goto out; ret = copy_insn(uprobe, file); if (ret) goto out; ret = -ENOTSUPP; if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn)) goto out; ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) goto out; smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: up_write(&uprobe->consumer_rwsem); return ret; } static inline bool consumer_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { return !uc->filter || uc->filter(uc, ctx, mm); } static bool filter_chain(struct uprobe *uprobe, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { struct uprobe_consumer *uc; bool ret = false; down_read(&uprobe->consumer_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { ret = consumer_filter(uc, ctx, mm); if (ret) break; } up_read(&uprobe->consumer_rwsem); return ret; } static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr) { bool first_uprobe; int ret; ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr); if (ret) return ret; /* * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), * the task can hit this breakpoint right after __replace_page(). */ first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); if (first_uprobe) set_bit(MMF_HAS_UPROBES, &mm->flags); ret = set_swbp(&uprobe->arch, mm, vaddr); if (!ret) clear_bit(MMF_RECALC_UPROBES, &mm->flags); else if (first_uprobe) clear_bit(MMF_HAS_UPROBES, &mm->flags); return ret; } static int remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { set_bit(MMF_RECALC_UPROBES, &mm->flags); return set_orig_insn(&uprobe->arch, mm, vaddr); } static inline bool uprobe_is_active(struct uprobe *uprobe) { return !RB_EMPTY_NODE(&uprobe->rb_node); } /* * There could be threads that have already hit the breakpoint. They * will recheck the current insn and restart if find_uprobe() fails. * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { if (WARN_ON(!uprobe_is_active(uprobe))) return; spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock(&uprobes_treelock); RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ put_uprobe(uprobe); } struct map_info { struct map_info *next; struct mm_struct *mm; unsigned long vaddr; }; static inline struct map_info *free_map_info(struct map_info *info) { struct map_info *next = info->next; kfree(info); return next; } static struct map_info * build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { unsigned long pgoff = offset >> PAGE_SHIFT; struct vm_area_struct *vma; struct map_info *curr = NULL; struct map_info *prev = NULL; struct map_info *info; int more = 0; again: i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; if (!prev && !more) { /* * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through * reclaim. This is optimistic, no harm done if it fails. */ prev = kmalloc(sizeof(struct map_info), GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); if (prev) prev->next = NULL; } if (!prev) { more++; continue; } if (!mmget_not_zero(vma->vm_mm)) continue; info = prev; prev = prev->next; info->next = curr; curr = info; info->mm = vma->vm_mm; info->vaddr = offset_to_vaddr(vma, offset); } i_mmap_unlock_read(mapping); if (!more) goto out; prev = curr; while (curr) { mmput(curr->mm); curr = curr->next; } do { info = kmalloc(sizeof(struct map_info), GFP_KERNEL); if (!info) { curr = ERR_PTR(-ENOMEM); goto out; } info->next = prev; prev = info; } while (--more); goto again; out: while (prev) prev = free_map_info(prev); return curr; } static int register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) { bool is_register = !!new; struct map_info *info; int err = 0; percpu_down_write(&dup_mmap_sem); info = build_map_info(uprobe->inode->i_mapping, uprobe->offset, is_register); if (IS_ERR(info)) { err = PTR_ERR(info); goto out; } while (info) { struct mm_struct *mm = info->mm; struct vm_area_struct *vma; if (err && is_register) goto free; mmap_write_lock(mm); vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || file_inode(vma->vm_file) != uprobe->inode) goto unlock; if (vma->vm_start > info->vaddr || vaddr_to_offset(vma, info->vaddr) != uprobe->offset) goto unlock; if (is_register) { /* consult only the "caller", new consumer. */ if (consumer_filter(new, UPROBE_FILTER_REGISTER, mm)) err = install_breakpoint(uprobe, mm, vma, info->vaddr); } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { if (!filter_chain(uprobe, UPROBE_FILTER_UNREGISTER, mm)) err |= remove_breakpoint(uprobe, mm, info->vaddr); } unlock: mmap_write_unlock(mm); free: mmput(mm); info = free_map_info(info); } out: percpu_up_write(&dup_mmap_sem); return err; } static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { int err; if (WARN_ON(!consumer_del(uprobe, uc))) return; err = register_for_each_vma(uprobe, NULL); /* TODO : cant unregister? schedule a worker thread */ if (!uprobe->consumers && !err) delete_uprobe(uprobe); } /* * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. */ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; uprobe = find_uprobe(inode, offset); if (WARN_ON(!uprobe)) return; down_write(&uprobe->register_rwsem); __uprobe_unregister(uprobe, uc); up_write(&uprobe->register_rwsem); put_uprobe(uprobe); } EXPORT_SYMBOL_GPL(uprobe_unregister); /* * __uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. * @uc: information on howto handle the probe.. * * Apart from the access refcount, __uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe * unregisters. Caller of __uprobe_register() is required to keep @inode * (and the containing mount) referenced. * * Return errno if it cannot successully install probes * else return 0 (success) */ static int __uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; /* Uprobe must have at least one set consumer */ if (!uc->handler && !uc->ret_handler) return -EINVAL; /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping)) return -EIO; /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) return -EINVAL; /* * This ensures that copy_from_page(), copy_to_page() and * __update_ref_ctr() can't cross page boundary. */ if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) return -EINVAL; if (!IS_ALIGNED(ref_ctr_offset, sizeof(short))) return -EINVAL; retry: uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (!uprobe) return -ENOMEM; if (IS_ERR(uprobe)) return PTR_ERR(uprobe); /* * We can race with uprobe_unregister()->delete_uprobe(). * Check uprobe_is_active() and retry if it is false. */ down_write(&uprobe->register_rwsem); ret = -EAGAIN; if (likely(uprobe_is_active(uprobe))) { consumer_add(uprobe, uc); ret = register_for_each_vma(uprobe, uc); if (ret) __uprobe_unregister(uprobe, uc); } up_write(&uprobe->register_rwsem); put_uprobe(uprobe); if (unlikely(ret == -EAGAIN)) goto retry; return ret; } int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return __uprobe_register(inode, offset, 0, uc); } EXPORT_SYMBOL_GPL(uprobe_register); int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { return __uprobe_register(inode, offset, ref_ctr_offset, uc); } EXPORT_SYMBOL_GPL(uprobe_register_refctr); /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints * @add: add or remove the breakpoints */ int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) { struct uprobe *uprobe; struct uprobe_consumer *con; int ret = -ENOENT; uprobe = find_uprobe(inode, offset); if (WARN_ON(!uprobe)) return ret; down_write(&uprobe->register_rwsem); for (con = uprobe->consumers; con && con != uc ; con = con->next) ; if (con) ret = register_for_each_vma(uprobe, add ? uc : NULL); up_write(&uprobe->register_rwsem); put_uprobe(uprobe); return ret; } static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) { struct vm_area_struct *vma; int err = 0; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { unsigned long vaddr; loff_t offset; if (!valid_vma(vma, false) || file_inode(vma->vm_file) != uprobe->inode) continue; offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; if (uprobe->offset < offset || uprobe->offset >= offset + vma->vm_end - vma->vm_start) continue; vaddr = offset_to_vaddr(vma, uprobe->offset); err |= remove_breakpoint(uprobe, mm, vaddr); } mmap_read_unlock(mm); return err; } static struct rb_node * find_node_in_range(struct inode *inode, loff_t min, loff_t max) { struct rb_node *n = uprobes_tree.rb_node; while (n) { struct uprobe *u = rb_entry(n, struct uprobe, rb_node); if (inode < u->inode) { n = n->rb_left; } else if (inode > u->inode) { n = n->rb_right; } else { if (max < u->offset) n = n->rb_left; else if (min > u->offset) n = n->rb_right; else break; } } return n; } /* * For a given range in vma, build a list of probes that need to be inserted. */ static void build_probe_list(struct inode *inode, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *head) { loff_t min, max; struct rb_node *n, *t; struct uprobe *u; INIT_LIST_HEAD(head); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); if (n) { for (t = n; t; t = rb_prev(t)) { u = rb_entry(t, struct uprobe, rb_node); if (u->inode != inode || u->offset < min) break; list_add(&u->pending_list, head); get_uprobe(u); } for (t = n; (t = rb_next(t)); ) { u = rb_entry(t, struct uprobe, rb_node); if (u->inode != inode || u->offset > max) break; list_add(&u->pending_list, head); get_uprobe(u); } } spin_unlock(&uprobes_treelock); } /* @vma contains reference counter, not the probed instruction. */ static int delayed_ref_ctr_inc(struct vm_area_struct *vma) { struct list_head *pos, *q; struct delayed_uprobe *du; unsigned long vaddr; int ret = 0, err = 0; mutex_lock(&delayed_uprobe_lock); list_for_each_safe(pos, q, &delayed_uprobe_list) { du = list_entry(pos, struct delayed_uprobe, list); if (du->mm != vma->vm_mm || !valid_ref_ctr_vma(du->uprobe, vma)) continue; vaddr = offset_to_vaddr(vma, du->uprobe->ref_ctr_offset); ret = __update_ref_ctr(vma->vm_mm, vaddr, 1); if (ret) { update_ref_ctr_warn(du->uprobe, vma->vm_mm, 1); if (!err) err = ret; } delayed_uprobe_delete(du); } mutex_unlock(&delayed_uprobe_lock); return err; } /* * Called from mmap_region/vma_adjust with mm->mmap_lock acquired. * * Currently we ignore all errors and always return 0, the callers * can't handle the failure anyway. */ int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; if (no_uprobe_events()) return 0; if (vma->vm_file && (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags)) delayed_ref_ctr_inc(vma); if (!valid_vma(vma, true)) return 0; inode = file_inode(vma->vm_file); if (!inode) return 0; mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); /* * We can race with uprobe_unregister(), this uprobe can be already * removed. But in this case filter_chain() must return false, all * consumers have gone away. */ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { if (!fatal_signal_pending(current) && filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } put_uprobe(uprobe); } mutex_unlock(uprobes_mmap_hash(inode)); return 0; } static bool vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) { loff_t min, max; struct inode *inode; struct rb_node *n; inode = file_inode(vma->vm_file); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); spin_unlock(&uprobes_treelock); return !!n; } /* * Called in context of a munmap of a vma. */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (no_uprobe_events() || !valid_vma(vma, false)) return; if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ return; if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) return; if (vma_has_uprobes(vma, start, end)) set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); } /* Slot allocation for XOL */ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) { struct vm_area_struct *vma; int ret; if (mmap_write_lock_killable(mm)) return -EINTR; if (mm->uprobes_state.xol_area) { ret = -EALREADY; goto fail; } if (!area->vaddr) { /* Try to map as high as possible, this is only a hint. */ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0); if (IS_ERR_VALUE(area->vaddr)) { ret = area->vaddr; goto fail; } } vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE, VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO, &area->xol_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto fail; } ret = 0; /* pairs with get_xol_area() */ smp_store_release(&mm->uprobes_state.xol_area, area); /* ^^^ */ fail: mmap_write_unlock(mm); return ret; } static struct xol_area *__create_xol_area(unsigned long vaddr) { struct mm_struct *mm = current->mm; uprobe_opcode_t insn = UPROBE_SWBP_INSN; struct xol_area *area; area = kmalloc(sizeof(*area), GFP_KERNEL); if (unlikely(!area)) goto out; area->bitmap = kcalloc(BITS_TO_LONGS(UINSNS_PER_PAGE), sizeof(long), GFP_KERNEL); if (!area->bitmap) goto free_area; area->xol_mapping.name = "[uprobes]"; area->xol_mapping.fault = NULL; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER); if (!area->pages[0]) goto free_bitmap; area->pages[1] = NULL; area->vaddr = vaddr; init_waitqueue_head(&area->wq); /* Reserve the 1st slot for get_trampoline_vaddr() */ set_bit(0, area->bitmap); atomic_set(&area->slot_count, 1); arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE); if (!xol_add_vma(mm, area)) return area; __free_page(area->pages[0]); free_bitmap: kfree(area->bitmap); free_area: kfree(area); out: return NULL; } /* * get_xol_area - Allocate process's xol_area if necessary. * This area will be used for storing instructions for execution out of line. * * Returns the allocated area or NULL. */ static struct xol_area *get_xol_area(void) { struct mm_struct *mm = current->mm; struct xol_area *area; if (!mm->uprobes_state.xol_area) __create_xol_area(0); /* Pairs with xol_add_vma() smp_store_release() */ area = READ_ONCE(mm->uprobes_state.xol_area); /* ^^^ */ return area; } /* * uprobe_clear_state - Free the area allocated for slots. */ void uprobe_clear_state(struct mm_struct *mm) { struct xol_area *area = mm->uprobes_state.xol_area; mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(NULL, mm); mutex_unlock(&delayed_uprobe_lock); if (!area) return; put_page(area->pages[0]); kfree(area->bitmap); kfree(area); } void uprobe_start_dup_mmap(void) { percpu_down_read(&dup_mmap_sem); } void uprobe_end_dup_mmap(void) { percpu_up_read(&dup_mmap_sem); } void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { set_bit(MMF_HAS_UPROBES, &newmm->flags); /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ set_bit(MMF_RECALC_UPROBES, &newmm->flags); } } /* * - search for a free slot. */ static unsigned long xol_take_insn_slot(struct xol_area *area) { unsigned long slot_addr; int slot_nr; do { slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE); if (slot_nr < UINSNS_PER_PAGE) { if (!test_and_set_bit(slot_nr, area->bitmap)) break; slot_nr = UINSNS_PER_PAGE; continue; } wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE)); } while (slot_nr >= UINSNS_PER_PAGE); slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES); atomic_inc(&area->slot_count); return slot_addr; } /* * xol_get_insn_slot - allocate a slot for xol. * Returns the allocated slot address or 0. */ static unsigned long xol_get_insn_slot(struct uprobe *uprobe) { struct xol_area *area; unsigned long xol_vaddr; area = get_xol_area(); if (!area) return 0; xol_vaddr = xol_take_insn_slot(area); if (unlikely(!xol_vaddr)) return 0; arch_uprobe_copy_ixol(area->pages[0], xol_vaddr, &uprobe->arch.ixol, sizeof(uprobe->arch.ixol)); return xol_vaddr; } /* * xol_free_insn_slot - If slot was earlier allocated by * @xol_get_insn_slot(), make the slot available for * subsequent requests. */ static void xol_free_insn_slot(struct task_struct *tsk) { struct xol_area *area; unsigned long vma_end; unsigned long slot_addr; if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask) return; slot_addr = tsk->utask->xol_vaddr; if (unlikely(!slot_addr)) return; area = tsk->mm->uprobes_state.xol_area; vma_end = area->vaddr + PAGE_SIZE; if (area->vaddr <= slot_addr && slot_addr < vma_end) { unsigned long offset; int slot_nr; offset = slot_addr - area->vaddr; slot_nr = offset / UPROBE_XOL_SLOT_BYTES; if (slot_nr >= UINSNS_PER_PAGE) return; clear_bit(slot_nr, area->bitmap); atomic_dec(&area->slot_count); smp_mb__after_atomic(); /* pairs with prepare_to_wait() */ if (waitqueue_active(&area->wq)) wake_up(&area->wq); tsk->utask->xol_vaddr = 0; } } void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len) { /* Initialize the slot */ copy_to_page(page, vaddr, src, len); /* * We probably need flush_icache_user_page() but it needs vma. * This should work on most of architectures by default. If * architecture needs to do something different it can define * its own version of the function. */ flush_dcache_page(page); } /** * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs * @regs: Reflects the saved state of the task after it has hit a breakpoint * instruction. * Return the address of the breakpoint instruction. */ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs) { return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE; } unsigned long uprobe_get_trap_addr(struct pt_regs *regs) { struct uprobe_task *utask = current->utask; if (unlikely(utask && utask->active_uprobe)) return utask->vaddr; return instruction_pointer(regs); } static struct return_instance *free_ret_instance(struct return_instance *ri) { struct return_instance *next = ri->next; put_uprobe(ri->uprobe); kfree(ri); return next; } /* * Called with no locks held. * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; struct return_instance *ri; if (!utask) return; if (utask->active_uprobe) put_uprobe(utask->active_uprobe); ri = utask->return_instances; while (ri) ri = free_ret_instance(ri); xol_free_insn_slot(t); kfree(utask); t->utask = NULL; } /* * Allocate a uprobe_task object for the task if necessary. * Called when the thread hits a breakpoint. * * Returns: * - pointer to new uprobe_task on success * - NULL otherwise */ static struct uprobe_task *get_utask(void) { if (!current->utask) current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); return current->utask; } static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask) { struct uprobe_task *n_utask; struct return_instance **p, *o, *n; n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); if (!n_utask) return -ENOMEM; t->utask = n_utask; p = &n_utask->return_instances; for (o = o_utask->return_instances; o; o = o->next) { n = kmalloc(sizeof(struct return_instance), GFP_KERNEL); if (!n) return -ENOMEM; *n = *o; get_uprobe(n->uprobe); n->next = NULL; *p = n; p = &n->next; n_utask->depth++; } return 0; } static void uprobe_warn(struct task_struct *t, const char *msg) { pr_warn("uprobe: %s:%d failed to %s\n", current->comm, current->pid, msg); } static void dup_xol_work(struct callback_head *work) { if (current->flags & PF_EXITING) return; if (!__create_xol_area(current->utask->dup_xol_addr) && !fatal_signal_pending(current)) uprobe_warn(current, "dup xol area"); } /* * Called in context of a new clone/fork from copy_process. */ void uprobe_copy_process(struct task_struct *t, unsigned long flags) { struct uprobe_task *utask = current->utask; struct mm_struct *mm = current->mm; struct xol_area *area; t->utask = NULL; if (!utask || !utask->return_instances) return; if (mm == t->mm && !(flags & CLONE_VFORK)) return; if (dup_utask(t, utask)) return uprobe_warn(t, "dup ret instances"); /* The task can fork() after dup_xol_work() fails */ area = mm->uprobes_state.xol_area; if (!area) return uprobe_warn(t, "dup xol area"); if (mm == t->mm) return; t->utask->dup_xol_addr = area->vaddr; init_task_work(&t->utask->dup_xol_work, dup_xol_work); task_work_add(t, &t->utask->dup_xol_work, TWA_RESUME); } /* * Current area->vaddr notion assume the trampoline address is always * equal area->vaddr. * * Returns -1 in case the xol_area is not allocated. */ static unsigned long get_trampoline_vaddr(void) { struct xol_area *area; unsigned long trampoline_vaddr = -1; /* Pairs with xol_add_vma() smp_store_release() */ area = READ_ONCE(current->mm->uprobes_state.xol_area); /* ^^^ */ if (area) trampoline_vaddr = area->vaddr; return trampoline_vaddr; } static void cleanup_return_instances(struct uprobe_task *utask, bool chained, struct pt_regs *regs) { struct return_instance *ri = utask->return_instances; enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL; while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) { ri = free_ret_instance(ri); utask->depth--; } utask->return_instances = ri; } static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs) { struct return_instance *ri; struct uprobe_task *utask; unsigned long orig_ret_vaddr, trampoline_vaddr; bool chained; if (!get_xol_area()) return; utask = get_utask(); if (!utask) return; if (utask->depth >= MAX_URETPROBE_DEPTH) { printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to" " nestedness limit pid/tgid=%d/%d\n", current->pid, current->tgid); return; } ri = kmalloc(sizeof(struct return_instance), GFP_KERNEL); if (!ri) return; trampoline_vaddr = get_trampoline_vaddr(); orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs); if (orig_ret_vaddr == -1) goto fail; /* drop the entries invalidated by longjmp() */ chained = (orig_ret_vaddr == trampoline_vaddr); cleanup_return_instances(utask, chained, regs); /* * We don't want to keep trampoline address in stack, rather keep the * original return address of first caller thru all the consequent * instances. This also makes breakpoint unwrapping easier. */ if (chained) { if (!utask->return_instances) { /* * This situation is not possible. Likely we have an * attack from user-space. */ uprobe_warn(current, "handle tail call"); goto fail; } orig_ret_vaddr = utask->return_instances->orig_ret_vaddr; } ri->uprobe = get_uprobe(uprobe); ri->func = instruction_pointer(regs); ri->stack = user_stack_pointer(regs); ri->orig_ret_vaddr = orig_ret_vaddr; ri->chained = chained; utask->depth++; ri->next = utask->return_instances; utask->return_instances = ri; return; fail: kfree(ri); } /* Prepare to single-step probed instruction out of line. */ static int pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr) { struct uprobe_task *utask; unsigned long xol_vaddr; int err; utask = get_utask(); if (!utask) return -ENOMEM; xol_vaddr = xol_get_insn_slot(uprobe); if (!xol_vaddr) return -ENOMEM; utask->xol_vaddr = xol_vaddr; utask->vaddr = bp_vaddr; err = arch_uprobe_pre_xol(&uprobe->arch, regs); if (unlikely(err)) { xol_free_insn_slot(current); return err; } utask->active_uprobe = uprobe; utask->state = UTASK_SSTEP; return 0; } /* * If we are singlestepping, then ensure this thread is not connected to * non-fatal signals until completion of singlestep. When xol insn itself * triggers the signal, restart the original insn even if the task is * already SIGKILL'ed (since coredump should report the correct ip). This * is even more important if the task has a handler for SIGSEGV/etc, The * _same_ instruction should be repeated again after return from the signal * handler, and SSTEP can never finish in this case. */ bool uprobe_deny_signal(void) { struct task_struct *t = current; struct uprobe_task *utask = t->utask; if (likely(!utask || !utask->active_uprobe)) return false; WARN_ON_ONCE(utask->state != UTASK_SSTEP); if (signal_pending(t)) { spin_lock_irq(&t->sighand->siglock); clear_tsk_thread_flag(t, TIF_SIGPENDING); spin_unlock_irq(&t->sighand->siglock); if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) { utask->state = UTASK_SSTEP_TRAPPED; set_tsk_thread_flag(t, TIF_UPROBE); } } return true; } static void mmf_recalc_uprobes(struct mm_struct *mm) { struct vm_area_struct *vma; for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!valid_vma(vma, false)) continue; /* * This is not strictly accurate, we can race with * uprobe_unregister() and see the already removed * uprobe if delete_uprobe() was not yet called. * Or this uprobe can be filtered out. */ if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) return; } clear_bit(MMF_HAS_UPROBES, &mm->flags); } static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) { struct page *page; uprobe_opcode_t opcode; int result; if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE))) return -EINVAL; pagefault_disable(); result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr); pagefault_enable(); if (likely(result == 0)) goto out; /* * The NULL 'tsk' here ensures that any faults that occur here * will not be accounted to the task. 'mm' *is* current->mm, * but we treat this as a 'remote' access since it is * essentially a kernel access to the memory. */ result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page, NULL, NULL); if (result < 0) return result; copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); put_page(page); out: /* This needs to return true for any variant of the trap insn */ return is_trap_insn(&opcode); } static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) { struct mm_struct *mm = current->mm; struct uprobe *uprobe = NULL; struct vm_area_struct *vma; mmap_read_lock(mm); vma = find_vma(mm, bp_vaddr); if (vma && vma->vm_start <= bp_vaddr) { if (valid_vma(vma, false)) { struct inode *inode = file_inode(vma->vm_file); loff_t offset = vaddr_to_offset(vma, bp_vaddr); uprobe = find_uprobe(inode, offset); } if (!uprobe) *is_swbp = is_trap_at_addr(mm, bp_vaddr); } else { *is_swbp = -EFAULT; } if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) mmf_recalc_uprobes(mm); mmap_read_unlock(mm); return uprobe; } static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) { struct uprobe_consumer *uc; int remove = UPROBE_HANDLER_REMOVE; bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { int rc = 0; if (uc->handler) { rc = uc->handler(uc, regs); WARN(rc & ~UPROBE_HANDLER_MASK, "bad rc=0x%x from %ps()\n", rc, uc->handler); } if (uc->ret_handler) need_prep = true; remove &= rc; } if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ if (remove && uprobe->consumers) { WARN_ON(!uprobe_is_active(uprobe)); unapply_uprobe(uprobe, current->mm); } up_read(&uprobe->register_rwsem); } static void handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs) { struct uprobe *uprobe = ri->uprobe; struct uprobe_consumer *uc; down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { if (uc->ret_handler) uc->ret_handler(uc, ri->func, regs); } up_read(&uprobe->register_rwsem); } static struct return_instance *find_next_ret_chain(struct return_instance *ri) { bool chained; do { chained = ri->chained; ri = ri->next; /* can't be NULL if chained */ } while (chained); return ri; } static void handle_trampoline(struct pt_regs *regs) { struct uprobe_task *utask; struct return_instance *ri, *next; bool valid; utask = current->utask; if (!utask) goto sigill; ri = utask->return_instances; if (!ri) goto sigill; do { /* * We should throw out the frames invalidated by longjmp(). * If this chain is valid, then the next one should be alive * or NULL; the latter case means that nobody but ri->func * could hit this trampoline on return. TODO: sigaltstack(). */ next = find_next_ret_chain(ri); valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs); instruction_pointer_set(regs, ri->orig_ret_vaddr); do { if (valid) handle_uretprobe_chain(ri, regs); ri = free_ret_instance(ri); utask->depth--; } while (ri != next); } while (!valid); utask->return_instances = ri; return; sigill: uprobe_warn(current, "handle uretprobe, sending SIGILL."); force_sig(SIGILL); } bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs) { return false; } bool __weak arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, struct pt_regs *regs) { return true; } /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { struct uprobe *uprobe; unsigned long bp_vaddr; int is_swbp; bp_vaddr = uprobe_get_swbp_addr(regs); if (bp_vaddr == get_trampoline_vaddr()) return handle_trampoline(regs); uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ force_sig(SIGTRAP); } else { /* * Either we raced with uprobe_unregister() or we can't * access this memory. The latter is only possible if * another thread plays with our ->mm. In both cases * we can simply restart. If this vma was unmapped we * can pretend this insn was not executed yet and get * the (correct) SIGSEGV after restart. */ instruction_pointer_set(regs, bp_vaddr); } return; } /* change it in advance for ->handler() and restart */ instruction_pointer_set(regs, bp_vaddr); /* * TODO: move copy_insn/etc into _register and remove this hack. * After we hit the bp, _unregister + _register can install the * new and not-yet-analyzed uprobe at the same address, restart. */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) goto out; /* * Pairs with the smp_wmb() in prepare_uprobe(). * * Guarantees that if we see the UPROBE_COPY_INSN bit set, then * we must also see the stores to &uprobe->arch performed by the * prepare_uprobe() call. */ smp_rmb(); /* Tracing handlers use ->utask to communicate with fetch methods */ if (!get_utask()) goto out; if (arch_uprobe_ignore(&uprobe->arch, regs)) goto out; handler_chain(uprobe, regs); if (arch_uprobe_skip_sstep(&uprobe->arch, regs)) goto out; if (!pre_ssout(uprobe, regs, bp_vaddr)) return; /* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */ out: put_uprobe(uprobe); } /* * Perform required fix-ups and disable singlestep. * Allow pending signals to take effect. */ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) { struct uprobe *uprobe; int err = 0; uprobe = utask->active_uprobe; if (utask->state == UTASK_SSTEP_ACK) err = arch_uprobe_post_xol(&uprobe->arch, regs); else if (utask->state == UTASK_SSTEP_TRAPPED) arch_uprobe_abort_xol(&uprobe->arch, regs); else WARN_ON_ONCE(1); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; xol_free_insn_slot(current); spin_lock_irq(¤t->sighand->siglock); recalc_sigpending(); /* see uprobe_deny_signal() */ spin_unlock_irq(¤t->sighand->siglock); if (unlikely(err)) { uprobe_warn(current, "execute the probed insn, sending SIGILL."); force_sig(SIGILL); } } /* * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and * allows the thread to return from interrupt. After that handle_swbp() * sets utask->active_uprobe. * * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag * and allows the thread to return from interrupt. * * While returning to userspace, thread notices the TIF_UPROBE flag and calls * uprobe_notify_resume(). */ void uprobe_notify_resume(struct pt_regs *regs) { struct uprobe_task *utask; clear_thread_flag(TIF_UPROBE); utask = current->utask; if (utask && utask->active_uprobe) handle_singlestep(utask, regs); else handle_swbp(regs); } /* * uprobe_pre_sstep_notifier gets called from interrupt context as part of * notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit. */ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { if (!current->mm) return 0; if (!test_bit(MMF_HAS_UPROBES, ¤t->mm->flags) && (!current->utask || !current->utask->return_instances)) return 0; set_thread_flag(TIF_UPROBE); return 1; } /* * uprobe_post_sstep_notifier gets called in interrupt context as part of notifier * mechanism. Set TIF_UPROBE flag and indicate completion of singlestep. */ int uprobe_post_sstep_notifier(struct pt_regs *regs) { struct uprobe_task *utask = current->utask; if (!current->mm || !utask || !utask->active_uprobe) /* task is currently not uprobed */ return 0; utask->state = UTASK_SSTEP_ACK; set_thread_flag(TIF_UPROBE); return 1; } static struct notifier_block uprobe_exception_nb = { .notifier_call = arch_uprobe_exception_notify, .priority = INT_MAX-1, /* notified after kprobes, kgdb */ }; void __init uprobes_init(void) { int i; for (i = 0; i < UPROBES_HASH_SZ; i++) mutex_init(&uprobes_mmap_mutex[i]); BUG_ON(register_die_notifier(&uprobe_exception_nb)); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !atomic_read(&lock.val); } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { u32 val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { u32 val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 43 28 13 5 8 2 9 8 3 9 11 10 6 10 12 12 13 1 6 2 1 1 3 2 1 14 1 6 8 5 2 2 2 2 11 1 1 1 1 6 1 1 1 19 1 3 7 11 5 4 1 2 2 13 3 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 | // SPDX-License-Identifier: GPL-2.0-only /* * Longest prefix match list implementation * * Copyright (c) 2016,2017 Daniel Mack * Copyright (c) 2016 David Herrmann */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <net/ipv6.h> #include <uapi/linux/btf.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) struct lpm_trie_node; struct lpm_trie_node { struct rcu_head rcu; struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; u8 data[]; }; struct lpm_trie { struct bpf_map map; struct lpm_trie_node __rcu *root; size_t n_entries; size_t max_prefixlen; size_t data_size; spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to * match IP addresses to a stored set of ranges. * * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is * interpreted as big endian, so data[0] stores the most significant byte. * * Match ranges are internally stored in instances of struct lpm_trie_node * which each contain their prefix length as well as two pointers that may * lead to more nodes containing more specific matches. Each node also stores * a value that is defined by and returned to userspace via the update_elem * and lookup functions. * * For instance, let's start with a trie that was created with a prefix length * of 32, so it can be used for IPv4 addresses, and one single element that * matches 192.168.0.0/16. The data array would hence contain * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will * stick to IP-address notation for readability though. * * As the trie is empty initially, the new node (1) will be places as root * node, denoted as (R) in the example below. As there are no other node, both * child pointers are %NULL. * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already * a node with the same data and a smaller prefix (ie, a less specific one), * node (2) will become a child of (1). In child index depends on the next bit * that is outside of what (1) matches, and that bit is 0, so (2) will be * child[0] of (1): * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | * +----------------+ * | (2) | * | 192.168.0.0/24 | * | value: 2 | * | [0] [1] | * +----------------+ * * The child[1] slot of (1) could be filled with another node which has bit #17 * (the next bit after the ones that (1) matches on) set to 1. For instance, * 192.168.128.0/24: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (2) | | (3) | * | 192.168.0.0/24 | | 192.168.128.0/24 | * | value: 2 | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * * Let's add another node (4) to the game for 192.168.1.0/24. In order to place * it, node (1) is looked at first, and because (4) of the semantics laid out * above (bit #17 is 0), it would normally be attached to (1) as child[0]. * However, that slot is already allocated, so a new node is needed in between. * That node does not have a value attached to it and it will never be * returned to users as result of a lookup. It is only there to differentiate * the traversal further. It will get a prefix as wide as necessary to * distinguish its two children: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (4) (I) | | (3) | * | 192.168.0.0/23 | | 192.168.128.0/24 | * | value: --- | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * | | * +----------------+ +----------------+ * | (2) | | (5) | * | 192.168.0.0/24 | | 192.168.1.0/24 | * | value: 2 | | value: 5 | * | [0] [1] | | [0] [1] | * +----------------+ +----------------+ * * 192.168.1.1/32 would be a child of (5) etc. * * An intermediate node will be turned into a 'real' node on demand. In the * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie. * * A fully populated trie would have a height of 32 nodes, as the trie was * created with a prefix length of 32. * * The lookup starts at the root node. If the current node matches and if there * is a child that can be used to become more specific, the trie is traversed * downwards. The last node in the traversal that is a non-intermediate one is * returned. */ static inline int extract_bit(const u8 *data, size_t index) { return !!(data[index / 8] & (1 << (7 - (index % 8)))); } /** * longest_prefix_match() - determine the longest prefix * @trie: The trie to get internal sizes from * @node: The node to operate on * @key: The key to compare to @node * * Determine the longest prefix of @node that matches the bits in @key. */ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) /* data_size >= 16 has very small probability. * We do not use a loop for optimal code generation. */ if (trie->data_size >= 8) { u64 diff = be64_to_cpu(*(__be64 *)node->data ^ *(__be64 *)key->data); prefixlen = 64 - fls64(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i = 8; } #endif while (trie->data_size >= i + 4) { u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^ *(__be32 *)&key->data[i]); prefixlen += 32 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 4; } if (trie->data_size >= i + 2) { u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ *(__be16 *)&key->data[i]); prefixlen += 16 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 2; } if (trie->data_size >= i + 1) { prefixlen += 8 - fls(node->data[i] ^ key->data[i]); if (prefixlen >= limit) return limit; } return prefixlen; } /* Called from syscall or from eBPF program */ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; struct bpf_lpm_trie_key *key = _key; /* Start walking the trie from the root node ... */ for (node = rcu_dereference(trie->root); node;) { unsigned int next_bit; size_t matchlen; /* Determine the longest prefix of @node that matches @key. * If it's the maximum possible prefix for this trie, we have * an exact match and can return it directly. */ matchlen = longest_prefix_match(trie, node, key); if (matchlen == trie->max_prefixlen) { found = node; break; } /* If the number of bits that match is smaller than the prefix * length of @node, bail out and return the node we have seen * last in the traversal (ie, the parent). */ if (matchlen < node->prefixlen) break; /* Consider this node as return candidate unless it is an * artificially added intermediate one. */ if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) found = node; /* If the node match is fully satisfied, let's see if we can * become more specific. Determine the next bit in the key and * traverse down. */ next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } if (!found) return NULL; return found->data + trie->data_size; } static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, const void *value) { struct lpm_trie_node *node; size_t size = sizeof(struct lpm_trie_node) + trie->data_size; if (value) size += trie->map.value_size; node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, trie->map.numa_node); if (!node) return NULL; node->flags = 0; if (value) memcpy(node->data + trie->data_size, value, trie->map.value_size); return node; } /* Called from syscall or from eBPF program */ static int trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; spin_lock_irqsave(&trie->lock, irq_flags); /* Allocate and fill a new node */ if (trie->n_entries == trie->map.max_entries) { ret = -ENOSPC; goto out; } new_node = lpm_trie_node_alloc(trie, value); if (!new_node) { ret = -ENOMEM; goto out; } trie->n_entries++; new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); RCU_INIT_POINTER(new_node->child[1], NULL); memcpy(new_node->data, key->data, trie->data_size); /* Now find a slot to attach the new node. To do that, walk the tree * from the root and match as many bits as possible for each node until * we either find an empty slot or a slot that needs to be replaced by * an intermediate node. */ slot = &trie->root; while ((node = rcu_dereference_protected(*slot, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen || node->prefixlen == trie->max_prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); slot = &node->child[next_bit]; } /* If the slot is empty (a free child pointer or an empty root), * simply assign the @new_node to that slot and be done. */ if (!node) { rcu_assign_pointer(*slot, new_node); goto out; } /* If the slot we picked already exists, replace it with @new_node * which already has the correct data array set. */ if (node->prefixlen == matchlen) { new_node->child[0] = node->child[0]; new_node->child[1] = node->child[1]; if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) trie->n_entries--; rcu_assign_pointer(*slot, new_node); kfree_rcu(node, rcu); goto out; } /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. */ if (matchlen == key->prefixlen) { next_bit = extract_bit(node->data, matchlen); rcu_assign_pointer(new_node->child[next_bit], node); rcu_assign_pointer(*slot, new_node); goto out; } im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { ret = -ENOMEM; goto out; } im_node->prefixlen = matchlen; im_node->flags |= LPM_TREE_NODE_FLAG_IM; memcpy(im_node->data, node->data, trie->data_size); /* Now determine which child to install in which slot */ if (extract_bit(key->data, matchlen)) { rcu_assign_pointer(im_node->child[0], node); rcu_assign_pointer(im_node->child[1], new_node); } else { rcu_assign_pointer(im_node->child[0], new_node); rcu_assign_pointer(im_node->child[1], node); } /* Finally, assign the intermediate node to the determined spot */ rcu_assign_pointer(*slot, im_node); out: if (ret) { if (new_node) trie->n_entries--; kfree(new_node); kfree(im_node); } spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } /* Called from syscall or from eBPF program */ static int trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; spin_lock_irqsave(&trie->lock, irq_flags); /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node * we wish to delete, and the slot that points to the node we want * to delete. We may also need to know the nodes parent and the * slot that contains it. */ trim = &trie->root; trim2 = trim; parent = NULL; while ((node = rcu_dereference_protected( *trim, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; parent = node; trim2 = trim; next_bit = extract_bit(key->data, node->prefixlen); trim = &node->child[next_bit]; } if (!node || node->prefixlen != key->prefixlen || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; } trie->n_entries--; /* If the node we are removing has two children, simply mark it * as intermediate and we are done. */ if (rcu_access_pointer(node->child[0]) && rcu_access_pointer(node->child[1])) { node->flags |= LPM_TREE_NODE_FLAG_IM; goto out; } /* If the parent of the node we are about to delete is an intermediate * node, and the deleted node doesn't have any children, we can delete * the intermediate parent as well and promote its other child * up the tree. Doing this maintains the invariant that all * intermediate nodes have exactly 2 children and that there are no * unnecessary intermediate nodes in the tree. */ if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && !node->child[0] && !node->child[1]) { if (node == rcu_access_pointer(parent->child[0])) rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[1])); else rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[0])); kfree_rcu(parent, rcu); kfree_rcu(node, rcu); goto out; } /* The node we are removing has either zero or one child. If there * is a child, move it into the removed node's slot then delete * the node. Otherwise just clear the slot and delete the node. */ if (node->child[0]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); else if (node->child[1]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); else RCU_INIT_POINTER(*trim, NULL); kfree_rcu(node, rcu); out: spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } #define LPM_DATA_SIZE_MAX 256 #define LPM_DATA_SIZE_MIN 1 #define LPM_VAL_SIZE_MAX (KMALLOC_MAX_SIZE - LPM_DATA_SIZE_MAX - \ sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 #define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) #define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK) static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; u64 cost = sizeof(*trie), cost_per_node; int ret; if (!bpf_capable()) return ERR_PTR(-EPERM); /* check sanity of attributes */ if (attr->max_entries == 0 || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->map_flags & ~LPM_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN); if (!trie) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; cost_per_node = sizeof(struct lpm_trie_node) + attr->value_size + trie->data_size; cost += (u64) attr->max_entries * cost_per_node; ret = bpf_map_charge_init(&trie->map.memory, cost); if (ret) goto out_err; spin_lock_init(&trie->lock); return &trie->map; out_err: kfree(trie); return ERR_PTR(ret); } static void trie_free(struct bpf_map *map) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent * and start over. */ for (;;) { slot = &trie->root; for (;;) { node = rcu_dereference_protected(*slot, 1); if (!node) goto out; if (rcu_access_pointer(node->child[0])) { slot = &node->child[0]; continue; } if (rcu_access_pointer(node->child[1])) { slot = &node->child[1]; continue; } kfree(node); RCU_INIT_POINTER(*slot, NULL); break; } } out: kfree(trie); } static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; size_t matchlen; /* The get_next_key follows postorder. For the 4 node example in * the top of this file, the trie_get_next_key() returns the following * one after another: * 192.168.0.0/24 * 192.168.1.0/24 * 192.168.128.0/24 * 192.168.0.0/16 * * The idea is to return more specific keys before less specific ones. */ /* Empty trie */ search_root = rcu_dereference(trie->root); if (!search_root) return -ENOENT; /* For invalid key, find the leftmost node in the trie */ if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; node_stack = kmalloc_array(trie->max_prefixlen, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) return -ENOMEM; /* Try to find the exact node for the given key */ for (node = search_root; node;) { node_stack[++stack_ptr] = node; matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } if (!node || node->prefixlen != key->prefixlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) goto find_leftmost; /* The node with the exactly-matching key has been found, * find the first node in postorder after the matched node. */ node = node_stack[stack_ptr]; while (stack_ptr > 0) { parent = node_stack[stack_ptr - 1]; if (rcu_dereference(parent->child[0]) == node) { search_root = rcu_dereference(parent->child[1]); if (search_root) goto find_leftmost; } if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) { next_node = parent; goto do_copy; } node = parent; stack_ptr--; } /* did not find anything */ err = -ENOENT; goto free_stack; find_leftmost: /* Find the leftmost non-intermediate node, all intermediate nodes * have exact two children, so this function will never return NULL. */ for (node = search_root; node;) { if (node->flags & LPM_TREE_NODE_FLAG_IM) { node = rcu_dereference(node->child[0]); } else { next_node = node; node = rcu_dereference(node->child[0]); if (!node) node = rcu_dereference(next_node->child[1]); } } do_copy: next_key->prefixlen = next_node->prefixlen; memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); return err; } static int trie_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { /* Keys must have struct bpf_lpm_trie_key embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } static int trie_map_btf_id; const struct bpf_map_ops trie_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = trie_alloc, .map_free = trie_free, .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, .map_check_btf = trie_check_btf, .map_btf_name = "lpm_trie", .map_btf_id = &trie_map_btf_id, }; |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 | /* SPDX-License-Identifier: GPL-2.0 */ /* interrupt.h */ #ifndef _LINUX_INTERRUPT_H #define _LINUX_INTERRUPT_H #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/irqreturn.h> #include <linux/irqnr.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/hrtimer.h> #include <linux/kref.h> #include <linux/workqueue.h> #include <linux/atomic.h> #include <asm/ptrace.h> #include <asm/irq.h> #include <asm/sections.h> /* * These correspond to the IORESOURCE_IRQ_* defines in * linux/ioport.h to select the interrupt line behaviour. When * requesting an interrupt without specifying a IRQF_TRIGGER, the * setting should be assumed to be "as already configured", which * may be as per machine or firmware initialisation. */ #define IRQF_TRIGGER_NONE 0x00000000 #define IRQF_TRIGGER_RISING 0x00000001 #define IRQF_TRIGGER_FALLING 0x00000002 #define IRQF_TRIGGER_HIGH 0x00000004 #define IRQF_TRIGGER_LOW 0x00000008 #define IRQF_TRIGGER_MASK (IRQF_TRIGGER_HIGH | IRQF_TRIGGER_LOW | \ IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING) #define IRQF_TRIGGER_PROBE 0x00000010 /* * These flags used only by the kernel as part of the * irq handling routines. * * IRQF_SHARED - allow sharing the irq among several devices * IRQF_PROBE_SHARED - set by callers when they expect sharing mismatches to occur * IRQF_TIMER - Flag to mark this interrupt as timer interrupt * IRQF_PERCPU - Interrupt is per cpu * IRQF_NOBALANCING - Flag to exclude this interrupt from irq balancing * IRQF_IRQPOLL - Interrupt is used for polling (only the interrupt that is * registered first in a shared interrupt is considered for * performance reasons) * IRQF_ONESHOT - Interrupt is not reenabled after the hardirq handler finished. * Used by threaded interrupts which need to keep the * irq line disabled until the threaded handler has been run. * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend. Does not guarantee * that this interrupt will wake the system from a suspended * state. See Documentation/power/suspend-and-interrupts.rst * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set * IRQF_NO_THREAD - Interrupt cannot be threaded * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device * resume time. * IRQF_COND_SUSPEND - If the IRQ is shared with a NO_SUSPEND user, execute this * interrupt handler after suspending interrupts. For system * wakeup devices users need to implement wakeup detection in * their interrupt handlers. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 #define __IRQF_TIMER 0x00000200 #define IRQF_PERCPU 0x00000400 #define IRQF_NOBALANCING 0x00000800 #define IRQF_IRQPOLL 0x00001000 #define IRQF_ONESHOT 0x00002000 #define IRQF_NO_SUSPEND 0x00004000 #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 #define IRQF_EARLY_RESUME 0x00020000 #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) /* * These values can be returned by request_any_context_irq() and * describe the context the interrupt will be run in. * * IRQC_IS_HARDIRQ - interrupt runs in hardirq context * IRQC_IS_NESTED - interrupt runs in a nested threaded context */ enum { IRQC_IS_HARDIRQ = 0, IRQC_IS_NESTED, }; typedef irqreturn_t (*irq_handler_t)(int, void *); /** * struct irqaction - per interrupt action descriptor * @handler: interrupt handler function * @name: name of the device * @dev_id: cookie to identify the device * @percpu_dev_id: cookie to identify the device * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @flags: flags (see IRQF_* above) * @thread_fn: interrupt handler function for threaded interrupts * @thread: thread pointer for threaded interrupts * @secondary: pointer to secondary irqaction (force threading) * @thread_flags: flags related to @thread * @thread_mask: bitmask for keeping track of @thread activity * @dir: pointer to the proc/irq/NN/name entry */ struct irqaction { irq_handler_t handler; void *dev_id; void __percpu *percpu_dev_id; struct irqaction *next; irq_handler_t thread_fn; struct task_struct *thread; struct irqaction *secondary; unsigned int irq; unsigned int flags; unsigned long thread_flags; unsigned long thread_mask; const char *name; struct proc_dir_entry *dir; } ____cacheline_internodealigned_in_smp; extern irqreturn_t no_action(int cpl, void *dev_id); /* * If a (PCI) device interrupt is not connected we set dev->irq to * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we * can distingiush that case from other error returns. * * 0x80000000 is guaranteed to be outside the available range of interrupts * and easy to distinguish from other possible incorrect values. */ #define IRQ_NOTCONNECTED (1U << 31) extern int __must_check request_threaded_irq(unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long flags, const char *name, void *dev); /** * request_irq - Add a handler for an interrupt line * @irq: The interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Primary handler for threaded interrupts * If NULL, the default primary handler is installed * @flags: Handling flags * @name: Name of the device generating this interrupt * @dev: A cookie passed to the handler function * * This call allocates an interrupt and establishes a handler; see * the documentation for request_threaded_irq() for details. */ static inline int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev) { return request_threaded_irq(irq, handler, NULL, flags, name, dev); } extern int __must_check request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); extern int __must_check __request_percpu_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *devname, void __percpu *percpu_dev_id); extern int __must_check request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev); static inline int __must_check request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id) { return __request_percpu_irq(irq, handler, 0, devname, percpu_dev_id); } extern int __must_check request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *dev); extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); extern const void *free_nmi(unsigned int irq, void *dev_id); extern void free_percpu_nmi(unsigned int irq, void __percpu *percpu_dev_id); struct device; extern int __must_check devm_request_threaded_irq(struct device *dev, unsigned int irq, irq_handler_t handler, irq_handler_t thread_fn, unsigned long irqflags, const char *devname, void *dev_id); static inline int __must_check devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) { return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags, devname, dev_id); } extern int __must_check devm_request_any_context_irq(struct device *dev, unsigned int irq, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id); extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); /* * On lockdep we dont want to enable hardirqs in hardirq * context. Use local_irq_enable_in_hardirq() to annotate * kernel code that has to do this nevertheless (pretty much * the only valid case is for old/broken hardware that is * insanely slow). * * NOTE: in theory this might break fragile code that relies * on hardirq delivery - in practice we dont seem to have such * places left. So the only effect should be slightly increased * irqs-off latencies. */ #ifdef CONFIG_LOCKDEP # define local_irq_enable_in_hardirq() do { } while (0) #else # define local_irq_enable_in_hardirq() local_irq_enable() #endif extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); extern void disable_irq(unsigned int irq); extern void disable_percpu_irq(unsigned int irq); extern void enable_irq(unsigned int irq); extern void enable_percpu_irq(unsigned int irq, unsigned int type); extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); extern void disable_nmi_nosync(unsigned int irq); extern void disable_percpu_nmi(unsigned int irq); extern void enable_nmi(unsigned int irq); extern void enable_percpu_nmi(unsigned int irq, unsigned int type); extern int prepare_percpu_nmi(unsigned int irq); extern void teardown_percpu_nmi(unsigned int irq); extern int irq_inject_interrupt(unsigned int irq); /* The following three functions are for the core kernel use only. */ extern void suspend_device_irqs(void); extern void resume_device_irqs(void); extern void rearm_wake_irq(unsigned int irq); /** * struct irq_affinity_notify - context for notification of IRQ affinity changes * @irq: Interrupt to which notification applies * @kref: Reference count, for internal use * @work: Work item, for internal use * @notify: Function to be called on change. This will be * called in process context. * @release: Function to be called on release. This will be * called in process context. Once registered, the * structure must only be freed when this function is * called or later. */ struct irq_affinity_notify { unsigned int irq; struct kref kref; struct work_struct work; void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); void (*release)(struct kref *ref); }; #define IRQ_AFFINITY_MAX_SETS 4 /** * struct irq_affinity - Description for automatic irq affinity assignements * @pre_vectors: Don't apply affinity to @pre_vectors at beginning of * the MSI(-X) vector space * @post_vectors: Don't apply affinity to @post_vectors at end of * the MSI(-X) vector space * @nr_sets: The number of interrupt sets for which affinity * spreading is required * @set_size: Array holding the size of each interrupt set * @calc_sets: Callback for calculating the number and size * of interrupt sets * @priv: Private data for usage by @calc_sets, usually a * pointer to driver/device specific data. */ struct irq_affinity { unsigned int pre_vectors; unsigned int post_vectors; unsigned int nr_sets; unsigned int set_size[IRQ_AFFINITY_MAX_SETS]; void (*calc_sets)(struct irq_affinity *, unsigned int nvecs); void *priv; }; /** * struct irq_affinity_desc - Interrupt affinity descriptor * @mask: cpumask to hold the affinity assignment * @is_managed: 1 if the interrupt is managed internally */ struct irq_affinity_desc { struct cpumask mask; unsigned int is_managed : 1; }; #if defined(CONFIG_SMP) extern cpumask_var_t irq_default_affinity; /* Internal implementation. Use the helpers below */ extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask, bool force); /** * irq_set_affinity - Set the irq affinity of a given irq * @irq: Interrupt to set affinity * @cpumask: cpumask * * Fails if cpumask does not contain an online CPU */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) { return __irq_set_affinity(irq, cpumask, false); } /** * irq_force_affinity - Force the irq affinity of a given irq * @irq: Interrupt to set affinity * @cpumask: cpumask * * Same as irq_set_affinity, but without checking the mask against * online cpus. * * Solely for low level cpu hotplug code, where we need to make per * cpu interrupts affine before the cpu becomes online. */ static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) { return __irq_set_affinity(irq, cpumask, true); } extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); extern int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); struct irq_affinity_desc * irq_create_affinity_masks(unsigned int nvec, struct irq_affinity *affd); unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec, const struct irq_affinity *affd); #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) { return -EINVAL; } static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) { return 0; } static inline int irq_can_set_affinity(unsigned int irq) { return 0; } static inline int irq_select_affinity(unsigned int irq) { return 0; } static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) { return -EINVAL; } static inline int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) { return 0; } static inline struct irq_affinity_desc * irq_create_affinity_masks(unsigned int nvec, struct irq_affinity *affd) { return NULL; } static inline unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec, const struct irq_affinity *affd) { return maxvec; } #endif /* CONFIG_SMP */ /* * Special lockdep variants of irq disabling/enabling. * These should be used for locking constructs that * know that a particular irq context which is disabled, * and which is the only irq-context user of a lock, * that it's safe to take the lock in the irq-disabled * section without disabling hardirqs. * * On !CONFIG_LOCKDEP they are equivalent to the normal * irq disable/enable methods. */ static inline void disable_irq_nosync_lockdep(unsigned int irq) { disable_irq_nosync(irq); #ifdef CONFIG_LOCKDEP local_irq_disable(); #endif } static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags) { disable_irq_nosync(irq); #ifdef CONFIG_LOCKDEP local_irq_save(*flags); #endif } static inline void disable_irq_lockdep(unsigned int irq) { disable_irq(irq); #ifdef CONFIG_LOCKDEP local_irq_disable(); #endif } static inline void enable_irq_lockdep(unsigned int irq) { #ifdef CONFIG_LOCKDEP local_irq_enable(); #endif enable_irq(irq); } static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags) { #ifdef CONFIG_LOCKDEP local_irq_restore(*flags); #endif enable_irq(irq); } /* IRQ wakeup (PM) control: */ extern int irq_set_irq_wake(unsigned int irq, unsigned int on); static inline int enable_irq_wake(unsigned int irq) { return irq_set_irq_wake(irq, 1); } static inline int disable_irq_wake(unsigned int irq) { return irq_set_irq_wake(irq, 0); } /* * irq_get_irqchip_state/irq_set_irqchip_state specific flags */ enum irqchip_irq_state { IRQCHIP_STATE_PENDING, /* Is interrupt pending? */ IRQCHIP_STATE_ACTIVE, /* Is interrupt in progress? */ IRQCHIP_STATE_MASKED, /* Is interrupt masked? */ IRQCHIP_STATE_LINE_LEVEL, /* Is IRQ line high? */ }; extern int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool *state); extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, bool state); #ifdef CONFIG_IRQ_FORCED_THREADING # ifdef CONFIG_PREEMPT_RT # define force_irqthreads (true) # else extern bool force_irqthreads; # endif #else #define force_irqthreads (0) #endif #ifndef local_softirq_pending #ifndef local_softirq_pending_ref #define local_softirq_pending_ref irq_stat.__softirq_pending #endif #define local_softirq_pending() (__this_cpu_read(local_softirq_pending_ref)) #define set_softirq_pending(x) (__this_cpu_write(local_softirq_pending_ref, (x))) #define or_softirq_pending(x) (__this_cpu_or(local_softirq_pending_ref, (x))) #endif /* local_softirq_pending */ /* Some architectures might implement lazy enabling/disabling of * interrupts. In some cases, such as stop_machine, we might want * to ensure that after a local_irq_disable(), interrupts have * really been disabled in hardware. Such architectures need to * implement the following hook. */ #ifndef hard_irq_disable #define hard_irq_disable() do { } while(0) #endif /* PLEASE, avoid to allocate new softirqs, if you need not _really_ high frequency threaded job scheduling. For almost all the purposes tasklets are more than enough. F.e. all serial device BHs et al. should be converted to tasklets, not to softirqs. */ enum { HI_SOFTIRQ=0, TIMER_SOFTIRQ, NET_TX_SOFTIRQ, NET_RX_SOFTIRQ, BLOCK_SOFTIRQ, IRQ_POLL_SOFTIRQ, TASKLET_SOFTIRQ, SCHED_SOFTIRQ, HRTIMER_SOFTIRQ, RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */ NR_SOFTIRQS }; #define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ)) /* Softirq's where the handling might be long: */ #define LONG_SOFTIRQ_MASK ((1 << NET_TX_SOFTIRQ) | \ (1 << NET_RX_SOFTIRQ) | \ (1 << BLOCK_SOFTIRQ) | \ (1 << IRQ_POLL_SOFTIRQ) | \ (1 << TASKLET_SOFTIRQ)) /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. */ extern const char * const softirq_to_name[NR_SOFTIRQS]; /* softirq mask and active fields moved to irq_cpustat_t in * asm/hardirq.h to get better cache usage. KAO */ struct softirq_action { void (*action)(struct softirq_action *); }; asmlinkage void do_softirq(void); asmlinkage void __do_softirq(void); #ifdef __ARCH_HAS_DO_SOFTIRQ void do_softirq_own_stack(void); #else static inline void do_softirq_own_stack(void) { __do_softirq(); } #endif extern void open_softirq(int nr, void (*action)(struct softirq_action *)); extern void softirq_init(void); extern void __raise_softirq_irqoff(unsigned int nr); extern void raise_softirq_irqoff(unsigned int nr); extern void raise_softirq(unsigned int nr); DECLARE_PER_CPU(struct task_struct *, ksoftirqd); DECLARE_PER_CPU(__u32, active_softirqs); static inline struct task_struct *this_cpu_ksoftirqd(void) { return this_cpu_read(ksoftirqd); } /* Tasklets --- multithreaded analogue of BHs. This API is deprecated. Please consider using threaded IRQs instead: https://lore.kernel.org/lkml/20200716081538.2sivhkj4hcyrusem@linutronix.de Main feature differing them of generic softirqs: tasklet is running only on one CPU simultaneously. Main feature differing them of BHs: different tasklets may be run simultaneously on different CPUs. Properties: * If tasklet_schedule() is called, then tasklet is guaranteed to be executed on some cpu at least once after this. * If the tasklet is already scheduled, but its execution is still not started, it will be executed only once. * If this tasklet is already running on another CPU (or schedule is called from tasklet itself), it is rescheduled for later. * Tasklet is strictly serialized wrt itself, but not wrt another tasklets. If client needs some intertask synchronization, he makes it with spinlocks. */ struct tasklet_struct { struct tasklet_struct *next; unsigned long state; atomic_t count; bool use_callback; union { void (*func)(unsigned long data); void (*callback)(struct tasklet_struct *t); }; unsigned long data; }; #define DECLARE_TASKLET(name, _callback) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(0), \ .callback = _callback, \ .use_callback = true, \ } #define DECLARE_TASKLET_DISABLED(name, _callback) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(1), \ .callback = _callback, \ .use_callback = true, \ } #define from_tasklet(var, callback_tasklet, tasklet_fieldname) \ container_of(callback_tasklet, typeof(*var), tasklet_fieldname) #define DECLARE_TASKLET_OLD(name, _func) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(0), \ .func = _func, \ } #define DECLARE_TASKLET_DISABLED_OLD(name, _func) \ struct tasklet_struct name = { \ .count = ATOMIC_INIT(1), \ .func = _func, \ } enum { TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ }; #ifdef CONFIG_SMP static inline int tasklet_trylock(struct tasklet_struct *t) { return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); } static inline void tasklet_unlock(struct tasklet_struct *t) { smp_mb__before_atomic(); clear_bit(TASKLET_STATE_RUN, &(t)->state); } static inline void tasklet_unlock_wait(struct tasklet_struct *t) { while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } } #else #define tasklet_trylock(t) 1 #define tasklet_unlock_wait(t) do { } while (0) #define tasklet_unlock(t) do { } while (0) #endif extern void __tasklet_schedule(struct tasklet_struct *t); static inline void tasklet_schedule(struct tasklet_struct *t) { if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) __tasklet_schedule(t); } extern void __tasklet_hi_schedule(struct tasklet_struct *t); static inline void tasklet_hi_schedule(struct tasklet_struct *t) { if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) __tasklet_hi_schedule(t); } static inline void tasklet_disable_nosync(struct tasklet_struct *t) { atomic_inc(&t->count); smp_mb__after_atomic(); } static inline void tasklet_disable(struct tasklet_struct *t) { tasklet_disable_nosync(t); tasklet_unlock_wait(t); smp_mb(); } static inline void tasklet_enable(struct tasklet_struct *t) { smp_mb__before_atomic(); atomic_dec(&t->count); } extern void tasklet_kill(struct tasklet_struct *t); extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); extern void tasklet_setup(struct tasklet_struct *t, void (*callback)(struct tasklet_struct *)); /* * Autoprobing for irqs: * * probe_irq_on() and probe_irq_off() provide robust primitives * for accurate IRQ probing during kernel initialization. They are * reasonably simple to use, are not "fooled" by spurious interrupts, * and, unlike other attempts at IRQ probing, they do not get hung on * stuck interrupts (such as unused PS2 mouse interfaces on ASUS boards). * * For reasonably foolproof probing, use them as follows: * * 1. clear and/or mask the device's internal interrupt. * 2. sti(); * 3. irqs = probe_irq_on(); // "take over" all unassigned idle IRQs * 4. enable the device and cause it to trigger an interrupt. * 5. wait for the device to interrupt, using non-intrusive polling or a delay. * 6. irq = probe_irq_off(irqs); // get IRQ number, 0=none, negative=multiple * 7. service the device to clear its pending interrupt. * 8. loop again if paranoia is required. * * probe_irq_on() returns a mask of allocated irq's. * * probe_irq_off() takes the mask as a parameter, * and returns the irq number which occurred, * or zero if none occurred, or a negative irq number * if more than one irq occurred. */ #if !defined(CONFIG_GENERIC_IRQ_PROBE) static inline unsigned long probe_irq_on(void) { return 0; } static inline int probe_irq_off(unsigned long val) { return 0; } static inline unsigned int probe_irq_mask(unsigned long val) { return 0; } #else extern unsigned long probe_irq_on(void); /* returns 0 on failure */ extern int probe_irq_off(unsigned long); /* returns 0 or negative on failure */ extern unsigned int probe_irq_mask(unsigned long); /* returns mask of ISA interrupts */ #endif #ifdef CONFIG_PROC_FS /* Initialize /proc/irq/ */ extern void init_irq_proc(void); #else static inline void init_irq_proc(void) { } #endif #ifdef CONFIG_IRQ_TIMINGS void irq_timings_enable(void); void irq_timings_disable(void); u64 irq_timings_next_event(u64 now); #endif struct seq_file; int show_interrupts(struct seq_file *p, void *v); int arch_show_interrupts(struct seq_file *p, int prec); extern int early_irq_init(void); extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); /* * We want to know which function is an entrypoint of a hardirq or a softirq. */ #ifndef __irq_entry # define __irq_entry __section(".irqentry.text") #endif #define __softirq_entry __section(".softirqentry.text") #endif |
| 5 5 5 5 5 5 14 1 2 2 1 5 2 2 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 | #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/irq_work.h> #include <linux/slab.h> #include <linux/filter.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/wait.h> #include <linux/poll.h> #include <linux/kmemleak.h> #include <uapi/linux/btf.h> #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) /* non-mmap()'able part of bpf_ringbuf (everything up to consumer page) */ #define RINGBUF_PGOFF \ (offsetof(struct bpf_ringbuf, consumer_pos) >> PAGE_SHIFT) /* consumer page and producer page */ #define RINGBUF_POS_PAGES 2 #define RINGBUF_MAX_RECORD_SZ (UINT_MAX/4) /* Maximum size of ring buffer area is limited by 32-bit page offset within * record header, counted in pages. Reserve 8 bits for extensibility, and take * into account few extra pages for consumer/producer pages and * non-mmap()'able parts. This gives 64GB limit, which seems plenty for single * ring buffer. */ #define RINGBUF_MAX_DATA_SZ \ (((1ULL << 24) - RINGBUF_POS_PAGES - RINGBUF_PGOFF) * PAGE_SIZE) struct bpf_ringbuf { wait_queue_head_t waitq; struct irq_work work; u64 mask; struct page **pages; int nr_pages; spinlock_t spinlock ____cacheline_aligned_in_smp; /* Consumer and producer counters are put into separate pages to allow * mapping consumer page as r/w, but restrict producer page to r/o. * This protects producer position from being modified by user-space * application and ruining in-kernel position tracking. */ unsigned long consumer_pos __aligned(PAGE_SIZE); unsigned long producer_pos __aligned(PAGE_SIZE); char data[] __aligned(PAGE_SIZE); }; struct bpf_ringbuf_map { struct bpf_map map; struct bpf_map_memory memory; struct bpf_ringbuf *rb; }; /* 8-byte ring buffer record header structure */ struct bpf_ringbuf_hdr { u32 len; u32 pg_off; }; static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | __GFP_ZERO; int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; struct page **pages, *page; struct bpf_ringbuf *rb; size_t array_size; int i; /* Each data page is mapped twice to allow "virtual" * continuous read of samples wrapping around the end of ring * buffer area: * ------------------------------------------------------ * | meta pages | real data pages | same data pages | * ------------------------------------------------------ * | | 1 2 3 4 5 6 7 8 9 | 1 2 3 4 5 6 7 8 9 | * ------------------------------------------------------ * | | TA DA | TA DA | * ------------------------------------------------------ * ^^^^^^^ * | * Here, no need to worry about special handling of wrapped-around * data due to double-mapped data pages. This works both in kernel and * when mmap()'ed in user-space, simplifying both kernel and * user-space implementations significantly. */ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); if (array_size > PAGE_SIZE) pages = vmalloc_node(array_size, numa_node); else pages = kmalloc_node(array_size, flags, numa_node); if (!pages) return NULL; for (i = 0; i < nr_pages; i++) { page = alloc_pages_node(numa_node, flags, 0); if (!page) { nr_pages = i; goto err_free_pages; } pages[i] = page; if (i >= nr_meta_pages) pages[nr_data_pages + i] = page; } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { kmemleak_not_leak(pages); rb->pages = pages; rb->nr_pages = nr_pages; return rb; } err_free_pages: for (i = 0; i < nr_pages; i++) __free_page(pages[i]); kvfree(pages); return NULL; } static void bpf_ringbuf_notify(struct irq_work *work) { struct bpf_ringbuf *rb = container_of(work, struct bpf_ringbuf, work); wake_up_all(&rb->waitq); } static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) { struct bpf_ringbuf *rb; rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) return ERR_PTR(-ENOMEM); spin_lock_init(&rb->spinlock); init_waitqueue_head(&rb->waitq); init_irq_work(&rb->work, bpf_ringbuf_notify); rb->mask = data_sz - 1; rb->consumer_pos = 0; rb->producer_pos = 0; return rb; } static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { struct bpf_ringbuf_map *rb_map; u64 cost; int err; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size || attr->value_size || !is_power_of_2(attr->max_entries) || !PAGE_ALIGNED(attr->max_entries)) return ERR_PTR(-EINVAL); #ifdef CONFIG_64BIT /* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */ if (attr->max_entries > RINGBUF_MAX_DATA_SZ) return ERR_PTR(-E2BIG); #endif rb_map = kzalloc(sizeof(*rb_map), GFP_USER); if (!rb_map) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&rb_map->map, attr); cost = sizeof(struct bpf_ringbuf_map) + sizeof(struct bpf_ringbuf) + attr->max_entries; err = bpf_map_charge_init(&rb_map->map.memory, cost); if (err) goto err_free_map; rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); if (IS_ERR(rb_map->rb)) { err = PTR_ERR(rb_map->rb); goto err_uncharge; } return &rb_map->map; err_uncharge: bpf_map_charge_finish(&rb_map->map.memory); err_free_map: kfree(rb_map); return ERR_PTR(err); } static void bpf_ringbuf_free(struct bpf_ringbuf *rb) { /* copy pages pointer and nr_pages to local variable, as we are going * to unmap rb itself with vunmap() below */ struct page **pages = rb->pages; int i, nr_pages = rb->nr_pages; vunmap(rb); for (i = 0; i < nr_pages; i++) __free_page(pages[i]); kvfree(pages); } static void ringbuf_map_free(struct bpf_map *map) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); bpf_ringbuf_free(rb_map->rb); kfree(rb_map); } static void *ringbuf_map_lookup_elem(struct bpf_map *map, void *key) { return ERR_PTR(-ENOTSUPP); } static int ringbuf_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { return -ENOTSUPP; } static int ringbuf_map_delete_elem(struct bpf_map *map, void *key) { return -ENOTSUPP; } static int ringbuf_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static int ringbuf_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); if (vma->vm_flags & VM_WRITE) { /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; } else { vma->vm_flags &= ~VM_MAYWRITE; } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); } static unsigned long ringbuf_avail_data_sz(struct bpf_ringbuf *rb) { unsigned long cons_pos, prod_pos; cons_pos = smp_load_acquire(&rb->consumer_pos); prod_pos = smp_load_acquire(&rb->producer_pos); return prod_pos - cons_pos; } static __poll_t ringbuf_map_poll(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts) { struct bpf_ringbuf_map *rb_map; rb_map = container_of(map, struct bpf_ringbuf_map, map); poll_wait(filp, &rb_map->rb->waitq, pts); if (ringbuf_avail_data_sz(rb_map->rb)) return EPOLLIN | EPOLLRDNORM; return 0; } static int ringbuf_map_btf_id; const struct bpf_map_ops ringbuf_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = ringbuf_map_alloc, .map_free = ringbuf_map_free, .map_mmap = ringbuf_map_mmap, .map_poll = ringbuf_map_poll, .map_lookup_elem = ringbuf_map_lookup_elem, .map_update_elem = ringbuf_map_update_elem, .map_delete_elem = ringbuf_map_delete_elem, .map_get_next_key = ringbuf_map_get_next_key, .map_btf_name = "bpf_ringbuf_map", .map_btf_id = &ringbuf_map_btf_id, }; /* Given pointer to ring buffer record metadata and struct bpf_ringbuf itself, * calculate offset from record metadata to ring buffer in pages, rounded * down. This page offset is stored as part of record metadata and allows to * restore struct bpf_ringbuf * from record pointer. This page offset is * stored at offset 4 of record metadata header. */ static size_t bpf_ringbuf_rec_pg_off(struct bpf_ringbuf *rb, struct bpf_ringbuf_hdr *hdr) { return ((void *)hdr - (void *)rb) >> PAGE_SHIFT; } /* Given pointer to ring buffer record header, restore pointer to struct * bpf_ringbuf itself by using page offset stored at offset 4 */ static struct bpf_ringbuf * bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr) { unsigned long addr = (unsigned long)(void *)hdr; unsigned long off = (unsigned long)hdr->pg_off << PAGE_SHIFT; return (void*)((addr & PAGE_MASK) - off); } static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) { unsigned long cons_pos, prod_pos, new_prod_pos, flags; u32 len, pg_off; struct bpf_ringbuf_hdr *hdr; if (unlikely(size > RINGBUF_MAX_RECORD_SZ)) return NULL; len = round_up(size + BPF_RINGBUF_HDR_SZ, 8); if (len > rb->mask + 1) return NULL; cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { if (!spin_trylock_irqsave(&rb->spinlock, flags)) return NULL; } else { spin_lock_irqsave(&rb->spinlock, flags); } prod_pos = rb->producer_pos; new_prod_pos = prod_pos + len; /* check for out of ringbuf space by ensuring producer position * doesn't advance more than (ringbuf_size - 1) ahead */ if (new_prod_pos - cons_pos > rb->mask) { spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } hdr = (void *)rb->data + (prod_pos & rb->mask); pg_off = bpf_ringbuf_rec_pg_off(rb, hdr); hdr->len = size | BPF_RINGBUF_BUSY_BIT; hdr->pg_off = pg_off; /* pairs with consumer's smp_load_acquire() */ smp_store_release(&rb->producer_pos, new_prod_pos); spin_unlock_irqrestore(&rb->spinlock, flags); return (void *)hdr + BPF_RINGBUF_HDR_SZ; } BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) { struct bpf_ringbuf_map *rb_map; if (unlikely(flags)) return 0; rb_map = container_of(map, struct bpf_ringbuf_map, map); return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size); } const struct bpf_func_proto bpf_ringbuf_reserve_proto = { .func = bpf_ringbuf_reserve, .ret_type = RET_PTR_TO_ALLOC_MEM_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, }; static void bpf_ringbuf_commit(void *sample, u64 flags, bool discard) { unsigned long rec_pos, cons_pos; struct bpf_ringbuf_hdr *hdr; struct bpf_ringbuf *rb; u32 new_len; hdr = sample - BPF_RINGBUF_HDR_SZ; rb = bpf_ringbuf_restore_from_rec(hdr); new_len = hdr->len ^ BPF_RINGBUF_BUSY_BIT; if (discard) new_len |= BPF_RINGBUF_DISCARD_BIT; /* update record header with correct final size prefix */ xchg(&hdr->len, new_len); /* if consumer caught up and is waiting for our record, notify about * new data availability */ rec_pos = (void *)hdr - (void *)rb->data; cons_pos = smp_load_acquire(&rb->consumer_pos) & rb->mask; if (flags & BPF_RB_FORCE_WAKEUP) irq_work_queue(&rb->work); else if (cons_pos == rec_pos && !(flags & BPF_RB_NO_WAKEUP)) irq_work_queue(&rb->work); } BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) { bpf_ringbuf_commit(sample, flags, false /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_submit_proto = { .func = bpf_ringbuf_submit, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_ALLOC_MEM, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) { bpf_ringbuf_commit(sample, flags, true /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_discard_proto = { .func = bpf_ringbuf_discard, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_ALLOC_MEM, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_ringbuf_output, struct bpf_map *, map, void *, data, u64, size, u64, flags) { struct bpf_ringbuf_map *rb_map; void *rec; if (unlikely(flags & ~(BPF_RB_NO_WAKEUP | BPF_RB_FORCE_WAKEUP))) return -EINVAL; rb_map = container_of(map, struct bpf_ringbuf_map, map); rec = __bpf_ringbuf_reserve(rb_map->rb, size); if (!rec) return -EAGAIN; memcpy(rec, data, size); bpf_ringbuf_commit(rec, flags, false /* discard */); return 0; } const struct bpf_func_proto bpf_ringbuf_output_proto = { .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_ringbuf_query, struct bpf_map *, map, u64, flags) { struct bpf_ringbuf *rb; rb = container_of(map, struct bpf_ringbuf_map, map)->rb; switch (flags) { case BPF_RB_AVAIL_DATA: return ringbuf_avail_data_sz(rb); case BPF_RB_RING_SIZE: return rb->mask + 1; case BPF_RB_CONS_POS: return smp_load_acquire(&rb->consumer_pos); case BPF_RB_PROD_POS: return smp_load_acquire(&rb->producer_pos); default: return 0; } } const struct bpf_func_proto bpf_ringbuf_query_proto = { .func = bpf_ringbuf_query, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; |
| 303 51 283 283 13 274 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2018 Christoph Hellwig. */ #include <linux/module.h> #include <linux/compiler.h> #include <linux/fs.h> #include <linux/iomap.h> #include "trace.h" /* * Execute a iomap write on a segment of the mapping that spans a * contiguous range of pages that have identical block mapping state. * * This avoids the need to map pages individually, do individual allocations * for each page and most importantly avoid the need for filesystem specific * locking per page. Instead, all the operations are amortised over the entire * range of pages. It is assumed that the filesystems will lock whatever * resources they require in the iomap_begin call, and release them in the * iomap_end call. */ loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, const struct iomap_ops *ops, void *data, iomap_actor_t actor) { struct iomap iomap = { .type = IOMAP_HOLE }; struct iomap srcmap = { .type = IOMAP_HOLE }; loff_t written = 0, ret; u64 end; trace_iomap_apply(inode, pos, length, flags, ops, actor, _RET_IP_); /* * Need to map a range from start position for length bytes. This can * span multiple pages - it is only guaranteed to return a range of a * single type of pages (e.g. all into a hole, all mapped or all * unwritten). Failure at this point has nothing to undo. * * If allocation is required for this range, reserve the space now so * that the allocation is guaranteed to succeed later on. Once we copy * the data into the page cache pages, then we cannot fail otherwise we * expose transient stale data. If the reserve fails, we can safely * back out at this point as there is nothing to undo. */ ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap); if (ret) return ret; if (WARN_ON(iomap.offset > pos)) { written = -EIO; goto out; } if (WARN_ON(iomap.length == 0)) { written = -EIO; goto out; } trace_iomap_apply_dstmap(inode, &iomap); if (srcmap.type != IOMAP_HOLE) trace_iomap_apply_srcmap(inode, &srcmap); /* * Cut down the length to the one actually provided by the filesystem, * as it might not be able to give us the whole size that we requested. */ end = iomap.offset + iomap.length; if (srcmap.type != IOMAP_HOLE) end = min(end, srcmap.offset + srcmap.length); if (pos + length > end) length = end - pos; /* * Now that we have guaranteed that the space allocation will succeed, * we can do the copy-in page by page without having to worry about * failures exposing transient data. * * To support COW operations, we read in data for partially blocks from * the srcmap if the file system filled it in. In that case we the * length needs to be limited to the earlier of the ends of the iomaps. * If the file system did not provide a srcmap we pass in the normal * iomap into the actors so that they don't need to have special * handling for the two cases. */ written = actor(inode, pos, length, data, &iomap, srcmap.type != IOMAP_HOLE ? &srcmap : &iomap); out: /* * Now the data has been copied, commit the range we've copied. This * should not fail unless the filesystem has had a fatal error. */ if (ops->iomap_end) { ret = ops->iomap_end(inode, pos, length, written > 0 ? written : 0, flags, &iomap); } return written ? written : ret; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 | #undef TRACE_SYSTEM #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_QDISC_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/pkt_sched.h> #include <net/sch_generic.h> TRACE_EVENT(qdisc_dequeue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, int packets, struct sk_buff *skb), TP_ARGS(qdisc, txq, packets, skb), TP_STRUCT__entry( __field( struct Qdisc *, qdisc ) __field(const struct netdev_queue *, txq ) __field( int, packets ) __field( void *, skbaddr ) __field( int, ifindex ) __field( u32, handle ) __field( u32, parent ) __field( unsigned long, txq_state) ), /* skb==NULL indicate packets dequeued was 0, even when packets==1 */ TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->packets = skb ? packets : 0; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; __entry->txq_state = txq->state; ), TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); TRACE_EVENT(qdisc_reset, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_destroy, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev, qdisc_dev(q)); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_create, TP_PROTO(const struct Qdisc_ops *ops, struct net_device *dev, u32 parent), TP_ARGS(ops, dev, parent), TP_STRUCT__entry( __string( dev, dev->name ) __string( kind, ops->id ) __field( u32, parent ) ), TP_fast_assign( __assign_str(dev, dev->name); __assign_str(kind, ops->id); __entry->parent = parent; ), TP_printk("dev=%s kind=%s parent=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent)) ); #endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 2 3 3 3 31 31 30 2 24 3 27 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 | // SPDX-License-Identifier: LGPL-2.1 /* * Copyright IBM Corporation, 2007 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * */ #include <linux/slab.h> #include "ext4_jbd2.h" #include "ext4_extents.h" /* * The contiguous blocks details which can be * represented by a single extent */ struct migrate_struct { ext4_lblk_t first_block, last_block, curr_block; ext4_fsblk_t first_pblock, last_pblock; }; static int finish_range(handle_t *handle, struct inode *inode, struct migrate_struct *lb) { int retval = 0, needed; struct ext4_extent newext; struct ext4_ext_path *path; if (lb->first_pblock == 0) return 0; /* Add the extent to temp inode*/ newext.ee_block = cpu_to_le32(lb->first_block); newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1); ext4_ext_store_pblock(&newext, lb->first_pblock); /* Locking only for convinience since we are operating on temp inode */ down_write(&EXT4_I(inode)->i_data_sem); path = ext4_find_extent(inode, lb->first_block, NULL, 0); if (IS_ERR(path)) { retval = PTR_ERR(path); path = NULL; goto err_out; } /* * Calculate the credit needed to inserting this extent * Since we are doing this in loop we may accumalate extra * credit. But below we try to not accumalate too much * of them by restarting the journal. */ needed = ext4_ext_calc_credits_for_single_extent(inode, lb->last_block - lb->first_block + 1, path); retval = ext4_datasem_ensure_credits(handle, inode, needed, needed, 0); if (retval < 0) goto err_out; retval = ext4_ext_insert_extent(handle, inode, &path, &newext, 0); err_out: up_write((&EXT4_I(inode)->i_data_sem)); ext4_ext_drop_refs(path); kfree(path); lb->first_pblock = 0; return retval; } static int update_extent_range(handle_t *handle, struct inode *inode, ext4_fsblk_t pblock, struct migrate_struct *lb) { int retval; /* * See if we can add on to the existing range (if it exists) */ if (lb->first_pblock && (lb->last_pblock+1 == pblock) && (lb->last_block+1 == lb->curr_block)) { lb->last_pblock = pblock; lb->last_block = lb->curr_block; lb->curr_block++; return 0; } /* * Start a new range. */ retval = finish_range(handle, inode, lb); lb->first_pblock = lb->last_pblock = pblock; lb->first_block = lb->last_block = lb->curr_block; lb->curr_block++; return retval; } static int update_ind_extent_range(handle_t *handle, struct inode *inode, ext4_fsblk_t pblock, struct migrate_struct *lb) { struct buffer_head *bh; __le32 *i_data; int i, retval = 0; unsigned long max_entries = inode->i_sb->s_blocksize >> 2; bh = ext4_sb_bread(inode->i_sb, pblock, 0); if (IS_ERR(bh)) return PTR_ERR(bh); i_data = (__le32 *)bh->b_data; for (i = 0; i < max_entries; i++) { if (i_data[i]) { retval = update_extent_range(handle, inode, le32_to_cpu(i_data[i]), lb); if (retval) break; } else { lb->curr_block++; } } put_bh(bh); return retval; } static int update_dind_extent_range(handle_t *handle, struct inode *inode, ext4_fsblk_t pblock, struct migrate_struct *lb) { struct buffer_head *bh; __le32 *i_data; int i, retval = 0; unsigned long max_entries = inode->i_sb->s_blocksize >> 2; bh = ext4_sb_bread(inode->i_sb, pblock, 0); if (IS_ERR(bh)) return PTR_ERR(bh); i_data = (__le32 *)bh->b_data; for (i = 0; i < max_entries; i++) { if (i_data[i]) { retval = update_ind_extent_range(handle, inode, le32_to_cpu(i_data[i]), lb); if (retval) break; } else { /* Only update the file block number */ lb->curr_block += max_entries; } } put_bh(bh); return retval; } static int update_tind_extent_range(handle_t *handle, struct inode *inode, ext4_fsblk_t pblock, struct migrate_struct *lb) { struct buffer_head *bh; __le32 *i_data; int i, retval = 0; unsigned long max_entries = inode->i_sb->s_blocksize >> 2; bh = ext4_sb_bread(inode->i_sb, pblock, 0); if (IS_ERR(bh)) return PTR_ERR(bh); i_data = (__le32 *)bh->b_data; for (i = 0; i < max_entries; i++) { if (i_data[i]) { retval = update_dind_extent_range(handle, inode, le32_to_cpu(i_data[i]), lb); if (retval) break; } else { /* Only update the file block number */ lb->curr_block += max_entries * max_entries; } } put_bh(bh); return retval; } static int free_dind_blocks(handle_t *handle, struct inode *inode, __le32 i_data) { int i; __le32 *tmp_idata; struct buffer_head *bh; struct super_block *sb = inode->i_sb; unsigned long max_entries = inode->i_sb->s_blocksize >> 2; int err; bh = ext4_sb_bread(sb, le32_to_cpu(i_data), 0); if (IS_ERR(bh)) return PTR_ERR(bh); tmp_idata = (__le32 *)bh->b_data; for (i = 0; i < max_entries; i++) { if (tmp_idata[i]) { err = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, ext4_free_metadata_revoke_credits(sb, 1)); if (err < 0) { put_bh(bh); return err; } ext4_free_blocks(handle, inode, NULL, le32_to_cpu(tmp_idata[i]), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } } put_bh(bh); err = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, ext4_free_metadata_revoke_credits(sb, 1)); if (err < 0) return err; ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return 0; } static int free_tind_blocks(handle_t *handle, struct inode *inode, __le32 i_data) { int i, retval = 0; __le32 *tmp_idata; struct buffer_head *bh; unsigned long max_entries = inode->i_sb->s_blocksize >> 2; bh = ext4_sb_bread(inode->i_sb, le32_to_cpu(i_data), 0); if (IS_ERR(bh)) return PTR_ERR(bh); tmp_idata = (__le32 *)bh->b_data; for (i = 0; i < max_entries; i++) { if (tmp_idata[i]) { retval = free_dind_blocks(handle, inode, tmp_idata[i]); if (retval) { put_bh(bh); return retval; } } } put_bh(bh); retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, ext4_free_metadata_revoke_credits(inode->i_sb, 1)); if (retval < 0) return retval; ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return 0; } static int free_ind_block(handle_t *handle, struct inode *inode, __le32 *i_data) { int retval; /* ei->i_data[EXT4_IND_BLOCK] */ if (i_data[0]) { retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, ext4_free_metadata_revoke_credits(inode->i_sb, 1)); if (retval < 0) return retval; ext4_free_blocks(handle, inode, NULL, le32_to_cpu(i_data[0]), 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } /* ei->i_data[EXT4_DIND_BLOCK] */ if (i_data[1]) { retval = free_dind_blocks(handle, inode, i_data[1]); if (retval) return retval; } /* ei->i_data[EXT4_TIND_BLOCK] */ if (i_data[2]) { retval = free_tind_blocks(handle, inode, i_data[2]); if (retval) return retval; } return 0; } static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode, struct inode *tmp_inode) { int retval, retval2 = 0; __le32 i_data[3]; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode); /* * One credit accounted for writing the * i_data field of the original inode */ retval = ext4_journal_ensure_credits(handle, 1, 0); if (retval < 0) goto err_out; i_data[0] = ei->i_data[EXT4_IND_BLOCK]; i_data[1] = ei->i_data[EXT4_DIND_BLOCK]; i_data[2] = ei->i_data[EXT4_TIND_BLOCK]; down_write(&EXT4_I(inode)->i_data_sem); /* * if EXT4_STATE_EXT_MIGRATE is cleared a block allocation * happened after we started the migrate. We need to * fail the migrate */ if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) { retval = -EAGAIN; up_write(&EXT4_I(inode)->i_data_sem); goto err_out; } else ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); /* * We have the extent map build with the tmp inode. * Now copy the i_data across */ ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS); memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data)); /* * Update i_blocks with the new blocks that got * allocated while adding extents for extent index * blocks. * * While converting to extents we need not * update the original inode i_blocks for extent blocks * via quota APIs. The quota update happened via tmp_inode already. */ spin_lock(&inode->i_lock); inode->i_blocks += tmp_inode->i_blocks; spin_unlock(&inode->i_lock); up_write(&EXT4_I(inode)->i_data_sem); /* * We mark the inode dirty after, because we decrement the * i_blocks when freeing the indirect meta-data blocks */ retval = free_ind_block(handle, inode, i_data); retval2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(retval2 && !retval)) retval = retval2; err_out: return retval; } static int free_ext_idx(handle_t *handle, struct inode *inode, struct ext4_extent_idx *ix) { int i, retval = 0; ext4_fsblk_t block; struct buffer_head *bh; struct ext4_extent_header *eh; block = ext4_idx_pblock(ix); bh = ext4_sb_bread(inode->i_sb, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = (struct ext4_extent_header *)bh->b_data; if (eh->eh_depth != 0) { ix = EXT_FIRST_INDEX(eh); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) { retval = free_ext_idx(handle, inode, ix); if (retval) { put_bh(bh); return retval; } } } put_bh(bh); retval = ext4_journal_ensure_credits(handle, EXT4_RESERVE_TRANS_BLOCKS, ext4_free_metadata_revoke_credits(inode->i_sb, 1)); if (retval < 0) return retval; ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return 0; } /* * Free the extent meta data blocks only */ static int free_ext_block(handle_t *handle, struct inode *inode) { int i, retval = 0; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent_header *eh = (struct ext4_extent_header *)ei->i_data; struct ext4_extent_idx *ix; if (eh->eh_depth == 0) /* * No extra blocks allocated for extent meta data */ return 0; ix = EXT_FIRST_INDEX(eh); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) { retval = free_ext_idx(handle, inode, ix); if (retval) return retval; } return retval; } int ext4_ext_migrate(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; int retval = 0, i; __le32 *i_data; struct ext4_inode_info *ei; struct inode *tmp_inode = NULL; struct migrate_struct lb; unsigned long max_entries; __u32 goal; uid_t owner[2]; /* * If the filesystem does not support extents, or the inode * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) /* * don't migrate fast symlink */ return retval; percpu_down_write(&sbi->s_writepages_rwsem); /* * Worst case we can touch the allocation bitmaps and a block * group descriptor block. We do need need to worry about * credits for modifying the quota inode. */ handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); goto out_unlock; } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; owner[0] = i_uid_read(inode); owner[1] = i_gid_read(inode); tmp_inode = ext4_new_inode(handle, d_inode(inode->i_sb->s_root), S_IFREG, NULL, goal, owner, 0); if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); goto out_unlock; } /* * Use the correct seed for checksum (i.e. the seed from 'inode'). This * is so that the metadata blocks will have the correct checksum after * the migration. */ ei = EXT4_I(inode); EXT4_I(tmp_inode)->i_csum_seed = ei->i_csum_seed; i_size_write(tmp_inode, i_size_read(inode)); /* * Set the i_nlink to zero so it will be deleted later * when we drop inode reference. */ clear_nlink(tmp_inode); ext4_ext_tree_init(handle, tmp_inode); ext4_journal_stop(handle); /* * start with one credit accounted for * superblock modification. * * For the tmp_inode we already have committed the * transaction that created the inode. Later as and * when we add extents we extent the journal */ /* * Even though we take i_mutex we can still cause block * allocation via mmap write to holes. If we have allocated * new blocks we fail migrate. New block allocation will * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated * with i_data_sem held to prevent racing with block * allocation. */ down_read(&EXT4_I(inode)->i_data_sem); ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE); up_read((&EXT4_I(inode)->i_data_sem)); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { retval = PTR_ERR(handle); goto out_tmp_inode; } i_data = ei->i_data; memset(&lb, 0, sizeof(lb)); /* 32 bit block address 4 bytes */ max_entries = inode->i_sb->s_blocksize >> 2; for (i = 0; i < EXT4_NDIR_BLOCKS; i++) { if (i_data[i]) { retval = update_extent_range(handle, tmp_inode, le32_to_cpu(i_data[i]), &lb); if (retval) goto err_out; } else lb.curr_block++; } if (i_data[EXT4_IND_BLOCK]) { retval = update_ind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_IND_BLOCK]), &lb); if (retval) goto err_out; } else lb.curr_block += max_entries; if (i_data[EXT4_DIND_BLOCK]) { retval = update_dind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_DIND_BLOCK]), &lb); if (retval) goto err_out; } else lb.curr_block += max_entries * max_entries; if (i_data[EXT4_TIND_BLOCK]) { retval = update_tind_extent_range(handle, tmp_inode, le32_to_cpu(i_data[EXT4_TIND_BLOCK]), &lb); if (retval) goto err_out; } /* * Build the last extent */ retval = finish_range(handle, tmp_inode, &lb); err_out: if (retval) /* * Failure case delete the extent information with the * tmp_inode */ free_ext_block(handle, tmp_inode); else { retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode); if (retval) /* * if we fail to swap inode data free the extent * details of the tmp inode */ free_ext_block(handle, tmp_inode); } /* We mark the tmp_inode dirty via ext4_ext_tree_init. */ retval = ext4_journal_ensure_credits(handle, 1, 0); if (retval < 0) goto out_stop; /* * Mark the tmp_inode as of size zero */ i_size_write(tmp_inode, 0); /* * set the i_blocks count to zero * so that the ext4_evict_inode() does the * right job * * We don't need to take the i_lock because * the inode is not visible to user space. */ tmp_inode->i_blocks = 0; /* Reset the extent details */ ext4_ext_tree_init(handle, tmp_inode); out_stop: ext4_journal_stop(handle); out_tmp_inode: unlock_new_inode(tmp_inode); iput(tmp_inode); out_unlock: percpu_up_write(&sbi->s_writepages_rwsem); return retval; } /* * Migrate a simple extent-based inode to use the i_blocks[] array */ int ext4_ind_migrate(struct inode *inode) { struct ext4_extent_header *eh; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_super_block *es = sbi->s_es; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_extent *ex; unsigned int i, len; ext4_lblk_t start, end; ext4_fsblk_t blk; handle_t *handle; int ret, ret2 = 0; if (!ext4_has_feature_extents(inode->i_sb) || (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EINVAL; if (ext4_has_feature_bigalloc(inode->i_sb)) return -EOPNOTSUPP; /* * In order to get correct extent info, force all delayed allocation * blocks to be allocated, otherwise delayed allocation blocks may not * be reflected and bypass the checks on extent header. */ if (test_opt(inode->i_sb, DELALLOC)) ext4_alloc_da_blocks(inode); percpu_down_write(&sbi->s_writepages_rwsem); handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_unlock; } down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_check_inode(inode); if (ret) goto errout; eh = ext_inode_hdr(inode); ex = EXT_FIRST_EXTENT(eh); if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS || eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) { ret = -EOPNOTSUPP; goto errout; } if (eh->eh_entries == 0) blk = len = start = end = 0; else { len = le16_to_cpu(ex->ee_len); blk = ext4_ext_pblock(ex); start = le32_to_cpu(ex->ee_block); end = start + len - 1; if (end >= EXT4_NDIR_BLOCKS) { ret = -EOPNOTSUPP; goto errout; } } ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); memset(ei->i_data, 0, sizeof(ei->i_data)); for (i = start; i <= end; i++) ei->i_data[i] = cpu_to_le32(blk++); ret2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret2 && !ret)) ret = ret2; errout: ext4_journal_stop(handle); up_write(&EXT4_I(inode)->i_data_sem); out_unlock: percpu_up_write(&sbi->s_writepages_rwsem); return ret; } |
| 38 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * net busy poll support * Copyright(c) 2013 Intel Corporation. * * Author: Eliezer Tamir * * Contact Information: * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> */ #ifndef _LINUX_NET_BUSY_POLL_H #define _LINUX_NET_BUSY_POLL_H #include <linux/netdevice.h> #include <linux/sched/clock.h> #include <linux/sched/signal.h> #include <net/ip.h> /* 0 - Reserved to indicate value not set * 1..NR_CPUS - Reserved for sender_cpu * NR_CPUS+1..~0 - Region available for NAPI IDs */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) #ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; extern unsigned int sysctl_net_busy_read __read_mostly; extern unsigned int sysctl_net_busy_poll __read_mostly; static inline bool net_busy_loop_on(void) { return sysctl_net_busy_poll; } static inline bool sk_can_busy_loop(const struct sock *sk) { return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current); } bool sk_busy_loop_end(void *p, unsigned long start_time); void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg); #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { return 0; } static inline bool sk_can_busy_loop(struct sock *sk) { return false; } #endif /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long busy_loop_current_time(void) { #ifdef CONFIG_NET_RX_BUSY_POLL return (unsigned long)(local_clock() >> 10); #else return 0; #endif } /* in poll/select we use the global sysctl_net_ll_poll value */ static inline bool busy_loop_timeout(unsigned long start_time) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned long bp_usec = READ_ONCE(sysctl_net_busy_poll); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } #endif return true; } static inline bool sk_busy_loop_timeout(struct sock *sk, unsigned long start_time) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned long bp_usec = READ_ONCE(sk->sk_ll_usec); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } #endif return true; } static inline void sk_busy_loop(struct sock *sk, int nonblock) { #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int napi_id = READ_ONCE(sk->sk_napi_id); if (napi_id >= MIN_NAPI_ID) napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk); #endif } /* used in the NIC receive handler to mark the skb */ static inline void skb_mark_napi_id(struct sk_buff *skb, struct napi_struct *napi) { #ifdef CONFIG_NET_RX_BUSY_POLL /* If the skb was already marked with a valid NAPI ID, avoid overwriting * it. */ if (skb->napi_id < MIN_NAPI_ID) skb->napi_id = napi->napi_id; #endif } /* used in the protocol hanlder to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif sk_rx_queue_set(sk, skb); } /* variant used for unconnected sockets */ static inline void sk_mark_napi_id_once(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL if (!READ_ONCE(sk->sk_napi_id)) WRITE_ONCE(sk->sk_napi_id, skb->napi_id); #endif } #endif /* _LINUX_NET_BUSY_POLL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(flags) 0 #endif #ifndef arch_vm_get_page_prot #define arch_vm_get_page_prot(vm_flags) __pgprot(0) #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | arch_calc_vm_flag_bits(flags); } unsigned long vm_commit_limit(void); #endif /* _LINUX_MMAN_H */ |
| 164 88 79 244 196 243 243 244 163 92 5 90 90 45 91 91 91 99 14 91 91 91 91 91 322 324 324 361 57 161 193 180 137 129 180 1 330 323 315 315 315 212 134 656 656 656 617 101 101 617 100 655 656 655 621 78 45 1 44 48 48 49 2 18 182 194 182 194 185 18 194 182 1206 1206 49 2 2 17 1230 101 1034 1228 655 1020 102 91 1022 1037 226 655 483 655 192 1 184 20 178 188 340 340 340 279 362 346 349 283 296 496 496 435 2 8 433 357 355 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/mm.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_mutex * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->lock_page (access_process_vm) * * ->i_mutex (generic_perform_write) * ->mmap_lock (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_adjust) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->pgdat->lru_lock (follow_page->mark_page_accessed) * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * * ->i_mmap_rwsem * ->tasklist_lock (memory_failure, collect_procs_ao) */ static void page_cache_delete(struct address_space *mapping, struct page *page, void *shadow) { XA_STATE(xas, &mapping->i_pages, page->index); unsigned int nr = 1; mapping_set_update(&xas, mapping); /* hugetlb pages are represented by a single entry in the xarray */ if (!PageHuge(page)) { xas_set_order(&xas, page->index, compound_order(page)); nr = compound_nr(page); } VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(nr != 1 && shadow, page); xas_store(&xas, shadow); xas_init_marks(&xas); page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ if (shadow) { mapping->nrexceptional += nr; /* * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing * with reclaim does not see both counters 0 at the * same time and miss a shadow entry. */ smp_wmb(); } mapping->nrpages -= nr; } static void unaccount_page_cache_page(struct address_space *mapping, struct page *page) { int nr; /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave * stale data around in the cleancache once our page is gone */ if (PageUptodate(page) && PageMappedToDisk(page)) cleancache_put_page(page); else cleancache_invalidate_page(mapping, page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_mapped(page), page); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { int mapcount; pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); dump_page(page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); mapcount = page_mapcount(page); if (mapping_exiting(mapping) && page_count(page) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped, * and we'd prefer not to leak it: if we're wrong, * some other bad page check should catch it later. */ page_mapcount_reset(page); page_ref_sub(page, mapcount); } } /* hugetlb pages do not participate in page cache accounting. */ if (PageHuge(page)) return; nr = thp_nr_pages(page); __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { __dec_node_page_state(page, NR_FILE_THPS); filemap_nr_thps_dec(mapping); } /* * At this point page must be either written or cleaned by * truncate. Dirty page here signals a bug and loss of * unwritten data. * * This fixes dirty accounting after removing the page entirely * but leaves PageDirty set: it has no effect for truncated * page and anyway will be cleared before returning page into * buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; trace_mm_filemap_delete_from_page_cache(page); unaccount_page_cache_page(mapping, page); page_cache_delete(mapping, page, shadow); } static void page_cache_free_page(struct address_space *mapping, struct page *page) { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; if (freepage) freepage(page); if (PageTransHuge(page) && !PageHuge(page)) { page_ref_sub(page, thp_nr_pages(page)); VM_BUG_ON_PAGE(page_count(page) <= 0, page); } else { put_page(page); } } /** * delete_from_page_cache - delete page from page cache * @page: the page which the kernel is trying to remove from page cache * * This must be called only on pages that have been verified to be in the page * cache and locked. It will never put the page into the free list, the caller * has a reference on the page. */ void delete_from_page_cache(struct page *page) { struct address_space *mapping = page_mapping(page); unsigned long flags; BUG_ON(!PageLocked(page)); xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); page_cache_free_page(mapping, page); } EXPORT_SYMBOL(delete_from_page_cache); /* * page_cache_delete_batch - delete several pages from page cache * @mapping: the mapping to which pages belong * @pvec: pagevec with pages to delete * * The function walks over mapping->i_pages and removes pages passed in @pvec * from the mapping. The function expects @pvec to be sorted by page index * and is optimised for it to be dense. * It tolerates holes in @pvec (mapping entries at those indices are not * modified). The function expects only THP head pages to be present in the * @pvec. * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct pagevec *pvec) { XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); int total_pages = 0; int i = 0; struct page *page; mapping_set_update(&xas, mapping); xas_for_each(&xas, page, ULONG_MAX) { if (i >= pagevec_count(pvec)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(page)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (page != pvec->pages[i]) { VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, page); continue; } WARN_ON_ONCE(!PageLocked(page)); if (page->index == xas.xa_index) page->mapping = NULL; /* Leave page->index set: truncation lookup relies on it */ /* * Move to the next page in the vector if this is a regular * page or the index is of the last sub-page of this compound * page. */ if (page->index + compound_nr(page) - 1 == xas.xa_index) i++; xas_store(&xas, NULL); total_pages++; } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec) { int i; unsigned long flags; if (!pagevec_count(pvec)) return; xa_lock_irqsave(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); unaccount_page_cache_page(mapping, pvec->pages[i]); } page_cache_delete_batch(mapping, pvec); xa_unlock_irqrestore(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) page_cache_free_page(mapping, pvec->pages[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); return ret; } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct page *page; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { page = xas_find(&xas, max); if (xas_retry(&xas, page)) continue; /* Shadow entries don't count */ if (xa_is_value(page)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return page != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct pagevec pvec; int nr_pages; if (end_byte < start_byte) return; pagevec_init(&pvec); while (index <= end) { unsigned i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, PAGECACHE_TAG_WRITEBACK); if (!nr_pages) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; wait_on_page_writeback(page); ClearPageError(page); } pagevec_release(&pvec); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { if (dax_mapping(mapping)) return mapping->nrexceptional; return mapping->nrpages; } /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) { int err2 = filemap_fdatawait_range(mapping, lstart, lend); if (!err) err = err2; } else { /* Clear any previously stored errors */ filemap_check_errors(mapping); } } else { err = filemap_check_errors(mapping); } return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_page - replace a pagecache page with a new one * @old: page to be replaced * @new: page to replace with * @gfp_mask: allocation mode * * This function replaces a page in the pagecache with a new one. On * success it acquires the pagecache reference for the new page and * drops it for the old page. Both the old and new pages must be * locked. This function does not add the new page to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. * * Return: %0 */ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); get_page(new); new->mapping = mapping; new->index = offset; mem_cgroup_migrate(old, new); xas_lock_irqsave(&xas, flags); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irqrestore(&xas, flags); if (freepage) freepage(old); put_page(old); return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); int error; bool charged = false; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); mapping_set_update(&xas, mapping); get_page(page); page->mapping = mapping; page->index = offset; if (!huge) { error = mem_cgroup_charge(page, current->mm, gfp); if (error) goto error; charged = true; } gfp &= GFP_RECLAIM_MASK; do { unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; if (order > thp_order(page)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } } if (old) { if (shadowp) *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); if (order > thp_order(page)) { xas_split(&xas, old, order); xas_reset(&xas); } } xas_store(&xas, page); if (xas_error(&xas)) goto unlock; if (old) mapping->nrexceptional--; mapping->nrpages++; /* hugetlb pages do not participate in page cache accounting */ if (!huge) __inc_lruvec_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); if (charged) mem_cgroup_uncharge(page); goto error; } trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ put_page(page); return error; } ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add * @mapping: the page's address_space * @offset: page index * @gfp_mask: page allocation mode * * This function is used to add a page to the pagecache. It must be locked. * This function does not add the page to the LRU. The caller must do that. * * Return: %0 on success, negative error code otherwise. */ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { return __add_to_page_cache_locked(page, mapping, offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { void *shadow = NULL; int ret; __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, gfp_mask, &shadow); if (unlikely(ret)) __ClearPageLocked(page); else { /* * The page might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed page. * The exception is pages getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(PageActive(page)); if (!(gfp_mask & __GFP_WRITE) && shadow) workingset_refault(page, shadow); lru_cache_add(page); } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA struct page *__page_cache_alloc(gfp_t gfp) { int n; struct page *page; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = __alloc_pages_node(n, gfp, 0); } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } return alloc_pages(gfp, 0); } EXPORT_SYMBOL(__page_cache_alloc); #endif /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *page_waitqueue(struct page *page) { return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&page_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->page->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->page->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in wait_on_page_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void wake_up_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; key.page = page; key.bit_nr = bit_nr; key.page_match = 0; bookmark.flags = 0; bookmark.private = NULL; bookmark.func = NULL; INIT_LIST_HEAD(&bookmark.entry); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); while (bookmark.flags & WQ_FLAG_BOOKMARK) { /* * Take a breather from holding the lock, * allow pages that finish wake up asynchronously * to acquire the lock and remove themselves * from wait queue */ spin_unlock_irqrestore(&q->lock, flags); cpu_relax(); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); } /* * It is possible for other pages to have collided on the waitqueue * hash, so in that case check for a page match. That prevents a long- * term waiter * * It is still possible to miss a case here, when we woke page waiters * and removed them from the waitqueue, but there are still other * page waiters. */ if (!waitqueue_active(q) || !key.page_match) { ClearPageWaiters(page); /* * It's possible to miss clearing Waiters here, when we woke * our page waiters, but the hashed waitqueue has waiters for * other pages on it. * * That's okay, it's a rare case. The next waker will clear it. */ } spin_unlock_irqrestore(&q->lock, flags); } static void wake_up_page(struct page *page, int bit) { if (!PageWaiters(page)) return; wake_up_page_bit(page, bit); } /* * A choice of three behaviors for wait_on_page_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __lock_page() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like put_and_wait_on_page_locked() on PG_locked. */ }; /* * Attempt to check (or get) the page bit, and mark us done * if successful. */ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &page->flags)) return false; } else if (test_bit(bit_nr, &page->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline __sched int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, enum behavior behavior) { int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; bool delayacct = false; unsigned long pflags; if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { if (!PageSwapBacked(page)) { delayacct_thrashing_start(); delayacct = true; } psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the SetPageWaiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); SetPageWaiters(page); if (!trylock_page_bit_common(page, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the page. */ if (behavior == DROP) put_page(page); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, &page->flags))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the PageWaiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { if (delayacct) delayacct_thrashing_end(); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } __sched void wait_on_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit); __sched int wait_on_page_bit_killable(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit_killable); static int __wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait, bool set) { struct wait_queue_head *q = page_waitqueue(page); int ret = 0; wait->page = page; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); SetPageWaiters(page); if (set) ret = !trylock_page(page); else ret = PageLocked(page); /* * If we were succesful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } static int wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait) { if (!PageLocked(page)) return 0; return __wait_on_page_locked_async(compound_head(page), wait, false); } /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. * * The caller should hold a reference on @page. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the page to * come unlocked. After this function returns, the caller should not * dereference @page. */ void put_and_wait_on_page_locked(struct page *page) { wait_queue_head_t *q; page = compound_head(page); q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); } /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue * @page: Page defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) { wait_queue_head_t *q = page_waitqueue(page); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); SetPageWaiters(page); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(add_page_wait_queue); #ifndef clear_bit_unlock_is_negative_byte /* * PG_waiters is the high bit in the same byte as PG_lock. * * On x86 (and on many other architectures), we can clear PG_lock and * test the sign bit at the same time. But if the architecture does * not support that special operation, we just do this all by hand * instead. * * The read of PG_waiters has to be after (or concurrently with) PG_locked * being cleared, but a memory barrier should be unnecessary since it is * in the same byte as PG_locked. */ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) { clear_bit_unlock(nr, mem); /* smp_mb__after_atomic(); */ return test_bit(PG_waiters, mem); } #endif /** * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in wait_on_page_locked(). * Also wakes sleepers in wait_on_page_writeback() because the wakeup * mechanism between PageLocked pages and PageWriteback pages is shared. * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. * * Note that this depends on PG_waiters being the sign bit in the byte * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to * clear the PG_locked bit and test PG_waiters at the same time fairly * portably (architectures that do LL/SC can test any bit, while x86 can * test the sign bit). */ void unlock_page(struct page *page) { BUILD_BUG_ON(PG_waiters != 7); page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) wake_up_page_bit(page, PG_locked); } EXPORT_SYMBOL(unlock_page); /** * end_page_writeback - end writeback against a page * @page: the page */ void end_page_writeback(struct page *page) { /* * TestClearPageReclaim could be used here but it is an atomic * operation and overkill in this particular case. Failing to * shuffle a page marked for immediate reclaim is too mild to * justify taking an atomic operation penalty at the end of * ever page writeback. */ if (PageReclaim(page)) { ClearPageReclaim(page); rotate_reclaimable_page(page); } /* * Writeback does not hold a page reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the page is not freed and * reused before the wake_up_page(). */ get_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); put_page(page); } EXPORT_SYMBOL(end_page_writeback); /* * After completing I/O on a page, call this routine to update the page * flags appropriately */ void page_endio(struct page *page, bool is_write, int err) { if (!is_write) { if (!err) { SetPageUptodate(page); } else { ClearPageUptodate(page); SetPageError(page); } unlock_page(page); } else { if (err) { struct address_space *mapping; SetPageError(page); mapping = page_mapping(page); if (mapping) mapping_set_error(mapping, err); } end_page_writeback(page); } } EXPORT_SYMBOL_GPL(page_endio); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @__page: the page to lock */ __sched void __lock_page(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__lock_page); __sched int __lock_page_killable(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__lock_page_killable); __sched int __lock_page_async(struct page *page, struct wait_page_queue *wait) { return __wait_on_page_locked_async(page, wait, true); } /* * Return values: * 1 - page is locked; mmap_lock is still held. * 0 - page is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 * with the page locked and the mmap_lock unperturbed. */ __sched int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return 0; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) wait_on_page_locked_killable(page); else wait_on_page_locked(page); return 0; } else { if (flags & FAULT_FLAG_KILLABLE) { int ret; ret = __lock_page_killable(page); if (ret) { mmap_read_unlock(mm); return 0; } } else __lock_page(page); return 1; } } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == 0) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /** * find_get_entry - find and get a page cache entry * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, the head page is returned with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; rcu_read_lock(); repeat: xas_reset(&xas); page = xas_load(&xas); if (xas_retry(&xas, page)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!page || xa_is_value(page)) goto out; if (!page_cache_get_speculative(page)) goto repeat; /* * Has the page moved or been split? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != xas_reload(&xas))) { put_page(page); goto repeat; } out: rcu_read_unlock(); return page; } /** * find_lock_entry - Locate and lock a page cache entry. * @mapping: The address_space to search. * @index: The page cache index. * * Looks up the page at @mapping & @index. If there is a page in the * cache, the head page is returned locked and with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Context: May sleep. * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) { struct page *page; repeat: page = find_get_entry(mapping, index); if (page && !xa_is_value(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } return page; } /** * pagecache_get_page - Find and get a reference to a page. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the page is returned. * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * * * %FGP_ACCESSED - The page will be marked accessed. * * %FGP_LOCK - The page is returned locked. * * %FGP_HEAD - If the page is present and a THP, return the head page * rather than the exact page specified by the index. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. * * %FGP_WRITE - The page will be written * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask * * %FGP_NOWAIT - Don't get blocked by page lock * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * * Return: The found page or %NULL otherwise. */ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp_mask) { struct page *page; repeat: page = find_get_entry(mapping, index); if (xa_is_value(page)) page = NULL; trace_android_vh_pagecache_get_page(mapping, index, fgp_flags, gfp_mask, page); if (!page) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!trylock_page(page)) { put_page(page); return NULL; } } else { lock_page(page); } /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } if (fgp_flags & FGP_ACCESSED) mark_page_accessed(page); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (page_is_idle(page)) clear_page_idle(page); } if (!(fgp_flags & FGP_HEAD)) page = find_subpage(page, index); no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp_mask |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp_mask &= ~__GFP_FS; page = __page_cache_alloc(gfp_mask); if (!page) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); err = add_to_page_cache_lru(page, mapping, index, gfp_mask); if (unlikely(err)) { put_page(page); page = NULL; if (err == -EEXIST) goto repeat; } /* * add_to_page_cache_lru locks the page, and for mmap we expect * an unlocked page. */ if (page && (fgp_flags & FGP_FOR_MMAP)) unlock_page(page); } return page; } EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @nr_entries: The maximum number of entries * @entries: Where the resulting entries are placed * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a group of up to * @nr_entries entries in the mapping. The entries are placed at * @entries. find_get_entries() takes a reference against any actual * pages it returns. * * The search returns a group of mapping-contiguous page cache entries * with ascending indexes. There may be holes in the indices due to * not-present pages. * * Any shadow entries of evicted pages, or swap entries from * shmem/tmpfs, are included in the returned array. * * If it finds a Transparent Huge Page, head or tail, find_get_entries() * stops at that page: the caller is likely to have a better way to handle * the compound page as a whole, and then skip its extent, than repeatedly * calling find_get_entries() to return all its tails. * * Return: the number of pages and shadow entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (xa_is_value(page)) goto export; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; /* * Terminate early on finding a THP, to allow the caller to * handle it all at once; but continue if this is hugetlbfs. */ if (PageTransHuge(page) && !PageHuge(page)) { page = find_subpage(page, xas.xa_index); nr_entries = ret + 1; } export: indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } /** * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_range() will search for and return a group of up to @nr_pages * pages in the mapping starting at index @start and up to index @end * (inclusive). The pages are placed at @pages. find_get_pages_range() takes * a reference against the returned pages. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. * We also update @start to index the next page for the traversal. * * Return: the number of pages which were found. If this number is * smaller than @nr_pages, the end of specified range has been * reached. */ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *start); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each(&xas, page, end) { if (xas_retry(&xas, page)) continue; /* Skip over shadow, swap and DAX entries */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broken anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return ret; } /** * find_get_pages_contig - gang contiguous pagecache lookup * @mapping: The address_space to search * @index: The starting page index * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_contig() works exactly like find_get_pages(), except * that the returned number of pages are guaranteed to be contiguous. * * Return: the number of pages which were found. */ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(page)) break; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_contig); /** * find_get_pages_range_tag - find and return pages in given range matching @tag * @mapping: the address_space to search * @index: the starting page index * @end: The final page index (inclusive) * @tag: the tag index * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * * Like find_get_pages, except we only return pages which are tagged with * @tag. We update @index to index the next page for the traversal. * * Return: the number of pages which were found. */ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *index); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each_marked(&xas, page, end, tag) { if (xas_retry(&xas, page)) continue; /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *index = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when we got to @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the * iteration when there is a page at index -1 but that is already * broken anyway. */ if (end == (pgoff_t)-1) *index = (pgoff_t)-1; else *index = end + 1; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_range_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /** * generic_file_buffered_read - generic file read routine * @iocb: the iocb to read * @iter: data destination * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. * * Return: * * total number of bytes copied, including those the were already @written * * negative error code if nothing was copied */ ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t written) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; loff_t *ppos = &iocb->ki_pos; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error = 0; if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; prev_offset = ra->prev_pos & (PAGE_SIZE-1); last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if (written && (iocb->ki_flags & IOCB_WAITQ)) iocb->ki_flags |= IOCB_NOWAIT; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: if (fatal_signal_pending(current)) { error = -EINTR; goto out; } page = find_get_page(mapping, index); if (!page) { if (iocb->ki_flags & IOCB_NOIO) goto would_block; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { if (iocb->ki_flags & IOCB_NOIO) { put_page(page); goto out; } page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } if (!PageUptodate(page)) { /* * See comment in do_read_cache_page on why * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = wait_on_page_locked_async(page, iocb->ki_waitq); } else { if (iocb->ki_flags & IOCB_NOWAIT) { put_page(page); goto would_block; } error = wait_on_page_locked_killable(page); } if (unlikely(error)) goto readpage_error; if (PageUptodate(page)) goto page_ok; if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; /* Did it get truncated before we got the lock? */ if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } page_ok: /* * i_size must be checked after we know the page is Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ nr = PAGE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { put_page(page); goto out; } } nr = nr - offset; /* If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; prev_offset = offset; put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; if (ret < nr) { error = -EFAULT; goto out; } continue; page_not_up_to_date: /* Get exclusive access to the page ... */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); put_page(page); continue; } /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) { unlock_page(page); put_page(page); goto would_block; } /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. * PG_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page. */ error = mapping->a_ops->readpage(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { put_page(page); error = 0; goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_mapping_pages got it */ unlock_page(page); put_page(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(ra); error = -EIO; goto readpage_error; } unlock_page(page); } goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ put_page(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ page = page_cache_alloc(mapping); if (!page) { error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { put_page(page); if (error == -EEXIST) { error = 0; goto find_page; } goto out; } goto readpage; } would_block: error = -EAGAIN; out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; } EXPORT_SYMBOL_GPL(generic_file_buffered_read); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) goto out; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t size; size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_has_page(mapping, iocb->ki_pos, iocb->ki_pos + count - 1)) return -EAGAIN; } else { retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); if (retval < 0) goto out; } file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || iocb->ki_pos >= size || IS_DAX(inode)) goto out; } retval = generic_file_buffered_read(iocb, iter, retval); out: return retval; } EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @page - the page to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_page_or_retry in that it can drop the mmap_lock. * It differs in that it actually returns the page locked if it returns 1 and 0 * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin * will point to the pinned file and needs to be fput()'ed at a later point. */ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { if (trylock_page(page)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__lock_page_killable(page)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals * if we return VM_FAULT_RETRY, so we need to drop the * mmap_lock here and return 0 if we don't have a fpin. */ if (*fpin == NULL) mmap_read_unlock(vmf->vma->vm_mm); return 0; } } else __lock_page(page); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vmf->vma->vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; do_page_cache_ra(&ractl, ra->size, ra->async_size); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct page *page) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; unsigned int mmap_miss; pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (PageReadahead(page)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); } return fpin; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; pgoff_t max_off; struct page *page = NULL; vm_fault_t ret = 0; bool retry = false; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) return VM_FAULT_SIGBUS; trace_android_vh_filemap_fault_get_page(vmf, &page, &retry); if (unlikely(retry)) goto out_retry; if (unlikely(page)) goto page_ok; /* * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { /* * We found the page, so try async readahead before * waiting for the lock. */ fpin = do_async_mmap_readahead(vmf, page); } else if (!page) { /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: page = pagecache_get_page(mapping, offset, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (!page) { if (fpin) goto out_retry; return VM_FAULT_OOM; } } if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(compound_head(page)->mapping != mapping)) { unlock_page(page); put_page(page); goto retry_find; } VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ if (unlikely(!PageUptodate(page))) goto page_not_uptodate; /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { unlock_page(page); goto out_retry; } page_ok: /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) { unlock_page(page); put_page(page); return VM_FAULT_SIGBUS; } vmf->page = page; return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ ClearPageError(page); fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } if (fpin) goto out_retry; put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; shrink_readahead_size_eio(ra); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (page) { trace_android_vh_filemap_fault_cache_page(vmf, page); put_page(page); } if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { unlock_page(page); put_page(page); return true; } if (pmd_none(*vmf->pmd) && PageTransHuge(page)) { vm_fault_t ret = do_set_pmd(vmf, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ unlock_page(page); return true; } } if (pmd_none(*vmf->pmd)) { if (vmf->flags & FAULT_FLAG_SPECULATIVE) { unlock_page(page); put_page(page); return true; } vmf->ptl = pmd_lock(mm, vmf->pmd); if (likely(pmd_none(*vmf->pmd))) { mm_inc_nr_ptes(mm); pmd_populate(mm, vmf->pmd, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } spin_unlock(vmf->ptl); } /* See comment in handle_pte_fault() */ if (pmd_devmap_trans_unstable(vmf->pmd)) { unlock_page(page); put_page(page); return true; } return false; } static struct page *next_uptodate_page(struct page *page, struct address_space *mapping, struct xa_state *xas, pgoff_t end_pgoff) { unsigned long max_idx; do { if (!page) return NULL; if (xas_retry(xas, page)) continue; if (xa_is_value(page)) continue; if (PageLocked(page)) continue; if (!page_cache_get_speculative(page)) continue; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(xas))) goto skip; if (!PageUptodate(page) || PageReadahead(page)) goto skip; if (PageHWPoison(page)) goto skip; if (!trylock_page(page)) goto skip; if (page->mapping != mapping) goto unlock; if (!PageUptodate(page)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return page; unlock: unlock_page(page); skip: put_page(page); } while ((page = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } static inline struct page *first_map_page(struct address_space *mapping, struct xa_state *xas, pgoff_t end_pgoff) { return next_uptodate_page(xas_find(xas, end_pgoff), mapping, xas, end_pgoff); } static inline struct page *next_map_page(struct address_space *mapping, struct xa_state *xas, pgoff_t end_pgoff) { return next_uptodate_page(xas_next_entry(xas, end_pgoff), mapping, xas, end_pgoff); } #ifdef CONFIG_SPECULATIVE_PAGE_FAULT bool filemap_allow_speculation(void) { return true; } EXPORT_SYMBOL_GPL(filemap_allow_speculation); #endif vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *head, *page; unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); vm_fault_t ret = 0; rcu_read_lock(); head = first_map_page(mapping, &xas, end_pgoff); if (!head) goto out; if (filemap_map_pmd(vmf, head)) { if (pmd_none(*vmf->pmd) && vmf->flags & FAULT_FLAG_SPECULATIVE) { ret = VM_FAULT_RETRY; goto out; } ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (!pte_map_lock_addr(vmf, addr)) { unlock_page(head); put_page(head); ret = VM_FAULT_RETRY; goto out; } do { page = find_subpage(head, xas.xa_index); if (PageHWPoison(page)) goto unlock; if (mmap_miss > 0) mmap_miss--; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; if (!pte_none(*vmf->pte)) goto unlock; /* We're about to handle the fault */ if (vmf->address == addr) ret = VM_FAULT_NOPAGE; do_set_pte(vmf, page, addr); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, addr, vmf->pte); unlock_page(head); continue; unlock: unlock_page(head); put_page(head); } while ((head = next_map_page(mapping, &xas, end_pgoff)) != NULL); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the page dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty page and writeprotect it again. */ set_page_dirty(page); wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, #ifdef CONFIG_SPECULATIVE_PAGE_FAULT .allow_speculation = filemap_allow_speculation, #endif }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *wait_on_page_read(struct page *page) { if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { put_page(page); page = ERR_PTR(-EIO); } } return page; } static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data, gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } filler: if (filler) err = filler(data, page); else err = mapping->a_ops->readpage(data, page); if (err < 0) { put_page(page); return ERR_PTR(err); } page = wait_on_page_read(page); if (IS_ERR(page)) return page; goto out; } if (PageUptodate(page)) goto out; /* * Page is not up to date and may be locked due to one of the following * case a: Page is being filled and the page lock is held * case b: Read/write error clearing the page uptodate status * case c: Truncation in progress (page locked) * case d: Reclaim in progress * * Case a, the page will be up to date when the page is unlocked. * There is no need to serialise on the page lock here as the page * is pinned so the lock gives no additional protection. Even if the * page is truncated, the data is still valid if PageUptodate as * it's a race vs truncate race. * Case b, the page will not be up to date * Case c, the page may be truncated but in itself, the data may still * be valid after IO completes as it's a read vs truncate race. The * operation must restart if the page is not uptodate on unlock but * otherwise serialising on page lock to stabilise the mapping gives * no additional guarantees to the caller as the page lock is * released before return. * Case d, similar to truncation. If reclaim holds the page lock, it * will be a race with remove_mapping that determines if the mapping * is valid on unlock but otherwise the data is valid and there is * no need to serialise with page lock. * * As the page lock gives no additional guarantee, we optimistically * wait on the page to be unlocked and check if it's up to date and * use the page if it is. Otherwise, the page lock is required to * distinguish between the different cases. The motivation is that we * avoid spurious serialisations and wakeups when multiple processes * wait on the same page for IO to complete. */ wait_on_page_locked(page); if (PageUptodate(page)) goto out; /* Distinguish between all the cases under the safety of the lock */ lock_page(page); /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); put_page(page); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (PageUptodate(page)) { unlock_page(page); goto out; } /* * A previous I/O error may have been due to temporary * failures. * Clear page error before actual read, PG_error will be * set again if read page fails. */ ClearPageError(page); goto filler; out: mark_page_accessed(page); return page; } /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); } EXPORT_SYMBOL(pagecache_write_begin); int pagecache_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); /* * Warn about a page cache invalidation failure during a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; struct inode *inode = file_inode(filp); char *path; errseq_set(&inode->i_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written; size_t write_len; pgoff_t end; write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ if (filemap_range_has_page(inode->i_mapping, pos, pos + write_len - 1)) return -EAGAIN; } else { written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) goto out; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ if (written) { if (written == -EBUSY) return 0; goto out; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0 && mapping->nrpages && invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end)) dio_warn_stale_pagecache(file); if (written > 0) { pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; } EXPORT_SYMBOL(generic_file_direct_write); /* * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { struct page *page; int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; if (flags & AOP_FLAG_NOFS) fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; unsigned int flags = 0; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ void *fsdata; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * Not only is this an optimisation, but it is also required * to check that the address is actually valid, when atomic * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) break; copied = status; cond_resched(); iov_iter_advance(i, copied); if (unlikely(copied == 0)) { /* * If we were unable to copy any data at all, we must * fall back to a single segment length write. * * If we didn't fallback here, we could livelock * because not all segments in the iov can be copied at * once without a pagefault. */ bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } pos += copied; written += copied; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); return written ? written : status; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_mutex to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; ssize_t status; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; err = file_update_time(file); if (err) goto out; if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos, endbyte; written = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; status = generic_perform_write(file, from, pos = iocb->ki_pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ if (unlikely(status < 0)) { err = status; goto out; } /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + status - 1; err = filemap_write_and_wait_range(mapping, pos, endbyte); if (err == 0) { iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return * the number of bytes which were direct-written */ } } else { written = generic_perform_write(file, from, iocb->ki_pos); if (likely(written > 0)) iocb->ki_pos += written; } out: current->backing_dev_info = NULL; return written ? written : err; } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page * * @page: the page which the kernel is trying to free * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page * (presumably at page->private). * * This may also be called if PG_fscache is set on a page, indicating that the * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). * * Return: %1 if the release was successful, otherwise return zero. */ int try_to_release_page(struct page *page, gfp_t gfp_mask) { struct address_space * const mapping = page->mapping; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping && mapping->a_ops->releasepage) return mapping->a_ops->releasepage(page, gfp_mask); return try_to_free_buffers(page); } EXPORT_SYMBOL(try_to_release_page); |
| 2289 2287 52 2276 279 2108 2 2 21 11 21 20 1002 1001 1107 21 21 21 1107 1103 570 32 1107 1107 287 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 | // 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 @nextid 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 (!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 |
| 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 | /* SPDX-License-Identifier: GPL-2.0 */ /* Rewritten and vastly simplified by Rusty Russell for in-kernel * module loader: * Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation */ #ifndef _LINUX_KALLSYMS_H #define _LINUX_KALLSYMS_H #include <linux/errno.h> #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/mm.h> #include <linux/module.h> #include <asm/sections.h> #define KSYM_NAME_LEN 128 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1) struct cred; struct module; static inline int is_kernel_inittext(unsigned long addr) { if (addr >= (unsigned long)_sinittext && addr <= (unsigned long)_einittext) return 1; return 0; } static inline int is_kernel_text(unsigned long addr) { if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) || arch_is_kernel_text(addr)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) return 1; return in_gate_area_no_mm(addr); } static inline int is_ksym_addr(unsigned long addr) { if (IS_ENABLED(CONFIG_KALLSYMS_ALL)) return is_kernel(addr); return is_kernel_text(addr) || is_kernel_inittext(addr); } static inline void *dereference_symbol_descriptor(void *ptr) { #ifdef HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR struct module *mod; ptr = dereference_kernel_function_descriptor(ptr); if (is_ksym_addr((unsigned long)ptr)) return ptr; preempt_disable(); mod = __module_address((unsigned long)ptr); preempt_enable(); if (mod) ptr = dereference_module_function_descriptor(mod, ptr); #endif return ptr; } #ifdef CONFIG_KALLSYMS /* Lookup the address for a symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name); /* Call a function on each kallsyms symbol in the core kernel */ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); extern int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset); /* Lookup an address. modname is set to NULL if it's in the kernel. */ const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf); /* Look up a kernel symbol and return it in a text buffer. */ extern int sprint_symbol(char *buffer, unsigned long address); extern int sprint_symbol_no_offset(char *buffer, unsigned long address); extern int sprint_backtrace(char *buffer, unsigned long address); int lookup_symbol_name(unsigned long addr, char *symname); int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* How and when do we show kallsyms values? */ extern bool kallsyms_show_value(const struct cred *cred); #else /* !CONFIG_KALLSYMS */ static inline unsigned long kallsyms_lookup_name(const char *name) { return 0; } static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) { return 0; } static inline int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { return 0; } static inline const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf) { return NULL; } static inline int sprint_symbol(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_symbol_no_offset(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int sprint_backtrace(char *buffer, unsigned long addr) { *buffer = '\0'; return 0; } static inline int lookup_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) { return -ERANGE; } static inline bool kallsyms_show_value(const struct cred *cred) { return false; } #endif /*CONFIG_KALLSYMS*/ static inline void print_ip_sym(const char *loglvl, unsigned long ip) { printk("%s[<%px>] %pS\n", loglvl, (void *) ip, (void *) ip); } #endif /*_LINUX_KALLSYMS_H*/ |
| 707 704 2657 2250 704 704 703 702 707 674 2661 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | // SPDX-License-Identifier: GPL-2.0 /* * A fast, small, non-recursive O(n log n) sort for the Linux kernel * * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is stil valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 (swap_func_t)0 #define SWAP_WORDS_32 (swap_func_t)1 #define SWAP_BYTES (swap_func_t)2 /* * The function pointer is last to make tail calls most efficient if the * compiler decides not to inline this function. */ static void do_swap(void *a, void *b, size_t size, swap_func_t swap_func) { if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, (int)size); } #define _CMP_WRAPPER ((cmp_r_func_t)0L) static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((cmp_func_t)(priv))(a, b); return cmp(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /** * sort_r - sort an array of elements * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * This function does a heapsort on the given array. You may provide * a swap_func function if you need to do something more than a memory * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_func_t swap_func, const void *priv) { /* pre-scale counters for performance */ size_t n = num * size, a = (num/2) * size; const unsigned int lsbit = size & -size; /* Used to find parent */ if (!a) /* num < 2 || size == 0 */ return; if (!swap_func) { if (is_aligned(base, size, 8)) swap_func = SWAP_WORDS_64; else if (is_aligned(base, size, 4)) swap_func = SWAP_WORDS_32; else swap_func = SWAP_BYTES; } /* * Loop invariants: * 1. elements [a,n) satisfy the heap property (compare greater than * all of their children), * 2. elements [n,num*size) are sorted, and * 3. a <= b <= c <= d <= n (whenever they are valid). */ for (;;) { size_t b, c, d; if (a) /* Building heap: sift down --a */ a -= size; else if (n -= size) /* Sorting: Extract root to --n */ do_swap(base, base + n, size, swap_func); else /* Sort complete */ break; /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + size, (d = c + size) < n;) b = do_cmp(base + c, base + d, cmp_func, priv) >= 0 ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0) b = parent(b, lsbit, size); c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = parent(b, lsbit, size); do_swap(base + b, base + c, size, swap_func); } } } EXPORT_SYMBOL(sort_r); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { return sort_r(base, num, size, _CMP_WRAPPER, swap_func, cmp_func); } EXPORT_SYMBOL(sort); |
| 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm6_policy.c: based on xfrm4_policy.c * * Authors: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * YOSHIFUJI Hideaki * Split up af-specific portion * */ #include <linux/err.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/addrconf.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/l3mdev.h> static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct flowi6 fl6; struct dst_entry *dst; int err; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif); fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; fl6.flowi6_mark = mark; memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr)); if (saddr) memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr)); dst = ip6_route_output(net, NULL, &fl6); err = dst->error; if (dst->error) { dst_release(dst); dst = ERR_PTR(err); } return dst; } static int xfrm6_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr, u32 mark) { struct dst_entry *dst; struct net_device *dev; dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; dev = ip6_dst_idev(dst)->dev; ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); dst_release(dst); return 0; } static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { struct rt6_info *rt = (struct rt6_info *)xdst->route; xdst->u.dst.dev = dev; dev_hold(dev); xdst->u.rt6.rt6i_idev = in6_dev_get(dev); if (!xdst->u.rt6.rt6i_idev) { dev_put(dev); return -ENODEV; } /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); xdst->route_cookie = rt6_get_cookie(rt); xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; xdst->u.rt6.rt6i_src = rt->rt6i_src; INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached); rt6_uncached_list_add(&xdst->u.rt6); atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache); return 0; } static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->redirect(path, sk, skb); } static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); if (xdst->u.rt6.rt6i_uncached_list) rt6_uncached_list_del(&xdst->u.rt6); xfrm_dst_destroy(xdst); } static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int unregister) { struct xfrm_dst *xdst; if (!unregister) return; xdst = (struct xfrm_dst *)dst; if (xdst->u.rt6.rt6i_idev->dev == dev) { struct inet6_dev *loopback_idev = in6_dev_get(dev_net(dev)->loopback_dev); do { in6_dev_put(xdst->u.rt6.rt6i_idev); xdst->u.rt6.rt6i_idev = loopback_idev; in6_dev_hold(loopback_idev); xdst = (struct xfrm_dst *)xfrm_dst_child(&xdst->u.dst); } while (xdst->u.dst.xfrm); __in6_dev_put(loopback_idev); } xfrm_dst_ifdown(dst, dev); } static struct dst_ops xfrm6_dst_ops_template = { .family = AF_INET6, .update_pmtu = xfrm6_update_pmtu, .redirect = xfrm6_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, .gc_thresh = 32768, }; static const struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .dst_ops = &xfrm6_dst_ops_template, .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, .fill_dst = xfrm6_fill_dst, .blackhole_route = ip6_blackhole_route, }; static int __init xfrm6_policy_init(void) { return xfrm_policy_register_afinfo(&xfrm6_policy_afinfo, AF_INET6); } static void xfrm6_policy_fini(void) { xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo); } #ifdef CONFIG_SYSCTL static struct ctl_table xfrm6_policy_table[] = { { .procname = "xfrm6_gc_thresh", .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static int __net_init xfrm6_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = xfrm6_policy_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh; } hdr = register_net_sysctl(net, "net/ipv6", table); if (!hdr) goto err_reg; net->ipv6.sysctl.xfrm6_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit xfrm6_net_sysctl_exit(struct net *net) { struct ctl_table *table; if (!net->ipv6.sysctl.xfrm6_hdr) return; table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else /* CONFIG_SYSCTL */ static inline int xfrm6_net_sysctl_init(struct net *net) { return 0; } static inline void xfrm6_net_sysctl_exit(struct net *net) { } #endif static int __net_init xfrm6_net_init(struct net *net) { int ret; memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template, sizeof(xfrm6_dst_ops_template)); ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops); if (ret) return ret; ret = xfrm6_net_sysctl_init(net); if (ret) dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); return ret; } static void __net_exit xfrm6_net_exit(struct net *net) { xfrm6_net_sysctl_exit(net); dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); } static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, }; int __init xfrm6_init(void) { int ret; ret = xfrm6_policy_init(); if (ret) goto out; ret = xfrm6_state_init(); if (ret) goto out_policy; ret = xfrm6_protocol_init(); if (ret) goto out_state; register_pernet_subsys(&xfrm6_net_ops); out: return ret; out_state: xfrm6_state_fini(); out_policy: xfrm6_policy_fini(); goto out; } void xfrm6_fini(void) { unregister_pernet_subsys(&xfrm6_net_ops); xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); } |
| 903 898 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TRACE_SYSCALL_H #define _TRACE_SYSCALL_H #include <linux/tracepoint.h> #include <linux/unistd.h> #include <linux/trace_events.h> #include <linux/thread_info.h> #include <asm/ptrace.h> /* * A syscall entry in the ftrace syscalls array. * * @name: name of the syscall * @syscall_nr: number of the syscall * @nb_args: number of parameters it takes * @types: list of types as strings * @args: list of args as strings (args[i] matches types[i]) * @enter_fields: list of fields for syscall_enter trace event * @enter_event: associated syscall_enter trace event * @exit_event: associated syscall_exit trace event */ struct syscall_metadata { const char *name; int syscall_nr; int nb_args; const char **types; const char **args; struct list_head enter_fields; struct trace_event_call *enter_event; struct trace_event_call *exit_event; }; #if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS) static inline void syscall_tracepoint_update(struct task_struct *p) { if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT); else clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT); } #else static inline void syscall_tracepoint_update(struct task_struct *p) { } #endif #endif /* _TRACE_SYSCALL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } #else static inline int posix_acl_chmod(struct inode *inode, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */ |
| 1 249 35 4 4 4 4305 4301 4301 4 3115 3116 3120 3118 11 11 11 11 11 481 482 14 1343 1340 2 1343 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; DEFINE_RAW_SPINLOCK(timekeeper_lock); /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the timekeeper_lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) { u64 max_cycles = tk->tkr_mono.clock->max_cycles; const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", offset, name, max_cycles); printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } } if (tk->underflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->underflow_seen = 0; } if (tk->overflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->overflow_seen = 0; } } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; unsigned int seq; /* * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; } while (read_seqcount_retry(&tk_core.seq, seq)); delta = clocksource_delta(now, last, mask); /* * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) { tk->underflow_seen = 1; delta = 0; } /* Cap delta value to the max_cycles values to avoid mult overflows */ if (unlikely(delta > max)) { tk->overflow_seen = 1; delta = tkr->clock->max_cycles; } return delta; } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; /* read clocksource */ cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); return delta; } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET static u32 default_arch_gettimeoffset(void) { return 0; } u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; #else static inline u32 arch_gettimeoffset(void) { return 0; } #endif static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; nsec = delta * tkr->mult + tkr->xtime_nsec; nsec >>= tkr->shift; /* If arch requires, add in get_arch_timeoffset() */ return nsec + arch_gettimeoffset(); } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; delta = timekeeping_get_delta(tkr); return timekeeping_delta_to_ns(tkr, delta); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); return timekeeping_delta_to_ns(tkr, delta); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_delta_to_ns(tkr, clocksource_delta( tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } u64 ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); u64 ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update(tk, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; u64 basem, baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_delta_to_ns(tkr, clocksource_delta(tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) *mono = basem + delta; return baser + delta; } /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. */ u64 ktime_get_real_fast_ns(void) { return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * ktime_get_fast_timestamps: - NMI safe timestamps * @snapshot: Pointer to timestamp storage * * Stores clock monotonic, boottime and realtime timestamps. * * Boot time is a racy access on 32bit systems if the sleep time injection * happens late during resume and not in timekeeping_resume(). That could * be avoided by expanding struct tk_read_base with boot offset for 32bit * and adding more overhead to the update. As this is a hard to observe * once per resume event which can be filtered with reasonable effort using * the accurate mono/real timestamps, it's probably not worth the trouble. * * Aside of that it might be possible on 32 and 64 bit to observe the * following when the sleep time injection happens late: * * CPU 0 CPU 1 * timekeeping_resume() * ktime_get_fast_timestamps() * mono, real = __ktime_get_real_fast() * inject_sleep_time() * update boot offset * boot = mono + bootoffset; * * That means that boot time already has the sleep time adjustment, but * real time does not. On the next readout both are in sync again. * * Preventing this for 64bit is not really feasible without destroying the * careful cache layout of the timekeeper because the sequence count and * struct tk_read_base would then need two cache lines instead of one. * * Access to the time keeper clock source is disabled accross the innermost * steps of suspend/resume. The accessors still work, but the timestamps * are frozen until time keeping is resumed which happens very early. * * For regular suspend/resume there is no observable difference vs. sched * clock, but it might affect some of the nasty low level debug printks. * * OTOH, access to sched clock is not guaranteed accross suspend/resume on * all systems either so it depends on the hardware in use. * * If that turns out to be a real problem then this could be mitigated by * using sched clock in a similar way as during early boot. But it's not as * trivial as on early boot because it needs some careful protection * against the clock monotonic timestamp jumping backwards on resume. */ void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) { struct timekeeper *tk = &tk_core.timekeeper; snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); } /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * The mirroring of the data to the shadow-timekeeper needs * to happen last here to ensure we don't over-write the * timekeeper structure on the next update with stale data */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); } /** * timekeeping_forward_now - update clock to the current time * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift; tk_normalize_xtime(tk); } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert mononotic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. This replaces the * get_seconds() interface which is not y2038 safe on 32bit systems. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * cycle_between - true if test occurs chronologically between before and after */ static bool cycle_between(u64 before, u64 test, u64 after) { if (test > before && test < after) return true; if (test < before && before > after) return true; return false; } /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource associated with the captured * system counter value is the same as the currently installed * timekeeper clocksource */ if (tk->tkr_mono.clock != system_counterval.cs) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!cycle_between(interval_start, cycles, now)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, system_counterval.cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, system_counterval.cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value occurs after the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !cycle_between(history_begin->cycles, system_counterval.cycles, cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); xt = tk_xtime(tk); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; goto out; } tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); if (!ret) audit_tk_injoffset(ts_delta); return ret; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @tv: pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 tmp; int ret = 0; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /** * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic * */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /** * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* * If the cs is in module, get a module reference. Succeeds * for built-in code (owner == NULL) as well. */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { old = tk->tkr_mono.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); module_put(old->owner); } else { module_put(new->owner); } } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * * Weak dummy function for arches that do not yet support it. * wall_time - current time as returned by persistent clock * boot_offset - offset that is defined as wall_time - boot_time * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tk, clock); tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @delta: pointer to a timespec delta value * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /** * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /** * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); suspend_timing_needed = false; timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); tick_resume(); hrtimers_resume(); } int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tk->tkr_mono.clock; cycle_now = tk->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update(tk, TK_MIRROR); halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplfies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tick_length())) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tick_length(); mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /** * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. * */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /** * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static void timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; u64 offset; int shift = 0, maxshift; unsigned int clock_set = 0; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; if (mode != TK_ADV_TICK) goto out; #else offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; #endif /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * * We could avoid this memcpy by switching pointers, but that * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this * memcpy under the tk_core.seq against one before we start * updating. */ timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) /* Have to call _delayed version, since in irq context*/ clock_was_set_delayed(); } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { timekeeping_advance(TK_ADV_TICK); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be postive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; unsigned long flags; struct timespec64 ts; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } tk_update_leap_state(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) timekeeping_advance(TK_ADV_FREQ); if (tai != orig_tai) clock_was_set(); ntp_notify_cmos_timer(); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ /** * xtime_update() - advances the timekeeping infrastructure * @ticks: number of ticks, that have elapsed since the last call. * * Must be called with interrupts disabled. */ void xtime_update(unsigned long ticks) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); do_timer(ticks); write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); update_wall_time(); } |
| 1184 1183 1184 819 1 1 1 2 2 1 1 1 1 1 2 1 2 5 5 2 2 2 5 1 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 | /* * This file implement the Wireless Extensions core API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * * (As all part of the Linux kernel, this file is GPL) */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/wireless.h> #include <linux/uaccess.h> #include <linux/export.h> #include <net/cfg80211.h> #include <net/iw_handler.h> #include <net/netlink.h> #include <net/wext.h> #include <net/net_namespace.h> typedef int (*wext_ioctl_func)(struct net_device *, struct iwreq *, unsigned int, struct iw_request_info *, iw_handler); /* * Meta-data about all the standard Wireless Extension request we * know about. */ static const struct iw_ioctl_description standard_ioctl[] = { [IW_IOCTL_IDX(SIOCSIWCOMMIT)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWNAME)] = { .header_type = IW_HEADER_TYPE_CHAR, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWNWID)] = { .header_type = IW_HEADER_TYPE_PARAM, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWNWID)] = { .header_type = IW_HEADER_TYPE_PARAM, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWFREQ)] = { .header_type = IW_HEADER_TYPE_FREQ, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWFREQ)] = { .header_type = IW_HEADER_TYPE_FREQ, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWMODE)] = { .header_type = IW_HEADER_TYPE_UINT, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWMODE)] = { .header_type = IW_HEADER_TYPE_UINT, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWSENS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWSENS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWRANGE)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWRANGE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_range), .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWPRIV)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWPRIV)] = { /* (handled directly by us) */ .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct iw_priv_args), .max_tokens = 16, .flags = IW_DESCR_FLAG_NOMAX, }, [IW_IOCTL_IDX(SIOCSIWSTATS)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWSTATS)] = { /* (handled directly by us) */ .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_statistics), .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr), .max_tokens = IW_MAX_SPY, }, [IW_IOCTL_IDX(SIOCGIWSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr) + sizeof(struct iw_quality), .max_tokens = IW_MAX_SPY, }, [IW_IOCTL_IDX(SIOCSIWTHRSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct iw_thrspy), .min_tokens = 1, .max_tokens = 1, }, [IW_IOCTL_IDX(SIOCGIWTHRSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct iw_thrspy), .min_tokens = 1, .max_tokens = 1, }, [IW_IOCTL_IDX(SIOCSIWAP)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_IOCTL_IDX(SIOCGIWAP)] = { .header_type = IW_HEADER_TYPE_ADDR, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWMLME)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_mlme), .max_tokens = sizeof(struct iw_mlme), }, [IW_IOCTL_IDX(SIOCGIWAPLIST)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr) + sizeof(struct iw_quality), .max_tokens = IW_MAX_AP, .flags = IW_DESCR_FLAG_NOMAX, }, [IW_IOCTL_IDX(SIOCSIWSCAN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = 0, .max_tokens = sizeof(struct iw_scan_req), }, [IW_IOCTL_IDX(SIOCGIWSCAN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_SCAN_MAX_DATA, .flags = IW_DESCR_FLAG_NOMAX, }, [IW_IOCTL_IDX(SIOCSIWESSID)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWESSID)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWNICKN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, }, [IW_IOCTL_IDX(SIOCGIWNICKN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, }, [IW_IOCTL_IDX(SIOCSIWRATE)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWRATE)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWRTS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWRTS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWFRAG)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWFRAG)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWTXPOW)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWTXPOW)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWRETRY)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWRETRY)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWENCODE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ENCODING_TOKEN_MAX, .flags = IW_DESCR_FLAG_EVENT | IW_DESCR_FLAG_RESTRICT, }, [IW_IOCTL_IDX(SIOCGIWENCODE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ENCODING_TOKEN_MAX, .flags = IW_DESCR_FLAG_DUMP | IW_DESCR_FLAG_RESTRICT, }, [IW_IOCTL_IDX(SIOCSIWPOWER)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWPOWER)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWGENIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_IOCTL_IDX(SIOCGIWGENIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_IOCTL_IDX(SIOCSIWAUTH)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWAUTH)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWENCODEEXT)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_encode_ext), .max_tokens = sizeof(struct iw_encode_ext) + IW_ENCODING_TOKEN_MAX, }, [IW_IOCTL_IDX(SIOCGIWENCODEEXT)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_encode_ext), .max_tokens = sizeof(struct iw_encode_ext) + IW_ENCODING_TOKEN_MAX, }, [IW_IOCTL_IDX(SIOCSIWPMKSA)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_pmksa), .max_tokens = sizeof(struct iw_pmksa), }, }; static const unsigned int standard_ioctl_num = ARRAY_SIZE(standard_ioctl); /* * Meta-data about all the additional standard Wireless Extension events * we know about. */ static const struct iw_ioctl_description standard_event[] = { [IW_EVENT_IDX(IWEVTXDROP)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_EVENT_IDX(IWEVQUAL)] = { .header_type = IW_HEADER_TYPE_QUAL, }, [IW_EVENT_IDX(IWEVCUSTOM)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_CUSTOM_MAX, }, [IW_EVENT_IDX(IWEVREGISTERED)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_EVENT_IDX(IWEVEXPIRED)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_EVENT_IDX(IWEVGENIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_EVENT_IDX(IWEVMICHAELMICFAILURE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_michaelmicfailure), }, [IW_EVENT_IDX(IWEVASSOCREQIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_EVENT_IDX(IWEVASSOCRESPIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_EVENT_IDX(IWEVPMKIDCAND)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_pmkid_cand), }, }; static const unsigned int standard_event_num = ARRAY_SIZE(standard_event); /* Size (in bytes) of various events */ static const int event_type_size[] = { IW_EV_LCP_LEN, /* IW_HEADER_TYPE_NULL */ 0, IW_EV_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ 0, IW_EV_UINT_LEN, /* IW_HEADER_TYPE_UINT */ IW_EV_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ IW_EV_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ 0, IW_EV_POINT_LEN, /* Without variable payload */ IW_EV_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ IW_EV_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ }; #ifdef CONFIG_COMPAT static const int compat_event_type_size[] = { IW_EV_COMPAT_LCP_LEN, /* IW_HEADER_TYPE_NULL */ 0, IW_EV_COMPAT_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ 0, IW_EV_COMPAT_UINT_LEN, /* IW_HEADER_TYPE_UINT */ IW_EV_COMPAT_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ IW_EV_COMPAT_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ 0, IW_EV_COMPAT_POINT_LEN, /* Without variable payload */ IW_EV_COMPAT_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ IW_EV_COMPAT_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ }; #endif /* IW event code */ void wireless_nlevent_flush(void) { struct sk_buff *skb; struct net *net; down_read(&net_rwsem); for_each_net(net) { while ((skb = skb_dequeue(&net->wext_nlevents))) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); } up_read(&net_rwsem); } EXPORT_SYMBOL_GPL(wireless_nlevent_flush); static int wext_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { /* * When a netdev changes state in any way, flush all pending messages * to avoid them going out in a strange order, e.g. RTM_NEWLINK after * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() * or similar - all of which could otherwise happen due to delays from * schedule_work(). */ wireless_nlevent_flush(); return NOTIFY_OK; } static struct notifier_block wext_netdev_notifier = { .notifier_call = wext_netdev_notifier_call, }; static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); return 0; } static void __net_exit wext_pernet_exit(struct net *net) { skb_queue_purge(&net->wext_nlevents); } static struct pernet_operations wext_pernet_ops = { .init = wext_pernet_init, .exit = wext_pernet_exit, }; static int __init wireless_nlevent_init(void) { int err = register_pernet_subsys(&wext_pernet_ops); if (err) return err; err = register_netdevice_notifier(&wext_netdev_notifier); if (err) unregister_pernet_subsys(&wext_pernet_ops); return err; } subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { wireless_nlevent_flush(); } static DECLARE_WORK(wireless_nlevent_work, wireless_nlevent_process); static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, struct sk_buff *skb) { struct ifinfomsg *r; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, 0, 0, RTM_NEWLINK, sizeof(*r), 0); if (!nlh) return NULL; r = nlmsg_data(nlh); r->ifi_family = AF_UNSPEC; r->__ifi_pad = 0; r->ifi_type = dev->type; r->ifi_index = dev->ifindex; r->ifi_flags = dev_get_flags(dev); r->ifi_change = 0; /* Wireless changes don't affect those flags */ if (nla_put_string(skb, IFLA_IFNAME, dev->name)) goto nla_put_failure; return nlh; nla_put_failure: nlmsg_cancel(skb, nlh); return NULL; } /* * Main event dispatcher. Called from other parts and drivers. * Send the event on the appropriate channels. * May be called from interrupt context. */ void wireless_send_event(struct net_device * dev, unsigned int cmd, union iwreq_data * wrqu, const char * extra) { const struct iw_ioctl_description * descr = NULL; int extra_len = 0; struct iw_event *event; /* Mallocated whole event */ int event_len; /* Its size */ int hdr_len; /* Size of the event header */ int wrqu_off = 0; /* Offset in wrqu */ /* Don't "optimise" the following variable, it will crash */ unsigned int cmd_index; /* *MUST* be unsigned */ struct sk_buff *skb; struct nlmsghdr *nlh; struct nlattr *nla; #ifdef CONFIG_COMPAT struct __compat_iw_event *compat_event; struct compat_iw_point compat_wrqu; struct sk_buff *compskb; #endif /* * Nothing in the kernel sends scan events with data, be safe. * This is necessary because we cannot fix up scan event data * for compat, due to being contained in 'extra', but normally * applications are required to retrieve the scan data anyway * and no data is included in the event, this codifies that * practice. */ if (WARN_ON(cmd == SIOCGIWSCAN && extra)) extra = NULL; /* Get the description of the Event */ if (cmd <= SIOCIWLAST) { cmd_index = IW_IOCTL_IDX(cmd); if (cmd_index < standard_ioctl_num) descr = &(standard_ioctl[cmd_index]); } else { cmd_index = IW_EVENT_IDX(cmd); if (cmd_index < standard_event_num) descr = &(standard_event[cmd_index]); } /* Don't accept unknown events */ if (descr == NULL) { /* Note : we don't return an error to the driver, because * the driver would not know what to do about it. It can't * return an error to the user, because the event is not * initiated by a user request. * The best the driver could do is to log an error message. * We will do it ourselves instead... */ netdev_err(dev, "(WE) : Invalid/Unknown Wireless Event (0x%04X)\n", cmd); return; } /* Check extra parameters and set extra_len */ if (descr->header_type == IW_HEADER_TYPE_POINT) { /* Check if number of token fits within bounds */ if (wrqu->data.length > descr->max_tokens) { netdev_err(dev, "(WE) : Wireless Event (cmd=0x%04X) too big (%d)\n", cmd, wrqu->data.length); return; } if (wrqu->data.length < descr->min_tokens) { netdev_err(dev, "(WE) : Wireless Event (cmd=0x%04X) too small (%d)\n", cmd, wrqu->data.length); return; } /* Calculate extra_len - extra is NULL for restricted events */ if (extra != NULL) extra_len = wrqu->data.length * descr->token_size; /* Always at an offset in wrqu */ wrqu_off = IW_EV_POINT_OFF; } /* Total length of the event */ hdr_len = event_type_size[descr->header_type]; event_len = hdr_len + extra_len; /* * The problem for 64/32 bit. * * On 64-bit, a regular event is laid out as follows: * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | * | event.len | event.cmd | p a d d i n g | * | wrqu data ... (with the correct size) | * * This padding exists because we manipulate event->u, * and 'event' is not packed. * * An iw_point event is laid out like this instead: * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | * | event.len | event.cmd | p a d d i n g | * | iwpnt.len | iwpnt.flg | p a d d i n g | * | extra data ... * * The second padding exists because struct iw_point is extended, * but this depends on the platform... * * On 32-bit, all the padding shouldn't be there. */ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; /* Send via the RtNetlink event channel */ nlh = rtnetlink_ifinfo_prep(dev, skb); if (WARN_ON(!nlh)) { kfree_skb(skb); return; } /* Add the wireless events in the netlink packet */ nla = nla_reserve(skb, IFLA_WIRELESS, event_len); if (!nla) { kfree_skb(skb); return; } event = nla_data(nla); /* Fill event - first clear to avoid data leaking */ memset(event, 0, hdr_len); event->len = event_len; event->cmd = cmd; memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); if (extra_len) memcpy(((char *) event) + hdr_len, extra, extra_len); nlmsg_end(skb, nlh); #ifdef CONFIG_COMPAT hdr_len = compat_event_type_size[descr->header_type]; event_len = hdr_len + extra_len; compskb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!compskb) { kfree_skb(skb); return; } /* Send via the RtNetlink event channel */ nlh = rtnetlink_ifinfo_prep(dev, compskb); if (WARN_ON(!nlh)) { kfree_skb(skb); kfree_skb(compskb); return; } /* Add the wireless events in the netlink packet */ nla = nla_reserve(compskb, IFLA_WIRELESS, event_len); if (!nla) { kfree_skb(skb); kfree_skb(compskb); return; } compat_event = nla_data(nla); compat_event->len = event_len; compat_event->cmd = cmd; if (descr->header_type == IW_HEADER_TYPE_POINT) { compat_wrqu.length = wrqu->data.length; compat_wrqu.flags = wrqu->data.flags; memcpy(&compat_event->pointer, ((char *) &compat_wrqu) + IW_EV_COMPAT_POINT_OFF, hdr_len - IW_EV_COMPAT_LCP_LEN); if (extra_len) memcpy(((char *) compat_event) + hdr_len, extra, extra_len); } else { /* extra_len must be zero, so no if (extra) needed */ memcpy(&compat_event->pointer, wrqu, hdr_len - IW_EV_COMPAT_LCP_LEN); } nlmsg_end(compskb, nlh); skb_shinfo(skb)->frag_list = compskb; #endif skb_queue_tail(&dev_net(dev)->wext_nlevents, skb); schedule_work(&wireless_nlevent_work); } EXPORT_SYMBOL(wireless_send_event); /* IW handlers */ struct iw_statistics *get_wireless_stats(struct net_device *dev) { #ifdef CONFIG_WIRELESS_EXT if ((dev->wireless_handlers != NULL) && (dev->wireless_handlers->get_wireless_stats != NULL)) return dev->wireless_handlers->get_wireless_stats(dev); #endif #ifdef CONFIG_CFG80211_WEXT if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy && dev->ieee80211_ptr->wiphy->wext && dev->ieee80211_ptr->wiphy->wext->get_wireless_stats) return dev->ieee80211_ptr->wiphy->wext->get_wireless_stats(dev); #endif /* not found */ return NULL; } /* noinline to avoid a bogus warning with -O3 */ static noinline int iw_handler_get_iwstats(struct net_device * dev, struct iw_request_info * info, union iwreq_data * wrqu, char * extra) { /* Get stats from the driver */ struct iw_statistics *stats; stats = get_wireless_stats(dev); if (stats) { /* Copy statistics to extra */ memcpy(extra, stats, sizeof(struct iw_statistics)); wrqu->data.length = sizeof(struct iw_statistics); /* Check if we need to clear the updated flag */ if (wrqu->data.flags != 0) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; return 0; } else return -EOPNOTSUPP; } static iw_handler get_handler(struct net_device *dev, unsigned int cmd) { /* Don't "optimise" the following variable, it will crash */ unsigned int index; /* *MUST* be unsigned */ const struct iw_handler_def *handlers = NULL; #ifdef CONFIG_CFG80211_WEXT if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy) handlers = dev->ieee80211_ptr->wiphy->wext; #endif #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) handlers = dev->wireless_handlers; #endif if (!handlers) return NULL; /* Try as a standard command */ index = IW_IOCTL_IDX(cmd); if (index < handlers->num_standard) return handlers->standard[index]; #ifdef CONFIG_WEXT_PRIV /* Try as a private command */ index = cmd - SIOCIWFIRSTPRIV; if (index < handlers->num_private) return handlers->private[index]; #endif /* Not found */ return NULL; } static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, const struct iw_ioctl_description *descr, iw_handler handler, struct net_device *dev, struct iw_request_info *info) { int err, extra_size, user_length = 0, essid_compat = 0; char *extra; /* Calculate space needed by arguments. Always allocate * for max space. */ extra_size = descr->max_tokens * descr->token_size; /* Check need for ESSID compatibility for WE < 21 */ switch (cmd) { case SIOCSIWESSID: case SIOCGIWESSID: case SIOCSIWNICKN: case SIOCGIWNICKN: if (iwp->length == descr->max_tokens + 1) essid_compat = 1; else if (IW_IS_SET(cmd) && (iwp->length != 0)) { char essid[IW_ESSID_MAX_SIZE + 1]; unsigned int len; len = iwp->length * descr->token_size; if (len > IW_ESSID_MAX_SIZE) return -EFAULT; err = copy_from_user(essid, iwp->pointer, len); if (err) return -EFAULT; if (essid[iwp->length - 1] == '\0') essid_compat = 1; } break; default: break; } iwp->length -= essid_compat; /* Check what user space is giving us */ if (IW_IS_SET(cmd)) { /* Check NULL pointer */ if (!iwp->pointer && iwp->length != 0) return -EFAULT; /* Check if number of token fits within bounds */ if (iwp->length > descr->max_tokens) return -E2BIG; if (iwp->length < descr->min_tokens) return -EINVAL; } else { /* Check NULL pointer */ if (!iwp->pointer) return -EFAULT; /* Save user space buffer size for checking */ user_length = iwp->length; /* Don't check if user_length > max to allow forward * compatibility. The test user_length < min is * implied by the test at the end. */ /* Support for very large requests */ if ((descr->flags & IW_DESCR_FLAG_NOMAX) && (user_length > descr->max_tokens)) { /* Allow userspace to GET more than max so * we can support any size GET requests. * There is still a limit : -ENOMEM. */ extra_size = user_length * descr->token_size; /* Note : user_length is originally a __u16, * and token_size is controlled by us, * so extra_size won't get negative and * won't overflow... */ } } /* kzalloc() ensures NULL-termination for essid_compat. */ extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) return -ENOMEM; /* If it is a SET, get all the extra data in here */ if (IW_IS_SET(cmd) && (iwp->length != 0)) { if (copy_from_user(extra, iwp->pointer, iwp->length * descr->token_size)) { err = -EFAULT; goto out; } if (cmd == SIOCSIWENCODEEXT) { struct iw_encode_ext *ee = (void *) extra; if (iwp->length < sizeof(*ee) + ee->key_len) { err = -EFAULT; goto out; } } } if (IW_IS_GET(cmd) && !(descr->flags & IW_DESCR_FLAG_NOMAX)) { /* * If this is a GET, but not NOMAX, it means that the extra * data is not bounded by userspace, but by max_tokens. Thus * set the length to max_tokens. This matches the extra data * allocation. * The driver should fill it with the number of tokens it * provided, and it may check iwp->length rather than having * knowledge of max_tokens. If the driver doesn't change the * iwp->length, this ioctl just copies back max_token tokens * filled with zeroes. Hopefully the driver isn't claiming * them to be valid data. */ iwp->length = descr->max_tokens; } err = handler(dev, info, (union iwreq_data *) iwp, extra); iwp->length += essid_compat; /* If we have something to return to the user */ if (!err && IW_IS_GET(cmd)) { /* Check if there is enough buffer up there */ if (user_length < iwp->length) { err = -E2BIG; goto out; } if (copy_to_user(iwp->pointer, extra, iwp->length * descr->token_size)) { err = -EFAULT; goto out; } } /* Generate an event to notify listeners of the change */ if ((descr->flags & IW_DESCR_FLAG_EVENT) && ((err == 0) || (err == -EIWCOMMIT))) { union iwreq_data *data = (union iwreq_data *) iwp; if (descr->flags & IW_DESCR_FLAG_RESTRICT) /* If the event is restricted, don't * export the payload. */ wireless_send_event(dev, cmd, data, NULL); else wireless_send_event(dev, cmd, data, extra); } out: kfree(extra); return err; } /* * Call the commit handler in the driver * (if exist and if conditions are right) * * Note : our current commit strategy is currently pretty dumb, * but we will be able to improve on that... * The goal is to try to agreagate as many changes as possible * before doing the commit. Drivers that will define a commit handler * are usually those that need a reset after changing parameters, so * we want to minimise the number of reset. * A cool idea is to use a timer : at each "set" command, we re-set the * timer, when the timer eventually fires, we call the driver. * Hopefully, more on that later. * * Also, I'm waiting to see how many people will complain about the * netif_running(dev) test. I'm open on that one... * Hopefully, the driver will remember to do a commit in "open()" ;-) */ int call_commit_handler(struct net_device *dev) { #ifdef CONFIG_WIRELESS_EXT if (netif_running(dev) && dev->wireless_handlers && dev->wireless_handlers->standard[0]) /* Call the commit handler on the driver */ return dev->wireless_handlers->standard[0](dev, NULL, NULL, NULL); else return 0; /* Command completed successfully */ #else /* cfg80211 has no commit */ return 0; #endif } /* * Main IOCTl dispatcher. * Check the type of IOCTL and call the appropriate wrapper... */ static int wireless_process_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, wext_ioctl_func standard, wext_ioctl_func private) { struct net_device *dev; iw_handler handler; /* Permissions are already checked in dev_ioctl() before calling us. * The copy_to/from_user() of ifr is also dealt with in there */ /* Make sure the device exist */ if ((dev = __dev_get_by_name(net, iwr->ifr_name)) == NULL) return -ENODEV; /* A bunch of special cases, then the generic case... * Note that 'cmd' is already filtered in dev_ioctl() with * (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) */ if (cmd == SIOCGIWSTATS) return standard(dev, iwr, cmd, info, &iw_handler_get_iwstats); #ifdef CONFIG_WEXT_PRIV if (cmd == SIOCGIWPRIV && dev->wireless_handlers) return standard(dev, iwr, cmd, info, iw_handler_get_private); #endif /* Basic check */ if (!netif_device_present(dev)) return -ENODEV; /* New driver API : try to find the handler */ handler = get_handler(dev, cmd); if (handler) { /* Standard and private are not the same */ if (cmd < SIOCIWFIRSTPRIV) return standard(dev, iwr, cmd, info, handler); else if (private) return private(dev, iwr, cmd, info, handler); } return -EOPNOTSUPP; } /* If command is `set a parameter', or `get the encoding parameters', * check if the user has the right to do it. */ static int wext_permission_check(unsigned int cmd) { if ((IW_IS_SET(cmd) || cmd == SIOCGIWENCODE || cmd == SIOCGIWENCODEEXT) && !capable(CAP_NET_ADMIN)) return -EPERM; return 0; } /* entry point from dev ioctl */ static int wext_ioctl_dispatch(struct net *net, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, wext_ioctl_func standard, wext_ioctl_func private) { int ret = wext_permission_check(cmd); if (ret) return ret; dev_load(net, iwr->ifr_name); rtnl_lock(); ret = wireless_process_ioctl(net, iwr, cmd, info, standard, private); rtnl_unlock(); return ret; } /* * Wrapper to call a standard Wireless Extension handler. * We do various checks and also take care of moving data between * user space and kernel space. */ static int ioctl_standard_call(struct net_device * dev, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, iw_handler handler) { const struct iw_ioctl_description * descr; int ret = -EINVAL; /* Get the description of the IOCTL */ if (IW_IOCTL_IDX(cmd) >= standard_ioctl_num) return -EOPNOTSUPP; descr = &(standard_ioctl[IW_IOCTL_IDX(cmd)]); /* Check if we have a pointer to user space data or not */ if (descr->header_type != IW_HEADER_TYPE_POINT) { /* No extra arguments. Trivial to handle */ ret = handler(dev, info, &(iwr->u), NULL); /* Generate an event to notify listeners of the change */ if ((descr->flags & IW_DESCR_FLAG_EVENT) && ((ret == 0) || (ret == -EIWCOMMIT))) wireless_send_event(dev, cmd, &(iwr->u), NULL); } else { ret = ioctl_standard_iw_point(&iwr->u.data, cmd, descr, handler, dev, info); } /* Call commit handler if needed and defined */ if (ret == -EIWCOMMIT) ret = call_commit_handler(dev); /* Here, we will generate the appropriate event if needed */ return ret; } int wext_handle_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct iw_request_info info = { .cmd = cmd, .flags = 0 }; struct iwreq iwr; int ret; if (copy_from_user(&iwr, arg, sizeof(iwr))) return -EFAULT; iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0; ret = wext_ioctl_dispatch(net, &iwr, cmd, &info, ioctl_standard_call, ioctl_private_call); if (ret >= 0 && IW_IS_GET(cmd) && copy_to_user(arg, &iwr, sizeof(struct iwreq))) return -EFAULT; return ret; } #ifdef CONFIG_COMPAT static int compat_standard_call(struct net_device *dev, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, iw_handler handler) { const struct iw_ioctl_description *descr; struct compat_iw_point *iwp_compat; struct iw_point iwp; int err; descr = standard_ioctl + IW_IOCTL_IDX(cmd); if (descr->header_type != IW_HEADER_TYPE_POINT) return ioctl_standard_call(dev, iwr, cmd, info, handler); iwp_compat = (struct compat_iw_point *) &iwr->u.data; iwp.pointer = compat_ptr(iwp_compat->pointer); iwp.length = iwp_compat->length; iwp.flags = iwp_compat->flags; err = ioctl_standard_iw_point(&iwp, cmd, descr, handler, dev, info); iwp_compat->pointer = ptr_to_compat(iwp.pointer); iwp_compat->length = iwp.length; iwp_compat->flags = iwp.flags; return err; } int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct iw_request_info info; struct iwreq iwr; char *colon; int ret; if (copy_from_user(&iwr, argp, sizeof(struct iwreq))) return -EFAULT; iwr.ifr_name[IFNAMSIZ-1] = 0; colon = strchr(iwr.ifr_name, ':'); if (colon) *colon = 0; info.cmd = cmd; info.flags = IW_REQUEST_FLAG_COMPAT; ret = wext_ioctl_dispatch(net, &iwr, cmd, &info, compat_standard_call, compat_private_call); if (ret >= 0 && IW_IS_GET(cmd) && copy_to_user(argp, &iwr, sizeof(struct iwreq))) return -EFAULT; return ret; } #endif char *iwe_stream_add_event(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, int event_len) { int lcp_len = iwe_stream_lcp_len(info); event_len = iwe_stream_event_len_adjust(info, event_len); /* Check if it's possible */ if (likely((stream + event_len) < ends)) { iwe->len = event_len; /* Beware of alignement issues on 64 bits */ memcpy(stream, (char *) iwe, IW_EV_LCP_PK_LEN); memcpy(stream + lcp_len, &iwe->u, event_len - lcp_len); stream += event_len; } return stream; } EXPORT_SYMBOL(iwe_stream_add_event); char *iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, char *extra) { int event_len = iwe_stream_point_len(info) + iwe->u.data.length; int point_len = iwe_stream_point_len(info); int lcp_len = iwe_stream_lcp_len(info); /* Check if it's possible */ if (likely((stream + event_len) < ends)) { iwe->len = event_len; memcpy(stream, (char *) iwe, IW_EV_LCP_PK_LEN); memcpy(stream + lcp_len, ((char *) &iwe->u) + IW_EV_POINT_OFF, IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); if (iwe->u.data.length && extra) memcpy(stream + point_len, extra, iwe->u.data.length); stream += event_len; } return stream; } EXPORT_SYMBOL(iwe_stream_add_point); char *iwe_stream_add_value(struct iw_request_info *info, char *event, char *value, char *ends, struct iw_event *iwe, int event_len) { int lcp_len = iwe_stream_lcp_len(info); /* Don't duplicate LCP */ event_len -= IW_EV_LCP_LEN; /* Check if it's possible */ if (likely((value + event_len) < ends)) { /* Add new value */ memcpy(value, &iwe->u, event_len); value += event_len; /* Patch LCP */ iwe->len = value - event; memcpy(event, (char *) iwe, lcp_len); } return value; } EXPORT_SYMBOL(iwe_stream_add_value); |
| 91 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM printk #if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PRINTK_H #include <linux/tracepoint.h> TRACE_EVENT(console, TP_PROTO(const char *text, size_t len), TP_ARGS(text, len), TP_STRUCT__entry( __dynamic_array(char, msg, len + 1) ), TP_fast_assign( /* * Each trace entry is printed in a new line. * If the msg finishes with '\n', cut it off * to avoid blank lines in the trace. */ if ((len > 0) && (text[len-1] == '\n')) len -= 1; memcpy(__get_str(msg), text, len); __get_str(msg)[len] = 0; ), TP_printk("%s", __get_str(msg)) ); #endif /* _TRACE_PRINTK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 156 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.h - generic kernel object infrastructure. * * Copyright (c) 2002-2003 Patrick Mochel * Copyright (c) 2002-2003 Open Source Development Labs * Copyright (c) 2006-2008 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2008 Novell Inc. * * Please read Documentation/core-api/kobject.rst before using the kobject * interface, ESPECIALLY the parts about reference counts and object * destructors. */ #ifndef _KOBJECT_H_ #define _KOBJECT_H_ #include <linux/types.h> #include <linux/list.h> #include <linux/sysfs.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> #include <linux/uidgid.h> #include <linux/android_kabi.h> #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 64 /* number of env pointers */ #define UEVENT_BUFFER_SIZE 2048 /* buffer for the variables */ #ifdef CONFIG_UEVENT_HELPER /* path to the userspace helper executed on an event */ extern char uevent_helper[]; #endif /* counter to tag the uevent, read only except for the kobject core */ extern u64 uevent_seqnum; /* * The actions here must match the index to the string array * in lib/kobject_uevent.c * * Do not add new actions here without checking with the driver-core * maintainers. Action strings are not meant to express subsystem * or device specific properties. In most cases you want to send a * kobject_uevent_env(kobj, KOBJ_CHANGE, env) with additional event * specific variables added to the event environment. */ enum kobject_action { KOBJ_ADD, KOBJ_REMOVE, KOBJ_CHANGE, KOBJ_MOVE, KOBJ_ONLINE, KOBJ_OFFLINE, KOBJ_BIND, KOBJ_UNBIND, }; struct kobject { const char *name; struct list_head entry; struct kobject *parent; struct kset *kset; struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; #endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; unsigned int uevent_suppress:1; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); extern __printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); extern struct kobject *kobject_get(struct kobject *kobj); extern struct kobject * __must_check kobject_get_unless_zero( struct kobject *kobj); extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); /** * kobject_has_children - Returns whether a kobject has children. * @kobj: the object to test * * This will return whether a kobject has other kobjects as children. * * It does NOT account for the presence of attribute files, only sub * directories. It also assumes there is no concurrent addition or * removal of such children, and thus relies on external locking. */ static inline bool kobject_has_children(struct kobject *kobj) { WARN_ON_ONCE(kref_read(&kobj->kref) == 0); return kobj->sd && kobj->sd->dir.subdirs; } struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; struct kobj_uevent_env { char *argv[3]; char *envp[UEVENT_NUM_ENVP]; int envp_idx; char buf[UEVENT_BUFFER_SIZE]; int buflen; }; struct kset_uevent_ops { int (* const filter)(struct kset *kset, struct kobject *kobj); const char *(* const name)(struct kset *kset, struct kobject *kobj); int (* const uevent)(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { struct attribute attr; ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr, char *buf); ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count); }; extern const struct sysfs_ops kobj_sysfs_ops; struct sock; /** * struct kset - a set of kobjects of a specific type, belonging to a specific subsystem. * * A kset defines a group of kobjects. They can be individually * different "types" but overall these kobjects all want to be grouped * together and operated on in the same manner. ksets are used to * define the attribute callbacks and other common events that happen to * a kobject. * * @list: the list of all kobjects for this kset * @list_lock: a lock for iterating over the kobjects * @kobj: the embedded kobject for this kset (recursion, isn't it fun...) * @uevent_ops: the set of uevent operations for this kset. These are * called whenever a kobject has something happen to it so that the kset * can add new environment variables, or filter out the uevents if so * desired. */ struct kset { struct list_head list; spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); } __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); extern void kset_unregister(struct kset *kset); extern struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { return kobj ? container_of(kobj, struct kset, kobj) : NULL; } static inline struct kset *kset_get(struct kset *k) { return k ? to_kset(kobject_get(&k->kobj)) : NULL; } static inline void kset_put(struct kset *k) { kobject_put(&k->kobj); } static inline struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } extern struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; /* The global /sys/kernel/mm/ kobject for people to chain off of */ extern struct kobject *mm_kobj; /* The global /sys/hypervisor/ kobject for people to chain off of */ extern struct kobject *hypervisor_kobj; /* The global /sys/power/ kobject for people to chain off of */ extern struct kobject *power_kobj; /* The global /sys/firmware/ kobject for people to chain off of */ extern struct kobject *firmware_kobj; int kobject_uevent(struct kobject *kobj, enum kobject_action action); int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp[]); int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count); __printf(2, 3) int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...); #endif /* _KOBJECT_H_ */ |
| 10 10 10 10 8 10 17 17 17 17 17 2 2 2 2 2 17 17 17 17 17 17 18 18 8 17 17 1182 1183 2 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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> */ #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 "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->header_ops != NULL mac_header -> ll header data -> ll header dev->header_ops == NULL (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); static int packet_direct_xmit(struct sk_buff *skb) { 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); if (likely(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 bool packet_use_direct_xmit(const struct packet_sock *po) { return po->xmit == packet_direct_xmit; } 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 (!po->running) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); po->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); po->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 (po->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; h.raw = frame; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_status = status; flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: h.h2->tp_status = status; flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: 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(); h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return h.h1->tp_status; case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return h.h2->tp_status; case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return 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, 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, 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 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) { 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 { 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) { int pressure, ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (READ_ONCE(po->pressure) != pressure) WRITE_ONCE(po->pressure, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (READ_ONCE(po->pressure) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) WRITE_ONCE(po->pressure, 0); } 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; } sk_refcnt_debug_dec(sk); } 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 = prandom_u32() % 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 prandom_u32_max(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 && !READ_ONCE(po_next->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; 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; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (po->running && 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) { __dev_remove_pack(&po->prot_hook); /* 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); __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; strlcpy(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) { 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); } 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)) { 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 = sk->sk_priority; skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); 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) { struct virtio_net_hdr vnet_hdr; if (*len < sizeof(vnet_hdr)) return -EINVAL; *len -= sizeof(vnet_hdr); if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr)); } /* * 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 * sequencially, 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) { struct sock *sk; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; bool is_drop_n_account = false; 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->len; 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(po->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_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: is_drop_n_account = true; atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: if (!is_drop_n_account) consume_skb(skb); else kfree_skb(skb); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; 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; bool is_drop_n_account = false; unsigned int slot_id = 0; bool do_vnet = false; /* 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->len; 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->ip_summed == CHECKSUM_COMPLETE || skb_csum_unnecessary(skb))) status |= TP_STATUS_CSUM_VALID; 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; if (po->has_vnet_hdr) { netoff += sizeof(struct virtio_net_hdr); do_vnet = true; } 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 (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; do_vnet = false; } } } 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; do_vnet = false; } } 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 (do_vnet && 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_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, 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 { 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 = skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(po->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: if (!is_drop_n_account) consume_skb(skb); else kfree_skb(skb); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); is_drop_n_account = true; sk->sk_data_ready(sk); kfree_skb(copy_skb); 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); if (!packet_read_pending(&po->tx_ring)) 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) { if (*len < sizeof(*vnet_hdr)) return -EINVAL; *len -= sizeof(*vnet_hdr); if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; return __packet_snd_vnet_parse(vnet_hdr, *len); } 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 = po->sk.sk_priority; skb->mark = po->sk.sk_mark; skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); 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(%lu)\n", 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(po->tp_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); 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) && !po->has_vnet_hdr) 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 (po->has_vnet_hdr) { vnet_hdr = data; data += sizeof(*vnet_hdr); tp_len -= sizeof(*vnet_hdr); 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 && !po->has_vnet_hdr && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (po->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 (po->has_vnet_hdr) { 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 = po->xmit(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; skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, 0); 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); bool has_vnet_hdr = false; 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 = 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 (po->has_vnet_hdr) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr); if (err) goto out_unlock; has_vnet_hdr = true; } 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)) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, sockc.tsflags); 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 = sk->sk_priority; skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; if (has_vnet_hdr) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += sizeof(vnet_hdr); virtio_net_hdr_set_proto(skb, &vnet_hdr); } packet_parse_headers(skb, sock); if (unlikely(extra_len == 4)) skb->no_fcs = 1; err = po->xmit(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: if (dev) 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); preempt_disable(); sock_prot_inuse_add(net, sk->sk_prot, -1); preempt_enable(); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { dev_put(po->prot_hook.dev); 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); sk_refcnt_debug_release(sk); 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_curr; __be16 proto_curr; bool need_rehook; struct net_device *dev = NULL; int ret = 0; bool unlisted = false; lock_sock(sk); spin_lock(&po->bind_lock); 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; } } if (dev) dev_hold(dev); proto_curr = po->prot_hook.type; dev_curr = po->prot_hook.dev; need_rehook = proto_curr != proto || dev_curr != dev; if (need_rehook) { if (po->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(); dev_curr = po->prot_hook.dev; if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(po->running); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } if (dev_curr) dev_put(dev_curr); 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->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) + 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)); name[sizeof(uaddr->sa_data)] = 0; return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); } 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 ? : pkt_sk(sk)->num); } 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; sock_init_data(sock, sk); po = pkt_sk(sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; po->xmit = dev_queue_xmit; err = packet_alloc_pending(po); if (err) goto out2; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; sk_refcnt_debug_inc(sk); /* * 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); preempt_disable(); sock_prot_inuse_add(net, &packet_proto, 1); preempt_enable(); return 0; out2: 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 = 0; 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, flags & MSG_DONTWAIT, &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 (pkt_sk(sk)->has_vnet_hdr) { err = packet_rcv_vnet(msg, skb, &len); if (err) goto out_free; vnet_hdr_len = sizeof(struct virtio_net_hdr); } /* 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 = skb->protocol; } sock_recv_ts_and_drops(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 (pkt_sk(sk)->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->ip_summed == CHECKSUM_COMPLETE || skb_csum_unnecessary(skb))) aux.tp_status |= TP_STATUS_CSUM_VALID; 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 { 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)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); 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; memcpy(sll->sll_addr, 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; int len; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: len = sizeof(req_u.req); break; case TPACKET_V3: default: len = sizeof(req_u.req3); break; } if (optlen < len) { ret = -EINVAL; } else { if (copy_from_sockptr(&req_u.req, optval, len)) ret = -EFAULT; else 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; 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 { po->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; lock_sock(sk); po->auxdata = !!val; release_sock(sk); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); po->origdev = !!val; release_sock(sk); return 0; } case PACKET_VNET_HDR: { int val; if (sock->type != SOCK_RAW) return -EINVAL; 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 { po->has_vnet_hdr = !!val; 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; 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; 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) { ret = -EBUSY; } else { po->tp_tx_has_off = !!val; ret = 0; } 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; po->xmit = val ? packet_direct_xmit : dev_queue_xmit; 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 = po->auxdata; break; case PACKET_ORIGDEV: val = po->origdev; break; case PACKET_VNET_HDR: val = po->has_vnet_hdr; 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 = po->tp_loss; break; case PACKET_TIMESTAMP: val = 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 = 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 = po->tp_tx_has_off; break; case PACKET_QDISC_BYPASS: val = packet_use_direct_xmit(po); 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 (po->running) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); 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_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_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_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 = po->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_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_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %d\n", atomic_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_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, .sendpage = sock_no_sendpage, }; 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, .sendpage = sock_no_sendpage, }; 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_puts(seq, "sk RefCnt Type Proto Iface R Rmem User Inode\n"); 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), po->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) { unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); sock_unregister(PF_PACKET); proto_unregister(&packet_proto); } static int __init packet_init(void) { int rc; rc = proto_register(&packet_proto, 0); if (rc) goto out; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out_sock; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; return 0; out_pernet: unregister_pernet_subsys(&packet_net_ops); out_sock: sock_unregister(PF_PACKET); out_proto: proto_unregister(&packet_proto); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 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 */ #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(page) ( \ (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \ (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \ (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \ (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \ (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, int lru ), TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) __field(int, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); __entry->lru = lru; __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu lru=%d flags=%s%s%s%s%s%s", __entry->page, __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 page *page), TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu", __entry->page, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SIGNAL_H #define _LINUX_SIGNAL_H #include <linux/bug.h> #include <linux/signal_types.h> #include <linux/string.h> struct task_struct; /* for sysctl */ extern int print_fatal_signals; static inline void copy_siginfo(kernel_siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } #define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) static inline void copy_siginfo_to_external(siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*from)); memset(((char *)to) + sizeof(struct kernel_siginfo), 0, SI_EXPANSION_SIZE); } int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); enum siginfo_layout { SIL_KILL, SIL_TIMER, SIL_POLL, SIL_FAULT, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, SIL_CHLD, SIL_RT, SIL_SYS, }; enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. */ #ifndef __HAVE_ARCH_SIG_BITOPS #include <linux/bitops.h> /* We don't use <linux/bitops.h> for these because there is no need to be atomic. */ static inline void sigaddset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] |= 1UL << sig; else set->sig[sig / _NSIG_BPW] |= 1UL << (sig % _NSIG_BPW); } static inline void sigdelset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] &= ~(1UL << sig); else set->sig[sig / _NSIG_BPW] &= ~(1UL << (sig % _NSIG_BPW)); } static inline int sigismember(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) return 1 & (set->sig[0] >> sig); else return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW)); } #endif /* __HAVE_ARCH_SIG_BITOPS */ static inline int sigisemptyset(sigset_t *set) { switch (_NSIG_WORDS) { case 4: return (set->sig[3] | set->sig[2] | set->sig[1] | set->sig[0]) == 0; case 2: return (set->sig[1] | set->sig[0]) == 0; case 1: return set->sig[0] == 0; default: BUILD_BUG(); return 0; } } static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) { switch (_NSIG_WORDS) { case 4: return (set1->sig[3] == set2->sig[3]) && (set1->sig[2] == set2->sig[2]) && (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 2: return (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 1: return set1->sig[0] == set2->sig[0]; } return 0; } #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS #include <linux/string.h> #define _SIG_SET_BINOP(name, op) \ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ { \ unsigned long a0, a1, a2, a3, b0, b1, b2, b3; \ \ switch (_NSIG_WORDS) { \ case 4: \ a3 = a->sig[3]; a2 = a->sig[2]; \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_or(x,y) ((x) | (y)) _SIG_SET_BINOP(sigorsets, _sig_or) #define _sig_and(x,y) ((x) & (y)) _SIG_SET_BINOP(sigandsets, _sig_and) #define _sig_andn(x,y) ((x) & ~(y)) _SIG_SET_BINOP(sigandnsets, _sig_andn) #undef _SIG_SET_BINOP #undef _sig_or #undef _sig_and #undef _sig_andn #define _SIG_SET_OP(name, op) \ static inline void name(sigset_t *set) \ { \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_not(x) (~(x)) _SIG_SET_OP(signotset, _sig_not) #undef _SIG_SET_OP #undef _sig_not static inline void sigemptyset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; fallthrough; case 1: set->sig[0] = 0; break; } } static inline void sigfillset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; fallthrough; case 1: set->sig[0] = -1; break; } } /* Some extensions for manipulating the low 32 signals in particular. */ static inline void sigaddsetmask(sigset_t *set, unsigned long mask) { set->sig[0] |= mask; } static inline void sigdelsetmask(sigset_t *set, unsigned long mask) { set->sig[0] &= ~mask; } static inline int sigtestsetmask(sigset_t *set, unsigned long mask) { return (set->sig[0] & mask) != 0; } static inline void siginitset(sigset_t *set, unsigned long mask) { set->sig[0] = mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = 0; break; case 1: ; } } static inline void siginitsetinv(sigset_t *set, unsigned long mask) { set->sig[0] = ~mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = -1; break; case 1: ; } } #endif /* __HAVE_ARCH_SIG_SETOPS */ static inline void init_sigpending(struct sigpending *sig) { sigemptyset(&sig->signal); INIT_LIST_HEAD(&sig->list); } extern void flush_sigqueue(struct sigpending *queue); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) { return sig <= _NSIG ? 1 : 0; } struct timespec; struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; extern bool get_signal(struct ksignal *ksig); extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void exit_signals(struct task_struct *tsk); extern void kernel_sigaction(int, __sighandler_t); #define SIG_KTHREAD ((__force __sighandler_t)2) #define SIG_KTHREAD_KERNEL ((__force __sighandler_t)3) static inline void allow_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know it'll be handled, so that they don't get converted to * SIGKILL or just silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD); } static inline void allow_kernel_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know signals sent by the kernel will be handled, so that they * don't get silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD_KERNEL); } static inline void disallow_signal(int sig) { kernel_sigaction(sig, SIG_IGN); } extern struct kmem_cache *sighand_cachep; extern bool unhandled_signal(struct task_struct *tsk, int sig); /* * In POSIX a signal is sent either to a specific thread (Linux task) * or to the process as a whole (Linux thread group). How the signal * is sent determines whether it's to one thread or the whole group, * which determines which signal mask(s) are involved in blocking it * from being delivered until later. When the signal is delivered, * either it's caught or ignored by a user handler or it has a default * effect that applies to the whole thread group (POSIX process). * * The possible effects an unblocked signal set to SIG_DFL can have are: * ignore - Nothing Happens * terminate - kill the process, i.e. all threads in the group, * similar to exit_group. The group leader (only) reports * WIFSIGNALED status to its parent. * coredump - write a core dump file describing all threads using * the same mm and then kill all those threads * stop - stop all the threads in the group, i.e. TASK_STOPPED state * * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored. * Other signals when not blocked and set to SIG_DFL behaves as follows. * The job control signals also have other special effects. * * +--------------------+------------------+ * | POSIX signal | default action | * +--------------------+------------------+ * | SIGHUP | terminate | * | SIGINT | terminate | * | SIGQUIT | coredump | * | SIGILL | coredump | * | SIGTRAP | coredump | * | SIGABRT/SIGIOT | coredump | * | SIGBUS | coredump | * | SIGFPE | coredump | * | SIGKILL | terminate(+) | * | SIGUSR1 | terminate | * | SIGSEGV | coredump | * | SIGUSR2 | terminate | * | SIGPIPE | terminate | * | SIGALRM | terminate | * | SIGTERM | terminate | * | SIGCHLD | ignore | * | SIGCONT | ignore(*) | * | SIGSTOP | stop(*)(+) | * | SIGTSTP | stop(*) | * | SIGTTIN | stop(*) | * | SIGTTOU | stop(*) | * | SIGURG | ignore | * | SIGXCPU | coredump | * | SIGXFSZ | coredump | * | SIGVTALRM | terminate | * | SIGPROF | terminate | * | SIGPOLL/SIGIO | terminate | * | SIGSYS/SIGUNUSED | coredump | * | SIGSTKFLT | terminate | * | SIGWINCH | ignore | * | SIGPWR | terminate | * | SIGRTMIN-SIGRTMAX | terminate | * +--------------------+------------------+ * | non-POSIX signal | default action | * +--------------------+------------------+ * | SIGEMT | coredump | * +--------------------+------------------+ * * (+) For SIGKILL and SIGSTOP the action is "always", not just "default". * (*) Special job control effects: * When SIGCONT is sent, it resumes the process (all threads in the group) * from TASK_STOPPED state and also clears any pending/queued stop signals * (any of those marked with "stop(*)"). This happens regardless of blocking, * catching, or ignoring SIGCONT. When any stop signal is sent, it clears * any pending/queued SIGCONT signals; this happens regardless of blocking, * catching, or ignored the stop signal, though (except for SIGSTOP) the * default action of stopping the process may happen later or never. */ #ifdef SIGEMT #define SIGEMT_MASK rt_sigmask(SIGEMT) #else #define SIGEMT_MASK 0 #endif #if SIGRTMIN > BITS_PER_LONG #define rt_sigmask(sig) (1ULL << ((sig)-1)) #else #define rt_sigmask(sig) sigmask(sig) #endif #define siginmask(sig, mask) \ ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) #define SIG_KERNEL_STOP_MASK (\ rt_sigmask(SIGSTOP) | rt_sigmask(SIGTSTP) | \ rt_sigmask(SIGTTIN) | rt_sigmask(SIGTTOU) ) #define SIG_KERNEL_COREDUMP_MASK (\ rt_sigmask(SIGQUIT) | rt_sigmask(SIGILL) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGABRT) | \ rt_sigmask(SIGFPE) | rt_sigmask(SIGSEGV) | \ rt_sigmask(SIGBUS) | rt_sigmask(SIGSYS) | \ rt_sigmask(SIGXCPU) | rt_sigmask(SIGXFSZ) | \ SIGEMT_MASK ) #define SIG_KERNEL_IGNORE_MASK (\ rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) #define SIG_SPECIFIC_SICODES_MASK (\ rt_sigmask(SIGILL) | rt_sigmask(SIGFPE) | \ rt_sigmask(SIGSEGV) | rt_sigmask(SIGBUS) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGPOLL) | rt_sigmask(SIGSYS) | \ SIGEMT_MASK ) #define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) #define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) #define sig_specific_sicodes(sig) siginmask(sig, SIG_SPECIFIC_SICODES_MASK) #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL) void signals_init(void); int restore_altstack(const stack_t __user *); int __save_altstack(stack_t __user *, unsigned long); #define unsafe_save_altstack(uss, sp, label) do { \ stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ if (t->sas_ss_flags & SS_AUTODISARM) \ sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); #endif #ifndef arch_untagged_si_addr /* * Given a fault address and a signal and si_code which correspond to the * _sigfault union member, returns the address that must appear in si_addr if * the signal handler does not have SA_EXPOSE_TAGBITS enabled in sa_flags. */ static inline void __user *arch_untagged_si_addr(void __user *addr, unsigned long sig, unsigned long si_code) { return addr; } #endif #endif /* _LINUX_SIGNAL_H */ |
| 3 2 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resultion entity * * Authors: * net_random Alan Cox * net_ratelimit Andi Kleen * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/ratelimit.h> #include <linux/socket.h> #include <net/sock.h> #include <net/net_ratelimit.h> #include <net/ipv6.h> #include <asm/byteorder.h> #include <linux/uaccess.h> DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. */ int net_ratelimit(void) { return __ratelimit(&net_ratelimit_state); } EXPORT_SYMBOL(net_ratelimit); /* * Convert an ASCII string to binary IP. * This is outside of net/ipv4/ because various code that uses IP addresses * is otherwise not dependent on the TCP/IP stack. */ __be32 in_aton(const char *str) { unsigned int l; unsigned int val; int i; l = 0; for (i = 0; i < 4; i++) { l <<= 8; if (*str != '\0') { val = 0; while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; } l |= val; if (*str != '\0') str++; } } return htonl(l); } EXPORT_SYMBOL(in_aton); #define IN6PTON_XDIGIT 0x00010000 #define IN6PTON_DIGIT 0x00020000 #define IN6PTON_COLON_MASK 0x00700000 #define IN6PTON_COLON_1 0x00100000 /* single : requested */ #define IN6PTON_COLON_2 0x00200000 /* second : requested */ #define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ #define IN6PTON_DOT 0x00800000 /* . */ #define IN6PTON_DELIM 0x10000000 #define IN6PTON_NULL 0x20000000 /* first/tail */ #define IN6PTON_UNKNOWN 0x40000000 static inline int xdigit2bin(char c, int delim) { int val; if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; val = hex_to_bin(c); if (val >= 0) return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; } /** * in4_pton - convert an IPv4 address from literal to binary representation * @src: the start of the IPv4 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[4] array) representation of the IPv4 address * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s; u8 *d; u8 dbuf[4]; int ret = 0; int i; int w = 0; if (srclen < 0) srclen = strlen(src); s = src; d = dbuf; i = 0; while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) { goto out; } if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (w == 0) goto out; *d++ = w & 0xff; w = 0; i++; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (i != 4) goto out; break; } goto cont; } w = (w * 10) + c; if ((w & 0xffff) > 255) { goto out; } cont: if (i >= 4) goto out; s++; srclen--; } ret = 1; memcpy(dst, dbuf, sizeof(dbuf)); out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in4_pton); /** * in6_pton - convert an IPv6 address from literal to binary representation * @src: the start of the IPv6 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[16] array) representation of the IPv6 address * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s, *tok = NULL; u8 *d, *dc = NULL; u8 dbuf[16]; int ret = 0; int i; int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; int w = 0; memset(dbuf, 0, sizeof(dbuf)); s = src; d = dbuf; if (srclen < 0) srclen = strlen(src); while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & state)) goto out; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { /* process one 16-bit word */ if (!(state & IN6PTON_NULL)) { *d++ = (w >> 8) & 0xff; *d++ = w & 0xff; } w = 0; if (c & IN6PTON_DELIM) { /* We've processed last word */ break; } /* * COLON_1 => XDIGIT * COLON_2 => XDIGIT|DELIM * COLON_1_2 => COLON_2 */ switch (state & IN6PTON_COLON_MASK) { case IN6PTON_COLON_2: dc = d; state = IN6PTON_XDIGIT | IN6PTON_DELIM; if (dc - dbuf >= sizeof(dbuf)) state |= IN6PTON_NULL; break; case IN6PTON_COLON_1|IN6PTON_COLON_1_2: state = IN6PTON_XDIGIT | IN6PTON_COLON_2; break; case IN6PTON_COLON_1: state = IN6PTON_XDIGIT; break; case IN6PTON_COLON_1_2: state = IN6PTON_COLON_2; break; default: state = 0; } tok = s + 1; goto cont; } if (c & IN6PTON_DOT) { ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); if (ret > 0) { d += 4; break; } goto out; } w = (w << 4) | (0xff & c); state = IN6PTON_COLON_1 | IN6PTON_DELIM; if (!(w & 0xf000)) { state |= IN6PTON_XDIGIT; } if (!dc && d + 2 < dbuf + sizeof(dbuf)) { state |= IN6PTON_COLON_1_2; state &= ~IN6PTON_DELIM; } if (d + 2 >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); } cont: if ((dc && d + 4 < dbuf + sizeof(dbuf)) || d + 4 == dbuf + sizeof(dbuf)) { state |= IN6PTON_DOT; } if (d >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); } s++; srclen--; } i = 15; d--; if (dc) { while (d >= dc) dst[i--] = *d--; while (i >= dc - dbuf) dst[i--] = 0; while (i >= 0) dst[i--] = *d--; } else memcpy(dst, dbuf, sizeof(dbuf)); ret = 1; out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in6_pton); static int inet4_pton(const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; int srclen = strlen(src); if (srclen > INET_ADDRSTRLEN) return -EINVAL; if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr, '\n', NULL) == 0) return -EINVAL; addr4->sin_family = AF_INET; addr4->sin_port = htons(port_num); return 0; } static int inet6_pton(struct net *net, const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; const char *scope_delim; int srclen = strlen(src); if (srclen > INET6_ADDRSTRLEN) return -EINVAL; if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr, '%', &scope_delim) == 0) return -EINVAL; if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL && src + srclen != scope_delim && *scope_delim == '%') { struct net_device *dev; char scope_id[16]; size_t scope_len = min_t(size_t, sizeof(scope_id) - 1, src + srclen - scope_delim - 1); memcpy(scope_id, scope_delim + 1, scope_len); scope_id[scope_len] = '\0'; dev = dev_get_by_name(net, scope_id); if (dev) { addr6->sin6_scope_id = dev->ifindex; dev_put(dev); } else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) { return -EINVAL; } } addr6->sin6_family = AF_INET6; addr6->sin6_port = htons(port_num); return 0; } /** * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address * @net: net namespace (used for scope handling) * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either * @src: the start of the address string * @port: the start of the port string (or NULL for none) * @addr: output socket address * * Return zero on success, return errno when any error occurs. */ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, const char *src, const char *port, struct sockaddr_storage *addr) { u16 port_num; int ret = -EINVAL; if (port) { if (kstrtou16(port, 0, &port_num)) return -EINVAL; } else { port_num = 0; } switch (af) { case AF_INET: ret = inet4_pton(src, port_num, addr); break; case AF_INET6: ret = inet6_pton(net, src, port_num, addr); break; case AF_UNSPEC: ret = inet4_pton(src, port_num, addr); if (ret) ret = inet6_pton(net, src, port_num, addr); break; default: pr_err("unexpected address family %d\n", af); } return ret; } EXPORT_SYMBOL(inet_pton_with_scope); bool inet_addr_is_any(struct sockaddr *addr) { if (addr->sa_family == AF_INET6) { struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)addr; const struct sockaddr_in6 in6_any = { .sin6_addr = IN6ADDR_ANY_INIT }; if (!memcmp(in6->sin6_addr.s6_addr, in6_any.sin6_addr.s6_addr, 16)) return true; } else if (addr->sa_family == AF_INET) { struct sockaddr_in *in = (struct sockaddr_in *)addr; if (in->sin_addr.s_addr == htonl(INADDR_ANY)) return true; } else { pr_warn("unexpected address family %u\n", addr->sa_family); } return false; } EXPORT_SYMBOL(inet_addr_is_any); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(csum_sub(~(skb->csum), (__force __wsum)from), (__force __wsum)to); } else if (pseudohdr) *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), (__force __wsum)from), (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); /** * inet_proto_csum_replace16 - update layer 4 header checksum field * @sum: Layer 4 header checksum field * @skb: sk_buff for the packet * @from: old IPv6 address * @to: new IPv6 address * @pseudohdr: True if layer 4 header checksum includes pseudoheader * * Update layer 4 header as per the update in IPv6 src/dst address. * * There is no need to update skb->csum in this function, because update in two * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as * L4 Header checksum for skb->csum calculation. */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace16); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(diff, ~skb->csum); } else if (pseudohdr) { *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); |
| 19 2 17 17 13 6 3 2 1 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/sort.h> #include <linux/delay.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> #include <linux/fs_parser.h> #include <trace/events/cgroup.h> #include <trace/hooks/cgroup.h> /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls * Expiring in the middle is a performance problem not a correctness one. * 1 sec should be enough. */ #define CGROUP_PIDLIST_DESTROY_DELAY HZ /* Controllers blocked by the commandline in v1 */ static u16 cgroup_no_v1_mask; /* disable named v1 mounts */ static bool cgroup_no_v1_named; /* * pidlist destructions need to be flushed on cgroup destruction. Use a * separate workqueue as flush domain. */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; /* protects cgroup_subsys->release_agent_path */ static DEFINE_SPINLOCK(release_agent_path_lock); bool cgroup1_ssid_disabled(int ssid) { return cgroup_no_v1_mask & (1 << ssid); } /** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; mutex_lock(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; if (root == &cgrp_dfl_root) continue; spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return retval; } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /** * cgroup_trasnsfer_tasks - move tasks from one cgroup to another * @to: cgroup to which the tasks will be moved * @from: cgroup in which the tasks currently reside * * Locking rules between cgroup_post_fork() and the migration path * guarantee that, if a task is forking while being migrated, the new child * is guaranteed to be either visible in the source cgroup after the * parent's migration is complete or put into the target cgroup. No task * can slip out of migration through forking. */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { DEFINE_CGROUP_MGCTX(mgctx); struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ret; if (cgroup_on_dfl(to)) return -EINVAL; ret = cgroup_migrate_vet_dst(to); if (ret) return ret; mutex_lock(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &mgctx); spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_err; /* * Migrate tasks one-by-one until @from is empty. This fails iff * ->can_attach() fails. */ do { css_task_iter_start(&from->self, 0, &it); do { task = css_task_iter_next(&it); } while (task && (task->flags & PF_EXITING)); if (task) get_task_struct(task); css_task_iter_end(&it); if (task) { ret = cgroup_migrate(task, false, &mgctx); if (!ret) TRACE_CGROUP_PATH(transfer_tasks, to, task, false); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&mgctx); percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return ret; } /* * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), * but we cannot guarantee that the information we produce is correct * unless we produce it entirely atomically. * */ /* which pidlist file are we talking about? */ enum cgroup_filetype { CGROUP_FILE_PROCS, CGROUP_FILE_TASKS, }; /* * A pidlist is a list of pids that virtually represents the contents of one * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, * a pair (one each for procs, tasks) for each pid namespace that's relevant * to the cgroup. */ struct cgroup_pidlist { /* * used to find which pidlist is wanted. doesn't change as long as * this particular list stays in the list. */ struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* each of these stored in a list by its cgroup */ struct list_head links; /* pointer to the cgroup we belong to, for list removal purposes */ struct cgroup *owner; /* for delayed destruction */ struct delayed_work destroy_dwork; }; /* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */ void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) { struct cgroup_pidlist *l, *tmp_l; mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); mutex_unlock(&cgrp->pidlist_mutex); flush_workqueue(cgroup_pidlist_destroy_wq); BUG_ON(!list_empty(&cgrp->pidlists)); } static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, destroy_dwork); struct cgroup_pidlist *tofree = NULL; mutex_lock(&l->owner->pidlist_mutex); /* * Destroy iff we didn't get queued again. The state won't change * as destroy_dwork can only be queued while locked. */ if (!delayed_work_pending(dwork)) { list_del(&l->links); kvfree(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); } /* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * Returns the number of unique elements. */ static int pidlist_uniq(pid_t *list, int length) { int src, dest = 1; /* * we presume the 0th element is unique, so i starts at 1. trivial * edge cases first; no work needs to be done for either */ if (length == 0 || length == 1) return length; /* src and dest walk down the list; dest counts unique elements */ for (src = 1; src < length; src++) { /* find next unique element */ while (list[src] == list[src-1]) { src++; if (src == length) goto after; } /* dest always points to where the next unique element goes */ list[dest] = list[src]; dest++; } after: return dest; } /* * The two pid files - task and cgroup.procs - guaranteed that the result * is sorted, which forced this whole pidlist fiasco. As pid order is * different per namespace, each namespace needs differently sorted list, * making it impossible to use, for example, single rbtree of member tasks * sorted by task pointer. As pidlists can be fairly large, allocating one * per open file is dangerous, so cgroup had to implement shared pool of * pidlists keyed by cgroup and namespace. */ static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; } static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ struct pid_namespace *ns = task_active_pid_ns(current); lockdep_assert_held(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) if (l->key.type == type && l->key.ns == ns) return l; return NULL; } /* * find the appropriate pidlist for our purpose (given procs vs tasks) * returns with the lock on that pidlist already held, and takes care * of the use count, or returns NULL with no locks held if we're out of * memory. */ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); l = cgroup_pidlist_find(cgrp, type); if (l) return l; /* entry not found; create a new one */ l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); if (!l) return l; INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); l->key.type = type; /* don't need task_nsproxy() if we're looking at ourself */ l->key.ns = get_pid_ns(task_active_pid_ns(current)); l->owner = cgrp; list_add(&l->links, &cgrp->pidlists); return l; } /* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, struct cgroup_pidlist **lp) { pid_t *array; int length; int pid, n = 0; /* used for populating the array */ struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); /* * If cgroup gets more users after we read count, we won't have * enough space - tough. This race is indistinguishable to the * caller from the case that the additional cgroup users didn't * show up until sometime later on. */ length = cgroup_task_count(cgrp); array = kvmalloc_array(length, sizeof(pid_t), GFP_KERNEL); if (!array) return -ENOMEM; /* now, populate the array */ css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ if (type == CGROUP_FILE_PROCS) pid = task_tgid_vnr(tsk); else pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } css_task_iter_end(&it); length = n; /* now sort & (if procs) strip out duplicates */ sort(array, length, sizeof(pid_t), cmppid, NULL); if (type == CGROUP_FILE_PROCS) length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { kvfree(array); return -ENOMEM; } /* store array, freeing old if necessary */ kvfree(l->list); l->list = array; l->length = length; *lp = l; return 0; } /* * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid * in the cgroup->l->list array. */ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to * one more than the last pid shown (or 0 on the first call or * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; int index = 0, pid = *pos; int *iter, ret; mutex_lock(&cgrp->pidlist_mutex); /* * !NULL @ctx->procs1.pidlist indicates that this isn't the first * start() after open. If the matching pidlist is around, we can use * that. Look for it. Note that @ctx->procs1.pidlist can't be used * directly. It could already have been destroyed. */ if (ctx->procs1.pidlist) ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ if (!ctx->procs1.pidlist) { ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } l = ctx->procs1.pidlist; if (pid) { int end = l->length; while (index < end) { int mid = (index + end) / 2; if (l->list[mid] == pid) { index = mid; break; } else if (l->list[mid] <= pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ iter = l->list + index; *pos = *iter; return iter; } static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); } static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done */ p++; if (p >= end) { (*pos)++; return NULL; } else { *pos = *p; return p; } } static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; } static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct cgroup *cgrp; struct task_struct *task; const struct cred *cred, *tcred; ssize_t ret; bool locked; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &locked, cgrp); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* * Even if we're attaching all tasks in the thread group, we only need * to check permissions on one of them. Check permissions using the * credentials from file open to protect against inherited fd attacks. */ cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid) && !ns_capable(tcred->user_ns, CAP_SYS_NICE)) ret = -EACCES; put_cred(tcred); if (ret) goto out_finish; ret = cgroup_attach_task(cgrp, task, threadgroup); trace_android_vh_cgroup_set_task(ret, task); out_finish: cgroup_procs_write_finish(task, locked); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, true); } static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, false); } static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ ctx = of->priv; if ((ctx->ns->user_ns != &init_user_ns) || !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) return -EPERM; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); strlcpy(cgrp->root->release_agent_path, strstrip(buf), sizeof(cgrp->root->release_agent_path)); spin_unlock(&release_agent_path_lock); cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_release_agent_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; spin_lock(&release_agent_path_lock); seq_puts(seq, cgrp->root->release_agent_path); spin_unlock(&release_agent_path_lock); seq_putc(seq, '\n'); return 0; } static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; } static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); } static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; } static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); } static int cgroup_clone_children_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; } /* cgroup core interface files for the legacy hierarchies */ struct cftype cgroup1_base_files[] = { { .name = "cgroup.procs", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup1_procs_write, }, { .name = "cgroup.clone_children", .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, { .name = "cgroup.sane_behavior", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_sane_behavior_show, }, { .name = "tasks", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, .write = cgroup1_tasks_write, }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, { .name = "release_agent", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write = cgroup_release_agent_write, .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; /* Display information about each subsystem and each hierarchy */ int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); /* * ideally we don't want subsystems moving around while we do this. * cgroup_mutex is also necessary to guarantee an atomic snapshot of * subsys/hierarchy state. */ mutex_lock(&cgroup_mutex); for_each_subsys(ss, i) seq_printf(m, "%s\t%d\t%d\t%d\n", ss->legacy_name, ss->root->hierarchy_id, atomic_read(&ss->root->nr_cgrps), cgroup_ssid_enabled(i)); mutex_unlock(&cgroup_mutex); return 0; } /** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into * @dentry: A dentry entry belonging to the cgroup for which stats have * been requested. * * Build and fill cgroupstats so that taskstats can export it to user * space. */ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; /* it should be kernfs_node belonging to cgroupfs and is a directory */ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || kernfs_type(kn) != KERNFS_DIR) return -EINVAL; mutex_lock(&cgroup_mutex); /* * We aren't being called from kernfs and there's no guarantee on * @kn->priv's validity. For this and css_tryget_online_from_dir(), * @kn->priv is RCU safe. Let's do the RCU dancing. */ rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || cgroup_is_dead(cgrp)) { rcu_read_unlock(); mutex_unlock(&cgroup_mutex); return -ENOENT; } rcu_read_unlock(); css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { switch (tsk->state) { case TASK_RUNNING: stats->nr_running++; break; case TASK_INTERRUPTIBLE: stats->nr_sleeping++; break; case TASK_UNINTERRUPTIBLE: stats->nr_uninterruptible++; break; case TASK_STOPPED: stats->nr_stopped++; break; default: if (delayacct_is_task_waiting_on_io(tsk)) stats->nr_io_wait++; break; } } css_task_iter_end(&it); mutex_unlock(&cgroup_mutex); return 0; } void cgroup1_check_for_release(struct cgroup *cgrp) { if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) schedule_work(&cgrp->release_agent_work); } /* * Notify userspace when a cgroup is released, by running the * configured release agent with the name of the cgroup (path * relative to the root of cgroup file system) as the argument. * * Most likely, this user command will try to rmdir this cgroup. * * This races with the possibility that some other task will be * attached to this cgroup before it is removed, or that some other * user task will 'mkdir' a child cgroup of this cgroup. That's ok. * The presumed 'rmdir' will fail quietly if this cgroup is no longer * unused, and this cgroup will be reprieved from its death sentence, * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which * means only wait until the task is successfully execve()'d. The * separate release agent task is forked by call_usermodehelper(), * then control in this thread returns here, without waiting for the * release agent task. We don't bother to wait because the caller of * this routine has no use for the exit status of the release agent * task, so no sense holding our caller up for that. */ void cgroup1_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); char *pathbuf, *agentbuf; char *argv[3], *envp[3]; int ret; /* snoop agent path and exit early if empty */ if (!cgrp->root->release_agent_path[0]) return; /* prepare argument buffers */ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf || !agentbuf) goto out_free; spin_lock(&release_agent_path_lock); strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX); spin_unlock(&release_agent_path_lock); if (!agentbuf[0]) goto out_free; ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); if (ret < 0 || ret >= PATH_MAX) goto out_free; argv[0] = agentbuf; argv[1] = pathbuf; argv[2] = NULL; /* minimal command environment */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); out_free: kfree(agentbuf); kfree(pathbuf); } /* * cgroup_rename - Only allow simple rename of directories in place. */ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name_str) { struct cgroup *cgrp = kn->priv; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(new_name_str, '\n')) return -EINVAL; if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (kn->parent != new_parent) return -EIO; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. kernfs_rename() doesn't require active_ref * protection. Break them before grabbing cgroup_mutex. */ kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); mutex_lock(&cgroup_mutex); ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) TRACE_CGROUP_PATH(rename, cgrp); mutex_unlock(&cgroup_mutex); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); return ret; } static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_show_option(seq, ss->legacy_name, NULL); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) seq_puts(seq, ",cpuset_v2_mode"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_show_option(seq, "release_agent", root->release_agent_path); spin_unlock(&release_agent_path_lock); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_show_option(seq, "name", root->name); return 0; } enum cgroup1_param { Opt_all, Opt_clone_children, Opt_cpuset_v2_mode, Opt_name, Opt_none, Opt_noprefix, Opt_release_agent, Opt_xattr, }; const struct fs_parameter_spec cgroup1_fs_parameters[] = { fsparam_flag ("all", Opt_all), fsparam_flag ("clone_children", Opt_clone_children), fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), fsparam_string("name", Opt_name), fsparam_flag ("none", Opt_none), fsparam_flag ("noprefix", Opt_noprefix), fsparam_string("release_agent", Opt_release_agent), fsparam_flag ("xattr", Opt_xattr), {} }; int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_subsys *ss; struct fs_parse_result result; int opt, i; opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { if (param->type != fs_value_is_string) return invalf(fc, "Non-string source"); if (fc->source) return invalf(fc, "Multiple sources not supported"); fc->source = param->string; param->string = NULL; return 0; } for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name)) continue; if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) return invalfc(fc, "Disabled controller '%s'", param->key); ctx->subsys_mask |= (1 << i); return 0; } return invalfc(fc, "Unknown subsys name '%s'", param->key); } if (opt < 0) return opt; switch (opt) { case Opt_none: /* Explicitly have no subsystems */ ctx->none = true; break; case Opt_all: ctx->all_ss = true; break; case Opt_noprefix: ctx->flags |= CGRP_ROOT_NOPREFIX; break; case Opt_clone_children: ctx->cpuset_clone_children = true; break; case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; break; case Opt_xattr: ctx->flags |= CGRP_ROOT_XATTR; break; case Opt_release_agent: /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; case Opt_name: /* blocked by boot param? */ if (cgroup_no_v1_named) return -ENOENT; /* Can't specify an empty name */ if (!param->size) return invalfc(fc, "Empty name"); if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) return invalfc(fc, "Name too long"); /* Must match [\w.-]+ */ for (i = 0; i < param->size; i++) { char c = param->string[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return invalfc(fc, "Invalid name"); } /* Specifying two names is forbidden */ if (ctx->name) return invalfc(fc, "name respecified"); ctx->name = param->string; param->string = NULL; break; } return 0; } static int check_cgroupfs_options(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); u16 mask = U16_MAX; u16 enabled = 0; struct cgroup_subsys *ss; int i; #ifdef CONFIG_CPUSETS mask = ~((u16)1 << cpuset_cgrp_id); #endif for_each_subsys(ss, i) if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) enabled |= 1 << i; ctx->subsys_mask &= enabled; /* * In absense of 'none', 'name=' or subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) ctx->all_ss = true; if (ctx->all_ss) { /* Mutually exclusive option 'all' + subsystem name */ if (ctx->subsys_mask) return invalfc(fc, "subsys name conflicts with all"); /* 'all' => select all the subsystems */ ctx->subsys_mask = enabled; } /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!ctx->subsys_mask && !ctx->name) return invalfc(fc, "Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) return invalfc(fc, "noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ if (ctx->subsys_mask && ctx->none) return invalfc(fc, "none used incorrectly"); return 0; } int cgroup1_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); int ret = 0; u16 added_mask, removed_mask; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = check_cgroupfs_options(fc); if (ret) goto out_unlock; if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = ctx->subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~ctx->subsys_mask; /* Don't allow flags or name to change at remount */ if ((ctx->flags ^ root->flags) || (ctx->name && strcmp(ctx->name, root->name))) { errorfc(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (!list_empty(&root->cgrp.self.children)) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (ctx->release_agent) { spin_lock(&release_agent_path_lock); strcpy(root->release_agent_path, ctx->release_agent); spin_unlock(&release_agent_path_lock); } trace_cgroup_remount(root); out_unlock: mutex_unlock(&cgroup_mutex); return ret; } struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { .rename = cgroup1_rename, .show_options = cgroup1_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; /* * The guts of cgroup1 mount - find or create cgroup_root to use. * Called with cgroup_mutex held; returns 0 on success, -E... on * error and positive - in case when the candidate is busy dying. * On success it stashes a reference to cgroup_root into given * cgroup_fs_context; that reference is *NOT* counting towards the * cgroup_root refcount. */ static int cgroup1_root_to_use(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; struct cgroup_subsys *ss; int i, ret; /* First find the desired set of subsystems */ ret = check_cgroupfs_options(fc); if (ret) return ret; /* * Destruction of cgroup root is asynchronous, so subsystems may * still be dying after the previous unmount. Let's drain the * dying subsystems. We just need to ensure that the ones * unmounted previously finish dying and don't care about new ones * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { if (!(ctx->subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) return 1; /* restart */ cgroup_put(&ss->root->cgrp); } for_each_root(root) { bool name_match = false; if (root == &cgrp_dfl_root) continue; /* * If we asked for a name then it must match. Also, if * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ if (ctx->name) { if (strcmp(ctx->name, root->name)) continue; name_match = true; } /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ if ((ctx->subsys_mask || ctx->none) && (ctx->subsys_mask != root->subsys_mask)) { if (!name_match) continue; return -EBUSY; } if (root->flags ^ ctx->flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); ctx->root = root; return 0; } /* * No such thing, create a new one. name= matching without subsys * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ if (!ctx->subsys_mask && !ctx->none) return invalfc(fc, "No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ if (ctx->ns != &init_cgroup_ns) return -EPERM; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return -ENOMEM; ctx->root = root; init_cgroup_root(ctx); ret = cgroup_setup_root(root, ctx->subsys_mask); if (ret) cgroup_free_root(root); return ret; } int cgroup1_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; /* Check if the caller has permission to mount. */ if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); ret = cgroup1_root_to_use(fc); if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) ret = 1; /* restart */ mutex_unlock(&cgroup_mutex); if (!ret) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { fc_drop_locked(fc); ret = 1; } if (unlikely(ret > 0)) { msleep(10); return restart_syscall(); } return ret; } static int __init cgroup1_wq_init(void) { /* * Used to destroy pidlists and separate to serve as flush domain. * Cap @max_active to 1 too. */ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", 0, 1); BUG_ON(!cgroup_pidlist_destroy_wq); return 0; } core_initcall(cgroup1_wq_init); static int __init cgroup_no_v1(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "all")) { cgroup_no_v1_mask = U16_MAX; continue; } if (!strcmp(token, "named")) { cgroup_no_v1_named = true; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_no_v1_mask |= 1 << i; } } return 1; } __setup("cgroup_no_v1=", cgroup_no_v1); |
| 785 650 431 349 411 1353 1352 1173 1363 30 72 381 197 940 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/buffer_head.h * * Everything to do with buffer_heads. */ #ifndef _LINUX_BUFFER_HEAD_H #define _LINUX_BUFFER_HEAD_H #include <linux/types.h> #include <linux/fs.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/wait.h> #include <linux/atomic.h> #ifdef CONFIG_BLOCK enum bh_state_bits { BH_Uptodate, /* Contains valid data */ BH_Dirty, /* Is dirty */ BH_Lock, /* Is locked */ BH_Req, /* Has been submitted for I/O */ BH_Mapped, /* Has a disk mapping */ BH_New, /* Disk mapping was newly created by get_block */ BH_Async_Read, /* Is under end_buffer_async_read I/O */ BH_Async_Write, /* Is under end_buffer_async_write I/O */ BH_Delay, /* Buffer is not yet allocated on disk */ BH_Boundary, /* Block is followed by a discontiguity */ BH_Write_EIO, /* I/O error on write */ BH_Unwritten, /* Buffer is allocated on disk but not written */ BH_Quiet, /* Buffer Error Prinks to be quiet */ BH_Meta, /* Buffer contains metadata */ BH_Prio, /* Buffer should be submitted with REQ_PRIO */ BH_Defer_Completion, /* Defer AIO completion to workqueue */ BH_PrivateStart,/* not a state bit, but the first bit available * for private allocation by other entities */ }; #define MAX_BUF_PER_PAGE (PAGE_SIZE / 512) struct page; struct buffer_head; struct address_space; typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); /* * Historically, a buffer_head was used to map a single block * within a page, and of course as the unit of I/O through the * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within * a page (via a page_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { unsigned long b_state; /* buffer state bitmap (see above) */ struct buffer_head *b_this_page;/* circular list of page's buffers */ struct page *b_page; /* the page this bh is mapped to */ sector_t b_blocknr; /* start block number */ size_t b_size; /* size of mapping */ char *b_data; /* pointer to data within the page */ struct block_device *b_bdev; bh_end_io_t *b_end_io; /* I/O completion */ void *b_private; /* reserved for b_end_io */ struct list_head b_assoc_buffers; /* associated with another mapping */ struct address_space *b_assoc_map; /* mapping this buffer is associated with */ atomic_t b_count; /* users using this buffer_head */ spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to * serialise IO completion of other * buffers in the page */ }; /* * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() * and buffer_foo() functions. * To avoid reset buffer flags that are already set, because that causes * a costly cache line transition, check the flag first. */ #define BUFFER_FNS(bit, name) \ static __always_inline void set_buffer_##name(struct buffer_head *bh) \ { \ if (!test_bit(BH_##bit, &(bh)->b_state)) \ set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline void clear_buffer_##name(struct buffer_head *bh) \ { \ clear_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int buffer_##name(const struct buffer_head *bh) \ { \ return test_bit(BH_##bit, &(bh)->b_state); \ } /* * test_set_buffer_foo() and test_clear_buffer_foo() */ #define TAS_BUFFER_FNS(bit, name) \ static __always_inline int test_set_buffer_##name(struct buffer_head *bh) \ { \ return test_and_set_bit(BH_##bit, &(bh)->b_state); \ } \ static __always_inline int test_clear_buffer_##name(struct buffer_head *bh) \ { \ return test_and_clear_bit(BH_##bit, &(bh)->b_state); \ } \ /* * Emit the buffer bitops functions. Note that there are also functions * of the form "mark_buffer_foo()". These are higher-level functions which * do something in addition to setting a b_state bit. */ BUFFER_FNS(Uptodate, uptodate) BUFFER_FNS(Dirty, dirty) TAS_BUFFER_FNS(Dirty, dirty) BUFFER_FNS(Lock, locked) BUFFER_FNS(Req, req) TAS_BUFFER_FNS(Req, req) BUFFER_FNS(Mapped, mapped) BUFFER_FNS(New, new) BUFFER_FNS(Async_Read, async_read) BUFFER_FNS(Async_Write, async_write) BUFFER_FNS(Delay, delay) BUFFER_FNS(Boundary, boundary) BUFFER_FNS(Write_EIO, write_io_error) BUFFER_FNS(Unwritten, unwritten) BUFFER_FNS(Meta, meta) BUFFER_FNS(Prio, prio) BUFFER_FNS(Defer_Completion, defer_completion) #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) /* If we *know* page->private refers to buffer_heads */ #define page_buffers(page) \ ({ \ BUG_ON(!PagePrivate(page)); \ ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback); /* * Declarations */ void mark_buffer_dirty(struct buffer_head *bh); void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); int try_to_free_buffers(struct page *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); /* Things to do with buffers at mapping->private_list */ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode); int inode_has_buffers(struct inode *); void invalidate_inode_buffers(struct inode *); int remove_inode_buffers(struct inode *inode); int sync_mapping_buffers(struct address_space *mapping); void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len); static inline void clean_bdev_bh_alias(struct buffer_head *bh) { clean_bdev_aliases(bh->b_bdev, bh->b_blocknr, 1); } void mark_buffer_async_write(struct buffer_head *bh); void __wait_on_buffer(struct buffer_head *); wait_queue_head_t *bh_waitq_head(struct buffer_head *bh); struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block, unsigned size); struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp); void __brelse(struct buffer_head *); void __bforget(struct buffer_head *); void __breadahead(struct block_device *, sector_t block, unsigned int size); void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, gfp_t gfp); struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); void invalidate_bh_lrus_cpu(void); bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); void unlock_buffer(struct buffer_head *bh); void __lock_buffer(struct buffer_head *bh); void ll_rw_block(int, int, int, struct buffer_head * bh[]); int sync_dirty_buffer(struct buffer_head *bh); int __sync_dirty_buffer(struct buffer_head *bh, int op_flags); void write_dirty_buffer(struct buffer_head *bh, int op_flags); int submit_bh(int, int, struct buffer_head *); void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); extern int buffer_heads_over_limit; /* * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block); int block_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); int block_commit_write(struct page *page, unsigned from, unsigned to); int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block); /* Convert errno to return value from ->page_mkwrite() call */ static inline vm_fault_t block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_write_begin(struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); int nobh_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); int nobh_truncate_page(struct address_space *, loff_t, get_block_t *); int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc); void buffer_init(void); /* * inline definitions */ static inline void get_bh(struct buffer_head *bh) { atomic_inc(&bh->b_count); } static inline void put_bh(struct buffer_head *bh) { smp_mb__before_atomic(); atomic_dec(&bh->b_count); } static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } static inline void bforget(struct buffer_head *bh) { if (bh) __bforget(bh); } static inline struct buffer_head * sb_bread(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_bread_unmovable(struct super_block *sb, sector_t block) { return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline void sb_breadahead(struct super_block *sb, sector_t block) { __breadahead(sb->s_bdev, block, sb->s_blocksize); } static inline void sb_breadahead_unmovable(struct super_block *sb, sector_t block) { __breadahead_gfp(sb->s_bdev, block, sb->s_blocksize, 0); } static inline struct buffer_head * sb_getblk(struct super_block *sb, sector_t block) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE); } static inline struct buffer_head * sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp) { return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp); } static inline struct buffer_head * sb_find_get_block(struct super_block *sb, sector_t block) { return __find_get_block(sb->s_bdev, block, sb->s_blocksize); } static inline void map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block) { set_buffer_mapped(bh); bh->b_bdev = sb->s_bdev; bh->b_blocknr = block; bh->b_size = sb->s_blocksize; } static inline void wait_on_buffer(struct buffer_head *bh) { might_sleep(); if (buffer_locked(bh)) __wait_on_buffer(bh); } static inline int trylock_buffer(struct buffer_head *bh) { return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state)); } static inline void lock_buffer(struct buffer_head *bh) { might_sleep(); if (!trylock_buffer(bh)) __lock_buffer(bh); } static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, 0); } static inline struct buffer_head *__getblk(struct block_device *bdev, sector_t block, unsigned size) { return __getblk_gfp(bdev, block, size, __GFP_MOVABLE); } /** * __bread() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * * Reads a specified block, and returns buffer head that contains it. * The page cache is allocated from movable area so that it can be migrated. * It returns NULL if the block was unreadable. */ static inline struct buffer_head * __bread(struct block_device *bdev, sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } extern int __set_page_dirty_buffers(struct page *page); #else /* CONFIG_BLOCK */ static inline void buffer_init(void) {} static inline int try_to_free_buffers(struct page *page) { return 1; } static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } static inline void invalidate_bh_lrus_cpu(void) {} static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; } #define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ |
| 10 11 5 13 13 13 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 | /* * net/tipc/subscr.c: TIPC network topology service * * Copyright (c) 2000-2017, Ericsson AB * Copyright (c) 2005-2007, 2010-2013, Wind River Systems * 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. */ #include "core.h" #include "name_table.h" #include "subscr.h" static void tipc_sub_send_event(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, u32 event, u32 port, u32 node) { struct tipc_event *evt = &sub->evt; if (sub->inactive) return; tipc_evt_write(evt, event, event); tipc_evt_write(evt, found_lower, found_lower); tipc_evt_write(evt, found_upper, found_upper); tipc_evt_write(evt, port.ref, port); tipc_evt_write(evt, port.node, node); tipc_topsrv_queue_evt(sub->net, sub->conid, event, evt); } /** * tipc_sub_check_overlap - test for subscription overlap with the * given values * * Returns 1 if there is overlap, otherwise 0. */ int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower, u32 found_upper) { if (found_lower < seq->lower) found_lower = seq->lower; if (found_upper > seq->upper) found_upper = seq->upper; if (found_lower > found_upper) return 0; return 1; } void tipc_sub_report_overlap(struct tipc_subscription *sub, u32 found_lower, u32 found_upper, u32 event, u32 port, u32 node, u32 scope, int must) { struct tipc_subscr *s = &sub->evt.s; u32 filter = tipc_sub_read(s, filter); struct tipc_name_seq seq; seq.type = tipc_sub_read(s, seq.type); seq.lower = tipc_sub_read(s, seq.lower); seq.upper = tipc_sub_read(s, seq.upper); if (!tipc_sub_check_overlap(&seq, found_lower, found_upper)) return; if (!must && !(filter & TIPC_SUB_PORTS)) return; if (filter & TIPC_SUB_CLUSTER_SCOPE && scope == TIPC_NODE_SCOPE) return; if (filter & TIPC_SUB_NODE_SCOPE && scope != TIPC_NODE_SCOPE) return; spin_lock(&sub->lock); tipc_sub_send_event(sub, found_lower, found_upper, event, port, node); spin_unlock(&sub->lock); } static void tipc_sub_timeout(struct timer_list *t) { struct tipc_subscription *sub = from_timer(sub, t, timer); struct tipc_subscr *s = &sub->evt.s; spin_lock(&sub->lock); tipc_sub_send_event(sub, s->seq.lower, s->seq.upper, TIPC_SUBSCR_TIMEOUT, 0, 0); sub->inactive = true; spin_unlock(&sub->lock); } static void tipc_sub_kref_release(struct kref *kref) { kfree(container_of(kref, struct tipc_subscription, kref)); } void tipc_sub_put(struct tipc_subscription *subscription) { kref_put(&subscription->kref, tipc_sub_kref_release); } void tipc_sub_get(struct tipc_subscription *subscription) { kref_get(&subscription->kref); } struct tipc_subscription *tipc_sub_subscribe(struct net *net, struct tipc_subscr *s, int conid) { u32 filter = tipc_sub_read(s, filter); struct tipc_subscription *sub; u32 timeout; if ((filter & TIPC_SUB_PORTS && filter & TIPC_SUB_SERVICE) || (tipc_sub_read(s, seq.lower) > tipc_sub_read(s, seq.upper))) { pr_warn("Subscription rejected, illegal request\n"); return NULL; } sub = kmalloc(sizeof(*sub), GFP_ATOMIC); if (!sub) { pr_warn("Subscription rejected, no memory\n"); return NULL; } INIT_LIST_HEAD(&sub->service_list); INIT_LIST_HEAD(&sub->sub_list); sub->net = net; sub->conid = conid; sub->inactive = false; memcpy(&sub->evt.s, s, sizeof(*s)); spin_lock_init(&sub->lock); kref_init(&sub->kref); if (!tipc_nametbl_subscribe(sub)) { kfree(sub); return NULL; } timer_setup(&sub->timer, tipc_sub_timeout, 0); timeout = tipc_sub_read(&sub->evt.s, timeout); if (timeout != TIPC_WAIT_FOREVER) mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout)); return sub; } void tipc_sub_unsubscribe(struct tipc_subscription *sub) { tipc_nametbl_unsubscribe(sub); if (sub->evt.s.timeout != TIPC_WAIT_FOREVER) del_timer_sync(&sub->timer); list_del(&sub->sub_list); tipc_sub_put(sub); } |
| 258 45 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 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-or-later /* * x86 instruction attribute tables * * Written by Masami Hiramatsu <mhiramat@redhat.com> */ #include <asm/insn.h> /* __ignore_sync_check__ */ /* Attribute tables are generated from opcode map */ #include "inat-tables.c" /* Attribute search APIs */ insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode) { return inat_primary_table[opcode]; } int inat_get_last_prefix_id(insn_byte_t last_pfx) { insn_attr_t lpfx_attr; lpfx_attr = inat_get_opcode_attribute(last_pfx); return inat_last_prefix_id(lpfx_attr); } insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id, insn_attr_t esc_attr) { const insn_attr_t *table; int n; n = inat_escape_id(esc_attr); table = inat_escape_tables[n][0]; if (!table) return 0; if (inat_has_variant(table[opcode]) && lpfx_id) { table = inat_escape_tables[n][lpfx_id]; if (!table) return 0; } return table[opcode]; } insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id, insn_attr_t grp_attr) { const insn_attr_t *table; int n; n = inat_group_id(grp_attr); table = inat_group_tables[n][0]; if (!table) return inat_group_common_attribute(grp_attr); if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) { table = inat_group_tables[n][lpfx_id]; if (!table) return inat_group_common_attribute(grp_attr); } return table[X86_MODRM_REG(modrm)] | inat_group_common_attribute(grp_attr); } insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m, insn_byte_t vex_p) { const insn_attr_t *table; if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX) return 0; /* At first, this checks the master table */ table = inat_avx_tables[vex_m][0]; if (!table) return 0; if (!inat_is_group(table[opcode]) && vex_p) { /* If this is not a group, get attribute directly */ table = inat_avx_tables[vex_m][vex_p]; if (!table) return 0; } return table[opcode]; } |
| 2 2 2 2 9 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "noise.h" #include "device.h" #include "peer.h" #include "messages.h" #include "queueing.h" #include "peerlookup.h" #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/bitmap.h> #include <linux/scatterlist.h> #include <linux/highmem.h> #include <crypto/algapi.h> /* This implements Noise_IKpsk2: * * <- s * ****** * -> e, es, s, ss, {t} * <- e, ee, se, psk, {} */ static const u8 handshake_name[37] = "Noise_IKpsk2_25519_ChaChaPoly_BLAKE2s"; static const u8 identifier_name[34] = "WireGuard v1 zx2c4 Jason@zx2c4.com"; static u8 handshake_init_hash[NOISE_HASH_LEN] __ro_after_init; static u8 handshake_init_chaining_key[NOISE_HASH_LEN] __ro_after_init; static atomic64_t keypair_counter = ATOMIC64_INIT(0); void __init wg_noise_init(void) { struct blake2s_state blake; blake2s(handshake_init_chaining_key, handshake_name, NULL, NOISE_HASH_LEN, sizeof(handshake_name), 0); blake2s_init(&blake, NOISE_HASH_LEN); blake2s_update(&blake, handshake_init_chaining_key, NOISE_HASH_LEN); blake2s_update(&blake, identifier_name, sizeof(identifier_name)); blake2s_final(&blake, handshake_init_hash); } /* Must hold peer->handshake.static_identity->lock */ void wg_noise_precompute_static_static(struct wg_peer *peer) { down_write(&peer->handshake.lock); if (!peer->handshake.static_identity->has_identity || !curve25519(peer->handshake.precomputed_static_static, peer->handshake.static_identity->static_private, peer->handshake.remote_static)) memset(peer->handshake.precomputed_static_static, 0, NOISE_PUBLIC_KEY_LEN); up_write(&peer->handshake.lock); } void wg_noise_handshake_init(struct noise_handshake *handshake, struct noise_static_identity *static_identity, const u8 peer_public_key[NOISE_PUBLIC_KEY_LEN], const u8 peer_preshared_key[NOISE_SYMMETRIC_KEY_LEN], struct wg_peer *peer) { memset(handshake, 0, sizeof(*handshake)); init_rwsem(&handshake->lock); handshake->entry.type = INDEX_HASHTABLE_HANDSHAKE; handshake->entry.peer = peer; memcpy(handshake->remote_static, peer_public_key, NOISE_PUBLIC_KEY_LEN); if (peer_preshared_key) memcpy(handshake->preshared_key, peer_preshared_key, NOISE_SYMMETRIC_KEY_LEN); handshake->static_identity = static_identity; handshake->state = HANDSHAKE_ZEROED; wg_noise_precompute_static_static(peer); } static void handshake_zero(struct noise_handshake *handshake) { memset(&handshake->ephemeral_private, 0, NOISE_PUBLIC_KEY_LEN); memset(&handshake->remote_ephemeral, 0, NOISE_PUBLIC_KEY_LEN); memset(&handshake->hash, 0, NOISE_HASH_LEN); memset(&handshake->chaining_key, 0, NOISE_HASH_LEN); handshake->remote_index = 0; handshake->state = HANDSHAKE_ZEROED; } void wg_noise_handshake_clear(struct noise_handshake *handshake) { down_write(&handshake->lock); wg_index_hashtable_remove( handshake->entry.peer->device->index_hashtable, &handshake->entry); handshake_zero(handshake); up_write(&handshake->lock); } static struct noise_keypair *keypair_create(struct wg_peer *peer) { struct noise_keypair *keypair = kzalloc(sizeof(*keypair), GFP_KERNEL); if (unlikely(!keypair)) return NULL; spin_lock_init(&keypair->receiving_counter.lock); keypair->internal_id = atomic64_inc_return(&keypair_counter); keypair->entry.type = INDEX_HASHTABLE_KEYPAIR; keypair->entry.peer = peer; kref_init(&keypair->refcount); return keypair; } static void keypair_free_rcu(struct rcu_head *rcu) { kfree_sensitive(container_of(rcu, struct noise_keypair, rcu)); } static void keypair_free_kref(struct kref *kref) { struct noise_keypair *keypair = container_of(kref, struct noise_keypair, refcount); net_dbg_ratelimited("%s: Keypair %llu destroyed for peer %llu\n", keypair->entry.peer->device->dev->name, keypair->internal_id, keypair->entry.peer->internal_id); wg_index_hashtable_remove(keypair->entry.peer->device->index_hashtable, &keypair->entry); call_rcu(&keypair->rcu, keypair_free_rcu); } void wg_noise_keypair_put(struct noise_keypair *keypair, bool unreference_now) { if (unlikely(!keypair)) return; if (unlikely(unreference_now)) wg_index_hashtable_remove( keypair->entry.peer->device->index_hashtable, &keypair->entry); kref_put(&keypair->refcount, keypair_free_kref); } struct noise_keypair *wg_noise_keypair_get(struct noise_keypair *keypair) { RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(), "Taking noise keypair reference without holding the RCU BH read lock"); if (unlikely(!keypair || !kref_get_unless_zero(&keypair->refcount))) return NULL; return keypair; } void wg_noise_keypairs_clear(struct noise_keypairs *keypairs) { struct noise_keypair *old; spin_lock_bh(&keypairs->keypair_update_lock); /* We zero the next_keypair before zeroing the others, so that * wg_noise_received_with_keypair returns early before subsequent ones * are zeroed. */ old = rcu_dereference_protected(keypairs->next_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); RCU_INIT_POINTER(keypairs->next_keypair, NULL); wg_noise_keypair_put(old, true); old = rcu_dereference_protected(keypairs->previous_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); RCU_INIT_POINTER(keypairs->previous_keypair, NULL); wg_noise_keypair_put(old, true); old = rcu_dereference_protected(keypairs->current_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); RCU_INIT_POINTER(keypairs->current_keypair, NULL); wg_noise_keypair_put(old, true); spin_unlock_bh(&keypairs->keypair_update_lock); } void wg_noise_expire_current_peer_keypairs(struct wg_peer *peer) { struct noise_keypair *keypair; wg_noise_handshake_clear(&peer->handshake); wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); spin_lock_bh(&peer->keypairs.keypair_update_lock); keypair = rcu_dereference_protected(peer->keypairs.next_keypair, lockdep_is_held(&peer->keypairs.keypair_update_lock)); if (keypair) keypair->sending.is_valid = false; keypair = rcu_dereference_protected(peer->keypairs.current_keypair, lockdep_is_held(&peer->keypairs.keypair_update_lock)); if (keypair) keypair->sending.is_valid = false; spin_unlock_bh(&peer->keypairs.keypair_update_lock); } static void add_new_keypair(struct noise_keypairs *keypairs, struct noise_keypair *new_keypair) { struct noise_keypair *previous_keypair, *next_keypair, *current_keypair; spin_lock_bh(&keypairs->keypair_update_lock); previous_keypair = rcu_dereference_protected(keypairs->previous_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); next_keypair = rcu_dereference_protected(keypairs->next_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); current_keypair = rcu_dereference_protected(keypairs->current_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); if (new_keypair->i_am_the_initiator) { /* If we're the initiator, it means we've sent a handshake, and * received a confirmation response, which means this new * keypair can now be used. */ if (next_keypair) { /* If there already was a next keypair pending, we * demote it to be the previous keypair, and free the * existing current. Note that this means KCI can result * in this transition. It would perhaps be more sound to * always just get rid of the unused next keypair * instead of putting it in the previous slot, but this * might be a bit less robust. Something to think about * for the future. */ RCU_INIT_POINTER(keypairs->next_keypair, NULL); rcu_assign_pointer(keypairs->previous_keypair, next_keypair); wg_noise_keypair_put(current_keypair, true); } else /* If there wasn't an existing next keypair, we replace * the previous with the current one. */ rcu_assign_pointer(keypairs->previous_keypair, current_keypair); /* At this point we can get rid of the old previous keypair, and * set up the new keypair. */ wg_noise_keypair_put(previous_keypair, true); rcu_assign_pointer(keypairs->current_keypair, new_keypair); } else { /* If we're the responder, it means we can't use the new keypair * until we receive confirmation via the first data packet, so * we get rid of the existing previous one, the possibly * existing next one, and slide in the new next one. */ rcu_assign_pointer(keypairs->next_keypair, new_keypair); wg_noise_keypair_put(next_keypair, true); RCU_INIT_POINTER(keypairs->previous_keypair, NULL); wg_noise_keypair_put(previous_keypair, true); } spin_unlock_bh(&keypairs->keypair_update_lock); } bool wg_noise_received_with_keypair(struct noise_keypairs *keypairs, struct noise_keypair *received_keypair) { struct noise_keypair *old_keypair; bool key_is_new; /* We first check without taking the spinlock. */ key_is_new = received_keypair == rcu_access_pointer(keypairs->next_keypair); if (likely(!key_is_new)) return false; spin_lock_bh(&keypairs->keypair_update_lock); /* After locking, we double check that things didn't change from * beneath us. */ if (unlikely(received_keypair != rcu_dereference_protected(keypairs->next_keypair, lockdep_is_held(&keypairs->keypair_update_lock)))) { spin_unlock_bh(&keypairs->keypair_update_lock); return false; } /* When we've finally received the confirmation, we slide the next * into the current, the current into the previous, and get rid of * the old previous. */ old_keypair = rcu_dereference_protected(keypairs->previous_keypair, lockdep_is_held(&keypairs->keypair_update_lock)); rcu_assign_pointer(keypairs->previous_keypair, rcu_dereference_protected(keypairs->current_keypair, lockdep_is_held(&keypairs->keypair_update_lock))); wg_noise_keypair_put(old_keypair, true); rcu_assign_pointer(keypairs->current_keypair, received_keypair); RCU_INIT_POINTER(keypairs->next_keypair, NULL); spin_unlock_bh(&keypairs->keypair_update_lock); return true; } /* Must hold static_identity->lock */ void wg_noise_set_static_identity_private_key( struct noise_static_identity *static_identity, const u8 private_key[NOISE_PUBLIC_KEY_LEN]) { memcpy(static_identity->static_private, private_key, NOISE_PUBLIC_KEY_LEN); curve25519_clamp_secret(static_identity->static_private); static_identity->has_identity = curve25519_generate_public( static_identity->static_public, private_key); } static void hmac(u8 *out, const u8 *in, const u8 *key, const size_t inlen, const size_t keylen) { struct blake2s_state state; u8 x_key[BLAKE2S_BLOCK_SIZE] __aligned(__alignof__(u32)) = { 0 }; u8 i_hash[BLAKE2S_HASH_SIZE] __aligned(__alignof__(u32)); int i; if (keylen > BLAKE2S_BLOCK_SIZE) { blake2s_init(&state, BLAKE2S_HASH_SIZE); blake2s_update(&state, key, keylen); blake2s_final(&state, x_key); } else memcpy(x_key, key, keylen); for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) x_key[i] ^= 0x36; blake2s_init(&state, BLAKE2S_HASH_SIZE); blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); blake2s_update(&state, in, inlen); blake2s_final(&state, i_hash); for (i = 0; i < BLAKE2S_BLOCK_SIZE; ++i) x_key[i] ^= 0x5c ^ 0x36; blake2s_init(&state, BLAKE2S_HASH_SIZE); blake2s_update(&state, x_key, BLAKE2S_BLOCK_SIZE); blake2s_update(&state, i_hash, BLAKE2S_HASH_SIZE); blake2s_final(&state, i_hash); memcpy(out, i_hash, BLAKE2S_HASH_SIZE); memzero_explicit(x_key, BLAKE2S_BLOCK_SIZE); memzero_explicit(i_hash, BLAKE2S_HASH_SIZE); } /* This is Hugo Krawczyk's HKDF: * - https://eprint.iacr.org/2010/264.pdf * - https://tools.ietf.org/html/rfc5869 */ static void kdf(u8 *first_dst, u8 *second_dst, u8 *third_dst, const u8 *data, size_t first_len, size_t second_len, size_t third_len, size_t data_len, const u8 chaining_key[NOISE_HASH_LEN]) { u8 output[BLAKE2S_HASH_SIZE + 1]; u8 secret[BLAKE2S_HASH_SIZE]; WARN_ON(IS_ENABLED(DEBUG) && (first_len > BLAKE2S_HASH_SIZE || second_len > BLAKE2S_HASH_SIZE || third_len > BLAKE2S_HASH_SIZE || ((second_len || second_dst || third_len || third_dst) && (!first_len || !first_dst)) || ((third_len || third_dst) && (!second_len || !second_dst)))); /* Extract entropy from data into secret */ hmac(secret, data, chaining_key, data_len, NOISE_HASH_LEN); if (!first_dst || !first_len) goto out; /* Expand first key: key = secret, data = 0x1 */ output[0] = 1; hmac(output, output, secret, 1, BLAKE2S_HASH_SIZE); memcpy(first_dst, output, first_len); if (!second_dst || !second_len) goto out; /* Expand second key: key = secret, data = first-key || 0x2 */ output[BLAKE2S_HASH_SIZE] = 2; hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, BLAKE2S_HASH_SIZE); memcpy(second_dst, output, second_len); if (!third_dst || !third_len) goto out; /* Expand third key: key = secret, data = second-key || 0x3 */ output[BLAKE2S_HASH_SIZE] = 3; hmac(output, output, secret, BLAKE2S_HASH_SIZE + 1, BLAKE2S_HASH_SIZE); memcpy(third_dst, output, third_len); out: /* Clear sensitive data from stack */ memzero_explicit(secret, BLAKE2S_HASH_SIZE); memzero_explicit(output, BLAKE2S_HASH_SIZE + 1); } static void derive_keys(struct noise_symmetric_key *first_dst, struct noise_symmetric_key *second_dst, const u8 chaining_key[NOISE_HASH_LEN]) { u64 birthdate = ktime_get_coarse_boottime_ns(); kdf(first_dst->key, second_dst->key, NULL, NULL, NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, 0, chaining_key); first_dst->birthdate = second_dst->birthdate = birthdate; first_dst->is_valid = second_dst->is_valid = true; } static bool __must_check mix_dh(u8 chaining_key[NOISE_HASH_LEN], u8 key[NOISE_SYMMETRIC_KEY_LEN], const u8 private[NOISE_PUBLIC_KEY_LEN], const u8 public[NOISE_PUBLIC_KEY_LEN]) { u8 dh_calculation[NOISE_PUBLIC_KEY_LEN]; if (unlikely(!curve25519(dh_calculation, private, public))) return false; kdf(chaining_key, key, NULL, dh_calculation, NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, chaining_key); memzero_explicit(dh_calculation, NOISE_PUBLIC_KEY_LEN); return true; } static bool __must_check mix_precomputed_dh(u8 chaining_key[NOISE_HASH_LEN], u8 key[NOISE_SYMMETRIC_KEY_LEN], const u8 precomputed[NOISE_PUBLIC_KEY_LEN]) { static u8 zero_point[NOISE_PUBLIC_KEY_LEN]; if (unlikely(!crypto_memneq(precomputed, zero_point, NOISE_PUBLIC_KEY_LEN))) return false; kdf(chaining_key, key, NULL, precomputed, NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, 0, NOISE_PUBLIC_KEY_LEN, chaining_key); return true; } static void mix_hash(u8 hash[NOISE_HASH_LEN], const u8 *src, size_t src_len) { struct blake2s_state blake; blake2s_init(&blake, NOISE_HASH_LEN); blake2s_update(&blake, hash, NOISE_HASH_LEN); blake2s_update(&blake, src, src_len); blake2s_final(&blake, hash); } static void mix_psk(u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN], u8 key[NOISE_SYMMETRIC_KEY_LEN], const u8 psk[NOISE_SYMMETRIC_KEY_LEN]) { u8 temp_hash[NOISE_HASH_LEN]; kdf(chaining_key, temp_hash, key, psk, NOISE_HASH_LEN, NOISE_HASH_LEN, NOISE_SYMMETRIC_KEY_LEN, NOISE_SYMMETRIC_KEY_LEN, chaining_key); mix_hash(hash, temp_hash, NOISE_HASH_LEN); memzero_explicit(temp_hash, NOISE_HASH_LEN); } static void handshake_init(u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN], const u8 remote_static[NOISE_PUBLIC_KEY_LEN]) { memcpy(hash, handshake_init_hash, NOISE_HASH_LEN); memcpy(chaining_key, handshake_init_chaining_key, NOISE_HASH_LEN); mix_hash(hash, remote_static, NOISE_PUBLIC_KEY_LEN); } static void message_encrypt(u8 *dst_ciphertext, const u8 *src_plaintext, size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN], u8 hash[NOISE_HASH_LEN]) { chacha20poly1305_encrypt(dst_ciphertext, src_plaintext, src_len, hash, NOISE_HASH_LEN, 0 /* Always zero for Noise_IK */, key); mix_hash(hash, dst_ciphertext, noise_encrypted_len(src_len)); } static bool message_decrypt(u8 *dst_plaintext, const u8 *src_ciphertext, size_t src_len, u8 key[NOISE_SYMMETRIC_KEY_LEN], u8 hash[NOISE_HASH_LEN]) { if (!chacha20poly1305_decrypt(dst_plaintext, src_ciphertext, src_len, hash, NOISE_HASH_LEN, 0 /* Always zero for Noise_IK */, key)) return false; mix_hash(hash, src_ciphertext, src_len); return true; } static void message_ephemeral(u8 ephemeral_dst[NOISE_PUBLIC_KEY_LEN], const u8 ephemeral_src[NOISE_PUBLIC_KEY_LEN], u8 chaining_key[NOISE_HASH_LEN], u8 hash[NOISE_HASH_LEN]) { if (ephemeral_dst != ephemeral_src) memcpy(ephemeral_dst, ephemeral_src, NOISE_PUBLIC_KEY_LEN); mix_hash(hash, ephemeral_src, NOISE_PUBLIC_KEY_LEN); kdf(chaining_key, NULL, NULL, ephemeral_src, NOISE_HASH_LEN, 0, 0, NOISE_PUBLIC_KEY_LEN, chaining_key); } static void tai64n_now(u8 output[NOISE_TIMESTAMP_LEN]) { struct timespec64 now; ktime_get_real_ts64(&now); /* In order to prevent some sort of infoleak from precise timers, we * round down the nanoseconds part to the closest rounded-down power of * two to the maximum initiations per second allowed anyway by the * implementation. */ now.tv_nsec = ALIGN_DOWN(now.tv_nsec, rounddown_pow_of_two(NSEC_PER_SEC / INITIATIONS_PER_SECOND)); /* https://cr.yp.to/libtai/tai64.html */ *(__be64 *)output = cpu_to_be64(0x400000000000000aULL + now.tv_sec); *(__be32 *)(output + sizeof(__be64)) = cpu_to_be32(now.tv_nsec); } bool wg_noise_handshake_create_initiation(struct message_handshake_initiation *dst, struct noise_handshake *handshake) { u8 timestamp[NOISE_TIMESTAMP_LEN]; u8 key[NOISE_SYMMETRIC_KEY_LEN]; bool ret = false; /* We need to wait for crng _before_ taking any locks, since * curve25519_generate_secret uses get_random_bytes_wait. */ wait_for_random_bytes(); down_read(&handshake->static_identity->lock); down_write(&handshake->lock); if (unlikely(!handshake->static_identity->has_identity)) goto out; dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_INITIATION); handshake_init(handshake->chaining_key, handshake->hash, handshake->remote_static); /* e */ curve25519_generate_secret(handshake->ephemeral_private); if (!curve25519_generate_public(dst->unencrypted_ephemeral, handshake->ephemeral_private)) goto out; message_ephemeral(dst->unencrypted_ephemeral, dst->unencrypted_ephemeral, handshake->chaining_key, handshake->hash); /* es */ if (!mix_dh(handshake->chaining_key, key, handshake->ephemeral_private, handshake->remote_static)) goto out; /* s */ message_encrypt(dst->encrypted_static, handshake->static_identity->static_public, NOISE_PUBLIC_KEY_LEN, key, handshake->hash); /* ss */ if (!mix_precomputed_dh(handshake->chaining_key, key, handshake->precomputed_static_static)) goto out; /* {t} */ tai64n_now(timestamp); message_encrypt(dst->encrypted_timestamp, timestamp, NOISE_TIMESTAMP_LEN, key, handshake->hash); dst->sender_index = wg_index_hashtable_insert( handshake->entry.peer->device->index_hashtable, &handshake->entry); handshake->state = HANDSHAKE_CREATED_INITIATION; ret = true; out: up_write(&handshake->lock); up_read(&handshake->static_identity->lock); memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); return ret; } struct wg_peer * wg_noise_handshake_consume_initiation(struct message_handshake_initiation *src, struct wg_device *wg) { struct wg_peer *peer = NULL, *ret_peer = NULL; struct noise_handshake *handshake; bool replay_attack, flood_attack; u8 key[NOISE_SYMMETRIC_KEY_LEN]; u8 chaining_key[NOISE_HASH_LEN]; u8 hash[NOISE_HASH_LEN]; u8 s[NOISE_PUBLIC_KEY_LEN]; u8 e[NOISE_PUBLIC_KEY_LEN]; u8 t[NOISE_TIMESTAMP_LEN]; u64 initiation_consumption; down_read(&wg->static_identity.lock); if (unlikely(!wg->static_identity.has_identity)) goto out; handshake_init(chaining_key, hash, wg->static_identity.static_public); /* e */ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash); /* es */ if (!mix_dh(chaining_key, key, wg->static_identity.static_private, e)) goto out; /* s */ if (!message_decrypt(s, src->encrypted_static, sizeof(src->encrypted_static), key, hash)) goto out; /* Lookup which peer we're actually talking to */ peer = wg_pubkey_hashtable_lookup(wg->peer_hashtable, s); if (!peer) goto out; handshake = &peer->handshake; /* ss */ if (!mix_precomputed_dh(chaining_key, key, handshake->precomputed_static_static)) goto out; /* {t} */ if (!message_decrypt(t, src->encrypted_timestamp, sizeof(src->encrypted_timestamp), key, hash)) goto out; down_read(&handshake->lock); replay_attack = memcmp(t, handshake->latest_timestamp, NOISE_TIMESTAMP_LEN) <= 0; flood_attack = (s64)handshake->last_initiation_consumption + NSEC_PER_SEC / INITIATIONS_PER_SECOND > (s64)ktime_get_coarse_boottime_ns(); up_read(&handshake->lock); if (replay_attack || flood_attack) goto out; /* Success! Copy everything to peer */ down_write(&handshake->lock); memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN); if (memcmp(t, handshake->latest_timestamp, NOISE_TIMESTAMP_LEN) > 0) memcpy(handshake->latest_timestamp, t, NOISE_TIMESTAMP_LEN); memcpy(handshake->hash, hash, NOISE_HASH_LEN); memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN); handshake->remote_index = src->sender_index; initiation_consumption = ktime_get_coarse_boottime_ns(); if ((s64)(handshake->last_initiation_consumption - initiation_consumption) < 0) handshake->last_initiation_consumption = initiation_consumption; handshake->state = HANDSHAKE_CONSUMED_INITIATION; up_write(&handshake->lock); ret_peer = peer; out: memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); memzero_explicit(hash, NOISE_HASH_LEN); memzero_explicit(chaining_key, NOISE_HASH_LEN); up_read(&wg->static_identity.lock); if (!ret_peer) wg_peer_put(peer); return ret_peer; } bool wg_noise_handshake_create_response(struct message_handshake_response *dst, struct noise_handshake *handshake) { u8 key[NOISE_SYMMETRIC_KEY_LEN]; bool ret = false; /* We need to wait for crng _before_ taking any locks, since * curve25519_generate_secret uses get_random_bytes_wait. */ wait_for_random_bytes(); down_read(&handshake->static_identity->lock); down_write(&handshake->lock); if (handshake->state != HANDSHAKE_CONSUMED_INITIATION) goto out; dst->header.type = cpu_to_le32(MESSAGE_HANDSHAKE_RESPONSE); dst->receiver_index = handshake->remote_index; /* e */ curve25519_generate_secret(handshake->ephemeral_private); if (!curve25519_generate_public(dst->unencrypted_ephemeral, handshake->ephemeral_private)) goto out; message_ephemeral(dst->unencrypted_ephemeral, dst->unencrypted_ephemeral, handshake->chaining_key, handshake->hash); /* ee */ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private, handshake->remote_ephemeral)) goto out; /* se */ if (!mix_dh(handshake->chaining_key, NULL, handshake->ephemeral_private, handshake->remote_static)) goto out; /* psk */ mix_psk(handshake->chaining_key, handshake->hash, key, handshake->preshared_key); /* {} */ message_encrypt(dst->encrypted_nothing, NULL, 0, key, handshake->hash); dst->sender_index = wg_index_hashtable_insert( handshake->entry.peer->device->index_hashtable, &handshake->entry); handshake->state = HANDSHAKE_CREATED_RESPONSE; ret = true; out: up_write(&handshake->lock); up_read(&handshake->static_identity->lock); memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); return ret; } struct wg_peer * wg_noise_handshake_consume_response(struct message_handshake_response *src, struct wg_device *wg) { enum noise_handshake_state state = HANDSHAKE_ZEROED; struct wg_peer *peer = NULL, *ret_peer = NULL; struct noise_handshake *handshake; u8 key[NOISE_SYMMETRIC_KEY_LEN]; u8 hash[NOISE_HASH_LEN]; u8 chaining_key[NOISE_HASH_LEN]; u8 e[NOISE_PUBLIC_KEY_LEN]; u8 ephemeral_private[NOISE_PUBLIC_KEY_LEN]; u8 static_private[NOISE_PUBLIC_KEY_LEN]; u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]; down_read(&wg->static_identity.lock); if (unlikely(!wg->static_identity.has_identity)) goto out; handshake = (struct noise_handshake *)wg_index_hashtable_lookup( wg->index_hashtable, INDEX_HASHTABLE_HANDSHAKE, src->receiver_index, &peer); if (unlikely(!handshake)) goto out; down_read(&handshake->lock); state = handshake->state; memcpy(hash, handshake->hash, NOISE_HASH_LEN); memcpy(chaining_key, handshake->chaining_key, NOISE_HASH_LEN); memcpy(ephemeral_private, handshake->ephemeral_private, NOISE_PUBLIC_KEY_LEN); memcpy(preshared_key, handshake->preshared_key, NOISE_SYMMETRIC_KEY_LEN); up_read(&handshake->lock); if (state != HANDSHAKE_CREATED_INITIATION) goto fail; /* e */ message_ephemeral(e, src->unencrypted_ephemeral, chaining_key, hash); /* ee */ if (!mix_dh(chaining_key, NULL, ephemeral_private, e)) goto fail; /* se */ if (!mix_dh(chaining_key, NULL, wg->static_identity.static_private, e)) goto fail; /* psk */ mix_psk(chaining_key, hash, key, preshared_key); /* {} */ if (!message_decrypt(NULL, src->encrypted_nothing, sizeof(src->encrypted_nothing), key, hash)) goto fail; /* Success! Copy everything to peer */ down_write(&handshake->lock); /* It's important to check that the state is still the same, while we * have an exclusive lock. */ if (handshake->state != state) { up_write(&handshake->lock); goto fail; } memcpy(handshake->remote_ephemeral, e, NOISE_PUBLIC_KEY_LEN); memcpy(handshake->hash, hash, NOISE_HASH_LEN); memcpy(handshake->chaining_key, chaining_key, NOISE_HASH_LEN); handshake->remote_index = src->sender_index; handshake->state = HANDSHAKE_CONSUMED_RESPONSE; up_write(&handshake->lock); ret_peer = peer; goto out; fail: wg_peer_put(peer); out: memzero_explicit(key, NOISE_SYMMETRIC_KEY_LEN); memzero_explicit(hash, NOISE_HASH_LEN); memzero_explicit(chaining_key, NOISE_HASH_LEN); memzero_explicit(ephemeral_private, NOISE_PUBLIC_KEY_LEN); memzero_explicit(static_private, NOISE_PUBLIC_KEY_LEN); memzero_explicit(preshared_key, NOISE_SYMMETRIC_KEY_LEN); up_read(&wg->static_identity.lock); return ret_peer; } bool wg_noise_handshake_begin_session(struct noise_handshake *handshake, struct noise_keypairs *keypairs) { struct noise_keypair *new_keypair; bool ret = false; down_write(&handshake->lock); if (handshake->state != HANDSHAKE_CREATED_RESPONSE && handshake->state != HANDSHAKE_CONSUMED_RESPONSE) goto out; new_keypair = keypair_create(handshake->entry.peer); if (!new_keypair) goto out; new_keypair->i_am_the_initiator = handshake->state == HANDSHAKE_CONSUMED_RESPONSE; new_keypair->remote_index = handshake->remote_index; if (new_keypair->i_am_the_initiator) derive_keys(&new_keypair->sending, &new_keypair->receiving, handshake->chaining_key); else derive_keys(&new_keypair->receiving, &new_keypair->sending, handshake->chaining_key); handshake_zero(handshake); rcu_read_lock_bh(); if (likely(!READ_ONCE(container_of(handshake, struct wg_peer, handshake)->is_dead))) { add_new_keypair(keypairs, new_keypair); net_dbg_ratelimited("%s: Keypair %llu created for peer %llu\n", handshake->entry.peer->device->dev->name, new_keypair->internal_id, handshake->entry.peer->internal_id); ret = wg_index_hashtable_replace( handshake->entry.peer->device->index_hashtable, &handshake->entry, &new_keypair->entry); } else { kfree_sensitive(new_keypair); } rcu_read_unlock_bh(); out: up_write(&handshake->lock); return ret; } |
| 3 4 4 3 6 2 2 5 13 32 38 4 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 | // SPDX-License-Identifier: GPL-2.0-only /* * Minimal file system backend for holding eBPF maps and programs, * used by bpf(2) object pinning. * * Authors: * * Daniel Borkmann <daniel@iogearbox.net> */ #include <linux/init.h> #include <linux/magic.h> #include <linux/major.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/kdev_t.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include "preload/bpf_preload.h" enum bpf_type { BPF_TYPE_UNSPEC = 0, BPF_TYPE_PROG, BPF_TYPE_MAP, BPF_TYPE_LINK, }; static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: bpf_prog_inc(raw); break; case BPF_TYPE_MAP: bpf_map_inc_with_uref(raw); break; case BPF_TYPE_LINK: bpf_link_inc(raw); break; default: WARN_ON_ONCE(1); break; } return raw; } static void bpf_any_put(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: bpf_prog_put(raw); break; case BPF_TYPE_MAP: bpf_map_put_with_uref(raw); break; case BPF_TYPE_LINK: bpf_link_put(raw); break; default: WARN_ON_ONCE(1); break; } } static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) { void *raw; raw = bpf_map_get_with_uref(ufd); if (!IS_ERR(raw)) { *type = BPF_TYPE_MAP; return raw; } raw = bpf_prog_get(ufd); if (!IS_ERR(raw)) { *type = BPF_TYPE_PROG; return raw; } raw = bpf_link_get_from_fd(ufd); if (!IS_ERR(raw)) { *type = BPF_TYPE_LINK; return raw; } return ERR_PTR(-EINVAL); } static const struct inode_operations bpf_dir_iops; static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; static struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode) { struct inode *inode; switch (mode & S_IFMT) { case S_IFDIR: case S_IFREG: case S_IFLNK: break; default: return ERR_PTR(-EINVAL); } inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOSPC); inode->i_ino = get_next_ino(); inode->i_atime = current_time(inode); inode->i_mtime = inode->i_atime; inode->i_ctime = inode->i_atime; inode_init_owner(inode, dir, mode); return inode; } static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) { *type = BPF_TYPE_UNSPEC; if (inode->i_op == &bpf_prog_iops) *type = BPF_TYPE_PROG; else if (inode->i_op == &bpf_map_iops) *type = BPF_TYPE_MAP; else if (inode->i_op == &bpf_link_iops) *type = BPF_TYPE_LINK; else return -EACCES; return 0; } static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, struct inode *dir) { d_instantiate(dentry, inode); dget(dentry); dir->i_mtime = current_time(dir); dir->i_ctime = dir->i_mtime; } static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &bpf_dir_iops; inode->i_fop = &simple_dir_operations; inc_nlink(inode); inc_nlink(dir); bpf_dentry_finalize(dentry, inode, dir); return 0; } struct map_iter { void *key; bool done; }; static struct map_iter *map_iter(struct seq_file *m) { return m->private; } static struct bpf_map *seq_file_to_map(struct seq_file *m) { return file_inode(m->file)->i_private; } static void map_iter_free(struct map_iter *iter) { if (iter) { kfree(iter->key); kfree(iter); } } static struct map_iter *map_iter_alloc(struct bpf_map *map) { struct map_iter *iter; iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN); if (!iter) goto error; iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN); if (!iter->key) goto error; return iter; error: map_iter_free(iter); return NULL; } static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct bpf_map *map = seq_file_to_map(m); void *key = map_iter(m)->key; void *prev_key; (*pos)++; if (map_iter(m)->done) return NULL; if (unlikely(v == SEQ_START_TOKEN)) prev_key = NULL; else prev_key = key; rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; key = NULL; } rcu_read_unlock(); return key; } static void *map_seq_start(struct seq_file *m, loff_t *pos) { if (map_iter(m)->done) return NULL; return *pos ? map_iter(m)->key : SEQ_START_TOKEN; } static void map_seq_stop(struct seq_file *m, void *v) { } static int map_seq_show(struct seq_file *m, void *v) { struct bpf_map *map = seq_file_to_map(m); void *key = map_iter(m)->key; if (unlikely(v == SEQ_START_TOKEN)) { seq_puts(m, "# WARNING!! The output is for debug purpose only\n"); seq_puts(m, "# WARNING!! The output format will change\n"); } else { map->ops->map_seq_show_elem(map, key, m); } return 0; } static const struct seq_operations bpffs_map_seq_ops = { .start = map_seq_start, .next = map_seq_next, .show = map_seq_show, .stop = map_seq_stop, }; static int bpffs_map_open(struct inode *inode, struct file *file) { struct bpf_map *map = inode->i_private; struct map_iter *iter; struct seq_file *m; int err; iter = map_iter_alloc(map); if (!iter) return -ENOMEM; err = seq_open(file, &bpffs_map_seq_ops); if (err) { map_iter_free(iter); return err; } m = file->private_data; m->private = iter; return 0; } static int bpffs_map_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; map_iter_free(map_iter(m)); return seq_release(inode, file); } /* bpffs_map_fops should only implement the basic * read operation for a BPF map. The purpose is to * provide a simple user intuitive way to do * "cat bpffs/pathto/a-pinned-map". * * Other operations (e.g. write, lookup...) should be realized by * the userspace tools (e.g. bpftool) through the * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update * interface. */ static const struct file_operations bpffs_map_fops = { .open = bpffs_map_open, .read = seq_read, .release = bpffs_map_release, }; static int bpffs_obj_open(struct inode *inode, struct file *file) { return -EIO; } static const struct file_operations bpffs_obj_fops = { .open = bpffs_obj_open, }; static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, const struct inode_operations *iops, const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = iops; inode->i_fop = fops; inode->i_private = raw; bpf_dentry_finalize(dentry, inode, dir); return 0; } static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) { return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, &bpffs_obj_fops); } static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) { struct bpf_map *map = arg; return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, bpf_map_support_seq_show(map) ? &bpffs_map_fops : &bpffs_obj_fops); } static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg) { struct bpf_link *link = arg; return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops, bpf_link_is_iter(link) ? &bpf_iter_fops : &bpffs_obj_fops); } static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { /* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future * extensions. That allows popoulate_bpffs() create special files. */ if ((dir->i_mode & S_IALLUGO) && strchr(dentry->d_name.name, '.')) return ERR_PTR(-EPERM); return simple_lookup(dir, dentry, flags); } static int bpf_symlink(struct inode *dir, struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); struct inode *inode; if (!link) return -ENOMEM; inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK); if (IS_ERR(inode)) { kfree(link); return PTR_ERR(inode); } inode->i_op = &simple_symlink_inode_operations; inode->i_link = link; bpf_dentry_finalize(dentry, inode, dir); return 0; } static const struct inode_operations bpf_dir_iops = { .lookup = bpf_lookup, .mkdir = bpf_mkdir, .symlink = bpf_symlink, .rmdir = simple_rmdir, .rename = simple_rename, .link = simple_link, .unlink = simple_unlink, }; /* pin iterator link into bpffs */ static int bpf_iter_link_pin_kernel(struct dentry *parent, const char *name, struct bpf_link *link) { umode_t mode = S_IFREG | S_IRUSR; struct dentry *dentry; int ret; inode_lock(parent->d_inode); dentry = lookup_one_len(name, parent, strlen(name)); if (IS_ERR(dentry)) { inode_unlock(parent->d_inode); return PTR_ERR(dentry); } ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops, &bpf_iter_fops); dput(dentry); inode_unlock(parent->d_inode); return ret; } static int bpf_obj_do_pin(const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; struct inode *dir; struct path path; umode_t mode; int ret; dentry = user_path_create(AT_FDCWD, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); ret = security_path_mknod(&path, dentry, mode, 0); if (ret) goto out; dir = d_inode(path.dentry); if (dir->i_op != &bpf_dir_iops) { ret = -EPERM; goto out; } switch (type) { case BPF_TYPE_PROG: ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw); break; case BPF_TYPE_MAP: ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw); break; case BPF_TYPE_LINK: ret = vfs_mkobj(dentry, mode, bpf_mklink, raw); break; default: ret = -EPERM; } out: done_path_create(&path, dentry); return ret; } int bpf_obj_pin_user(u32 ufd, const char __user *pathname) { enum bpf_type type; void *raw; int ret; raw = bpf_fd_probe_obj(ufd, &type); if (IS_ERR(raw)) return PTR_ERR(raw); ret = bpf_obj_do_pin(pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); return ret; } static void *bpf_obj_do_get(const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; struct path path; void *raw; int ret; ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); inode = d_backing_inode(path.dentry); ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; ret = bpf_inode_type(inode, type); if (ret) goto out; raw = bpf_any_get(inode->i_private, *type); if (!IS_ERR(raw)) touch_atime(&path); path_put(&path); return raw; out: path_put(&path); return ERR_PTR(ret); } int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; int f_flags; void *raw; int ret; f_flags = bpf_get_file_flag(flags); if (f_flags < 0) return f_flags; raw = bpf_obj_do_get(pathname, &type, f_flags); if (IS_ERR(raw)) return PTR_ERR(raw); if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else if (type == BPF_TYPE_LINK) ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw); else return -ENOENT; if (ret < 0) bpf_any_put(raw, type); return ret; } static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; int ret = inode_permission(inode, MAY_READ); if (ret) return ERR_PTR(ret); if (inode->i_op == &bpf_map_iops) return ERR_PTR(-EINVAL); if (inode->i_op == &bpf_link_iops) return ERR_PTR(-EINVAL); if (inode->i_op != &bpf_prog_iops) return ERR_PTR(-EACCES); prog = inode->i_private; ret = security_bpf_prog(prog); if (ret < 0) return ERR_PTR(ret); if (!bpf_prog_get_ok(prog, &type, false)) return ERR_PTR(-EINVAL); bpf_prog_inc(prog); return prog; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { struct bpf_prog *prog; struct path path; int ret = kern_path(name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); prog = __get_prog_inode(d_backing_inode(path.dentry), type); if (!IS_ERR(prog)) touch_atime(&path); path_put(&path); return prog; } EXPORT_SYMBOL(bpf_prog_get_type_path); /* * Display the mount options in /proc/mounts. */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); return 0; } static void bpf_free_inode(struct inode *inode) { enum bpf_type type; if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); if (!bpf_inode_type(inode, &type)) bpf_any_put(inode->i_private, type); free_inode_nonrcu(inode); } static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, .free_inode = bpf_free_inode, }; enum { OPT_MODE, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32oct ("mode", OPT_MODE), {} }; struct bpf_mount_opts { umode_t mode; }; static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct bpf_mount_opts *opts = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ return opt == -ENOPARAM ? 0 : opt; switch (opt) { case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; } return 0; } struct bpf_preload_ops *bpf_preload_ops; EXPORT_SYMBOL_GPL(bpf_preload_ops); static bool bpf_preload_mod_get(void) { /* If bpf_preload.ko wasn't loaded earlier then load it now. * When bpf_preload is built into vmlinux the module's __init * function will populate it. */ if (!bpf_preload_ops) { request_module("bpf_preload"); if (!bpf_preload_ops) return false; } /* And grab the reference, so the module doesn't disappear while the * kernel is interacting with the kernel module and its UMD. */ if (!try_module_get(bpf_preload_ops->owner)) { pr_err("bpf_preload module get failed.\n"); return false; } return true; } static void bpf_preload_mod_put(void) { if (bpf_preload_ops) /* now user can "rmmod bpf_preload" if necessary */ module_put(bpf_preload_ops->owner); } static DEFINE_MUTEX(bpf_preload_lock); static int populate_bpffs(struct dentry *parent) { struct bpf_preload_info objs[BPF_PRELOAD_LINKS] = {}; struct bpf_link *links[BPF_PRELOAD_LINKS] = {}; int err = 0, i; /* grab the mutex to make sure the kernel interactions with bpf_preload * UMD are serialized */ mutex_lock(&bpf_preload_lock); /* if bpf_preload.ko wasn't built into vmlinux then load it */ if (!bpf_preload_mod_get()) goto out; if (!bpf_preload_ops->info.tgid) { /* preload() will start UMD that will load BPF iterator programs */ err = bpf_preload_ops->preload(objs); if (err) goto out_put; for (i = 0; i < BPF_PRELOAD_LINKS; i++) { links[i] = bpf_link_by_id(objs[i].link_id); if (IS_ERR(links[i])) { err = PTR_ERR(links[i]); goto out_put; } } for (i = 0; i < BPF_PRELOAD_LINKS; i++) { err = bpf_iter_link_pin_kernel(parent, objs[i].link_name, links[i]); if (err) goto out_put; /* do not unlink successfully pinned links even * if later link fails to pin */ links[i] = NULL; } /* finish() will tell UMD process to exit */ err = bpf_preload_ops->finish(); if (err) goto out_put; } out_put: bpf_preload_mod_put(); out: mutex_unlock(&bpf_preload_lock); for (i = 0; i < BPF_PRELOAD_LINKS && err; i++) if (!IS_ERR_OR_NULL(links[i])) bpf_link_put(links[i]); return err; } static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; struct bpf_mount_opts *opts = fc->fs_private; struct inode *inode; int ret; ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); inode->i_mode |= S_ISVTX | opts->mode; return 0; } static int bpf_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, bpf_fill_super); } static void bpf_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations bpf_context_ops = { .free = bpf_free_fc, .parse_param = bpf_parse_param, .get_tree = bpf_get_tree, }; /* * Set up the filesystem mount context. */ static int bpf_init_fs_context(struct fs_context *fc) { struct bpf_mount_opts *opts; opts = kzalloc(sizeof(struct bpf_mount_opts), GFP_KERNEL); if (!opts) return -ENOMEM; opts->mode = S_IRWXUGO; fc->fs_private = opts; fc->ops = &bpf_context_ops; return 0; } static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, .kill_sb = kill_litter_super, }; static int __init bpf_init(void) { int ret; mutex_init(&bpf_preload_lock); ret = sysfs_create_mount_point(fs_kobj, "bpf"); if (ret) return ret; ret = register_filesystem(&bpf_fs_type); if (ret) sysfs_remove_mount_point(fs_kobj, "bpf"); return ret; } fs_initcall(bpf_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNWIND_H #define _ASM_X86_UNWIND_H #include <linux/sched.h> #include <linux/ftrace.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> #define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) #define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; struct task_struct *task; int graph_idx; bool error; #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; /* * If non-NULL: The current frame is incomplete and doesn't contain a * valid BP. When looking for the next frame, use this instead of the * non-existent saved BP. */ unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; #endif }; void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame); bool unwind_next_frame(struct unwind_state *state); unsigned long unwind_get_return_address(struct unwind_state *state); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state); static inline bool unwind_done(struct unwind_state *state) { return state->stack_info.type == STACK_TYPE_UNKNOWN; } static inline bool unwind_error(struct unwind_state *state) { return state->error; } static inline void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { first_frame = first_frame ? : get_stack_pointer(task, regs); __unwind_start(state, task, regs, first_frame); } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) /* * If 'partial' returns true, only the iret frame registers are valid. */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { if (unwind_done(state)) return NULL; if (partial) { #ifdef CONFIG_UNWINDER_ORC *partial = !state->full_regs; #else *partial = false; #endif } return state->regs; } #else static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { return NULL; } #endif #ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); #else static inline void unwind_init(void) {} static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {} #endif /* * This disables KASAN checking when reading a value from another task's stack, * since the other task could be running on another CPU and could have poisoned * the stack in the meantime. */ #define READ_ONCE_TASK_STACK(task, x) \ ({ \ unsigned long val; \ if (task == current) \ val = READ_ONCE(x); \ else \ val = READ_ONCE_NOCHECK(x); \ val; \ }) static inline bool task_on_another_cpu(struct task_struct *task) { #ifdef CONFIG_SMP return task != current && task->on_cpu; #else return false; #endif } #endif /* _ASM_X86_UNWIND_H */ |
| 2 2 819 961 167 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | // SPDX-License-Identifier: GPL-2.0-only /* -*- linux-c -*- * sysctl_net.c: sysctl interface to net subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net directories for each protocol family. [MS] * * Revision 1.2 1996/05/08 20:24:40 shaver * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and * NET_IPV4_IP_FORWARD. * * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/sysctl.h> #include <linux/nsproxy.h> #include <net/sock.h> #ifdef CONFIG_INET #include <net/ip.h> #endif #ifdef CONFIG_NET #include <linux/if_ether.h> #endif static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->net_ns->sysctls; } static int is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->net_ns->sysctls == set; } /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); /* Allow network administrator to have same access as root. */ if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } return table->mode; } static void net_ctl_set_ownership(struct ctl_table_header *head, struct ctl_table *table, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(net->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); return 0; } static void __net_exit sysctl_net_exit(struct net *net) { retire_sysctl_set(&net->sysctls); } static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, }; static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; /* Avoid limitations in the sysctl implementation by * registering "/proc/sys/net" as an empty directory not in a * network namespace. */ net_header = register_sysctl("net", empty); if (!net_header) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; out: return ret; out1: unregister_sysctl_table(net_header); net_header = NULL; goto out; } struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { return __register_sysctl_table(&net->sysctls, path, table); } EXPORT_SYMBOL_GPL(register_net_sysctl); void unregister_net_sysctl_table(struct ctl_table_header *header) { unregister_sysctl_table(header); } EXPORT_SYMBOL_GPL(unregister_net_sysctl_table); |
| 1519 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Percpu refcounts: * (C) 2012 Google, Inc. * Author: Kent Overstreet <koverstreet@google.com> * * This implements a refcount with similar semantics to atomic_t - atomic_inc(), * atomic_dec_and_test() - but percpu. * * There's one important difference between percpu refs and normal atomic_t * refcounts; you have to keep track of your initial refcount, and then when you * start shutting down you call percpu_ref_kill() _before_ dropping the initial * refcount. * * The refcount will have a range of 0 to ((1U << 31) - 1), i.e. one bit less * than an atomic_t - this is because of the way shutdown works, see * percpu_ref_kill()/PERCPU_COUNT_BIAS. * * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill() * puts the ref back in single atomic_t mode, collecting the per cpu refs and * issuing the appropriate barriers, and then marks the ref as shutting down so * that percpu_ref_put() will check for the ref hitting 0. After it returns, * it's safe to drop the initial ref. * * USAGE: * * See fs/aio.c for some example usage; it's used there for struct kioctx, which * is created when userspaces calls io_setup(), and destroyed when userspace * calls io_destroy() or the process exits. * * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it * removes the kioctx from the proccess's table of kioctxs and kills percpu_ref. * After that, there can't be any new users of the kioctx (from lookup_ioctx()) * and it's then safe to drop the initial ref with percpu_ref_put(). * * Note that the free path, free_ioctx(), needs to go through explicit call_rcu() * to synchronize with RCU protected lookup_ioctx(). percpu_ref operations don't * imply RCU grace periods of any kind and if a user wants to combine percpu_ref * with RCU protection, it must be done explicitly. * * Code that does a two stage shutdown like this often needs some kind of * explicit synchronization to ensure the initial refcount can only be dropped * once - percpu_ref_kill() does this for you, it returns true once and false if * someone else already called it. The aio code uses it this way, but it's not * necessary if the code has some other mechanism to synchronize teardown. * around. */ #ifndef _LINUX_PERCPU_REFCOUNT_H #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/gfp.h> struct percpu_ref; typedef void (percpu_ref_func_t)(struct percpu_ref *); /* flags set in the lower bits of percpu_ref->percpu_count_ptr */ enum { __PERCPU_REF_ATOMIC = 1LU << 0, /* operating in atomic mode */ __PERCPU_REF_DEAD = 1LU << 1, /* (being) killed */ __PERCPU_REF_ATOMIC_DEAD = __PERCPU_REF_ATOMIC | __PERCPU_REF_DEAD, __PERCPU_REF_FLAG_BITS = 2, }; /* @flags for percpu_ref_init() */ enum { /* * Start w/ ref == 1 in atomic mode. Can be switched to percpu * operation using percpu_ref_switch_to_percpu(). If initialized * with this flag, the ref will stay in atomic mode until * percpu_ref_switch_to_percpu() is invoked on it. * Implies ALLOW_REINIT. */ PERCPU_REF_INIT_ATOMIC = 1 << 0, /* * Start dead w/ ref == 0 in atomic mode. Must be revived with * percpu_ref_reinit() before used. Implies INIT_ATOMIC and * ALLOW_REINIT. */ PERCPU_REF_INIT_DEAD = 1 << 1, /* * Allow switching from atomic mode to percpu mode. */ PERCPU_REF_ALLOW_REINIT = 1 << 2, }; struct percpu_ref_data { atomic_long_t count; percpu_ref_func_t *release; percpu_ref_func_t *confirm_switch; bool force_atomic:1; bool allow_reinit:1; struct rcu_head rcu; struct percpu_ref *ref; }; struct percpu_ref { /* * The low bit of the pointer indicates whether the ref is in percpu * mode; if set, then get/put will manipulate the atomic_t. */ unsigned long percpu_count_ptr; /* * 'percpu_ref' is often embedded into user structure, and only * 'percpu_count_ptr' is required in fast path, move other fields * into 'percpu_ref_data', so we can reduce memory footprint in * fast path. */ struct percpu_ref_data *data; }; int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp); void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch); void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref); void percpu_ref_switch_to_percpu(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); void percpu_ref_resurrect(struct percpu_ref *ref); void percpu_ref_reinit(struct percpu_ref *ref); bool percpu_ref_is_zero(struct percpu_ref *ref); /** * percpu_ref_kill - drop the initial ref * @ref: percpu_ref to kill * * Must be used to drop the initial ref on a percpu refcount; must be called * precisely once before shutdown. * * Switches @ref into atomic mode before gathering up the percpu counters * and dropping the initial ref. * * There are no implied RCU grace periods between kill and release. */ static inline void percpu_ref_kill(struct percpu_ref *ref) { percpu_ref_kill_and_confirm(ref, NULL); } /* * Internal helper. Don't use outside percpu-refcount proper. The * function doesn't return the pointer and let the caller test it for NULL * because doing so forces the compiler to generate two conditional * branches as it can't assume that @ref->percpu_count is not NULL. */ static inline bool __ref_is_percpu(struct percpu_ref *ref, unsigned long __percpu **percpu_countp) { unsigned long percpu_ptr; /* * The value of @ref->percpu_count_ptr is tested for * !__PERCPU_REF_ATOMIC, which may be set asynchronously, and then * used as a pointer. If the compiler generates a separate fetch * when using it as a pointer, __PERCPU_REF_ATOMIC may be set in * between contaminating the pointer value, meaning that * READ_ONCE() is required when fetching it. * * The dependency ordering from the READ_ONCE() pairs * with smp_store_release() in __percpu_ref_switch_to_percpu(). */ percpu_ptr = READ_ONCE(ref->percpu_count_ptr); /* * Theoretically, the following could test just ATOMIC; however, * then we'd have to mask off DEAD separately as DEAD may be * visible without ATOMIC if we race with percpu_ref_kill(). DEAD * implies ATOMIC anyway. Test them together. */ if (unlikely(percpu_ptr & __PERCPU_REF_ATOMIC_DEAD)) return false; *percpu_countp = (unsigned long __percpu *)percpu_ptr; return true; } /** * percpu_ref_get_many - increment a percpu refcount * @ref: percpu_ref to get * @nr: number of references to get * * Analogous to atomic_long_add(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_add(*percpu_count, nr); else atomic_long_add(nr, &ref->data->count); rcu_read_unlock(); } /** * percpu_ref_get - increment a percpu refcount * @ref: percpu_ref to get * * Analagous to atomic_long_inc(). * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_get(struct percpu_ref *ref) { percpu_ref_get_many(ref, 1); } /** * percpu_ref_tryget_many - try to increment a percpu refcount * @ref: percpu_ref to try-get * @nr: number of references to get * * Increment a percpu refcount by @nr unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; bool ret; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_add(*percpu_count, nr); ret = true; } else { ret = atomic_long_add_unless(&ref->data->count, nr, 0); } rcu_read_unlock(); return ret; } /** * percpu_ref_tryget - try to increment a percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless its count already reached zero. * Returns %true on success; %false on failure. * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget(struct percpu_ref *ref) { return percpu_ref_tryget_many(ref, 1); } /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get * * Increment a percpu refcount unless it has already been killed. Returns * %true on success; %false on failure. * * Completion of percpu_ref_kill() in itself doesn't guarantee that this * function will fail. For such guarantee, percpu_ref_kill_and_confirm() * should be used. After the confirm_kill callback is invoked, it's * guaranteed that no new reference will be given out by * percpu_ref_tryget_live(). * * This function is safe to call as long as @ref is between init and exit. */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; bool ret = false; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) { this_cpu_inc(*percpu_count); ret = true; } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { ret = atomic_long_inc_not_zero(&ref->data->count); } rcu_read_unlock(); return ret; } /** * percpu_ref_put_many - decrement a percpu refcount * @ref: percpu_ref to put * @nr: number of references to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr) { unsigned long __percpu *percpu_count; rcu_read_lock(); if (__ref_is_percpu(ref, &percpu_count)) this_cpu_sub(*percpu_count, nr); else if (unlikely(atomic_long_sub_and_test(nr, &ref->data->count))) ref->data->release(ref); rcu_read_unlock(); } /** * percpu_ref_put - decrement a percpu refcount * @ref: percpu_ref to put * * Decrement the refcount, and if 0, call the release function (which was passed * to percpu_ref_init()) * * This function is safe to call as long as @ref is between init and exit. */ static inline void percpu_ref_put(struct percpu_ref *ref) { percpu_ref_put_many(ref, 1); } /** * percpu_ref_is_dying - test whether a percpu refcount is dying or dead * @ref: percpu_ref to test * * Returns %true if @ref is dying or dead. * * This function is safe to call as long as @ref is between init and exit * and the caller is responsible for synchronizing against state changes. */ static inline bool percpu_ref_is_dying(struct percpu_ref *ref) { return ref->percpu_count_ptr & __PERCPU_REF_DEAD; } #endif |
| 49 860 860 838 852 159 159 159 158 37 37 37 37 3 12 15 15 15 212 210 4 210 210 208 212 212 212 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 | // 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); void static_key_slow_inc_cpuslocked(struct static_key *key) { int v, v1; STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc() 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. * * So give a special meaning to negative key->enabled: it sends * static_key_slow_inc() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). Note that * atomic_inc_unless_negative() checks >= 0, so roll our own. */ for (v = atomic_read(&key->enabled); v > 0; v = v1) { v1 = atomic_cmpxchg(&key->enabled, v, v + 1); if (likely(v1 == v)) return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * Ensure that if the above cmpxchg loop observes our positive * value, it must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { atomic_inc(&key->enabled); } jump_label_unlock(); } void static_key_slow_inc(struct static_key *key) { cpus_read_lock(); static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); } 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)) 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_slow_try_dec(struct static_key *key) { int val; val = atomic_fetch_add_unless(&key->enabled, -1, 1); if (val == 1) return false; /* * The negative count check is valid even when a negative * key->enabled is in use by static_key_slow_inc(); a * __static_key_slow_dec() before the first static_key_slow_inc() * returns is unbalanced, because all other static_key_slow_inc() * instances block while the update is in progress. */ WARN(val < 0, "jump label: negative count!\n"); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); if (static_key_slow_try_dec(key)) return; jump_label_lock(); if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); jump_label_unlock(); } 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_slow_try_dec(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_LABEL_NOP_SIZE > (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; } /* * Update code which is definitely not currently executing. * Architectures which need heavyweight synchronization to modify * running code can override this to make the non-live update case * cheaper. */ void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { arch_jump_label_transform(entry, type); } 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; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); if (init_section_contains((void *)jump_entry_code(iter), 1)) jump_entry_set_init(iter); 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(); } #ifdef CONFIG_MODULES static 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); } } /*** * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop() * @mod: module to patch * * Allow for run-time selection of the optimal nops. Before the module * loads patch these with arch_get_jump_label_nop(), which is specified by * the arch specific jump label code. */ void jump_label_apply_nops(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; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return; for (iter = iter_start; iter < iter_stop; iter++) { /* Only write NOPs for arch_branch_static(). */ if (jump_label_init_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); } } 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; if (within_module_init(jump_entry_code(iter), mod)) jump_entry_set_init(iter); 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; } 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 */ 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 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; 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; 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, system_state < SYSTEM_RUNNING); } #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 */ |
| 13 92 639 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Tracing hooks * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This file defines hook entry points called by core code where * user tracing/debugging support might need to do something. These * entry points are called tracehook_*(). Each hook declared below * has a detailed kerneldoc comment giving the context (locking et * al) from which it is called, and the meaning of its return value. * * Each function here typically has only one call site, so it is ok * to have some nontrivial tracehook_*() inlines. In all cases, the * fast path when no tracing is enabled should be very short. * * The purpose of this file and the tracehook_* layer is to consolidate * the interface that the kernel core and arch code uses to enable any * user debugging or tracing facility (such as ptrace). The interfaces * here are carefully documented so that maintainers of core and arch * code do not need to think about the implementation details of the * tracing facilities. Likewise, maintainers of the tracing code do not * need to understand all the calling core or arch code in detail, just * documented circumstances of each call, such as locking conditions. * * If the calling core code changes so that locking is different, then * it is ok to change the interface documented here. The maintainer of * core code changing should notify the maintainers of the tracing code * that they need to work out the change. * * Some tracehook_*() inlines take arguments that the current tracing * implementations might not necessarily use. These function signatures * are chosen to pass in all the information that is on hand in the * caller and might conceivably be relevant to a tracer, so that the * core code won't have to be updated when tracing adds more features. * If a call site changes so that some of those parameters are no longer * already on hand without extra work, then the tracehook_* interface * can change so there is no make-work burden on the core code. The * maintainer of core code changing should notify the maintainers of the * tracing code that they need to work out the change. */ #ifndef _LINUX_TRACEHOOK_H #define _LINUX_TRACEHOOK_H 1 #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/blk-cgroup.h> struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(struct pt_regs *regs, unsigned long message) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; current->ptrace_message = message; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (current->exit_code) { send_sig(current->exit_code, current, 1); current->exit_code = 0; } current->ptrace_message = 0; return fatal_signal_pending(current); } /** * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * tracehook_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %TIF_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); } /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use * * Called by the arch code after a signal handler has been set up. * Register and stack state reflects the user handler about to run. * Signal mask changes have already been made. * * Called without locks, shortly before returning to user mode * (or handling more signals). */ static inline void tracehook_signal_handler(int stepping) { if (stepping) ptrace_notify(SIGTRAP); } /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() * * Calling this arranges that @task will call tracehook_notify_resume() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call tracehook_notify_resume() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { #ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); #endif } /** * tracehook_notify_resume - report when about to return to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void tracehook_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); } #endif /* <linux/tracehook.h> */ |
| 11 11 672 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/blk-cgroup.h> #include <linux/ioprio.h> #include "mq-deadline-cgroup.h" static struct blkcg_policy dd_blkcg_policy; static struct blkcg_policy_data *dd_cpd_alloc(gfp_t gfp) { struct dd_blkcg *pd; pd = kzalloc(sizeof(*pd), gfp); if (!pd) return NULL; pd->stats = alloc_percpu_gfp(typeof(*pd->stats), GFP_KERNEL | __GFP_ZERO); if (!pd->stats) { kfree(pd); return NULL; } return &pd->cpd; } static void dd_cpd_free(struct blkcg_policy_data *cpd) { struct dd_blkcg *dd_blkcg = container_of(cpd, typeof(*dd_blkcg), cpd); free_percpu(dd_blkcg->stats); kfree(dd_blkcg); } static struct dd_blkcg *dd_blkcg_from_pd(struct blkg_policy_data *pd) { return container_of(blkcg_to_cpd(pd->blkg->blkcg, &dd_blkcg_policy), struct dd_blkcg, cpd); } /* * Convert an association between a block cgroup and a request queue into a * pointer to the mq-deadline information associated with a (blkcg, queue) pair. */ struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) { struct blkg_policy_data *pd; pd = blkg_to_pd(bio->bi_blkg, &dd_blkcg_policy); if (!pd) return NULL; return dd_blkcg_from_pd(pd); } static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) { static const char *const prio_class_name[] = { [IOPRIO_CLASS_NONE] = "NONE", [IOPRIO_CLASS_RT] = "RT", [IOPRIO_CLASS_BE] = "BE", [IOPRIO_CLASS_IDLE] = "IDLE", }; struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd); int res = 0; u8 prio; for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++) res += scnprintf(buf + res, size - res, " [%s] dispatched=%u inserted=%u merged=%u", prio_class_name[prio], ddcg_sum(blkcg, dispatched, prio) + ddcg_sum(blkcg, merged, prio) - ddcg_sum(blkcg, completed, prio), ddcg_sum(blkcg, inserted, prio) - ddcg_sum(blkcg, completed, prio), ddcg_sum(blkcg, merged, prio)); return res; } static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) { struct dd_blkg *pd; pd = kzalloc(sizeof(*pd), gfp); if (!pd) return NULL; return &pd->pd; } static void dd_pd_free(struct blkg_policy_data *pd) { struct dd_blkg *dd_blkg = container_of(pd, typeof(*dd_blkg), pd); kfree(dd_blkg); } static struct blkcg_policy dd_blkcg_policy = { .cpd_alloc_fn = dd_cpd_alloc, .cpd_free_fn = dd_cpd_free, .pd_alloc_fn = dd_pd_alloc, .pd_free_fn = dd_pd_free, .pd_stat_fn = dd_pd_stat, }; int dd_activate_policy(struct request_queue *q) { return blkcg_activate_policy(q, &dd_blkcg_policy); } void dd_deactivate_policy(struct request_queue *q) { blkcg_deactivate_policy(q, &dd_blkcg_policy); } int __init dd_blkcg_init(void) { return blkcg_policy_register(&dd_blkcg_policy); } void __exit dd_blkcg_exit(void) { blkcg_policy_unregister(&dd_blkcg_policy); } |
| 156 156 956 156 156 156 156 1080 1080 956 956 1081 959 1080 1080 1080 1080 1080 1031 55 1080 1080 1080 1080 956 956 932 24 956 156 121 35 156 956 956 956 156 956 956 1087 956 956 956 156 156 956 956 956 956 156 155 156 956 956 956 955 956 956 956 956 956 956 956 956 956 956 156 156 156 156 156 156 156 156 156 155 156 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/core.c - core driver model code (device registration, etc) * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2006 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2006 Novell, Inc. */ #include <linux/acpi.h> #include <linux/cpufreq.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fwnode.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/kdev_t.h> #include <linux/notifier.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/genhd.h> #include <linux/mutex.h> #include <linux/pm_runtime.h> #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/sysfs.h> #include "base.h" #include "power/power.h" #ifdef CONFIG_SYSFS_DEPRECATED #ifdef CONFIG_SYSFS_DEPRECATED_V2 long sysfs_deprecated = 1; #else long sysfs_deprecated = 0; #endif static int __init sysfs_deprecated_setup(char *arg) { return kstrtol(arg, 10, &sysfs_deprecated); } early_param("sysfs.deprecated", sysfs_deprecated_setup); #endif /* Device links support. */ static LIST_HEAD(deferred_sync); static unsigned int defer_sync_state_count = 1; static DEFINE_MUTEX(fwnode_link_lock); static bool fw_devlink_is_permissive(void); /** * fwnode_link_add - Create a link between two fwnode_handles. * @con: Consumer end of the link. * @sup: Supplier end of the link. * * Create a fwnode link between fwnode handles @con and @sup. The fwnode link * represents the detail that the firmware lists @sup fwnode as supplying a * resource to @con. * * The driver core will use the fwnode link to create a device link between the * two device objects corresponding to @con and @sup when they are created. The * driver core will automatically delete the fwnode link between @con and @sup * after doing that. * * Attempts to create duplicate links between the same pair of fwnode handles * are ignored and there is no reference counting. */ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup) { struct fwnode_link *link; int ret = 0; mutex_lock(&fwnode_link_lock); list_for_each_entry(link, &sup->consumers, s_hook) if (link->consumer == con) goto out; link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; goto out; } link->supplier = sup; INIT_LIST_HEAD(&link->s_hook); link->consumer = con; INIT_LIST_HEAD(&link->c_hook); list_add(&link->s_hook, &sup->consumers); list_add(&link->c_hook, &con->suppliers); out: mutex_unlock(&fwnode_link_lock); return ret; } /** * fwnode_links_purge_suppliers - Delete all supplier links of fwnode_handle. * @fwnode: fwnode whose supplier links need to be deleted * * Deletes all supplier links connecting directly to @fwnode. */ static void fwnode_links_purge_suppliers(struct fwnode_handle *fwnode) { struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { list_del(&link->s_hook); list_del(&link->c_hook); kfree(link); } mutex_unlock(&fwnode_link_lock); } /** * fwnode_links_purge_consumers - Delete all consumer links of fwnode_handle. * @fwnode: fwnode whose consumer links need to be deleted * * Deletes all consumer links connecting directly to @fwnode. */ static void fwnode_links_purge_consumers(struct fwnode_handle *fwnode) { struct fwnode_link *link, *tmp; mutex_lock(&fwnode_link_lock); list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { list_del(&link->s_hook); list_del(&link->c_hook); kfree(link); } mutex_unlock(&fwnode_link_lock); } /** * fwnode_links_purge - Delete all links connected to a fwnode_handle. * @fwnode: fwnode whose links needs to be deleted * * Deletes all links connecting directly to a fwnode. */ void fwnode_links_purge(struct fwnode_handle *fwnode) { fwnode_links_purge_suppliers(fwnode); fwnode_links_purge_consumers(fwnode); } static void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode) { struct fwnode_handle *child; /* Don't purge consumer links of an added child */ if (fwnode->dev) return; fwnode->flags |= FWNODE_FLAG_NOT_DEVICE; fwnode_links_purge_consumers(fwnode); fwnode_for_each_available_child_node(fwnode, child) fw_devlink_purge_absent_suppliers(child); } #ifdef CONFIG_SRCU static DEFINE_MUTEX(device_links_lock); DEFINE_STATIC_SRCU(device_links_srcu); static inline void device_links_write_lock(void) { mutex_lock(&device_links_lock); } static inline void device_links_write_unlock(void) { mutex_unlock(&device_links_lock); } int device_links_read_lock(void) __acquires(&device_links_srcu) { return srcu_read_lock(&device_links_srcu); } void device_links_read_unlock(int idx) __releases(&device_links_srcu) { srcu_read_unlock(&device_links_srcu, idx); } int device_links_read_lock_held(void) { return srcu_read_lock_held(&device_links_srcu); } static void device_link_synchronize_removal(void) { synchronize_srcu(&device_links_srcu); } static void device_link_remove_from_lists(struct device_link *link) { list_del_rcu(&link->s_node); list_del_rcu(&link->c_node); } #else /* !CONFIG_SRCU */ static DECLARE_RWSEM(device_links_lock); static inline void device_links_write_lock(void) { down_write(&device_links_lock); } static inline void device_links_write_unlock(void) { up_write(&device_links_lock); } int device_links_read_lock(void) { down_read(&device_links_lock); return 0; } void device_links_read_unlock(int not_used) { up_read(&device_links_lock); } #ifdef CONFIG_DEBUG_LOCK_ALLOC int device_links_read_lock_held(void) { return lockdep_is_held(&device_links_lock); } #endif static inline void device_link_synchronize_removal(void) { } static void device_link_remove_from_lists(struct device_link *link) { list_del(&link->s_node); list_del(&link->c_node); } #endif /* !CONFIG_SRCU */ static bool device_is_ancestor(struct device *dev, struct device *target) { while (target->parent) { target = target->parent; if (dev == target) return true; } return false; } /** * device_is_dependent - Check if one device depends on another one * @dev: Device to check dependencies for. * @target: Device to check against. * * Check if @target depends on @dev or any device dependent on it (its child or * its consumer etc). Return 1 if that is the case or 0 otherwise. */ int device_is_dependent(struct device *dev, void *target) { struct device_link *link; int ret; /* * The "ancestors" check is needed to catch the case when the target * device has not been completely initialized yet and it is still * missing from the list of children of its parent device. */ if (dev == target || device_is_ancestor(dev, target)) return 1; ret = device_for_each_child(dev, target, device_is_dependent); if (ret) return ret; list_for_each_entry(link, &dev->links.consumers, s_node) { if ((link->flags & ~DL_FLAG_INFERRED) == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; if (link->consumer == target) return 1; ret = device_is_dependent(link->consumer, target); if (ret) break; } return ret; } static void device_link_init_status(struct device_link *link, struct device *consumer, struct device *supplier) { switch (supplier->links.status) { case DL_DEV_PROBING: switch (consumer->links.status) { case DL_DEV_PROBING: /* * A consumer driver can create a link to a supplier * that has not completed its probing yet as long as it * knows that the supplier is already functional (for * example, it has just acquired some resources from the * supplier). */ link->status = DL_STATE_CONSUMER_PROBE; break; default: link->status = DL_STATE_DORMANT; break; } break; case DL_DEV_DRIVER_BOUND: switch (consumer->links.status) { case DL_DEV_PROBING: link->status = DL_STATE_CONSUMER_PROBE; break; case DL_DEV_DRIVER_BOUND: link->status = DL_STATE_ACTIVE; break; default: link->status = DL_STATE_AVAILABLE; break; } break; case DL_DEV_UNBINDING: link->status = DL_STATE_SUPPLIER_UNBIND; break; default: link->status = DL_STATE_DORMANT; break; } } static int device_reorder_to_tail(struct device *dev, void *not_used) { struct device_link *link; /* * Devices that have not been registered yet will be put to the ends * of the lists during the registration, so skip them here. */ if (device_is_registered(dev)) devices_kset_move_last(dev); if (device_pm_initialized(dev)) device_pm_move_last(dev); device_for_each_child(dev, NULL, device_reorder_to_tail); list_for_each_entry(link, &dev->links.consumers, s_node) { if ((link->flags & ~DL_FLAG_INFERRED) == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; device_reorder_to_tail(link->consumer, NULL); } return 0; } /** * device_pm_move_to_tail - Move set of devices to the end of device lists * @dev: Device to move * * This is a device_reorder_to_tail() wrapper taking the requisite locks. * * It moves the @dev along with all of its children and all of its consumers * to the ends of the device_kset and dpm_list, recursively. */ void device_pm_move_to_tail(struct device *dev) { int idx; idx = device_links_read_lock(); device_pm_lock(); device_reorder_to_tail(dev, NULL); device_pm_unlock(); device_links_read_unlock(idx); } #define to_devlink(dev) container_of((dev), struct device_link, link_dev) static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; switch (to_devlink(dev)->status) { case DL_STATE_NONE: output = "not tracked"; break; case DL_STATE_DORMANT: output = "dormant"; break; case DL_STATE_AVAILABLE: output = "available"; break; case DL_STATE_CONSUMER_PROBE: output = "consumer probing"; break; case DL_STATE_ACTIVE: output = "active"; break; case DL_STATE_SUPPLIER_UNBIND: output = "supplier unbinding"; break; default: output = "unknown"; break; } return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(status); static ssize_t auto_remove_on_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); const char *output; if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) output = "supplier unbind"; else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) output = "consumer unbind"; else output = "never"; return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(auto_remove_on); static ssize_t runtime_pm_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME)); } static DEVICE_ATTR_RO(runtime_pm); static ssize_t sync_state_only_show(struct device *dev, struct device_attribute *attr, char *buf) { struct device_link *link = to_devlink(dev); return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); } static DEVICE_ATTR_RO(sync_state_only); static struct attribute *devlink_attrs[] = { &dev_attr_status.attr, &dev_attr_auto_remove_on.attr, &dev_attr_runtime_pm.attr, &dev_attr_sync_state_only.attr, NULL, }; ATTRIBUTE_GROUPS(devlink); static void device_link_release_fn(struct work_struct *work) { struct device_link *link = container_of(work, struct device_link, rm_work); /* Ensure that all references to the link object have been dropped. */ device_link_synchronize_removal(); pm_runtime_release_supplier(link); pm_request_idle(link->supplier); put_device(link->consumer); put_device(link->supplier); kfree(link); } static void devlink_dev_release(struct device *dev) { struct device_link *link = to_devlink(dev); INIT_WORK(&link->rm_work, device_link_release_fn); /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or * supplier devices get deleted when it runs, so put it into the "long" * workqueue. */ queue_work(system_long_wq, &link->rm_work); } static struct class devlink_class = { .name = "devlink", .owner = THIS_MODULE, .dev_groups = devlink_groups, .dev_release = devlink_dev_release, }; static int devlink_add_symlinks(struct device *dev, struct class_interface *class_intf) { int ret; size_t len; struct device_link *link = to_devlink(dev); struct device *sup = link->supplier; struct device *con = link->consumer; char *buf; len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), strlen(dev_bus_name(con)) + strlen(dev_name(con))); len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier"); if (ret) goto out; ret = sysfs_create_link(&link->link_dev.kobj, &con->kobj, "consumer"); if (ret) goto err_con; snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); if (ret) goto err_con_dev; snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); if (ret) goto err_sup_dev; goto out; err_sup_dev: snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); err_con_dev: sysfs_remove_link(&link->link_dev.kobj, "consumer"); err_con: sysfs_remove_link(&link->link_dev.kobj, "supplier"); out: kfree(buf); return ret; } static void devlink_remove_symlinks(struct device *dev, struct class_interface *class_intf) { struct device_link *link = to_devlink(dev); size_t len; struct device *sup = link->supplier; struct device *con = link->consumer; char *buf; sysfs_remove_link(&link->link_dev.kobj, "consumer"); sysfs_remove_link(&link->link_dev.kobj, "supplier"); len = max(strlen(dev_bus_name(sup)) + strlen(dev_name(sup)), strlen(dev_bus_name(con)) + strlen(dev_name(con))); len += strlen(":"); len += strlen("supplier:") + 1; buf = kzalloc(len, GFP_KERNEL); if (!buf) { WARN(1, "Unable to properly free device link symlinks!\n"); return; } if (device_is_registered(con)) { snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup)); sysfs_remove_link(&con->kobj, buf); } snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con)); sysfs_remove_link(&sup->kobj, buf); kfree(buf); } static struct class_interface devlink_class_intf = { .class = &devlink_class, .add_dev = devlink_add_symlinks, .remove_dev = devlink_remove_symlinks, }; static int __init devlink_class_init(void) { int ret; ret = class_register(&devlink_class); if (ret) return ret; ret = class_interface_register(&devlink_class_intf); if (ret) class_unregister(&devlink_class); return ret; } postcore_initcall(devlink_class_init); #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ DL_FLAG_AUTOREMOVE_SUPPLIER | \ DL_FLAG_AUTOPROBE_CONSUMER | \ DL_FLAG_SYNC_STATE_ONLY | \ DL_FLAG_INFERRED) #define DL_ADD_VALID_FLAGS (DL_MANAGED_LINK_FLAGS | DL_FLAG_STATELESS | \ DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE) /** * device_link_add - Create a link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * @flags: Link flags. * * The caller is responsible for the proper synchronization of the link creation * with runtime PM. First, setting the DL_FLAG_PM_RUNTIME flag will cause the * runtime PM framework to take the link into account. Second, if the * DL_FLAG_RPM_ACTIVE flag is set in addition to it, the supplier devices will * be forced into the active metastate and reference-counted upon the creation * of the link. If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be * ignored. * * If DL_FLAG_STATELESS is set in @flags, the caller of this function is * expected to release the link returned by it directly with the help of either * device_link_del() or device_link_remove(). * * If that flag is not set, however, the caller of this function is handing the * management of the link over to the driver core entirely and its return value * can only be used to check whether or not the link is present. In that case, * the DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_AUTOREMOVE_SUPPLIER device link * flags can be used to indicate to the driver core when the link can be safely * deleted. Namely, setting one of them in @flags indicates to the driver core * that the link is not going to be used (by the given caller of this function) * after unbinding the consumer or supplier driver, respectively, from its * device, so the link can be deleted at that point. If none of them is set, * the link will be maintained until one of the devices pointed to by it (either * the consumer or the supplier) is unregistered. * * Also, if DL_FLAG_STATELESS, DL_FLAG_AUTOREMOVE_CONSUMER and * DL_FLAG_AUTOREMOVE_SUPPLIER are not set in @flags (that is, a persistent * managed device link is being added), the DL_FLAG_AUTOPROBE_CONSUMER flag can * be used to request the driver core to automaticall probe for a consmer * driver after successfully binding a driver to the supplier device. * * The combination of DL_FLAG_STATELESS and one of DL_FLAG_AUTOREMOVE_CONSUMER, * DL_FLAG_AUTOREMOVE_SUPPLIER, or DL_FLAG_AUTOPROBE_CONSUMER set in @flags at * the same time is invalid and will cause NULL to be returned upfront. * However, if a device link between the given @consumer and @supplier pair * exists already when this function is called for them, the existing link will * be returned regardless of its current type and status (the link's flags may * be modified then). The caller of this function is then expected to treat * the link as though it has just been created, so (in particular) if * DL_FLAG_STATELESS was passed in @flags, the link needs to be released * explicitly when not needed any more (as stated above). * * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). * * The supplier device is required to be registered when this function is called * and NULL will be returned if that is not the case. The consumer device need * not be registered, however. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags) { struct device_link *link; if (!consumer || !supplier || consumer == supplier || flags & ~DL_ADD_VALID_FLAGS || (flags & DL_FLAG_STATELESS && flags & DL_MANAGED_LINK_FLAGS) || (flags & DL_FLAG_SYNC_STATE_ONLY && (flags & ~DL_FLAG_INFERRED) != DL_FLAG_SYNC_STATE_ONLY) || (flags & DL_FLAG_AUTOPROBE_CONSUMER && flags & (DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER))) return NULL; if (flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) { if (pm_runtime_get_sync(supplier) < 0) { pm_runtime_put_noidle(supplier); return NULL; } } if (!(flags & DL_FLAG_STATELESS)) flags |= DL_FLAG_MANAGED; device_links_write_lock(); device_pm_lock(); /* * If the supplier has not been fully registered yet or there is a * reverse (non-SYNC_STATE_ONLY) dependency between the consumer and * the supplier already in the graph, return NULL. If the link is a * SYNC_STATE_ONLY link, we don't check for reverse dependencies * because it only affects sync_state() callbacks. */ if (!device_pm_initialized(supplier) || (!(flags & DL_FLAG_SYNC_STATE_ONLY) && device_is_dependent(consumer, supplier))) { link = NULL; goto out; } /* * SYNC_STATE_ONLY links are useless once a consumer device has probed. * So, only create it if the consumer hasn't probed yet. */ if (flags & DL_FLAG_SYNC_STATE_ONLY && consumer->links.status != DL_DEV_NO_DRIVER && consumer->links.status != DL_DEV_PROBING) { link = NULL; goto out; } /* * DL_FLAG_AUTOREMOVE_SUPPLIER indicates that the link will be needed * longer than for DL_FLAG_AUTOREMOVE_CONSUMER and setting them both * together doesn't make sense, so prefer DL_FLAG_AUTOREMOVE_SUPPLIER. */ if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer != consumer) continue; if (link->flags & DL_FLAG_INFERRED && !(flags & DL_FLAG_INFERRED)) link->flags &= ~DL_FLAG_INFERRED; if (flags & DL_FLAG_PM_RUNTIME) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) { pm_runtime_new_link(consumer); link->flags |= DL_FLAG_PM_RUNTIME; } if (flags & DL_FLAG_RPM_ACTIVE) refcount_inc(&link->rpm_active); } if (flags & DL_FLAG_STATELESS) { kref_get(&link->kref); if (link->flags & DL_FLAG_SYNC_STATE_ONLY && !(link->flags & DL_FLAG_STATELESS)) { link->flags |= DL_FLAG_STATELESS; goto reorder; } else { link->flags |= DL_FLAG_STATELESS; goto out; } } /* * If the life time of the link following from the new flags is * longer than indicated by the flags of the existing link, * update the existing link to stay around longer. */ if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) { if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { link->flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER; link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER; } } else if (!(flags & DL_FLAG_AUTOREMOVE_CONSUMER)) { link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER | DL_FLAG_AUTOREMOVE_SUPPLIER); } if (!(link->flags & DL_FLAG_MANAGED)) { kref_get(&link->kref); link->flags |= DL_FLAG_MANAGED; device_link_init_status(link, consumer, supplier); } if (link->flags & DL_FLAG_SYNC_STATE_ONLY && !(flags & DL_FLAG_SYNC_STATE_ONLY)) { link->flags &= ~DL_FLAG_SYNC_STATE_ONLY; goto reorder; } goto out; } link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) goto out; refcount_set(&link->rpm_active, 1); get_device(supplier); link->supplier = supplier; INIT_LIST_HEAD(&link->s_node); get_device(consumer); link->consumer = consumer; INIT_LIST_HEAD(&link->c_node); link->flags = flags; kref_init(&link->kref); link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); dev_set_name(&link->link_dev, "%s:%s--%s:%s", dev_bus_name(supplier), dev_name(supplier), dev_bus_name(consumer), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(&link->link_dev); link = NULL; goto out; } if (flags & DL_FLAG_PM_RUNTIME) { if (flags & DL_FLAG_RPM_ACTIVE) refcount_inc(&link->rpm_active); pm_runtime_new_link(consumer); } /* Determine the initial link state. */ if (flags & DL_FLAG_STATELESS) link->status = DL_STATE_NONE; else device_link_init_status(link, consumer, supplier); /* * Some callers expect the link creation during consumer driver probe to * resume the supplier even without DL_FLAG_RPM_ACTIVE. */ if (link->status == DL_STATE_CONSUMER_PROBE && flags & DL_FLAG_PM_RUNTIME) pm_runtime_resume(supplier); list_add_tail_rcu(&link->s_node, &supplier->links.consumers); list_add_tail_rcu(&link->c_node, &consumer->links.suppliers); if (flags & DL_FLAG_SYNC_STATE_ONLY) { dev_dbg(consumer, "Linked as a sync state only consumer to %s\n", dev_name(supplier)); goto out; } reorder: /* * Move the consumer and all of the devices depending on it to the end * of dpm_list and the devices_kset list. * * It is necessary to hold dpm_list locked throughout all that or else * we may end up suspending with a wrong ordering of it. */ device_reorder_to_tail(consumer, NULL); dev_dbg(consumer, "Linked as a consumer to %s\n", dev_name(supplier)); out: device_pm_unlock(); device_links_write_unlock(); if ((flags & DL_FLAG_PM_RUNTIME && flags & DL_FLAG_RPM_ACTIVE) && !link) pm_runtime_put(supplier); return link; } EXPORT_SYMBOL_GPL(device_link_add); static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); dev_dbg(link->consumer, "Dropping the link to %s\n", dev_name(link->supplier)); pm_runtime_drop_link(link); device_link_remove_from_lists(link); device_unregister(&link->link_dev); } static void device_link_put_kref(struct device_link *link) { if (link->flags & DL_FLAG_STATELESS) kref_put(&link->kref, __device_link_del); else WARN(1, "Unable to drop a managed device link reference\n"); } /** * device_link_del - Delete a stateless link between two devices. * @link: Device link to delete. * * The caller must ensure proper synchronization of this function with runtime * PM. If the link was added multiple times, it needs to be deleted as often. * Care is required for hotplugged devices: Their links are purged on removal * and calling device_link_del() is then no longer allowed. */ void device_link_del(struct device_link *link) { device_links_write_lock(); device_link_put_kref(link); device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_del); /** * device_link_remove - Delete a stateless link between two devices. * @consumer: Consumer end of the link. * @supplier: Supplier end of the link. * * The caller must ensure proper synchronization of this function with runtime * PM. */ void device_link_remove(void *consumer, struct device *supplier) { struct device_link *link; if (WARN_ON(consumer == supplier)) return; device_links_write_lock(); list_for_each_entry(link, &supplier->links.consumers, s_node) { if (link->consumer == consumer) { device_link_put_kref(link); break; } } device_links_write_unlock(); } EXPORT_SYMBOL_GPL(device_link_remove); static void device_links_missing_supplier(struct device *dev) { struct device_link *link; list_for_each_entry(link, &dev->links.suppliers, c_node) { if (link->status != DL_STATE_CONSUMER_PROBE) continue; if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) { WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } else { WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); WRITE_ONCE(link->status, DL_STATE_DORMANT); } } } /** * device_links_check_suppliers - Check presence of supplier drivers. * @dev: Consumer device. * * Check links from this device to any suppliers. Walk the list of the device's * links to suppliers and see if all of them are available. If not, simply * return -EPROBE_DEFER. * * We need to guarantee that the supplier will not go away after the check has * been positive here. It only can go away in __device_release_driver() and * that function checks the device's links to consumers. This means we need to * mark the link as "consumer probe in progress" to make the supplier removal * wait for us to complete (or bad things may happen). * * Links without the DL_FLAG_MANAGED flag set are ignored. */ int device_links_check_suppliers(struct device *dev) { struct device_link *link; int ret = 0; /* * Device waiting for supplier to become available is not allowed to * probe. */ mutex_lock(&fwnode_link_lock); if (dev->fwnode && !list_empty(&dev->fwnode->suppliers) && !fw_devlink_is_permissive()) { dev_dbg(dev, "probe deferral - wait for supplier %pfwP\n", list_first_entry(&dev->fwnode->suppliers, struct fwnode_link, c_hook)->supplier); mutex_unlock(&fwnode_link_lock); return -EPROBE_DEFER; } mutex_unlock(&fwnode_link_lock); device_links_write_lock(); list_for_each_entry(link, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_AVAILABLE && !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) { device_links_missing_supplier(dev); dev_dbg(dev, "probe deferral - supplier %s not ready\n", dev_name(link->supplier)); ret = -EPROBE_DEFER; break; } WRITE_ONCE(link->status, DL_STATE_CONSUMER_PROBE); } dev->links.status = DL_DEV_PROBING; device_links_write_unlock(); return ret; } /** * __device_links_queue_sync_state - Queue a device for sync_state() callback * @dev: Device to call sync_state() on * @list: List head to queue the @dev on * * Queues a device for a sync_state() callback when the device links write lock * isn't held. This allows the sync_state() execution flow to use device links * APIs. The caller must ensure this function is called with * device_links_write_lock() held. * * This function does a get_device() to make sure the device is not freed while * on this list. * * So the caller must also ensure that device_links_flush_sync_list() is called * as soon as the caller releases device_links_write_lock(). This is necessary * to make sure the sync_state() is called in a timely fashion and the * put_device() is called on this device. */ static void __device_links_queue_sync_state(struct device *dev, struct list_head *list) { struct device_link *link; if (!dev_has_sync_state(dev)) return; if (dev->state_synced) return; list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status != DL_STATE_ACTIVE) return; } /* * Set the flag here to avoid adding the same device to a list more * than once. This can happen if new consumers get added to the device * and probed before the list is flushed. */ dev->state_synced = true; if (WARN_ON(!list_empty(&dev->links.defer_sync))) return; get_device(dev); list_add_tail(&dev->links.defer_sync, list); } /** * device_links_flush_sync_list - Call sync_state() on a list of devices * @list: List of devices to call sync_state() on * @dont_lock_dev: Device for which lock is already held by the caller * * Calls sync_state() on all the devices that have been queued for it. This * function is used in conjunction with __device_links_queue_sync_state(). The * @dont_lock_dev parameter is useful when this function is called from a * context where a device lock is already held. */ static void device_links_flush_sync_list(struct list_head *list, struct device *dont_lock_dev) { struct device *dev, *tmp; list_for_each_entry_safe(dev, tmp, list, links.defer_sync) { list_del_init(&dev->links.defer_sync); if (dev != dont_lock_dev) device_lock(dev); if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); if (dev != dont_lock_dev) device_unlock(dev); put_device(dev); } } void device_links_supplier_sync_state_pause(void) { device_links_write_lock(); defer_sync_state_count++; device_links_write_unlock(); } void device_links_supplier_sync_state_resume(void) { struct device *dev, *tmp; LIST_HEAD(sync_list); device_links_write_lock(); if (!defer_sync_state_count) { WARN(true, "Unmatched sync_state pause/resume!"); goto out; } defer_sync_state_count--; if (defer_sync_state_count) goto out; list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) { /* * Delete from deferred_sync list before queuing it to * sync_list because defer_sync is used for both lists. */ list_del_init(&dev->links.defer_sync); __device_links_queue_sync_state(dev, &sync_list); } out: device_links_write_unlock(); device_links_flush_sync_list(&sync_list, NULL); } static int sync_state_resume_initcall(void) { device_links_supplier_sync_state_resume(); return 0; } late_initcall(sync_state_resume_initcall); static void __device_links_supplier_defer_sync(struct device *sup) { if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup)) list_add_tail(&sup->links.defer_sync, &deferred_sync); } static void device_link_drop_managed(struct device_link *link) { link->flags &= ~DL_FLAG_MANAGED; WRITE_ONCE(link->status, DL_STATE_NONE); kref_put(&link->kref, __device_link_del); } static ssize_t waiting_for_supplier_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = !list_empty(&dev->fwnode->suppliers); device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static DEVICE_ATTR_RO(waiting_for_supplier); /** * device_links_driver_bound - Update device links after probing its driver. * @dev: Device to update the links for. * * The probe has been successful, so update links from this device to any * consumers by changing their status to "available". * * Also change the status of @dev's links to suppliers to "active". * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_bound(struct device *dev) { struct device_link *link, *ln; LIST_HEAD(sync_list); /* * If a device binds successfully, it's expected to have created all * the device links it needs to or make new device links as it needs * them. So, fw_devlink no longer needs to create device links to any * of the device's suppliers. * * Also, if a child firmware node of this bound device is not added as * a device by now, assume it is never going to be added and make sure * other devices don't defer probe indefinitely by waiting for such a * child device. */ if (dev->fwnode && dev->fwnode->dev == dev) { struct fwnode_handle *child; fwnode_links_purge_suppliers(dev->fwnode); fwnode_for_each_available_child_node(dev->fwnode, child) fw_devlink_purge_absent_suppliers(child); } device_remove_file(dev, &dev_attr_waiting_for_supplier); device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; /* * Links created during consumer probe may be in the "consumer * probe" state to start with if the supplier is still probing * when they are created and they may become "active" if the * consumer probe returns first. Skip them here. */ if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) continue; WARN_ON(link->status != DL_STATE_DORMANT); WRITE_ONCE(link->status, DL_STATE_AVAILABLE); if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER) driver_deferred_probe_add(link->consumer); } if (defer_sync_state_count) __device_links_supplier_defer_sync(dev); else __device_links_queue_sync_state(dev, &sync_list); list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) { struct device *supplier; if (!(link->flags & DL_FLAG_MANAGED)) continue; supplier = link->supplier; if (link->flags & DL_FLAG_SYNC_STATE_ONLY) { /* * When DL_FLAG_SYNC_STATE_ONLY is set, it means no * other DL_MANAGED_LINK_FLAGS have been set. So, it's * save to drop the managed link completely. */ device_link_drop_managed(link); } else { WARN_ON(link->status != DL_STATE_CONSUMER_PROBE); WRITE_ONCE(link->status, DL_STATE_ACTIVE); } /* * This needs to be done even for the deleted * DL_FLAG_SYNC_STATE_ONLY device link in case it was the last * device link that was preventing the supplier from getting a * sync_state() call. */ if (defer_sync_state_count) __device_links_supplier_defer_sync(supplier); else __device_links_queue_sync_state(supplier, &sync_list); } dev->links.status = DL_DEV_DRIVER_BOUND; device_links_write_unlock(); device_links_flush_sync_list(&sync_list, dev); } /** * __device_links_no_driver - Update links of a device without a driver. * @dev: Device without a drvier. * * Delete all non-persistent links from this device to any suppliers. * * Persistent links stay around, but their status is changed to "available", * unless they already are in the "supplier unbind in progress" state in which * case they need not be updated. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ static void __device_links_no_driver(struct device *dev) { struct device_link *link, *ln; list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) { device_link_drop_managed(link); continue; } if (link->status != DL_STATE_CONSUMER_PROBE && link->status != DL_STATE_ACTIVE) continue; if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) { WRITE_ONCE(link->status, DL_STATE_AVAILABLE); } else { WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); WRITE_ONCE(link->status, DL_STATE_DORMANT); } } dev->links.status = DL_DEV_NO_DRIVER; } /** * device_links_no_driver - Update links after failing driver probe. * @dev: Device whose driver has just failed to probe. * * Clean up leftover links to consumers for @dev and invoke * %__device_links_no_driver() to update links to suppliers for it as * appropriate. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_no_driver(struct device *dev) { struct device_link *link; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; /* * The probe has failed, so if the status of the link is * "consumer probe" or "active", it must have been added by * a probing consumer while this device was still probing. * Change its state to "dormant", as it represents a valid * relationship, but it is not functionally meaningful. */ if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) WRITE_ONCE(link->status, DL_STATE_DORMANT); } __device_links_no_driver(dev); device_links_write_unlock(); } /** * device_links_driver_cleanup - Update links after driver removal. * @dev: Device whose driver has just gone away. * * Update links to consumers for @dev by changing their status to "dormant" and * invoke %__device_links_no_driver() to update links to suppliers for it as * appropriate. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_driver_cleanup(struct device *dev) { struct device_link *link, *ln; device_links_write_lock(); list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER); WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND); /* * autoremove the links between this @dev and its consumer * devices that are not active, i.e. where the link state * has moved to DL_STATE_SUPPLIER_UNBIND. */ if (link->status == DL_STATE_SUPPLIER_UNBIND && link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) device_link_drop_managed(link); WRITE_ONCE(link->status, DL_STATE_DORMANT); } list_del_init(&dev->links.defer_sync); __device_links_no_driver(dev); device_links_write_unlock(); } /** * device_links_busy - Check if there are any busy links to consumers. * @dev: Device to check. * * Check each consumer of the device and return 'true' if its link's status * is one of "consumer probe" or "active" (meaning that the given consumer is * probing right now or its driver is present). Otherwise, change the link * state to "supplier unbind" to prevent the consumer from being probed * successfully going forward. * * Return 'false' if there are no probing or active consumers. * * Links without the DL_FLAG_MANAGED flag set are ignored. */ bool device_links_busy(struct device *dev) { struct device_link *link; bool ret = false; device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { if (!(link->flags & DL_FLAG_MANAGED)) continue; if (link->status == DL_STATE_CONSUMER_PROBE || link->status == DL_STATE_ACTIVE) { ret = true; break; } WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND); } dev->links.status = DL_DEV_UNBINDING; device_links_write_unlock(); return ret; } /** * device_links_unbind_consumers - Force unbind consumers of the given device. * @dev: Device to unbind the consumers of. * * Walk the list of links to consumers for @dev and if any of them is in the * "consumer probe" state, wait for all device probes in progress to complete * and start over. * * If that's not the case, change the status of the link to "supplier unbind" * and check if the link was in the "active" state. If so, force the consumer * driver to unbind and start over (the consumer will not re-probe as we have * changed the state of the link already). * * Links without the DL_FLAG_MANAGED flag set are ignored. */ void device_links_unbind_consumers(struct device *dev) { struct device_link *link; start: device_links_write_lock(); list_for_each_entry(link, &dev->links.consumers, s_node) { enum device_link_state status; if (!(link->flags & DL_FLAG_MANAGED) || link->flags & DL_FLAG_SYNC_STATE_ONLY) continue; status = link->status; if (status == DL_STATE_CONSUMER_PROBE) { device_links_write_unlock(); wait_for_device_probe(); goto start; } WRITE_ONCE(link->status, DL_STATE_SUPPLIER_UNBIND); if (status == DL_STATE_ACTIVE) { struct device *consumer = link->consumer; get_device(consumer); device_links_write_unlock(); device_release_driver_internal(consumer, NULL, consumer->parent); put_device(consumer); goto start; } } device_links_write_unlock(); } /** * device_links_purge - Delete existing links to other devices. * @dev: Target device. */ static void device_links_purge(struct device *dev) { struct device_link *link, *ln; if (dev->class == &devlink_class) return; /* * Delete all of the remaining links from this device to any other * devices (either consumers or suppliers). */ device_links_write_lock(); list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) { WARN_ON(link->status == DL_STATE_ACTIVE); __device_link_del(&link->kref); } list_for_each_entry_safe_reverse(link, ln, &dev->links.consumers, s_node) { WARN_ON(link->status != DL_STATE_DORMANT && link->status != DL_STATE_NONE); __device_link_del(&link->kref); } device_links_write_unlock(); } #define FW_DEVLINK_FLAGS_PERMISSIVE (DL_FLAG_INFERRED | \ DL_FLAG_SYNC_STATE_ONLY) #define FW_DEVLINK_FLAGS_ON (DL_FLAG_INFERRED | \ DL_FLAG_AUTOPROBE_CONSUMER) #define FW_DEVLINK_FLAGS_RPM (FW_DEVLINK_FLAGS_ON | \ DL_FLAG_PM_RUNTIME) static u32 fw_devlink_flags = FW_DEVLINK_FLAGS_ON; static int __init fw_devlink_setup(char *arg) { if (!arg) return -EINVAL; if (strcmp(arg, "off") == 0) { fw_devlink_flags = 0; } else if (strcmp(arg, "permissive") == 0) { fw_devlink_flags = FW_DEVLINK_FLAGS_PERMISSIVE; } else if (strcmp(arg, "on") == 0) { fw_devlink_flags = FW_DEVLINK_FLAGS_ON; } else if (strcmp(arg, "rpm") == 0) { fw_devlink_flags = FW_DEVLINK_FLAGS_RPM; } return 0; } early_param("fw_devlink", fw_devlink_setup); static bool fw_devlink_strict = true; static int __init fw_devlink_strict_setup(char *arg) { return strtobool(arg, &fw_devlink_strict); } early_param("fw_devlink.strict", fw_devlink_strict_setup); u32 fw_devlink_get_flags(void) { return fw_devlink_flags; } static bool fw_devlink_is_permissive(void) { return fw_devlink_flags == FW_DEVLINK_FLAGS_PERMISSIVE; } bool fw_devlink_is_strict(void) { return fw_devlink_strict && !fw_devlink_is_permissive(); } static void fw_devlink_parse_fwnode(struct fwnode_handle *fwnode) { if (fwnode->flags & FWNODE_FLAG_LINKS_ADDED) return; fwnode_call_int_op(fwnode, add_links); fwnode->flags |= FWNODE_FLAG_LINKS_ADDED; } static void fw_devlink_parse_fwtree(struct fwnode_handle *fwnode) { struct fwnode_handle *child = NULL; fw_devlink_parse_fwnode(fwnode); while ((child = fwnode_get_next_available_child_node(fwnode, child))) fw_devlink_parse_fwtree(child); } /** * fw_devlink_relax_cycle - Convert cyclic links to SYNC_STATE_ONLY links * @con: Device to check dependencies for. * @sup: Device to check against. * * Check if @sup depends on @con or any device dependent on it (its child or * its consumer etc). When such a cyclic dependency is found, convert all * device links created solely by fw_devlink into SYNC_STATE_ONLY device links. * This is the equivalent of doing fw_devlink=permissive just between the * devices in the cycle. We need to do this because, at this point, fw_devlink * can't tell which of these dependencies is not a real dependency. * * Return 1 if a cycle is found. Otherwise, return 0. */ int fw_devlink_relax_cycle(struct device *con, void *sup) { struct device_link *link; int ret; if (con == sup) return 1; ret = device_for_each_child(con, sup, fw_devlink_relax_cycle); if (ret) return ret; list_for_each_entry(link, &con->links.consumers, s_node) { if ((link->flags & ~DL_FLAG_INFERRED) == (DL_FLAG_SYNC_STATE_ONLY | DL_FLAG_MANAGED)) continue; if (!fw_devlink_relax_cycle(link->consumer, sup)) continue; ret = 1; if (!(link->flags & DL_FLAG_INFERRED)) continue; pm_runtime_drop_link(link); link->flags = DL_FLAG_MANAGED | FW_DEVLINK_FLAGS_PERMISSIVE; dev_dbg(link->consumer, "Relaxing link with %s\n", dev_name(link->supplier)); } return ret; } /** * fw_devlink_create_devlink - Create a device link from a consumer to fwnode * @con - Consumer device for the device link * @sup_handle - fwnode handle of supplier * * This function will try to create a device link between the consumer device * @con and the supplier device represented by @sup_handle. * * The supplier has to be provided as a fwnode because incorrect cycles in * fwnode links can sometimes cause the supplier device to never be created. * This function detects such cases and returns an error if it cannot create a * device link from the consumer to a missing supplier. * * Returns, * 0 on successfully creating a device link * -EINVAL if the device link cannot be created as expected * -EAGAIN if the device link cannot be created right now, but it may be * possible to do that in the future */ static int fw_devlink_create_devlink(struct device *con, struct fwnode_handle *sup_handle, u32 flags) { struct device *sup_dev; int ret = 0; sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { /* * If it's one of those drivers that don't actually bind to * their device using driver core, then don't wait on this * supplier device indefinitely. */ if (sup_dev->links.status == DL_DEV_NO_DRIVER && sup_handle->flags & FWNODE_FLAG_INITIALIZED) { ret = -EINVAL; goto out; } /* * If this fails, it is due to cycles in device links. Just * give up on this link and treat it as invalid. */ if (!device_link_add(con, sup_dev, flags) && !(flags & DL_FLAG_SYNC_STATE_ONLY)) { dev_info(con, "Fixing up cyclic dependency with %s\n", dev_name(sup_dev)); device_links_write_lock(); fw_devlink_relax_cycle(con, sup_dev); device_links_write_unlock(); device_link_add(con, sup_dev, FW_DEVLINK_FLAGS_PERMISSIVE); ret = -EINVAL; } goto out; } /* Supplier that's already initialized without a struct device. */ if (sup_handle->flags & FWNODE_FLAG_INITIALIZED) return -EINVAL; /* * DL_FLAG_SYNC_STATE_ONLY doesn't block probing and supports * cycles. So cycle detection isn't necessary and shouldn't be * done. */ if (flags & DL_FLAG_SYNC_STATE_ONLY) return -EAGAIN; /* * If we can't find the supplier device from its fwnode, it might be * due to a cyclic dependency between fwnodes. Some of these cycles can * be broken by applying logic. Check for these types of cycles and * break them so that devices in the cycle probe properly. * * If the supplier's parent is dependent on the consumer, then the * consumer and supplier have a cyclic dependency. Since fw_devlink * can't tell which of the inferred dependencies are incorrect, don't * enforce probe ordering between any of the devices in this cyclic * dependency. Do this by relaxing all the fw_devlink device links in * this cycle and by treating the fwnode link between the consumer and * the supplier as an invalid dependency. */ sup_dev = fwnode_get_next_parent_dev(sup_handle); if (sup_dev && device_is_dependent(con, sup_dev)) { dev_info(con, "Fixing up cyclic dependency with %pfwP (%s)\n", sup_handle, dev_name(sup_dev)); device_links_write_lock(); fw_devlink_relax_cycle(con, sup_dev); device_links_write_unlock(); ret = -EINVAL; } else { /* * Can't check for cycles or no cycles. So let's try * again later. */ ret = -EAGAIN; } out: put_device(sup_dev); return ret; } /** * __fw_devlink_link_to_consumers - Create device links to consumers of a device * @dev - Device that needs to be linked to its consumers * * This function looks at all the consumer fwnodes of @dev and creates device * links between the consumer device and @dev (supplier). * * If the consumer device has not been added yet, then this function creates a * SYNC_STATE_ONLY link between @dev (supplier) and the closest ancestor device * of the consumer fwnode. This is necessary to make sure @dev doesn't get a * sync_state() callback before the real consumer device gets to be added and * then probed. * * Once device links are created from the real consumer to @dev (supplier), the * fwnode links are deleted. */ static void __fw_devlink_link_to_consumers(struct device *dev) { struct fwnode_handle *fwnode = dev->fwnode; struct fwnode_link *link, *tmp; list_for_each_entry_safe(link, tmp, &fwnode->consumers, s_hook) { u32 dl_flags = fw_devlink_get_flags(); struct device *con_dev; bool own_link = true; int ret; con_dev = get_dev_from_fwnode(link->consumer); /* * If consumer device is not available yet, make a "proxy" * SYNC_STATE_ONLY link from the consumer's parent device to * the supplier device. This is necessary to make sure the * supplier doesn't get a sync_state() callback before the real * consumer can create a device link to the supplier. * * This proxy link step is needed to handle the case where the * consumer's parent device is added before the supplier. */ if (!con_dev) { con_dev = fwnode_get_next_parent_dev(link->consumer); /* * However, if the consumer's parent device is also the * parent of the supplier, don't create a * consumer-supplier link from the parent to its child * device. Such a dependency is impossible. */ if (con_dev && fwnode_is_ancestor_of(con_dev->fwnode, fwnode)) { put_device(con_dev); con_dev = NULL; } else { own_link = false; dl_flags = FW_DEVLINK_FLAGS_PERMISSIVE; } } if (!con_dev) continue; ret = fw_devlink_create_devlink(con_dev, fwnode, dl_flags); put_device(con_dev); if (!own_link || ret == -EAGAIN) continue; list_del(&link->s_hook); list_del(&link->c_hook); kfree(link); } } /** * __fw_devlink_link_to_suppliers - Create device links to suppliers of a device * @dev - The consumer device that needs to be linked to its suppliers * @fwnode - Root of the fwnode tree that is used to create device links * * This function looks at all the supplier fwnodes of fwnode tree rooted at * @fwnode and creates device links between @dev (consumer) and all the * supplier devices of the entire fwnode tree at @fwnode. * * The function creates normal (non-SYNC_STATE_ONLY) device links between @dev * and the real suppliers of @dev. Once these device links are created, the * fwnode links are deleted. When such device links are successfully created, * this function is called recursively on those supplier devices. This is * needed to detect and break some invalid cycles in fwnode links. See * fw_devlink_create_devlink() for more details. * * In addition, it also looks at all the suppliers of the entire fwnode tree * because some of the child devices of @dev that have not been added yet * (because @dev hasn't probed) might already have their suppliers added to * driver core. So, this function creates SYNC_STATE_ONLY device links between * @dev (consumer) and these suppliers to make sure they don't execute their * sync_state() callbacks before these child devices have a chance to create * their device links. The fwnode links that correspond to the child devices * aren't delete because they are needed later to create the device links * between the real consumer and supplier devices. */ static void __fw_devlink_link_to_suppliers(struct device *dev, struct fwnode_handle *fwnode) { bool own_link = (dev->fwnode == fwnode); struct fwnode_link *link, *tmp; struct fwnode_handle *child = NULL; u32 dl_flags; if (own_link) dl_flags = fw_devlink_get_flags(); else dl_flags = FW_DEVLINK_FLAGS_PERMISSIVE; list_for_each_entry_safe(link, tmp, &fwnode->suppliers, c_hook) { int ret; struct device *sup_dev; struct fwnode_handle *sup = link->supplier; ret = fw_devlink_create_devlink(dev, sup, dl_flags); if (!own_link || ret == -EAGAIN) continue; list_del(&link->s_hook); list_del(&link->c_hook); kfree(link); /* If no device link was created, nothing more to do. */ if (ret) continue; /* * If a device link was successfully created to a supplier, we * now need to try and link the supplier to all its suppliers. * * This is needed to detect and delete false dependencies in * fwnode links that haven't been converted to a device link * yet. See comments in fw_devlink_create_devlink() for more * details on the false dependency. * * Without deleting these false dependencies, some devices will * never probe because they'll keep waiting for their false * dependency fwnode links to be converted to device links. */ sup_dev = get_dev_from_fwnode(sup); __fw_devlink_link_to_suppliers(sup_dev, sup_dev->fwnode); put_device(sup_dev); } /* * Make "proxy" SYNC_STATE_ONLY device links to represent the needs of * all the descendants. This proxy link step is needed to handle the * case where the supplier is added before the consumer's parent device * (@dev). */ while ((child = fwnode_get_next_available_child_node(fwnode, child))) __fw_devlink_link_to_suppliers(dev, child); } static void fw_devlink_link_device(struct device *dev) { struct fwnode_handle *fwnode = dev->fwnode; if (!fw_devlink_flags) return; fw_devlink_parse_fwtree(fwnode); mutex_lock(&fwnode_link_lock); __fw_devlink_link_to_consumers(dev); __fw_devlink_link_to_suppliers(dev, fwnode); mutex_unlock(&fwnode_link_lock); } /* Device links support end. */ int (*platform_notify)(struct device *dev) = NULL; int (*platform_notify_remove)(struct device *dev) = NULL; static struct kobject *dev_kobj; struct kobject *sysfs_dev_char_kobj; struct kobject *sysfs_dev_block_kobj; static DEFINE_MUTEX(device_hotplug_lock); void lock_device_hotplug(void) { mutex_lock(&device_hotplug_lock); } void unlock_device_hotplug(void) { mutex_unlock(&device_hotplug_lock); } int lock_device_hotplug_sysfs(void) { if (mutex_trylock(&device_hotplug_lock)) return 0; /* Avoid busy looping (5 ms of sleep should do). */ msleep(5); return restart_syscall(); } #ifdef CONFIG_BLOCK static inline int device_is_not_partition(struct device *dev) { return !(dev->type == &part_type); } #else static inline int device_is_not_partition(struct device *dev) { return 1; } #endif static int device_platform_notify(struct device *dev, enum kobject_action action) { int ret; ret = acpi_platform_notify(dev, action); if (ret) return ret; ret = software_node_notify(dev, action); if (ret) return ret; if (platform_notify && action == KOBJ_ADD) platform_notify(dev); else if (platform_notify_remove && action == KOBJ_REMOVE) platform_notify_remove(dev); return 0; } /** * dev_driver_string - Return a device's driver name, if at all possible * @dev: struct device to get the name of * * Will return the device's driver's name if it is bound to a device. If * the device is not bound to a driver, it will return the name of the bus * it is attached to. If it is not attached to a bus either, an empty * string will be returned. */ const char *dev_driver_string(const struct device *dev) { struct device_driver *drv; /* dev->driver can change to NULL underneath us because of unbinding, * so be careful about accessing it. dev->bus and dev->class should * never change once they are set, so they don't need special care. */ drv = READ_ONCE(dev->driver); return drv ? drv->name : dev_bus_name(dev); } EXPORT_SYMBOL(dev_driver_string); #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct device_attribute *dev_attr = to_dev_attr(attr); struct device *dev = kobj_to_dev(kobj); ssize_t ret = -EIO; if (dev_attr->show) ret = dev_attr->show(dev, dev_attr, buf); if (ret >= (ssize_t)PAGE_SIZE) { printk("dev_attr_show: %pS returned bad count\n", dev_attr->show); } return ret; } static ssize_t dev_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct device_attribute *dev_attr = to_dev_attr(attr); struct device *dev = kobj_to_dev(kobj); ssize_t ret = -EIO; if (dev_attr->store) ret = dev_attr->store(dev, dev_attr, buf, count); return ret; } static const struct sysfs_ops dev_sysfs_ops = { .show = dev_attr_show, .store = dev_attr_store, }; #define to_ext_attr(x) container_of(x, struct dev_ext_attribute, attr) ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); int ret; unsigned long new; ret = kstrtoul(buf, 0, &new); if (ret) return ret; *(unsigned long *)(ea->var) = new; /* Always return full write size even if we didn't consume all */ return size; } EXPORT_SYMBOL_GPL(device_store_ulong); ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%lx\n", *(unsigned long *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_ulong); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); int ret; long new; ret = kstrtol(buf, 0, &new); if (ret) return ret; if (new > INT_MAX || new < INT_MIN) return -EINVAL; *(int *)(ea->var) = new; /* Always return full write size even if we didn't consume all */ return size; } EXPORT_SYMBOL_GPL(device_store_int); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%d\n", *(int *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_int); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct dev_ext_attribute *ea = to_ext_attr(attr); if (strtobool(buf, ea->var) < 0) return -EINVAL; return size; } EXPORT_SYMBOL_GPL(device_store_bool); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf) { struct dev_ext_attribute *ea = to_ext_attr(attr); return sysfs_emit(buf, "%d\n", *(bool *)(ea->var)); } EXPORT_SYMBOL_GPL(device_show_bool); /** * device_release - free device structure. * @kobj: device's kobject. * * This is called once the reference count for the object * reaches 0. We forward the call to the device's release * method, which should handle actually freeing the structure. */ static void device_release(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); struct device_private *p = dev->p; /* * Some platform devices are driven without driver attached * and managed resources may have been acquired. Make sure * all resources are released. * * Drivers still can add resources into device after device * is deleted but alive, so release devres here to avoid * possible memory leak. */ devres_release_all(dev); kfree(dev->dma_range_map); if (dev->release) dev->release(dev); else if (dev->type && dev->type->release) dev->type->release(dev); else if (dev->class && dev->class->dev_release) dev->class->dev_release(dev); else WARN(1, KERN_ERR "Device '%s' does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", dev_name(dev)); kfree(p); } static const void *device_namespace(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); const void *ns = NULL; if (dev->class && dev->class->ns_type) ns = dev->class->namespace(dev); return ns; } static void device_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) { struct device *dev = kobj_to_dev(kobj); if (dev->class && dev->class->get_ownership) dev->class->get_ownership(dev, uid, gid); } static struct kobj_type device_ktype = { .release = device_release, .sysfs_ops = &dev_sysfs_ops, .namespace = device_namespace, .get_ownership = device_get_ownership, }; static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) { struct kobj_type *ktype = get_ktype(kobj); if (ktype == &device_ktype) { struct device *dev = kobj_to_dev(kobj); if (dev->bus) return 1; if (dev->class) return 1; } return 0; } static const char *dev_uevent_name(struct kset *kset, struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); if (dev->bus) return dev->bus->name; if (dev->class) return dev->class->name; return NULL; } static int dev_uevent(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env) { struct device *dev = kobj_to_dev(kobj); int retval = 0; /* add device node properties if present */ if (MAJOR(dev->devt)) { const char *tmp; const char *name; umode_t mode = 0; kuid_t uid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID; add_uevent_var(env, "MAJOR=%u", MAJOR(dev->devt)); add_uevent_var(env, "MINOR=%u", MINOR(dev->devt)); name = device_get_devnode(dev, &mode, &uid, &gid, &tmp); if (name) { add_uevent_var(env, "DEVNAME=%s", name); if (mode) add_uevent_var(env, "DEVMODE=%#o", mode & 0777); if (!uid_eq(uid, GLOBAL_ROOT_UID)) add_uevent_var(env, "DEVUID=%u", from_kuid(&init_user_ns, uid)); if (!gid_eq(gid, GLOBAL_ROOT_GID)) add_uevent_var(env, "DEVGID=%u", from_kgid(&init_user_ns, gid)); kfree(tmp); } } if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); if (dev->driver) add_uevent_var(env, "DRIVER=%s", dev->driver->name); /* Add common DT information about the device */ of_device_uevent(dev, env); /* have the bus specific function add its stuff */ if (dev->bus && dev->bus->uevent) { retval = dev->bus->uevent(dev, env); if (retval) pr_debug("device: '%s': %s: bus uevent() returned %d\n", dev_name(dev), __func__, retval); } /* have the class specific function add its stuff */ if (dev->class && dev->class->dev_uevent) { retval = dev->class->dev_uevent(dev, env); if (retval) pr_debug("device: '%s': %s: class uevent() " "returned %d\n", dev_name(dev), __func__, retval); } /* have the device type specific function add its stuff */ if (dev->type && dev->type->uevent) { retval = dev->type->uevent(dev, env); if (retval) pr_debug("device: '%s': %s: dev_type uevent() " "returned %d\n", dev_name(dev), __func__, retval); } return retval; } static const struct kset_uevent_ops device_uevent_ops = { .filter = dev_uevent_filter, .name = dev_uevent_name, .uevent = dev_uevent, }; static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, char *buf) { struct kobject *top_kobj; struct kset *kset; struct kobj_uevent_env *env = NULL; int i; int len = 0; int retval; /* search the kset, the device belongs to */ top_kobj = &dev->kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) goto out; kset = top_kobj->kset; if (!kset->uevent_ops || !kset->uevent_ops->uevent) goto out; /* respect filter */ if (kset->uevent_ops && kset->uevent_ops->filter) if (!kset->uevent_ops->filter(kset, &dev->kobj)) goto out; env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(kset, &dev->kobj, env); if (retval) goto out; /* copy keys to file */ for (i = 0; i < env->envp_idx; i++) len += sysfs_emit_at(buf, len, "%s\n", env->envp[i]); out: kfree(env); return len; } static ssize_t uevent_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int rc; rc = kobject_synth_uevent(&dev->kobj, buf, count); if (rc) { dev_err(dev, "uevent: failed to send synthetic uevent\n"); return rc; } return count; } static DEVICE_ATTR_RW(uevent); static ssize_t online_show(struct device *dev, struct device_attribute *attr, char *buf) { bool val; device_lock(dev); val = !dev->offline; device_unlock(dev); return sysfs_emit(buf, "%u\n", val); } static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { bool val; int ret; ret = strtobool(buf, &val); if (ret < 0) return ret; ret = lock_device_hotplug_sysfs(); if (ret) return ret; ret = val ? device_online(dev) : device_offline(dev); unlock_device_hotplug(); return ret < 0 ? ret : count; } static DEVICE_ATTR_RW(online); int device_add_groups(struct device *dev, const struct attribute_group **groups) { return sysfs_create_groups(&dev->kobj, groups); } EXPORT_SYMBOL_GPL(device_add_groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups) { sysfs_remove_groups(&dev->kobj, groups); } EXPORT_SYMBOL_GPL(device_remove_groups); union device_attr_group_devres { const struct attribute_group *group; const struct attribute_group **groups; }; static int devm_attr_group_match(struct device *dev, void *res, void *data) { return ((union device_attr_group_devres *)res)->group == data; } static void devm_attr_group_remove(struct device *dev, void *res) { union device_attr_group_devres *devres = res; const struct attribute_group *group = devres->group; dev_dbg(dev, "%s: removing group %p\n", __func__, group); sysfs_remove_group(&dev->kobj, group); } static void devm_attr_groups_remove(struct device *dev, void *res) { union device_attr_group_devres *devres = res; const struct attribute_group **groups = devres->groups; dev_dbg(dev, "%s: removing groups %p\n", __func__, groups); sysfs_remove_groups(&dev->kobj, groups); } /** * devm_device_add_group - given a device, create a managed attribute group * @dev: The device to create the group for * @grp: The attribute group to create * * This function creates a group for the first time. It will explicitly * warn and error if any of the attribute files being created already exist. * * Returns 0 on success or error code on failure. */ int devm_device_add_group(struct device *dev, const struct attribute_group *grp) { union device_attr_group_devres *devres; int error; devres = devres_alloc(devm_attr_group_remove, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; error = sysfs_create_group(&dev->kobj, grp); if (error) { devres_free(devres); return error; } devres->group = grp; devres_add(dev, devres); return 0; } EXPORT_SYMBOL_GPL(devm_device_add_group); /** * devm_device_remove_group: remove a managed group from a device * @dev: device to remove the group from * @grp: group to remove * * This function removes a group of attributes from a device. The attributes * previously have to have been created for this group, otherwise it will fail. */ void devm_device_remove_group(struct device *dev, const struct attribute_group *grp) { WARN_ON(devres_release(dev, devm_attr_group_remove, devm_attr_group_match, /* cast away const */ (void *)grp)); } EXPORT_SYMBOL_GPL(devm_device_remove_group); /** * devm_device_add_groups - create a bunch of managed attribute groups * @dev: The device to create the group for * @groups: The attribute groups to create, NULL terminated * * This function creates a bunch of managed attribute groups. If an error * occurs when creating a group, all previously created groups will be * removed, unwinding everything back to the original state when this * function was called. It will explicitly warn and error if any of the * attribute files being created already exist. * * Returns 0 on success or error code from sysfs_create_group on failure. */ int devm_device_add_groups(struct device *dev, const struct attribute_group **groups) { union device_attr_group_devres *devres; int error; devres = devres_alloc(devm_attr_groups_remove, sizeof(*devres), GFP_KERNEL); if (!devres) return -ENOMEM; error = sysfs_create_groups(&dev->kobj, groups); if (error) { devres_free(devres); return error; } devres->groups = groups; devres_add(dev, devres); return 0; } EXPORT_SYMBOL_GPL(devm_device_add_groups); /** * devm_device_remove_groups - remove a list of managed groups * * @dev: The device for the groups to be removed from * @groups: NULL terminated list of groups to be removed * * If groups is not NULL, remove the specified groups from the device. */ void devm_device_remove_groups(struct device *dev, const struct attribute_group **groups) { WARN_ON(devres_release(dev, devm_attr_groups_remove, devm_attr_group_match, /* cast away const */ (void *)groups)); } EXPORT_SYMBOL_GPL(devm_device_remove_groups); static int device_add_attrs(struct device *dev) { struct class *class = dev->class; const struct device_type *type = dev->type; int error; if (class) { error = device_add_groups(dev, class->dev_groups); if (error) return error; } if (type) { error = device_add_groups(dev, type->groups); if (error) goto err_remove_class_groups; } error = device_add_groups(dev, dev->groups); if (error) goto err_remove_type_groups; if (device_supports_offline(dev) && !dev->offline_disabled) { error = device_create_file(dev, &dev_attr_online); if (error) goto err_remove_dev_groups; } if (fw_devlink_flags && !fw_devlink_is_permissive() && dev->fwnode) { error = device_create_file(dev, &dev_attr_waiting_for_supplier); if (error) goto err_remove_dev_online; } return 0; err_remove_dev_online: device_remove_file(dev, &dev_attr_online); err_remove_dev_groups: device_remove_groups(dev, dev->groups); err_remove_type_groups: if (type) device_remove_groups(dev, type->groups); err_remove_class_groups: if (class) device_remove_groups(dev, class->dev_groups); return error; } static void device_remove_attrs(struct device *dev) { struct class *class = dev->class; const struct device_type *type = dev->type; device_remove_file(dev, &dev_attr_waiting_for_supplier); device_remove_file(dev, &dev_attr_online); device_remove_groups(dev, dev->groups); if (type) device_remove_groups(dev, type->groups); if (class) device_remove_groups(dev, class->dev_groups); } static ssize_t dev_show(struct device *dev, struct device_attribute *attr, char *buf) { return print_dev_t(buf, dev->devt); } static DEVICE_ATTR_RO(dev); /* /sys/devices/ */ struct kset *devices_kset; /** * devices_kset_move_before - Move device in the devices_kset's list. * @deva: Device to move. * @devb: Device @deva should come before. */ static void devices_kset_move_before(struct device *deva, struct device *devb) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s before %s\n", dev_name(deva), dev_name(devb)); spin_lock(&devices_kset->list_lock); list_move_tail(&deva->kobj.entry, &devb->kobj.entry); spin_unlock(&devices_kset->list_lock); } /** * devices_kset_move_after - Move device in the devices_kset's list. * @deva: Device to move * @devb: Device @deva should come after. */ static void devices_kset_move_after(struct device *deva, struct device *devb) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s after %s\n", dev_name(deva), dev_name(devb)); spin_lock(&devices_kset->list_lock); list_move(&deva->kobj.entry, &devb->kobj.entry); spin_unlock(&devices_kset->list_lock); } /** * devices_kset_move_last - move the device to the end of devices_kset's list. * @dev: device to move */ void devices_kset_move_last(struct device *dev) { if (!devices_kset) return; pr_debug("devices_kset: Moving %s to end of list\n", dev_name(dev)); spin_lock(&devices_kset->list_lock); list_move_tail(&dev->kobj.entry, &devices_kset->list); spin_unlock(&devices_kset->list_lock); } /** * device_create_file - create sysfs attribute file for device. * @dev: device. * @attr: device attribute descriptor. */ int device_create_file(struct device *dev, const struct device_attribute *attr) { int error = 0; if (dev) { WARN(((attr->attr.mode & S_IWUGO) && !attr->store), "Attribute %s: write permission without 'store'\n", attr->attr.name); WARN(((attr->attr.mode & S_IRUGO) && !attr->show), "Attribute %s: read permission without 'show'\n", attr->attr.name); error = sysfs_create_file(&dev->kobj, &attr->attr); } return error; } EXPORT_SYMBOL_GPL(device_create_file); /** * device_remove_file - remove sysfs attribute file. * @dev: device. * @attr: device attribute descriptor. */ void device_remove_file(struct device *dev, const struct device_attribute *attr) { if (dev) sysfs_remove_file(&dev->kobj, &attr->attr); } EXPORT_SYMBOL_GPL(device_remove_file); /** * device_remove_file_self - remove sysfs attribute file from its own method. * @dev: device. * @attr: device attribute descriptor. * * See kernfs_remove_self() for details. */ bool device_remove_file_self(struct device *dev, const struct device_attribute *attr) { if (dev) return sysfs_remove_file_self(&dev->kobj, &attr->attr); else return false; } EXPORT_SYMBOL_GPL(device_remove_file_self); /** * device_create_bin_file - create sysfs binary attribute file for device. * @dev: device. * @attr: device binary attribute descriptor. */ int device_create_bin_file(struct device *dev, const struct bin_attribute *attr) { int error = -EINVAL; if (dev) error = sysfs_create_bin_file(&dev->kobj, attr); return error; } EXPORT_SYMBOL_GPL(device_create_bin_file); /** * device_remove_bin_file - remove sysfs binary attribute file * @dev: device. * @attr: device binary attribute descriptor. */ void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr) { if (dev) sysfs_remove_bin_file(&dev->kobj, attr); } EXPORT_SYMBOL_GPL(device_remove_bin_file); static void klist_children_get(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); struct device *dev = p->device; get_device(dev); } static void klist_children_put(struct klist_node *n) { struct device_private *p = to_device_private_parent(n); struct device *dev = p->device; put_device(dev); } /** * device_initialize - init device structure. * @dev: device. * * This prepares the device for use by other layers by initializing * its fields. * It is the first half of device_register(), if called by * that function, though it can also be called separately, so one * may use @dev's fields. In particular, get_device()/put_device() * may be used for reference counting of @dev after calling this * function. * * All fields in @dev must be initialized by the caller to 0, except * for those explicitly set to some other value. The simplest * approach is to use kzalloc() to allocate the structure containing * @dev. * * NOTE: Use put_device() to give up your reference instead of freeing * @dev directly once you have called this function. */ void device_initialize(struct device *dev) { dev->kobj.kset = devices_kset; kobject_init(&dev->kobj, &device_ktype); INIT_LIST_HEAD(&dev->dma_pools); mutex_init(&dev->mutex); #ifdef CONFIG_PROVE_LOCKING mutex_init(&dev->lockdep_mutex); #endif lockdep_set_novalidate_class(&dev->mutex); spin_lock_init(&dev->devres_lock); INIT_LIST_HEAD(&dev->devres_head); device_pm_init(dev); set_dev_node(dev, -1); #ifdef CONFIG_GENERIC_MSI_IRQ INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); INIT_LIST_HEAD(&dev->links.defer_sync); dev->links.status = DL_DEV_NO_DRIVER; } EXPORT_SYMBOL_GPL(device_initialize); struct kobject *virtual_device_parent(struct device *dev) { static struct kobject *virtual_dir = NULL; if (!virtual_dir) virtual_dir = kobject_create_and_add("virtual", &devices_kset->kobj); return virtual_dir; } struct class_dir { struct kobject kobj; struct class *class; }; #define to_class_dir(obj) container_of(obj, struct class_dir, kobj) static void class_dir_release(struct kobject *kobj) { struct class_dir *dir = to_class_dir(kobj); kfree(dir); } static const struct kobj_ns_type_operations *class_dir_child_ns_type(struct kobject *kobj) { struct class_dir *dir = to_class_dir(kobj); return dir->class->ns_type; } static struct kobj_type class_dir_ktype = { .release = class_dir_release, .sysfs_ops = &kobj_sysfs_ops, .child_ns_type = class_dir_child_ns_type }; static struct kobject * class_dir_create_and_add(struct class *class, struct kobject *parent_kobj) { struct class_dir *dir; int retval; dir = kzalloc(sizeof(*dir), GFP_KERNEL); if (!dir) return ERR_PTR(-ENOMEM); dir->class = class; kobject_init(&dir->kobj, &class_dir_ktype); dir->kobj.kset = &class->p->glue_dirs; retval = kobject_add(&dir->kobj, parent_kobj, "%s", class->name); if (retval < 0) { kobject_put(&dir->kobj); return ERR_PTR(retval); } return &dir->kobj; } static DEFINE_MUTEX(gdp_mutex); static struct kobject *get_device_parent(struct device *dev, struct device *parent) { if (dev->class) { struct kobject *kobj = NULL; struct kobject *parent_kobj; struct kobject *k; #ifdef CONFIG_BLOCK /* block disks show up in /sys/block */ if (sysfs_deprecated && dev->class == &block_class) { if (parent && parent->class == &block_class) return &parent->kobj; return &block_class.p->subsys.kobj; } #endif /* * If we have no parent, we live in "virtual". * Class-devices with a non class-device as parent, live * in a "glue" directory to prevent namespace collisions. */ if (parent == NULL) parent_kobj = virtual_device_parent(dev); else if (parent->class && !dev->class->ns_type) return &parent->kobj; else parent_kobj = &parent->kobj; mutex_lock(&gdp_mutex); /* find our class-directory at the parent and reference it */ spin_lock(&dev->class->p->glue_dirs.list_lock); list_for_each_entry(k, &dev->class->p->glue_dirs.list, entry) if (k->parent == parent_kobj) { kobj = kobject_get(k); break; } spin_unlock(&dev->class->p->glue_dirs.list_lock); if (kobj) { mutex_unlock(&gdp_mutex); return kobj; } /* or create a new class-directory at the parent device */ k = class_dir_create_and_add(dev->class, parent_kobj); /* do not emit an uevent for this simple "glue" directory */ mutex_unlock(&gdp_mutex); return k; } /* subsystems can specify a default root directory for their devices */ if (!parent && dev->bus && dev->bus->dev_root) return &dev->bus->dev_root->kobj; if (parent) return &parent->kobj; return NULL; } static inline bool live_in_glue_dir(struct kobject *kobj, struct device *dev) { if (!kobj || !dev->class || kobj->kset != &dev->class->p->glue_dirs) return false; return true; } static inline struct kobject *get_glue_dir(struct device *dev) { return dev->kobj.parent; } /* * make sure cleaning up dir as the last step, we need to make * sure .release handler of kobject is run with holding the * global lock */ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir) { unsigned int ref; /* see if we live in a "glue" directory */ if (!live_in_glue_dir(glue_dir, dev)) return; mutex_lock(&gdp_mutex); /** * There is a race condition between removing glue directory * and adding a new device under the glue directory. * * CPU1: CPU2: * * device_add() * get_device_parent() * class_dir_create_and_add() * kobject_add_internal() * create_dir() // create glue_dir * * device_add() * get_device_parent() * kobject_get() // get glue_dir * * device_del() * cleanup_glue_dir() * kobject_del(glue_dir) * * kobject_add() * kobject_add_internal() * create_dir() // in glue_dir * sysfs_create_dir_ns() * kernfs_create_dir_ns(sd) * * sysfs_remove_dir() // glue_dir->sd=NULL * sysfs_put() // free glue_dir->sd * * // sd is freed * kernfs_new_node(sd) * kernfs_get(glue_dir) * kernfs_add_one() * kernfs_put() * * Before CPU1 remove last child device under glue dir, if CPU2 add * a new device under glue dir, the glue_dir kobject reference count * will be increase to 2 in kobject_get(k). And CPU2 has been called * kernfs_create_dir_ns(). Meanwhile, CPU1 call sysfs_remove_dir() * and sysfs_put(). This result in glue_dir->sd is freed. * * Then the CPU2 will see a stale "empty" but still potentially used * glue dir around in kernfs_new_node(). * * In order to avoid this happening, we also should make sure that * kernfs_node for glue_dir is released in CPU1 only when refcount * for glue_dir kobj is 1. */ ref = kref_read(&glue_dir->kref); if (!kobject_has_children(glue_dir) && !--ref) kobject_del(glue_dir); kobject_put(glue_dir); mutex_unlock(&gdp_mutex); } static int device_add_class_symlinks(struct device *dev) { struct device_node *of_node = dev_of_node(dev); int error; if (of_node) { error = sysfs_create_link(&dev->kobj, of_node_kobj(of_node), "of_node"); if (error) dev_warn(dev, "Error %d creating of_node link\n",error); /* An error here doesn't warrant bringing down the device */ } if (!dev->class) return 0; error = sysfs_create_link(&dev->kobj, &dev->class->p->subsys.kobj, "subsystem"); if (error) goto out_devnode; if (dev->parent && device_is_not_partition(dev)) { error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device"); if (error) goto out_subsys; } #ifdef CONFIG_BLOCK /* /sys/block has directories and does not need symlinks */ if (sysfs_deprecated && dev->class == &block_class) return 0; #endif /* link in the class directory pointing to the device */ error = sysfs_create_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); if (error) goto out_device; return 0; out_device: sysfs_remove_link(&dev->kobj, "device"); out_subsys: sysfs_remove_link(&dev->kobj, "subsystem"); out_devnode: sysfs_remove_link(&dev->kobj, "of_node"); return error; } static void device_remove_class_symlinks(struct device *dev) { if (dev_of_node(dev)) sysfs_remove_link(&dev->kobj, "of_node"); if (!dev->class) return; if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(&dev->kobj, "subsystem"); #ifdef CONFIG_BLOCK if (sysfs_deprecated && dev->class == &block_class) return; #endif sysfs_delete_link(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev)); } /** * dev_set_name - set a device name * @dev: device * @fmt: format string for the device's name */ int dev_set_name(struct device *dev, const char *fmt, ...) { va_list vargs; int err; va_start(vargs, fmt); err = kobject_set_name_vargs(&dev->kobj, fmt, vargs); va_end(vargs); return err; } EXPORT_SYMBOL_GPL(dev_set_name); /** * device_to_dev_kobj - select a /sys/dev/ directory for the device * @dev: device * * By default we select char/ for new entries. Setting class->dev_obj * to NULL prevents an entry from being created. class->dev_kobj must * be set (or cleared) before any devices are registered to the class * otherwise device_create_sys_dev_entry() and * device_remove_sys_dev_entry() will disagree about the presence of * the link. */ static struct kobject *device_to_dev_kobj(struct device *dev) { struct kobject *kobj; if (dev->class) kobj = dev->class->dev_kobj; else kobj = sysfs_dev_char_kobj; return kobj; } static int device_create_sys_dev_entry(struct device *dev) { struct kobject *kobj = device_to_dev_kobj(dev); int error = 0; char devt_str[15]; if (kobj) { format_dev_t(devt_str, dev->devt); error = sysfs_create_link(kobj, &dev->kobj, devt_str); } return error; } static void device_remove_sys_dev_entry(struct device *dev) { struct kobject *kobj = device_to_dev_kobj(dev); char devt_str[15]; if (kobj) { format_dev_t(devt_str, dev->devt); sysfs_remove_link(kobj, devt_str); } } static int device_private_init(struct device *dev) { dev->p = kzalloc(sizeof(*dev->p), GFP_KERNEL); if (!dev->p) return -ENOMEM; dev->p->device = dev; klist_init(&dev->p->klist_children, klist_children_get, klist_children_put); INIT_LIST_HEAD(&dev->p->deferred_probe); return 0; } /** * device_add - add device to device hierarchy. * @dev: device. * * This is part 2 of device_register(), though may be called * separately _iff_ device_initialize() has been called separately. * * This adds @dev to the kobject hierarchy via kobject_add(), adds it * to the global and sibling lists for the device, then * adds it to the other relevant subsystems of the driver model. * * Do not call this routine or device_register() more than once for * any device structure. The driver model core is not designed to work * with devices that get unregistered and then spring back to life. * (Among other things, it's very hard to guarantee that all references * to the previous incarnation of @dev have been dropped.) Allocate * and register a fresh new struct device instead. * * NOTE: _Never_ directly free @dev after calling this function, even * if it returned an error! Always use put_device() to give up your * reference instead. * * Rule of thumb is: if device_add() succeeds, you should call * device_del() when you want to get rid of it. If device_add() has * *not* succeeded, use *only* put_device() to drop the reference * count. */ int device_add(struct device *dev) { struct device *parent; struct kobject *kobj; struct class_interface *class_intf; int error = -EINVAL; struct kobject *glue_dir = NULL; dev = get_device(dev); if (!dev) goto done; if (!dev->p) { error = device_private_init(dev); if (error) goto done; } /* * for statically allocated devices, which should all be converted * some day, we need to initialize the name. We prevent reading back * the name, and force the use of dev_name() */ if (dev->init_name) { dev_set_name(dev, "%s", dev->init_name); dev->init_name = NULL; } /* subsystems can specify simple device enumeration */ if (!dev_name(dev) && dev->bus && dev->bus->dev_name) dev_set_name(dev, "%s%u", dev->bus->dev_name, dev->id); if (!dev_name(dev)) { error = -EINVAL; goto name_error; } pr_debug("device: '%s': %s\n", dev_name(dev), __func__); parent = get_device(dev->parent); kobj = get_device_parent(dev, parent); if (IS_ERR(kobj)) { error = PTR_ERR(kobj); goto parent_error; } if (kobj) dev->kobj.parent = kobj; /* use parent numa_node */ if (parent && (dev_to_node(dev) == NUMA_NO_NODE)) set_dev_node(dev, dev_to_node(parent)); /* first, register with generic layer. */ /* we require the name to be set before, and pass NULL */ error = kobject_add(&dev->kobj, dev->kobj.parent, NULL); if (error) { glue_dir = get_glue_dir(dev); goto Error; } /* notify platform of device entry */ error = device_platform_notify(dev, KOBJ_ADD); if (error) goto platform_error; error = device_create_file(dev, &dev_attr_uevent); if (error) goto attrError; error = device_add_class_symlinks(dev); if (error) goto SymlinkError; error = device_add_attrs(dev); if (error) goto AttrsError; error = bus_add_device(dev); if (error) goto BusError; error = dpm_sysfs_add(dev); if (error) goto DPMError; device_pm_add(dev); if (MAJOR(dev->devt)) { error = device_create_file(dev, &dev_attr_dev); if (error) goto DevAttrError; error = device_create_sys_dev_entry(dev); if (error) goto SysEntryError; devtmpfs_create_node(dev); } /* Notify clients of device addition. This call must come * after dpm_sysfs_add() and before kobject_uevent(). */ if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_ADD_DEVICE, dev); kobject_uevent(&dev->kobj, KOBJ_ADD); /* * Check if any of the other devices (consumers) have been waiting for * this device (supplier) to be added so that they can create a device * link to it. * * This needs to happen after device_pm_add() because device_link_add() * requires the supplier be registered before it's called. * * But this also needs to happen before bus_probe_device() to make sure * waiting consumers can link to it before the driver is bound to the * device and the driver sync_state callback is called for this device. */ if (dev->fwnode && !dev->fwnode->dev) { dev->fwnode->dev = dev; fw_devlink_link_device(dev); } bus_probe_device(dev); if (parent) klist_add_tail(&dev->p->knode_parent, &parent->p->klist_children); if (dev->class) { mutex_lock(&dev->class->p->mutex); /* tie the class to the device */ klist_add_tail(&dev->p->knode_class, &dev->class->p->klist_devices); /* notify any interfaces that the device is here */ list_for_each_entry(class_intf, &dev->class->p->interfaces, node) if (class_intf->add_dev) class_intf->add_dev(dev, class_intf); mutex_unlock(&dev->class->p->mutex); } done: put_device(dev); return error; SysEntryError: if (MAJOR(dev->devt)) device_remove_file(dev, &dev_attr_dev); DevAttrError: device_pm_remove(dev); dpm_sysfs_remove(dev); DPMError: bus_remove_device(dev); BusError: device_remove_attrs(dev); AttrsError: device_remove_class_symlinks(dev); SymlinkError: device_remove_file(dev, &dev_attr_uevent); attrError: device_platform_notify(dev, KOBJ_REMOVE); platform_error: kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); Error: cleanup_glue_dir(dev, glue_dir); parent_error: put_device(parent); name_error: kfree(dev->p); dev->p = NULL; goto done; } EXPORT_SYMBOL_GPL(device_add); /** * device_register - register a device with the system. * @dev: pointer to the device structure * * This happens in two clean steps - initialize the device * and add it to the system. The two steps can be called * separately, but this is the easiest and most common. * I.e. you should only call the two helpers separately if * have a clearly defined need to use and refcount the device * before it is added to the hierarchy. * * For more information, see the kerneldoc for device_initialize() * and device_add(). * * NOTE: _Never_ directly free @dev after calling this function, even * if it returned an error! Always use put_device() to give up the * reference initialized in this function instead. */ int device_register(struct device *dev) { device_initialize(dev); return device_add(dev); } EXPORT_SYMBOL_GPL(device_register); /** * get_device - increment reference count for device. * @dev: device. * * This simply forwards the call to kobject_get(), though * we do take care to provide for the case that we get a NULL * pointer passed in. */ struct device *get_device(struct device *dev) { return dev ? kobj_to_dev(kobject_get(&dev->kobj)) : NULL; } EXPORT_SYMBOL_GPL(get_device); /** * put_device - decrement reference count. * @dev: device in question. */ void put_device(struct device *dev) { /* might_sleep(); */ if (dev) kobject_put(&dev->kobj); } EXPORT_SYMBOL_GPL(put_device); bool kill_device(struct device *dev) { /* * Require the device lock and set the "dead" flag to guarantee that * the update behavior is consistent with the other bitfields near * it and that we cannot have an asynchronous probe routine trying * to run while we are tearing out the bus/class/sysfs from * underneath the device. */ lockdep_assert_held(&dev->mutex); if (dev->p->dead) return false; dev->p->dead = true; return true; } EXPORT_SYMBOL_GPL(kill_device); /** * device_del - delete device from system. * @dev: device. * * This is the first part of the device unregistration * sequence. This removes the device from the lists we control * from here, has it removed from the other driver model * subsystems it was added to in device_add(), and removes it * from the kobject hierarchy. * * NOTE: this should be called manually _iff_ device_add() was * also called manually. */ void device_del(struct device *dev) { struct device *parent = dev->parent; struct kobject *glue_dir = NULL; struct class_interface *class_intf; unsigned int noio_flag; device_lock(dev); kill_device(dev); device_unlock(dev); if (dev->fwnode && dev->fwnode->dev == dev) dev->fwnode->dev = NULL; /* Notify clients of device removal. This call must come * before dpm_sysfs_remove(). */ noio_flag = memalloc_noio_save(); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_DEL_DEVICE, dev); dpm_sysfs_remove(dev); if (parent) klist_del(&dev->p->knode_parent); if (MAJOR(dev->devt)) { devtmpfs_delete_node(dev); device_remove_sys_dev_entry(dev); device_remove_file(dev, &dev_attr_dev); } if (dev->class) { device_remove_class_symlinks(dev); mutex_lock(&dev->class->p->mutex); /* notify any interfaces that the device is now gone */ list_for_each_entry(class_intf, &dev->class->p->interfaces, node) if (class_intf->remove_dev) class_intf->remove_dev(dev, class_intf); /* remove the device from the class list */ klist_del(&dev->p->knode_class); mutex_unlock(&dev->class->p->mutex); } device_remove_file(dev, &dev_attr_uevent); device_remove_attrs(dev); bus_remove_device(dev); device_pm_remove(dev); driver_deferred_probe_del(dev); device_platform_notify(dev, KOBJ_REMOVE); device_remove_properties(dev); device_links_purge(dev); if (dev->bus) blocking_notifier_call_chain(&dev->bus->p->bus_notifier, BUS_NOTIFY_REMOVED_DEVICE, dev); kobject_uevent(&dev->kobj, KOBJ_REMOVE); glue_dir = get_glue_dir(dev); kobject_del(&dev->kobj); cleanup_glue_dir(dev, glue_dir); memalloc_noio_restore(noio_flag); put_device(parent); } EXPORT_SYMBOL_GPL(device_del); /** * device_unregister - unregister device from system. * @dev: device going away. * * We do this in two parts, like we do device_register(). First, * we remove it from all the subsystems with device_del(), then * we decrement the reference count via put_device(). If that * is the final reference count, the device will be cleaned up * via device_release() above. Otherwise, the structure will * stick around until the final reference to the device is dropped. */ void device_unregister(struct device *dev) { pr_debug("device: '%s': %s\n", dev_name(dev), __func__); device_del(dev); put_device(dev); } EXPORT_SYMBOL_GPL(device_unregister); static struct device *prev_device(struct klist_iter *i) { struct klist_node *n = klist_prev(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; } static struct device *next_device(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct device *dev = NULL; struct device_private *p; if (n) { p = to_device_private_parent(n); dev = p->device; } return dev; } /** * device_get_devnode - path of device node file * @dev: device * @mode: returned file access mode * @uid: returned file owner * @gid: returned file group * @tmp: possibly allocated string * * Return the relative path of a possible device node. * Non-default names may need to allocate a memory to compose * a name. This memory is returned in tmp and needs to be * freed by the caller. */ const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp) { char *s; *tmp = NULL; /* the device type may provide a specific name */ if (dev->type && dev->type->devnode) *tmp = dev->type->devnode(dev, mode, uid, gid); if (*tmp) return *tmp; /* the class may provide a specific name */ if (dev->class && dev->class->devnode) *tmp = dev->class->devnode(dev, mode); if (*tmp) return *tmp; /* return name without allocation, tmp == NULL */ if (strchr(dev_name(dev), '!') == NULL) return dev_name(dev); /* replace '!' in the name with '/' */ s = kstrdup(dev_name(dev), GFP_KERNEL); if (!s) return NULL; strreplace(s, '!', '/'); return *tmp = s; } /** * device_for_each_child - device child iterator. * @parent: parent struct device. * @fn: function to be called for each device. * @data: data for the callback. * * Iterate over @parent's child devices, and call @fn for each, * passing it @data. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. */ int device_for_each_child(struct device *parent, void *data, int (*fn)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; int error = 0; if (!parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); while (!error && (child = next_device(&i))) error = fn(child, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(device_for_each_child); /** * device_for_each_child_reverse - device child iterator in reversed order. * @parent: parent struct device. * @fn: function to be called for each device. * @data: data for the callback. * * Iterate over @parent's child devices, and call @fn for each, * passing it @data. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. */ int device_for_each_child_reverse(struct device *parent, void *data, int (*fn)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; int error = 0; if (!parent->p) return 0; klist_iter_init(&parent->p->klist_children, &i); while ((child = prev_device(&i)) && !error) error = fn(child, data); klist_iter_exit(&i); return error; } EXPORT_SYMBOL_GPL(device_for_each_child_reverse); /** * device_find_child - device iterator for locating a particular device. * @parent: parent struct device * @match: Callback function to check device * @data: Data to pass to match function * * This is similar to the device_for_each_child() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero and a reference to the * current device can be obtained, this function will return to the caller * and not iterate over any more devices. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_child(struct device *parent, void *data, int (*match)(struct device *dev, void *data)) { struct klist_iter i; struct device *child; if (!parent) return NULL; klist_iter_init(&parent->p->klist_children, &i); while ((child = next_device(&i))) if (match(child, data) && get_device(child)) break; klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child); /** * device_find_child_by_name - device iterator for locating a child device. * @parent: parent struct device * @name: name of the child device * * This is similar to the device_find_child() function above, but it * returns a reference to a device that has the name @name. * * NOTE: you will need to drop the reference with put_device() after use. */ struct device *device_find_child_by_name(struct device *parent, const char *name) { struct klist_iter i; struct device *child; if (!parent) return NULL; klist_iter_init(&parent->p->klist_children, &i); while ((child = next_device(&i))) if (sysfs_streq(dev_name(child), name) && get_device(child)) break; klist_iter_exit(&i); return child; } EXPORT_SYMBOL_GPL(device_find_child_by_name); int __init devices_init(void) { devices_kset = kset_create_and_add("devices", &device_uevent_ops, NULL); if (!devices_kset) return -ENOMEM; dev_kobj = kobject_create_and_add("dev", NULL); if (!dev_kobj) goto dev_kobj_err; sysfs_dev_block_kobj = kobject_create_and_add("block", dev_kobj); if (!sysfs_dev_block_kobj) goto block_kobj_err; sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; return 0; char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: kobject_put(dev_kobj); dev_kobj_err: kset_unregister(devices_kset); return -ENOMEM; } static int device_check_offline(struct device *dev, void *not_used) { int ret; ret = device_for_each_child(dev, NULL, device_check_offline); if (ret) return ret; return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0; } /** * device_offline - Prepare the device for hot-removal. * @dev: Device to be put offline. * * Execute the device bus type's .offline() callback, if present, to prepare * the device for a subsequent hot-removal. If that succeeds, the device must * not be used until either it is removed or its bus type's .online() callback * is executed. * * Call under device_hotplug_lock. */ int device_offline(struct device *dev) { int ret; if (dev->offline_disabled) return -EPERM; ret = device_for_each_child(dev, NULL, device_check_offline); if (ret) return ret; device_lock(dev); if (device_supports_offline(dev)) { if (dev->offline) { ret = 1; } else { ret = dev->bus->offline(dev); if (!ret) { kobject_uevent(&dev->kobj, KOBJ_OFFLINE); dev->offline = true; } } } device_unlock(dev); return ret; } /** * device_online - Put the device back online after successful device_offline(). * @dev: Device to be put back online. * * If device_offline() has been successfully executed for @dev, but the device * has not been removed subsequently, execute its bus type's .online() callback * to indicate that the device can be used again. * * Call under device_hotplug_lock. */ int device_online(struct device *dev) { int ret = 0; device_lock(dev); if (device_supports_offline(dev)) { if (dev->offline) { ret = dev->bus->online(dev); if (!ret) { kobject_uevent(&dev->kobj, KOBJ_ONLINE); dev->offline = false; } } else { ret = 1; } } device_unlock(dev); return ret; } struct root_device { struct device dev; struct module *owner; }; static inline struct root_device *to_root_device(struct device *d) { return container_of(d, struct root_device, dev); } static void root_device_release(struct device *dev) { kfree(to_root_device(dev)); } /** * __root_device_register - allocate and register a root device * @name: root device name * @owner: owner module of the root device, usually THIS_MODULE * * This function allocates a root device and registers it * using device_register(). In order to free the returned * device, use root_device_unregister(). * * Root devices are dummy devices which allow other devices * to be grouped under /sys/devices. Use this function to * allocate a root device and then use it as the parent of * any device which should appear under /sys/devices/{name} * * The /sys/devices/{name} directory will also contain a * 'module' symlink which points to the @owner directory * in sysfs. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: You probably want to use root_device_register(). */ struct device *__root_device_register(const char *name, struct module *owner) { struct root_device *root; int err = -ENOMEM; root = kzalloc(sizeof(struct root_device), GFP_KERNEL); if (!root) return ERR_PTR(err); err = dev_set_name(&root->dev, "%s", name); if (err) { kfree(root); return ERR_PTR(err); } root->dev.release = root_device_release; err = device_register(&root->dev); if (err) { put_device(&root->dev); return ERR_PTR(err); } #ifdef CONFIG_MODULES /* gotta find a "cleaner" way to do this */ if (owner) { struct module_kobject *mk = &owner->mkobj; err = sysfs_create_link(&root->dev.kobj, &mk->kobj, "module"); if (err) { device_unregister(&root->dev); return ERR_PTR(err); } root->owner = owner; } #endif return &root->dev; } EXPORT_SYMBOL_GPL(__root_device_register); /** * root_device_unregister - unregister and free a root device * @dev: device going away * * This function unregisters and cleans up a device that was created by * root_device_register(). */ void root_device_unregister(struct device *dev) { struct root_device *root = to_root_device(dev); if (root->owner) sysfs_remove_link(&root->dev.kobj, "module"); device_unregister(dev); } EXPORT_SYMBOL_GPL(root_device_unregister); static void device_create_release(struct device *dev) { pr_debug("device: '%s': %s\n", dev_name(dev), __func__); kfree(dev); } static __printf(6, 0) struct device * device_create_groups_vargs(struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, va_list args) { struct device *dev = NULL; int retval = -ENODEV; if (class == NULL || IS_ERR(class)) goto error; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) { retval = -ENOMEM; goto error; } device_initialize(dev); dev->devt = devt; dev->class = class; dev->parent = parent; dev->groups = groups; dev->release = device_create_release; dev_set_drvdata(dev, drvdata); retval = kobject_set_name_vargs(&dev->kobj, fmt, args); if (retval) goto error; retval = device_add(dev); if (retval) goto error; return dev; error: put_device(dev); return ERR_PTR(retval); } /** * device_create - creates a device and registers it with sysfs * @class: pointer to the struct class that this device should be registered to * @parent: pointer to the parent struct device of this new device, if any * @devt: the dev_t for the char device to be added * @drvdata: the data to be added to the device for callbacks * @fmt: string for the device's name * * This function can be used by char device classes. A struct device * will be created in sysfs, registered to the specified class. * * A "dev" file will be created, showing the dev_t for the device, if * the dev_t is not 0,0. * If a pointer to a parent struct device is passed in, the newly created * struct device will be a child of that device in sysfs. * The pointer to the struct device will be returned from the call. * Any further sysfs files that might be required can be created using this * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: the struct class passed to this function must have previously * been created with a call to class_create(). */ struct device *device_create(struct class *class, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...) { va_list vargs; struct device *dev; va_start(vargs, fmt); dev = device_create_groups_vargs(class, parent, devt, drvdata, NULL, fmt, vargs); va_end(vargs); return dev; } EXPORT_SYMBOL_GPL(device_create); /** * device_create_with_groups - creates a device and registers it with sysfs * @class: pointer to the struct class that this device should be registered to * @parent: pointer to the parent struct device of this new device, if any * @devt: the dev_t for the char device to be added * @drvdata: the data to be added to the device for callbacks * @groups: NULL-terminated list of attribute groups to be created * @fmt: string for the device's name * * This function can be used by char device classes. A struct device * will be created in sysfs, registered to the specified class. * Additional attributes specified in the groups parameter will also * be created automatically. * * A "dev" file will be created, showing the dev_t for the device, if * the dev_t is not 0,0. * If a pointer to a parent struct device is passed in, the newly created * struct device will be a child of that device in sysfs. * The pointer to the struct device will be returned from the call. * Any further sysfs files that might be required can be created using this * pointer. * * Returns &struct device pointer on success, or ERR_PTR() on error. * * Note: the struct class passed to this function must have previously * been created with a call to class_create(). */ struct device *device_create_with_groups(struct class *class, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...) { va_list vargs; struct device *dev; va_start(vargs, fmt); dev = device_create_groups_vargs(class, parent, devt, drvdata, groups, fmt, vargs); va_end(vargs); return dev; } EXPORT_SYMBOL_GPL(device_create_with_groups); /** * device_destroy - removes a device that was created with device_create() * @class: pointer to the struct class that this device was registered with * @devt: the dev_t of the device that was previously registered * * This call unregisters and cleans up a device that was created with a * call to device_create(). */ void device_destroy(struct class *class, dev_t devt) { struct device *dev; dev = class_find_device_by_devt(class, devt); if (dev) { put_device(dev); device_unregister(dev); } } EXPORT_SYMBOL_GPL(device_destroy); /** * device_rename - renames a device * @dev: the pointer to the struct device to be renamed * @new_name: the new name of the device * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of device_rename * on the same device to ensure that new_name is valid and * won't conflict with other devices. * * Note: Don't call this function. Currently, the networking layer calls this * function, but that will change. The following text from Kay Sievers offers * some insight: * * Renaming devices is racy at many levels, symlinks and other stuff are not * replaced atomically, and you get a "move" uevent, but it's not easy to * connect the event to the old and new device. Device nodes are not renamed at * all, there isn't even support for that in the kernel now. * * In the meantime, during renaming, your target name might be taken by another * driver, creating conflicts. Or the old name is taken directly after you * renamed it -- then you get events for the same DEVPATH, before you even see * the "move" event. It's just a mess, and nothing new should ever rely on * kernel device renaming. Besides that, it's not even implemented now for * other things than (driver-core wise very simple) network devices. * * We are currently about to change network renaming in udev to completely * disallow renaming of devices in the same namespace as the kernel uses, * because we can't solve the problems properly, that arise with swapping names * of multiple interfaces without races. Means, renaming of eth[0-9]* will only * be allowed to some other name than eth[0-9]*, for the aforementioned * reasons. * * Make up a "real" name in the driver before you register anything, or add * some other attributes for userspace to find the device, or use udev to add * symlinks -- but never rename kernel devices later, it's a complete mess. We * don't even want to get into that and try to implement the missing pieces in * the core. We really have other pieces to fix in the driver core mess. :) */ int device_rename(struct device *dev, const char *new_name) { struct kobject *kobj = &dev->kobj; char *old_device_name = NULL; int error; dev = get_device(dev); if (!dev) return -EINVAL; dev_dbg(dev, "renaming to %s\n", new_name); old_device_name = kstrdup(dev_name(dev), GFP_KERNEL); if (!old_device_name) { error = -ENOMEM; goto out; } if (dev->class) { error = sysfs_rename_link_ns(&dev->class->p->subsys.kobj, kobj, old_device_name, new_name, kobject_namespace(kobj)); if (error) goto out; } error = kobject_rename(kobj, new_name); if (error) goto out; out: put_device(dev); kfree(old_device_name); return error; } EXPORT_SYMBOL_GPL(device_rename); static int device_move_class_links(struct device *dev, struct device *old_parent, struct device *new_parent) { int error = 0; if (old_parent) sysfs_remove_link(&dev->kobj, "device"); if (new_parent) error = sysfs_create_link(&dev->kobj, &new_parent->kobj, "device"); return error; } /** * device_move - moves a device to a new parent * @dev: the pointer to the struct device to be moved * @new_parent: the new parent of the device (can be NULL) * @dpm_order: how to reorder the dpm_list */ int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order) { int error; struct device *old_parent; struct kobject *new_parent_kobj; dev = get_device(dev); if (!dev) return -EINVAL; device_pm_lock(); new_parent = get_device(new_parent); new_parent_kobj = get_device_parent(dev, new_parent); if (IS_ERR(new_parent_kobj)) { error = PTR_ERR(new_parent_kobj); put_device(new_parent); goto out; } pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev), __func__, new_parent ? dev_name(new_parent) : "<NULL>"); error = kobject_move(&dev->kobj, new_parent_kobj); if (error) { cleanup_glue_dir(dev, new_parent_kobj); put_device(new_parent); goto out; } old_parent = dev->parent; dev->parent = new_parent; if (old_parent) klist_remove(&dev->p->knode_parent); if (new_parent) { klist_add_tail(&dev->p->knode_parent, &new_parent->p->klist_children); set_dev_node(dev, dev_to_node(new_parent)); } if (dev->class) { error = device_move_class_links(dev, old_parent, new_parent); if (error) { /* We ignore errors on cleanup since we're hosed anyway... */ device_move_class_links(dev, new_parent, old_parent); if (!kobject_move(&dev->kobj, &old_parent->kobj)) { if (new_parent) klist_remove(&dev->p->knode_parent); dev->parent = old_parent; if (old_parent) { klist_add_tail(&dev->p->knode_parent, &old_parent->p->klist_children); set_dev_node(dev, dev_to_node(old_parent)); } } cleanup_glue_dir(dev, new_parent_kobj); put_device(new_parent); goto out; } } switch (dpm_order) { case DPM_ORDER_NONE: break; case DPM_ORDER_DEV_AFTER_PARENT: device_pm_move_after(dev, new_parent); devices_kset_move_after(dev, new_parent); break; case DPM_ORDER_PARENT_BEFORE_DEV: device_pm_move_before(new_parent, dev); devices_kset_move_before(new_parent, dev); break; case DPM_ORDER_DEV_LAST: device_pm_move_last(dev); devices_kset_move_last(dev); break; } put_device(old_parent); out: device_pm_unlock(); put_device(dev); return error; } EXPORT_SYMBOL_GPL(device_move); static int device_attrs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { struct kobject *kobj = &dev->kobj; struct class *class = dev->class; const struct device_type *type = dev->type; int error; if (class) { /* * Change the device groups of the device class for @dev to * @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, class->dev_groups, kuid, kgid); if (error) return error; } if (type) { /* * Change the device groups of the device type for @dev to * @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, type->groups, kuid, kgid); if (error) return error; } /* Change the device groups of @dev to @kuid/@kgid. */ error = sysfs_groups_change_owner(kobj, dev->groups, kuid, kgid); if (error) return error; if (device_supports_offline(dev) && !dev->offline_disabled) { /* Change online device attributes of @dev to @kuid/@kgid. */ error = sysfs_file_change_owner(kobj, dev_attr_online.attr.name, kuid, kgid); if (error) return error; } return 0; } /** * device_change_owner - change the owner of an existing device. * @dev: device. * @kuid: new owner's kuid * @kgid: new owner's kgid * * This changes the owner of @dev and its corresponding sysfs entries to * @kuid/@kgid. This function closely mirrors how @dev was added via driver * core. * * Returns 0 on success or error code on failure. */ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { int error; struct kobject *kobj = &dev->kobj; dev = get_device(dev); if (!dev) return -EINVAL; /* * Change the kobject and the default attributes and groups of the * ktype associated with it to @kuid/@kgid. */ error = sysfs_change_owner(kobj, kuid, kgid); if (error) goto out; /* * Change the uevent file for @dev to the new owner. The uevent file * was created in a separate step when @dev got added and we mirror * that step here. */ error = sysfs_file_change_owner(kobj, dev_attr_uevent.attr.name, kuid, kgid); if (error) goto out; /* * Change the device groups, the device groups associated with the * device class, and the groups associated with the device type of @dev * to @kuid/@kgid. */ error = device_attrs_change_owner(dev, kuid, kgid); if (error) goto out; error = dpm_sysfs_change_owner(dev, kuid, kgid); if (error) goto out; #ifdef CONFIG_BLOCK if (sysfs_deprecated && dev->class == &block_class) goto out; #endif /* * Change the owner of the symlink located in the class directory of * the device class associated with @dev which points to the actual * directory entry for @dev to @kuid/@kgid. This ensures that the * symlink shows the same permissions as its target. */ error = sysfs_link_change_owner(&dev->class->p->subsys.kobj, &dev->kobj, dev_name(dev), kuid, kgid); if (error) goto out; out: put_device(dev); return error; } EXPORT_SYMBOL_GPL(device_change_owner); /** * device_shutdown - call ->shutdown() on each device to shutdown. */ void device_shutdown(void) { struct device *dev, *parent; wait_for_device_probe(); device_block_probing(); cpufreq_suspend(); spin_lock(&devices_kset->list_lock); /* * Walk the devices list backward, shutting down each in turn. * Beware that device unplug events may also start pulling * devices offline, even as the system is shutting down. */ while (!list_empty(&devices_kset->list)) { dev = list_entry(devices_kset->list.prev, struct device, kobj.entry); /* * hold reference count of device's parent to * prevent it from being freed because parent's * lock is to be held */ parent = get_device(dev->parent); get_device(dev); /* * Make sure the device is off the kset list, in the * event that dev->*->shutdown() doesn't remove it. */ list_del_init(&dev->kobj.entry); spin_unlock(&devices_kset->list_lock); /* hold lock to avoid race with probe/release */ if (parent) device_lock(parent); device_lock(dev); /* Don't allow any more runtime suspends */ pm_runtime_get_noresume(dev); pm_runtime_barrier(dev); if (dev->class && dev->class->shutdown_pre) { if (initcall_debug) dev_info(dev, "shutdown_pre\n"); dev->class->shutdown_pre(dev); } if (dev->bus && dev->bus->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->bus->shutdown(dev); } else if (dev->driver && dev->driver->shutdown) { if (initcall_debug) dev_info(dev, "shutdown\n"); dev->driver->shutdown(dev); } device_unlock(dev); if (parent) device_unlock(parent); put_device(dev); put_device(parent); spin_lock(&devices_kset->list_lock); } spin_unlock(&devices_kset->list_lock); } /* * Device logging functions */ #ifdef CONFIG_PRINTK static void set_dev_info(const struct device *dev, struct dev_printk_info *dev_info) { const char *subsys; memset(dev_info, 0, sizeof(*dev_info)); if (dev->class) subsys = dev->class->name; else if (dev->bus) subsys = dev->bus->name; else return; strscpy(dev_info->subsystem, subsys, sizeof(dev_info->subsystem)); /* * Add device identifier DEVICE=: * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname */ if (MAJOR(dev->devt)) { char c; if (strcmp(subsys, "block") == 0) c = 'b'; else c = 'c'; snprintf(dev_info->device, sizeof(dev_info->device), "%c%u:%u", c, MAJOR(dev->devt), MINOR(dev->devt)); } else if (strcmp(subsys, "net") == 0) { struct net_device *net = to_net_dev(dev); snprintf(dev_info->device, sizeof(dev_info->device), "n%u", net->ifindex); } else { snprintf(dev_info->device, sizeof(dev_info->device), "+%s:%s", subsys, dev_name(dev)); } } int dev_vprintk_emit(int level, const struct device *dev, const char *fmt, va_list args) { struct dev_printk_info dev_info; set_dev_info(dev, &dev_info); return vprintk_emit(0, level, &dev_info, fmt, args); } EXPORT_SYMBOL(dev_vprintk_emit); int dev_printk_emit(int level, const struct device *dev, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = dev_vprintk_emit(level, dev, fmt, args); va_end(args); return r; } EXPORT_SYMBOL(dev_printk_emit); static void __dev_printk(const char *level, const struct device *dev, struct va_format *vaf) { if (dev) dev_printk_emit(level[1] - '0', dev, "%s %s: %pV", dev_driver_string(dev), dev_name(dev), vaf); else printk("%s(NULL device *): %pV", level, vaf); } void dev_printk(const char *level, const struct device *dev, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; __dev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(dev_printk); #define define_dev_printk_level(func, kern_level) \ void func(const struct device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __dev_printk(kern_level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_dev_printk_level(_dev_emerg, KERN_EMERG); define_dev_printk_level(_dev_alert, KERN_ALERT); define_dev_printk_level(_dev_crit, KERN_CRIT); define_dev_printk_level(_dev_err, KERN_ERR); define_dev_printk_level(_dev_warn, KERN_WARNING); define_dev_printk_level(_dev_notice, KERN_NOTICE); define_dev_printk_level(_dev_info, KERN_INFO); #endif /** * dev_err_probe - probe error check and log helper * @dev: the pointer to the struct device * @err: error value to test * @fmt: printf-style format string * @...: arguments as specified in the format string * * This helper implements common pattern present in probe functions for error * checking: print debug or error message depending if the error value is * -EPROBE_DEFER and propagate error upwards. * In case of -EPROBE_DEFER it sets also defer probe reason, which can be * checked later by reading devices_deferred debugfs attribute. * It replaces code sequence:: * * if (err != -EPROBE_DEFER) * dev_err(dev, ...); * else * dev_dbg(dev, ...); * return err; * * with:: * * return dev_err_probe(dev, err, ...); * * Returns @err. * */ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (err != -EPROBE_DEFER) { dev_err(dev, "error %pe: %pV", ERR_PTR(err), &vaf); } else { device_set_deferred_probe_reason(dev, &vaf); dev_dbg(dev, "error %pe: %pV", ERR_PTR(err), &vaf); } va_end(args); return err; } EXPORT_SYMBOL_GPL(dev_err_probe); static inline bool fwnode_is_primary(struct fwnode_handle *fwnode) { return fwnode && !IS_ERR(fwnode->secondary); } /** * set_primary_fwnode - Change the primary firmware node of a given device. * @dev: Device to handle. * @fwnode: New primary firmware node of the device. * * Set the device's firmware node pointer to @fwnode, but if a secondary * firmware node of the device is present, preserve it. */ void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { struct device *parent = dev->parent; struct fwnode_handle *fn = dev->fwnode; if (fwnode) { if (fwnode_is_primary(fn)) fn = fn->secondary; if (fn) { WARN_ON(fwnode->secondary); fwnode->secondary = fn; } dev->fwnode = fwnode; } else { if (fwnode_is_primary(fn)) { dev->fwnode = fn->secondary; if (!(parent && fn == parent->fwnode)) fn->secondary = NULL; } else { dev->fwnode = NULL; } } } EXPORT_SYMBOL_GPL(set_primary_fwnode); /** * set_secondary_fwnode - Change the secondary firmware node of a given device. * @dev: Device to handle. * @fwnode: New secondary firmware node of the device. * * If a primary firmware node of the device is present, set its secondary * pointer to @fwnode. Otherwise, set the device's firmware node pointer to * @fwnode. */ void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode) { if (fwnode) fwnode->secondary = ERR_PTR(-ENODEV); if (fwnode_is_primary(dev->fwnode)) dev->fwnode->secondary = fwnode; else dev->fwnode = fwnode; } EXPORT_SYMBOL_GPL(set_secondary_fwnode); /** * device_set_of_node_from_dev - reuse device-tree node of another device * @dev: device whose device-tree node is being set * @dev2: device whose device-tree node is being reused * * Takes another reference to the new device-tree node after first dropping * any reference held to the old node. */ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) { of_node_put(dev->of_node); dev->of_node = of_node_get(dev2->of_node); dev->of_node_reused = true; } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); int device_match_name(struct device *dev, const void *name) { return sysfs_streq(dev_name(dev), name); } EXPORT_SYMBOL_GPL(device_match_name); int device_match_of_node(struct device *dev, const void *np) { return dev->of_node == np; } EXPORT_SYMBOL_GPL(device_match_of_node); int device_match_fwnode(struct device *dev, const void *fwnode) { return dev_fwnode(dev) == fwnode; } EXPORT_SYMBOL_GPL(device_match_fwnode); int device_match_devt(struct device *dev, const void *pdevt) { return dev->devt == *(dev_t *)pdevt; } EXPORT_SYMBOL_GPL(device_match_devt); int device_match_acpi_dev(struct device *dev, const void *adev) { return ACPI_COMPANION(dev) == adev; } EXPORT_SYMBOL(device_match_acpi_dev); int device_match_any(struct device *dev, const void *unused) { return 1; } EXPORT_SYMBOL_GPL(device_match_any); |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Point-to-Point Tunneling Protocol for Linux * * Authors: Dmitry Kozlov <xeb@mail.ru> */ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/ppp_channel.h> #include <linux/ppp_defs.h> #include <linux/if_pppox.h> #include <linux/ppp-ioctl.h> #include <linux/notifier.h> #include <linux/file.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <net/sock.h> #include <net/protocol.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/gre.h> #include <net/pptp.h> #include <linux/uaccess.h> #define PPTP_DRIVER_VERSION "0.8.5" #define MAX_CALLID 65535 static DECLARE_BITMAP(callid_bitmap, MAX_CALLID + 1); static struct pppox_sock __rcu **callid_sock; static DEFINE_SPINLOCK(chan_lock); static struct proto pptp_sk_proto __read_mostly; static const struct ppp_channel_ops pptp_chan_ops; static const struct proto_ops pptp_ops; static struct pppox_sock *lookup_chan(u16 call_id, __be32 s_addr) { struct pppox_sock *sock; struct pptp_opt *opt; rcu_read_lock(); sock = rcu_dereference(callid_sock[call_id]); if (sock) { opt = &sock->proto.pptp; if (opt->dst_addr.sin_addr.s_addr != s_addr) sock = NULL; else sock_hold(sk_pppox(sock)); } rcu_read_unlock(); return sock; } static int lookup_chan_dst(u16 call_id, __be32 d_addr) { struct pppox_sock *sock; struct pptp_opt *opt; int i; rcu_read_lock(); i = 1; for_each_set_bit_from(i, callid_bitmap, MAX_CALLID) { sock = rcu_dereference(callid_sock[i]); if (!sock) continue; opt = &sock->proto.pptp; if (opt->dst_addr.call_id == call_id && opt->dst_addr.sin_addr.s_addr == d_addr) break; } rcu_read_unlock(); return i < MAX_CALLID; } static int add_chan(struct pppox_sock *sock, struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } sa->call_id = call_id; } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; } sock->proto.pptp.src_addr = *sa; set_bit(sa->call_id, callid_bitmap); rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; out_err: spin_unlock(&chan_lock); return -1; } static void del_chan(struct pppox_sock *sock) { spin_lock(&chan_lock); clear_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); RCU_INIT_POINTER(callid_sock[sock->proto.pptp.src_addr.call_id], NULL); spin_unlock(&chan_lock); } static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) { struct sock *sk = (struct sock *) chan->private; struct pppox_sock *po = pppox_sk(sk); struct net *net = sock_net(sk); struct pptp_opt *opt = &po->proto.pptp; struct pptp_gre_header *hdr; unsigned int header_len = sizeof(*hdr); struct flowi4 fl4; int islcp; int len; unsigned char *data; __u32 seq_recv; struct rtable *rt; struct net_device *tdev; struct iphdr *iph; int max_headroom; if (sk_pppox(po)->sk_state & PPPOX_DEAD) goto tx_error; rt = ip_route_output_ports(net, &fl4, NULL, opt->dst_addr.sin_addr.s_addr, opt->src_addr.sin_addr.s_addr, 0, 0, IPPROTO_GRE, RT_TOS(0), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto tx_error; tdev = rt->dst.dev; max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph) + sizeof(*hdr) + 2; if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); goto tx_error; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } data = skb->data; islcp = ((data[0] << 8) + data[1]) == PPP_LCP && 1 <= data[2] && data[2] <= 7; /* compress protocol field */ if ((opt->ppp_flags & SC_COMP_PROT) && data[0] == 0 && !islcp) skb_pull(skb, 1); /* Put in the address/control bytes if necessary */ if ((opt->ppp_flags & SC_COMP_AC) == 0 || islcp) { data = skb_push(skb, 2); data[0] = PPP_ALLSTATIONS; data[1] = PPP_UI; } len = skb->len; seq_recv = opt->seq_recv; if (opt->ack_sent == seq_recv) header_len -= sizeof(hdr->ack); /* Push down and install GRE header */ skb_push(skb, header_len); hdr = (struct pptp_gre_header *)(skb->data); hdr->gre_hd.flags = GRE_KEY | GRE_VERSION_1 | GRE_SEQ; hdr->gre_hd.protocol = GRE_PROTO_PPP; hdr->call_id = htons(opt->dst_addr.call_id); hdr->seq = htonl(++opt->seq_sent); if (opt->ack_sent != seq_recv) { /* send ack with this message */ hdr->gre_hd.flags |= GRE_ACK; hdr->ack = htonl(seq_recv); opt->ack_sent = seq_recv; } hdr->payload_len = htons(len); /* Push down and install the IP header. */ skb_reset_transport_header(skb); skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; if (ip_dont_fragment(sk, &rt->dst)) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->protocol = IPPROTO_GRE; iph->tos = 0; iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ip4_dst_hoplimit(&rt->dst); iph->tot_len = htons(skb->len); skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); nf_reset_ct(skb); skb->ip_summed = CHECKSUM_NONE; ip_select_ident(net, skb, NULL); ip_send_check(iph); ip_local_out(net, skb->sk, skb); return 1; tx_error: kfree_skb(skb); return 1; } static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) { struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; int headersize, payload_len, seq; __u8 *payload; struct pptp_gre_header *header; if (!(sk->sk_state & PPPOX_CONNECTED)) { if (sock_queue_rcv_skb(sk, skb)) goto drop; return NET_RX_SUCCESS; } header = (struct pptp_gre_header *)(skb->data); headersize = sizeof(*header); /* test if acknowledgement present */ if (GRE_IS_ACK(header->gre_hd.flags)) { __u32 ack; if (!pskb_may_pull(skb, headersize)) goto drop; header = (struct pptp_gre_header *)(skb->data); /* ack in different place if S = 0 */ ack = GRE_IS_SEQ(header->gre_hd.flags) ? header->ack : header->seq; ack = ntohl(ack); if (ack > opt->ack_recv) opt->ack_recv = ack; /* also handle sequence number wrap-around */ if (WRAPPED(ack, opt->ack_recv)) opt->ack_recv = ack; } else { headersize -= sizeof(header->ack); } /* test if payload present */ if (!GRE_IS_SEQ(header->gre_hd.flags)) goto drop; payload_len = ntohs(header->payload_len); seq = ntohl(header->seq); /* check for incomplete packet (length smaller than expected) */ if (!pskb_may_pull(skb, headersize + payload_len)) goto drop; payload = skb->data + headersize; /* check for expected sequence number */ if (seq < opt->seq_recv + 1 || WRAPPED(opt->seq_recv, seq)) { if ((payload[0] == PPP_ALLSTATIONS) && (payload[1] == PPP_UI) && (PPP_PROTOCOL(payload) == PPP_LCP) && ((payload[4] == PPP_LCP_ECHOREQ) || (payload[4] == PPP_LCP_ECHOREP))) goto allow_packet; } else { opt->seq_recv = seq; allow_packet: skb_pull(skb, headersize); if (payload[0] == PPP_ALLSTATIONS && payload[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto drop; skb_pull(skb, 2); } skb->ip_summed = CHECKSUM_NONE; skb_set_network_header(skb, skb->head-skb->data); ppp_input(&po->chan, skb); return NET_RX_SUCCESS; } drop: kfree_skb(skb); return NET_RX_DROP; } static int pptp_rcv(struct sk_buff *skb) { struct pppox_sock *po; struct pptp_gre_header *header; struct iphdr *iph; if (skb->pkt_type != PACKET_HOST) goto drop; if (!pskb_may_pull(skb, 12)) goto drop; iph = ip_hdr(skb); header = (struct pptp_gre_header *)skb->data; if (header->gre_hd.protocol != GRE_PROTO_PPP || /* PPTP-GRE protocol for PPTP */ GRE_IS_CSUM(header->gre_hd.flags) || /* flag CSUM should be clear */ GRE_IS_ROUTING(header->gre_hd.flags) || /* flag ROUTING should be clear */ !GRE_IS_KEY(header->gre_hd.flags) || /* flag KEY should be set */ (header->gre_hd.flags & GRE_FLAGS)) /* flag Recursion Ctrl should be clear */ /* if invalid, discard this packet */ goto drop; po = lookup_chan(htons(header->call_id), iph->saddr); if (po) { skb_dst_drop(skb); nf_reset_ct(skb); return sk_receive_skb(sk_pppox(po), skb, 0); } drop: kfree_skb(skb); return NET_RX_DROP; } static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) return -EINVAL; lock_sock(sk); if (sk->sk_state & PPPOX_DEAD) { error = -EALREADY; goto out; } if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; goto out; } if (add_chan(po, &sp->sa_addr.pptp)) error = -EBUSY; else sk->sk_state |= PPPOX_BOUND; out: release_sock(sk); return error; } static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; struct rtable *rt; struct flowi4 fl4; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) return -EINVAL; if (sp->sa_protocol != PX_PROTO_PPTP) return -EINVAL; if (lookup_chan_dst(sp->sa_addr.pptp.call_id, sp->sa_addr.pptp.sin_addr.s_addr)) return -EALREADY; lock_sock(sk); /* Check for already bound sockets */ if (sk->sk_state & PPPOX_CONNECTED) { error = -EBUSY; goto end; } /* Check for already disconnected sockets, on attempts to disconnect */ if (sk->sk_state & PPPOX_DEAD) { error = -EALREADY; goto end; } if (!opt->src_addr.sin_addr.s_addr || !sp->sa_addr.pptp.sin_addr.s_addr) { error = -EINVAL; goto end; } po->chan.private = sk; po->chan.ops = &pptp_chan_ops; rt = ip_route_output_ports(sock_net(sk), &fl4, sk, opt->dst_addr.sin_addr.s_addr, opt->src_addr.sin_addr.s_addr, 0, 0, IPPROTO_GRE, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) { error = -EHOSTUNREACH; goto end; } sk_setup_caps(sk, &rt->dst); po->chan.mtu = dst_mtu(&rt->dst); if (!po->chan.mtu) po->chan.mtu = PPP_MRU; po->chan.mtu -= PPTP_HEADER_OVERHEAD; po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header); error = ppp_register_channel(&po->chan); if (error) { pr_err("PPTP: failed to register PPP channel (%d)\n", error); goto end; } opt->dst_addr = sp->sa_addr.pptp; sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); return error; } static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; memset(&sp.sa_addr, 0, sizeof(sp.sa_addr)); sp.sa_family = AF_PPPOX; sp.sa_protocol = PX_PROTO_PPTP; sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr; memcpy(uaddr, &sp, len); return len; } static int pptp_release(struct socket *sock) { struct sock *sk = sock->sk; struct pppox_sock *po; int error = 0; if (!sk) return 0; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD)) { release_sock(sk); return -EBADF; } po = pppox_sk(sk); del_chan(po); synchronize_rcu(); pppox_unbind_sock(sk); sk->sk_state = PPPOX_DEAD; sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return error; } static void pptp_sock_destruct(struct sock *sk) { if (!(sk->sk_state & PPPOX_DEAD)) { del_chan(pppox_sk(sk)); pppox_unbind_sock(sk); } skb_queue_purge(&sk->sk_receive_queue); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); } static int pptp_create(struct net *net, struct socket *sock, int kern) { int error = -ENOMEM; struct sock *sk; struct pppox_sock *po; struct pptp_opt *opt; sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pptp_sk_proto, kern); if (!sk) goto out; sock_init_data(sock, sk); sock->state = SS_UNCONNECTED; sock->ops = &pptp_ops; sk->sk_backlog_rcv = pptp_rcv_core; sk->sk_state = PPPOX_NONE; sk->sk_type = SOCK_STREAM; sk->sk_family = PF_PPPOX; sk->sk_protocol = PX_PROTO_PPTP; sk->sk_destruct = pptp_sock_destruct; po = pppox_sk(sk); opt = &po->proto.pptp; opt->seq_sent = 0; opt->seq_recv = 0xffffffff; opt->ack_recv = 0; opt->ack_sent = 0xffffffff; error = 0; out: return error; } static int pptp_ppp_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) { struct sock *sk = (struct sock *) chan->private; struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; void __user *argp = (void __user *)arg; int __user *p = argp; int err, val; err = -EFAULT; switch (cmd) { case PPPIOCGFLAGS: val = opt->ppp_flags; if (put_user(val, p)) break; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; opt->ppp_flags = val & ~SC_RCV_BITS; err = 0; break; default: err = -ENOTTY; } return err; } static const struct ppp_channel_ops pptp_chan_ops = { .start_xmit = pptp_xmit, .ioctl = pptp_ppp_ioctl, }; static struct proto pptp_sk_proto __read_mostly = { .name = "PPTP", .owner = THIS_MODULE, .obj_size = sizeof(struct pppox_sock), }; static const struct proto_ops pptp_ops = { .family = AF_PPPOX, .owner = THIS_MODULE, .release = pptp_release, .bind = pptp_bind, .connect = pptp_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = pptp_getname, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = sock_no_sendmsg, .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = pppox_compat_ioctl, #endif }; static const struct pppox_proto pppox_pptp_proto = { .create = pptp_create, .owner = THIS_MODULE, }; static const struct gre_protocol gre_pptp_protocol = { .handler = pptp_rcv, }; static int __init pptp_init_module(void) { int err = 0; pr_info("PPTP driver version " PPTP_DRIVER_VERSION "\n"); callid_sock = vzalloc(array_size(sizeof(void *), (MAX_CALLID + 1))); if (!callid_sock) return -ENOMEM; err = gre_add_protocol(&gre_pptp_protocol, GREPROTO_PPTP); if (err) { pr_err("PPTP: can't add gre protocol\n"); goto out_mem_free; } err = proto_register(&pptp_sk_proto, 0); if (err) { pr_err("PPTP: can't register sk_proto\n"); goto out_gre_del_protocol; } err = register_pppox_proto(PX_PROTO_PPTP, &pppox_pptp_proto); if (err) { pr_err("PPTP: can't register pppox_proto\n"); goto out_unregister_sk_proto; } return 0; out_unregister_sk_proto: proto_unregister(&pptp_sk_proto); out_gre_del_protocol: gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP); out_mem_free: vfree(callid_sock); return err; } static void __exit pptp_exit_module(void) { unregister_pppox_proto(PX_PROTO_PPTP); proto_unregister(&pptp_sk_proto); gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP); vfree(callid_sock); } module_init(pptp_init_module); module_exit(pptp_exit_module); MODULE_DESCRIPTION("Point-to-Point Tunneling Protocol"); MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_PPTP); |
| 483 406 406 406 406 483 482 2 2 2 406 405 406 406 406 406 405 8 406 433 433 333 433 433 433 433 422 192 176 190 1 353 353 268 510 32 31 32 350 349 2 2 2 2 349 349 294 349 350 348 418 418 496 496 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" #undef CREATE_TRACE_POINT #include <trace/hooks/mm.h> /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that makes the machine dump writes/reads and block dirtyings. */ int block_dump; /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Unreclaimable memory (kernel memory or anonymous memory * without swap) can bring down the dirtyable pages below * the zone's dirty balance reserve and the above calculation * will underflow. However we still want to add in nodes * which are below threshold (negative values) to get a more * accurate calculation but make sure that the total never * underflows. */ if ((long)x < 0) x = 0; /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; if (bg_thresh >= thresh) bg_thresh = thresh / 2; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; return dirty; } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; } int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_inc(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac) { __fprop_inc_percpu_max(&dom->completions, completions, max_prop_frac); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from test_clear_page_writeback(). */ static inline void __wb_writeout_inc(struct bdi_writeback *wb) { struct wb_domain *cgdom; inc_wb_stat(wb, WB_WRITTEN); wb_domain_writeout_inc(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_inc(wb); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { min_ratio -= bdi->min_ratio; if (bdi_min_ratio + min_ratio < 100) { bdi_min_ratio += min_ratio; bdi->min_ratio += min_ratio; } else { ret = -EINVAL; } } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) { int ret = 0; if (max_ratio > 100) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; } spin_unlock_bh(&bdi_lock); return ret; } EXPORT_SYMBOL(bdi_set_max_ratio); static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } /** * __wb_calc_thresh - @wb's share of dirty throttling threshold * @dtc: dirty_throttle_context of interest * * Note that balance_dirty_pages() will only seriously take it as a hard limit * when sleeping max_pause per page is not enough to keep the dirty pages under * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty and PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this BDI's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / 100; if (wb_thresh > (thresh * wb_max_ratio) / 100) wb_thresh = thresh * wb_max_ratio / 100; return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb), .thresh = thresh }; return __wb_calc_thresh(&gdtc); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 .............* * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to account_page_redirty(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; wb->avg_write_bandwidth = avg; } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_bandwidth(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; wb->dirty_ratelimit = max(dirty_ratelimit, 1UL); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, unsigned long start_time, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed = now - wb->bw_time_stamp; unsigned long dirtied; unsigned long written; lockdep_assert_held(&wb->list_lock); /* * rate-limit, only update once every 200ms. */ if (elapsed < BANDWIDTH_INTERVAL) return; dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); /* * Skip quiet periods when disk bandwidth is under-utilized. * (at least 1s idle time between two flusher runs) */ if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) goto snapshot; if (update_ratelimit) { domain_update_bandwidth(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_bandwidth(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); snapshot: wb->dirtied_stamp = dirtied; wb->written_stamp = written; wb->bw_time_stamp = now; } void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, start_time, false); } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = wb->avg_write_bandwidth; unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(wb->avg_write_bandwidth); long lo = ilog2(wb->dirty_ratelimit); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static void balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty */ long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; unsigned long m_dirty = 0; /* stop bogus uninit warnings */ unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { wb_dirty_limits(gdtc); dirty = gdtc->wb_dirty; thresh = gdtc->wb_thresh; bg_thresh = gdtc->wb_bg_thresh; } else { dirty = gdtc->dirty; thresh = gdtc->thresh; bg_thresh = gdtc->bg_thresh; } if (mdtc) { unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc->dirty += writeback; mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); if (unlikely(strictlimit)) { wb_dirty_limits(mdtc); m_dirty = mdtc->wb_dirty; m_thresh = mdtc->wb_thresh; m_bg_thresh = mdtc->wb_bg_thresh; } else { m_dirty = mdtc->dirty; m_thresh = mdtc->thresh; m_bg_thresh = mdtc->bg_thresh; } } trace_android_vh_mm_dirty_limits(gdtc, strictlimit, dirty, bg_thresh, nr_reclaimable, pages_dirtied); /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the wb limits are ramping up in case of !strictlimit. * * In strictlimit case make decision based on the wb counters * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. * * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } if (dirty_exceeded && !wb->dirty_exceeded) wb->dirty_exceeded = 1; if (time_is_before_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL)) { spin_lock(&wb->list_lock); __wb_update_bandwidth(gdtc, mdtc, start_time, true); spin_unlock(&wb->list_lock); } /* throttle according to the chosen dtc */ dirty_ratelimit = wb->dirty_ratelimit; task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); __set_current_state(TASK_KILLABLE); wb->dirty_sleep = now; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponding NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } if (!dirty_exceeded && wb->dirty_exceeded) wb->dirty_exceeded = 0; if (writeback_in_progress(wb)) return; /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (laptop_mode) return; if (nr_reclaimable > gdtc->bg_thresh) wb_start_background_writeback(wb); } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited - balance dirty memory state * @mapping: address_space which was dirtied * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * On really big machines, get_writeback_state is expensive, so try to avoid * calling it too often (ratelimiting). But once we're over the dirty memory * limit we decrease the ratelimiting by a lot, to prevent individual processes * from overshooting the limit by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) balance_dirty_pages(wb, current->nr_dirtied); wb_put(wb); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; /* * Similar to balance_dirty_pages() but ignores pages being written * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; if (wb_stat(wb, WB_RECLAIMABLE) > wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { unsigned long filepages, headroom, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) return true; if (wb_stat(wb, WB_RECLAIMABLE) > wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } return false; } /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #ifdef CONFIG_BLOCK void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } #endif /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * If it is too low then SMP machines will call the (expensive) * get_writeback_state too often. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); } /** * tag_pages_for_writeback - tag pages to be written by write_cache_pages * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is * that write_cache_pages (or whoever calls this function) will then use * TOWRITE tag to identify pages eligible for writeback. This mechanism is * used to avoid livelocking of writeback by a process steadily creating new * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. * * To avoid livelocks (when other process dirties new pages), we first tag * pages which should be written back with TOWRITE tag and only then start * writing them. For data-integrity sync we have to be careful so that we do * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). * * To avoid deadlocks between range_cyclic writeback and callers that hold * pages in PageWriteback to aggregate IO until write_cache_pages() returns, * we do not loop back to the start of the file. Doing so causes a page * lock/page writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping back to the start * of the file violates that rule and causes deadlocks. * * Return: %0 on success, negative error code otherwise */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { int ret = 0; int done = 0; int error; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int range_whole = 0; xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { index = mapping->writeback_index; /* prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { tag_pages_for_writeback(mapping, index, end); tag = PAGECACHE_TAG_TOWRITE; } else { tag = PAGECACHE_TAG_DIRTY; } done_index = index; while (!done && (index <= end)) { int i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, tag); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; done_index = page->index; lock_page(page); /* * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no * real expectation of this data interity operation * even if there is now a new, dirty page at the same * pagecache address. */ if (unlikely(page->mapping != mapping)) { continue_unlock: unlock_page(page); continue; } if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) wait_on_page_writeback(page); else goto continue_unlock; } BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); error = (*writepage)(page, wbc, data); if (unlikely(error)) { /* * Handle errors according to the type of * writeback. There's no need to continue for * background writeback. Just push done_index * past this page so media errors won't choke * writeout for the entire file. For integrity * writeback, we must process the entire dirty * set regardless of errors because the fs may * still have state to clear for each page. In * that case we continue processing and return * the first error. */ if (error == AOP_WRITEPAGE_ACTIVATE) { unlock_page(page); error = 0; } else if (wbc->sync_mode != WB_SYNC_ALL) { ret = error; done_index = page->index + 1; done = 1; break; } if (!ret) ret = error; } /* * We stop writing back only if we are not doing * integrity sync. In case of integrity sync we have to * keep going until we have written all the pages * we tagged for writeback prior to entering this loop. */ if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } } pagevec_release(&pvec); cond_resched(); } /* * If we hit the last page and there is more work to be done: wrap * back the index back to the start of the file for the next * time we are called. */ if (wbc->range_cyclic && !done) done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; } EXPORT_SYMBOL(write_cache_pages); /* * Function used by generic_writepages to call the real writepage * function and set the mapping flags on error */ static int __writepage(struct page *page, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(page, wbc); mapping_set_error(mapping, ret); return ret; } /** * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * * This is a library function, which implements the writepages() * address_space_operation. * * Return: %0 on success, negative error code otherwise */ int generic_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct blk_plug plug; int ret; /* deal with chardevs and other special file */ if (!mapping->a_ops->writepage) return 0; blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, __writepage, mapping); blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(generic_writepages); int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (wbc->nr_to_write <= 0) return 0; while (1) { if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); else ret = generic_writepages(mapping, wbc); if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) break; cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); } return ret; } /** * write_one_page - write out a single page and wait on I/O * @page: the page to write * * The page must be locked by the caller and will be unlocked upon return. * * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this * function returns. * * Return: %0 on success, negative error code otherwise */ int write_one_page(struct page *page) { struct address_space *mapping = page->mapping; int ret = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 1, }; BUG_ON(!PageLocked(page)); wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { get_page(page); ret = mapping->a_ops->writepage(page, &wbc); if (ret == 0) wait_on_page_writeback(page); put_page(page); } else { unlock_page(page); } if (!ret) ret = filemap_check_errors(mapping); return ret; } EXPORT_SYMBOL(write_one_page); /* * For address_spaces which do not use buffers nor write back. */ int __set_page_dirty_no_writeback(struct page *page) { if (!PageDirty(page)) return !TestSetPageDirty(page); return 0; } /* * Helper function for set_page_dirty family. * * Caller must hold lock_page_memcg(). * * NOTE: This relies on being atomic wrt interrupts. */ void account_page_dirtied(struct page *page, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_page(page, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; inode_attach_wb(inode, page); wb = inode_to_wb(inode); __inc_lruvec_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); __inc_node_page_state(page, NR_DIRTIED); inc_wb_stat(wb, WB_RECLAIMABLE); inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); mem_cgroup_track_foreign_dirty(page, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold lock_page_memcg(). */ void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb) { if (mapping_can_writeback(mapping)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); task_io_account_cancelled_write(PAGE_SIZE); } } /* * For address_spaces which do not use buffers. Just tag the page as dirty in * the xarray. * * This is also used when a single buffer is being dirtied: we want to set the * page dirty in that case, but not all the buffers. This is a "bottom-up" * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will simply * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and * the pte lock held, which also locks out truncation. */ int __set_page_dirty_nobuffers(struct page *page) { lock_page_memcg(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); unsigned long flags; if (!mapping) { unlock_page_memcg(page); return 1; } xa_lock_irqsave(&mapping->i_pages, flags); BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } unlock_page_memcg(page); return 0; } EXPORT_SYMBOL(__set_page_dirty_nobuffers); /* * Call this whenever redirtying a page, to de-account the dirty counters * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to * systematic errors in balanced_dirty_ratelimit and the dirty pages position * control. */ void account_page_redirty(struct page *page) { struct address_space *mapping = page->mapping; if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); /* * When a writepage implementation decides that it doesn't want to write this * page for some reason, it should redirty the locked page via * redirty_page_for_writepage() and it should then unlock the page and return 0 */ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { int ret; wbc->pages_skipped++; ret = __set_page_dirty_nobuffers(page); account_page_redirty(page); return ret; } EXPORT_SYMBOL(redirty_page_for_writepage); /* * Dirty a page. * * For pages with a mapping this should be done under the page lock * for the benefit of asynchronous memory errors who prefer a consistent * dirty state. This rule can be broken in some special cases, * but should be better not to. * * If the mapping doesn't provide a set_page_dirty a_op, then * just fall through and assume that it wants buffer_heads. */ int set_page_dirty(struct page *page) { struct address_space *mapping = page_mapping(page); page = compound_head(page); if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; /* * readahead/lru_deactivate_page could remain * PG_readahead/PG_reclaim due to race with end_page_writeback * About readahead, if the page is written, the flags would be * reset. So no problem. * About lru_deactivate_page, if the page is redirty, the flag * will be reset. So no problem. but if the page is used by readahead * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ if (PageReclaim(page)) ClearPageReclaim(page); #ifdef CONFIG_BLOCK if (!spd) spd = __set_page_dirty_buffers; #endif return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) return 1; } return 0; } EXPORT_SYMBOL(set_page_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __cancel_dirty_page(struct page *page) { struct address_space *mapping = page_mapping(page); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; lock_page_memcg(page); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); } } EXPORT_SYMBOL(__cancel_dirty_page); /* * Clear a page's dirty flag, while caring for dirty memory accounting. * Returns true if the page was previously dirty. * * This is for preparing to put the page under writeout. We leave the page * tagged as dirty in the xarray so that a concurrent write-for-sync * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage * implementation will run either set_page_writeback() or set_page_dirty(), * at which stage we bring the page's dirty flag and xarray dirty tag * back into sync. * * This incoherency between the page's dirty flag and xarray tag is * unfortunate, but it only exists while the page is locked. */ int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); int ret = 0; VM_BUG_ON_PAGE(!PageLocked(page), page); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole page dirty if it was * dirty in a pagetable. Only to then * (c) clean the page again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "set_page_dirty(page)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the page "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (page_mkclean(page)) set_page_dirty(page); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the page dirty * at this point. We do this by having them hold the * page lock while dirtying the page, and pages are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page); } EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); struct mem_cgroup *memcg; struct lruvec *lruvec; int ret; memcg = lock_page_memcg(page); lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = TestClearPageWriteback(page); if (ret) { __xa_clear_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); dec_wb_stat(wb, WB_WRITEBACK); __wb_writeout_inc(wb); } } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = TestClearPageWriteback(page); } if (ret) { dec_lruvec_state(lruvec, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); inc_node_page_state(page, NR_WRITTEN); } __unlock_page_memcg(memcg); return ret; } int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret, access_ret; lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, page_index(page)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); ret = TestSetPageWriteback(page); if (!ret) { bool on_wblist; on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); /* * We can come through here when swapping anonymous * pages, so we don't necessarily have an inode to track * for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { ret = TestSetPageWriteback(page); } if (!ret) { inc_lruvec_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); } unlock_page_memcg(page); access_ret = arch_make_page_accessible(page); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_PAGE(access_ret != 0, page); return ret; } EXPORT_SYMBOL(__test_set_page_writeback); /* * Wait for a page to complete writeback */ void wait_on_page_writeback(struct page *page) { while (PageWriteback(page)) { trace_wait_on_page_writeback(page, page_mapping(page)); wait_on_page_bit(page, PG_writeback); } } EXPORT_SYMBOL_GPL(wait_on_page_writeback); /** * wait_for_stable_page() - wait for writeback to finish, if necessary. * @page: The page to wait on. * * This function determines if the given page is related to a backing device * that requires page contents to be held stable during writeback. If so, then * it will wait for any pending writeback to complete. */ void wait_for_stable_page(struct page *page) { page = thp_head(page); if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) wait_on_page_writeback(page); } EXPORT_SYMBOL_GPL(wait_for_stable_page); |
| 52 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | // SPDX-License-Identifier: GPL-2.0-only /* * "security" table * * This is for use by Mandatory Access Control (MAC) security models, * which need to be able to manage security policy in separate context * to DAC. * * Based on iptable_mangle.c * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org> * Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com> */ #include <linux/module.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/slab.h> #include <net/ip.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>"); MODULE_DESCRIPTION("iptables security table, for MAC rules"); #define SECURITY_VALID_HOOKS (1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT) static int __net_init iptable_security_table_init(struct net *net); static const struct xt_table security_table = { .name = "security", .valid_hooks = SECURITY_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV4, .priority = NF_IP_PRI_SECURITY, .table_init = iptable_security_table_init, }; static unsigned int iptable_security_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ipt_do_table(skb, state, state->net->ipv4.iptable_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; static int __net_init iptable_security_table_init(struct net *net) { struct ipt_replace *repl; int ret; if (net->ipv4.iptable_security) return 0; repl = ipt_alloc_initial_table(&security_table); if (repl == NULL) return -ENOMEM; ret = ipt_register_table(net, &security_table, repl, sectbl_ops, &net->ipv4.iptable_security); kfree(repl); return ret; } static void __net_exit iptable_security_net_pre_exit(struct net *net) { if (net->ipv4.iptable_security) ipt_unregister_table_pre_exit(net, net->ipv4.iptable_security, sectbl_ops); } static void __net_exit iptable_security_net_exit(struct net *net) { if (!net->ipv4.iptable_security) return; ipt_unregister_table_exit(net, net->ipv4.iptable_security); net->ipv4.iptable_security = NULL; } static struct pernet_operations iptable_security_net_ops = { .pre_exit = iptable_security_net_pre_exit, .exit = iptable_security_net_exit, }; static int __init iptable_security_init(void) { int ret; sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); if (IS_ERR(sectbl_ops)) return PTR_ERR(sectbl_ops); ret = register_pernet_subsys(&iptable_security_net_ops); if (ret < 0) { kfree(sectbl_ops); return ret; } ret = iptable_security_table_init(&init_net); if (ret) { unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); } return ret; } static void __exit iptable_security_fini(void) { unregister_pernet_subsys(&iptable_security_net_ops); kfree(sectbl_ops); } module_init(iptable_security_init); module_exit(iptable_security_fini); |
| 1029 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> #include <linux/llist.h> #include <asm/page.h> /* pgprot_t */ #include <linux/rbtree.h> #include <linux/overflow.h> #include <linux/android_vendor.h> #include <asm/vmalloc.h> struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ /* * VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC. * * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after * shadow memory has been mapped. It's used to handle allocation errors so that * we don't try to poision shadow on free if it was never allocated. * * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to * determine which allocations need the module shadow freed. */ /* bits [20..32] reserved for arch specific ioremap internals */ /* * Maximum alignment for ioremap() regions. * Can be overriden by arch-specific value. */ #ifndef IOREMAP_MAX_ORDER #define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ #endif struct vm_struct { struct vm_struct *next; void *addr; unsigned long size; unsigned long flags; struct page **pages; unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; ANDROID_OEM_DATA(1); }; struct vmap_area { unsigned long va_start; unsigned long va_end; struct rb_node rb_node; /* address sorted rbtree */ struct list_head list; /* address sorted list */ /* * The following three variables can be packed, because * a vmap_area object is always one of the three states: * 1) in "free" tree (root is vmap_area_root) * 2) in "busy" tree (root is free_vmap_area_root) * 3) in purge list (head is vmap_purge_list) */ union { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ struct llist_node purge_list; /* in purge list */ }; }; /* * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU extern void __init vmalloc_init(void); extern unsigned long vmalloc_nr_pages(void); #else static inline void vmalloc_init(void) { } static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif extern void *vmalloc(unsigned long size); extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot); extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() * needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 #endif /* * There is no default implementation for arch_sync_kernel_mappings(). It is * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK * is 0. */ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); /* * Lowlevel-APIs (not for driver use!) */ static inline size_t get_vm_area_size(const struct vm_struct *area) { if (!(area->flags & VM_NO_GUARD)) /* return actual size without guard page */ return area->size - PAGE_SIZE; else return area->size; } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller); void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); #ifdef CONFIG_MMU extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } #else static inline int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages) { return size >> PAGE_SHIFT; } #define map_kernel_range map_kernel_range_noflush static inline void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) { } #define unmap_kernel_range unmap_kernel_range_noflush static inline void set_vm_flush_reset_perms(void *addr) { } #endif /* for /dev/kmem */ extern long vread(char *buf, char *addr, unsigned long count); extern long vwrite(char *buf, char *addr, unsigned long count); /* * Internals. Dont't use.. */ extern struct list_head vmap_area_list; extern __init void vm_area_add_early(struct vm_struct *vm); extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); #ifdef CONFIG_SMP # ifdef CONFIG_MMU struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); # else static inline struct vm_struct ** pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { return NULL; } static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) { } # endif #endif #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) #else #define VMALLOC_TOTAL 0UL #endif int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); #endif /* _LINUX_VMALLOC_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_LOCAL_H #define _ASM_X86_LOCAL_H #include <linux/percpu.h> #include <linux/atomic.h> #include <asm/asm.h> typedef struct { atomic_long_t a; } local_t; #define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } #define local_read(l) atomic_long_read(&(l)->a) #define local_set(l, i) atomic_long_set(&(l)->a, (i)) static inline void local_inc(local_t *l) { asm volatile(_ASM_INC "%0" : "+m" (l->a.counter)); } static inline void local_dec(local_t *l) { asm volatile(_ASM_DEC "%0" : "+m" (l->a.counter)); } static inline void local_add(long i, local_t *l) { asm volatile(_ASM_ADD "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } static inline void local_sub(long i, local_t *l) { asm volatile(_ASM_SUB "%1,%0" : "+m" (l->a.counter) : "ir" (i)); } /** * local_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @l: pointer to type local_t * * Atomically subtracts @i from @l and returns * true if the result is zero, or false for all * other cases. */ static inline bool local_sub_and_test(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i); } /** * local_dec_and_test - decrement and test * @l: pointer to type local_t * * Atomically decrements @l by 1 and * returns true if the result is 0, or false for all other * cases. */ static inline bool local_dec_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e); } /** * local_inc_and_test - increment and test * @l: pointer to type local_t * * Atomically increments @l by 1 * and returns true if the result is zero, or false for all * other cases. */ static inline bool local_inc_and_test(local_t *l) { return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e); } /** * local_add_negative - add and test if negative * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static inline bool local_add_negative(long i, local_t *l) { return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i); } /** * local_add_return - add and return * @i: integer value to add * @l: pointer to type local_t * * Atomically adds @i to @l and returns @i + @l */ static inline long local_add_return(long i, local_t *l) { long __i = i; asm volatile(_ASM_XADD "%0, %1;" : "+r" (i), "+m" (l->a.counter) : : "memory"); return i + __i; } static inline long local_sub_return(long i, local_t *l) { return local_add_return(-i, l); } #define local_inc_return(l) (local_add_return(1, l)) #define local_dec_return(l) (local_sub_return(1, l)) #define local_cmpxchg(l, o, n) \ (cmpxchg_local(&((l)->a.counter), (o), (n))) /* Always has a lock prefix */ #define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) /** * local_add_unless - add unless the number is a given value * @l: pointer of type local_t * @a: the amount to add to l... * @u: ...unless l is equal to u. * * Atomically adds @a to @l, so long as it was not @u. * Returns non-zero if @l was not @u, and zero otherwise. */ #define local_add_unless(l, a, u) \ ({ \ long c, old; \ c = local_read((l)); \ for (;;) { \ if (unlikely(c == (u))) \ break; \ old = local_cmpxchg((l), c, c + (a)); \ if (likely(old == c)) \ break; \ c = old; \ } \ c != (u); \ }) #define local_inc_not_zero(l) local_add_unless((l), 1, 0) /* On x86_32, these are no better than the atomic variants. * On x86-64 these are better than the atomic variants on SMP kernels * because they dont use a lock prefix. */ #define __local_inc(l) local_inc(l) #define __local_dec(l) local_dec(l) #define __local_add(i, l) local_add((i), (l)) #define __local_sub(i, l) local_sub((i), (l)) #endif /* _ASM_X86_LOCAL_H */ |
| 3 1 3 2 1 1 7 1 1 9 2 7 8 819 819 819 819 5 2 1 1 1 1 1 1 819 819 819 819 819 819 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 virtual tunneling interface * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv6/ip6_tunnel.c */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/etherdevice.h> #define IP6_VTI_HASH_SIZE_SHIFT 5 #define IP6_VTI_HASH_SIZE (1 << IP6_VTI_HASH_SIZE_SHIFT) static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); return hash_32(hash, IP6_VTI_HASH_SIZE_SHIFT); } static int vti6_dev_init(struct net_device *dev); static void vti6_dev_setup(struct net_device *dev); static struct rtnl_link_ops vti6_link_ops __read_mostly; static unsigned int vti6_net_id __read_mostly; struct vti6_net { /* the vti6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[IP6_VTI_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; }; #define for_each_vti6_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /** * vti6_tnl_lookup - fetch tunnel matching the end-point addresses * @net: network namespace * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ static struct ip6_tnl * vti6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); struct ip6_tnl *t; struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct in6_addr any; for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && (t->dev->flags & IFF_UP)) return t; } hash = HASH(remote, &any); for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * vti6_tnl_bucket - get head of list matching given tunnel parameters * @p: parameters containing tunnel end-points * * Description: * vti6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } static void vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; for (tp = vti6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void vti6_dev_free(struct net_device *dev) { free_percpu(dev->tstats); } static int vti6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; dev->rtnl_link_ops = &vti6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); vti6_tnl_link(ip6n, t); return 0; out: return err; } static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err; if (p->name[0]) { if (!dev_valid_name(p->name)) goto failed; strlcpy(name, p->name, IFNAMSIZ); } else { sprintf(name, "ip6_vti%%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = vti6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: free_netdev(dev); failed: return NULL; } /** * vti6_locate - find or create tunnel matching given parameters * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * vti6_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or NULL **/ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct vti6_net *ip6n = net_generic(net, vti6_net_id); for (tp = vti6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) { if (create) return NULL; return t; } } if (!create) return NULL; return vti6_tnl_create(net, p); } /** * vti6_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * vti6_dev_uninit() removes tunnel from its list **/ static void vti6_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); dev_put(dev); } static int vti6_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); rcu_read_lock(); t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); goto discard; } ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); goto discard; } rcu_read_unlock(); XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t; XFRM_SPI_SKB_CB(skb)->family = AF_INET6; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); return xfrm_input(skb, nexthdr, spi, encap_type); } rcu_read_unlock(); return -EINVAL; discard: kfree_skb(skb); return 0; } static int vti6_rcv(struct sk_buff *skb) { int nexthdr = skb_network_header(skb)[IP6CB(skb)->nhoff]; return vti6_input_proto(skb, nexthdr, 0, 0); } static int vti6_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; u32 orig_mark = skb->mark; int ret; if (!t) return 1; dev = t->dev; if (err) { dev->stats.rx_errors++; dev->stats.rx_dropped++; return 0; } x = xfrm_input_state(skb); inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } family = inner_mode->family; skb->mark = be32_to_cpu(t->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); skb->mark = orig_mark; if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); return 0; } /** * vti6_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } static bool vti6_state_check(const struct xfrm_state *x, const struct in6_addr *dst, const struct in6_addr *src) { xfrm_address_t *daddr = (xfrm_address_t *)dst; xfrm_address_t *saddr = (xfrm_address_t *)src; /* if there is no transform then this tunnel is not functional. * Or if the xfrm is not mode tunnel. */ if (!x || x->props.mode != XFRM_MODE_TUNNEL || x->props.family != AF_INET6) return false; if (ipv6_addr_any(dst)) return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6); if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6)) return false; return true; } /** * vti6_xmit - send a packet * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @fl: the flow informations for the xfrm_lookup **/ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; struct xfrm_state *x; int pkt_len = skb->len; int err = -1; int mtu; if (!dst) { switch (skb->protocol) { case htons(ETH_P_IP): { struct rtable *rt; fl->u.ip4.flowi4_oif = dev->ifindex; fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) goto tx_err_link_failure; dst = &rt->dst; skb_dst_set(skb, dst); break; } case htons(ETH_P_IPV6): fl->u.ip6.flowi6_oif = dev->ifindex; fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); if (dst->error) { dst_release(dst); dst = NULL; goto tx_err_link_failure; } skb_dst_set(skb, dst); break; default: goto tx_err_link_failure; } } dst_hold(dst); dst = xfrm_lookup_route(t->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } if (dst->flags & DST_XFRM_QUEUE) goto queued; x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr, (const struct in6_addr *)&x->id.daddr)) goto tx_err_link_failure; tdev = dst->dev; if (tdev == dev) { stats->collisions++; net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } err = -EMSGSIZE; goto tx_err_dst_release; } queued: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static netdev_tx_t vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; struct flowi fl; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); break; case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); break; default: goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(t->parms.o_key); ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip6_tnl *t; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; int protocol = iph->nexthdr; t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr); if (!t) return -1; mark = be32_to_cpu(t->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data + offset); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data + offset); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct net_device *tdev = NULL; int mtu; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags & IP6_TNL_F_CAP_XMIT && p->flags & IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; if (keep_mtu && dev->mtu) { dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu); return; } if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (rt) tdev = rt->dst.dev; ip6_rt_put(rt); } if (!tdev && p->link) tdev = __dev_get_by_index(t->net, p->link); if (tdev) mtu = tdev->mtu - sizeof(struct ipv6hdr); else mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); dev->mtu = max_t(int, mtu, IPV4_MIN_MTU); } /** * vti6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * @keep_mtu: MTU was set from userspace, don't re-compute it * * Description: * vti6_tnl_change() updates the tunnel parameters **/ static int vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, bool keep_mtu) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.link = p->link; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); vti6_link_config(t, keep_mtu); return 0; } static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, bool keep_mtu) { struct net *net = dev_net(t->dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; vti6_tnl_unlink(ip6n, t); synchronize_net(); err = vti6_tnl_change(t, p, keep_mtu); vti6_tnl_link(ip6n, t); netdev_state_change(t->dev); return err; } static void vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; p->proto = u->proto; memcpy(p->name, u->name, sizeof(u->name)); } static void vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->link = p->link; u->i_key = p->i_key; u->o_key = p->o_key; if (u->i_key) u->i_flags |= GRE_KEY; if (u->o_key) u->o_flags |= GRE_KEY; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * vti6_ioctl - configure vti6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: parameters passed from userspace * @cmd: command to be performed * * Description: * vti6_ioctl() is used for managing vti6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6_vti0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip6_tnl_parm2 p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = NULL; struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; break; } vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); } else { memset(&p, 0, sizeof(p)); } if (!t) t = netdev_priv(dev); vti6_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != 0) break; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); err = vti6_update(t, &p1, false); } if (t) { err = 0; vti6_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; } else err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) break; err = -ENOENT; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); if (!t) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } static const struct net_device_ops vti6_netdev_ops = { .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_do_ioctl = vti6_ioctl, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; /** * vti6_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void vti6_dev_setup(struct net_device *dev) { dev->netdev_ops = &vti6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * vti6_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; t->net = dev_net(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; dev_hold(dev); return 0; } /** * vti6_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int vti6_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = vti6_dev_init_gen(dev); if (err) return err; vti6_link_config(t, true); return 0; } /** * vti6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int vti6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void vti6_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); if (data[IFLA_VTI_OKEY]) parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } static int vti6_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl *nt; nt = netdev_priv(dev); vti6_netlink_parms(data, &nt->parms); nt->parms.proto = IPPROTO_IPV6; if (vti6_locate(net, &nt->parms, 0)) return -EEXIST; return vti6_tnl_create2(dev); } static void vti6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t; struct __ip6_tnl_parm p; struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) return -EINVAL; vti6_netlink_parms(data, &p); t = vti6_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); return vti6_update(t, &p, tb && tb[IFLA_MTU]); } static size_t vti6_get_size(const struct net_device *dev) { return /* IFLA_VTI_LINK */ nla_total_size(4) + /* IFLA_VTI_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VTI_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VTI_IKEY */ nla_total_size(4) + /* IFLA_VTI_OKEY */ nla_total_size(4) + /* IFLA_VTI_FWMARK */ nla_total_size(4) + 0; } static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) || nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key) || nla_put_u32(skb, IFLA_VTI_FWMARK, parm->fwmark)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_VTI_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vti6_link_ops __read_mostly = { .kind = "vti6", .maxtype = IFLA_VTI_MAX, .policy = vti6_policy, .priv_size = sizeof(struct ip6_tnl), .setup = vti6_dev_setup, .validate = vti6_validate, .newlink = vti6_newlink, .dellink = vti6_dellink, .changelink = vti6_changelink, .get_size = vti6_get_size, .fill_info = vti6_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, struct list_head *list) { int h; struct ip6_tnl *t; for (h = 0; h < IP6_VTI_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } t = rtnl_dereference(ip6n->tnls_wc[0]); if (t) unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) { struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; if (!net_has_fallback_tunnels(net)) return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", NET_NAME_UNKNOWN, vti6_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops; err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static void __net_exit vti6_exit_batch_net(struct list_head *net_list) { struct vti6_net *ip6n; struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { ip6n = net_generic(net, vti6_net_id); vti6_destroy_tunnels(ip6n, &list); } unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { .handler = vti6_rcv, .input_handler = vti6_input_proto, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; static struct xfrm6_protocol vti_ah6_protocol __read_mostly = { .handler = vti6_rcv, .input_handler = vti6_input_proto, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .handler = vti6_rcv, .input_handler = vti6_input_proto, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) static int vti6_rcv_tunnel(struct sk_buff *skb) { const xfrm_address_t *saddr; __be32 spi; saddr = (const xfrm_address_t *)&ipv6_hdr(skb)->saddr; spi = xfrm6_tunnel_spi_lookup(dev_net(skb->dev), saddr); return vti6_input_proto(skb, IPPROTO_IPV6, spi, 0); } static struct xfrm6_tunnel vti_ipv6_handler __read_mostly = { .handler = vti6_rcv_tunnel, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 0, }; static struct xfrm6_tunnel vti_ip6ip_handler __read_mostly = { .handler = vti6_rcv_tunnel, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 0, }; #endif /** * vti6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init vti6_tunnel_init(void) { const char *msg; int err; msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) goto pernet_dev_failed; msg = "tunnel protocols"; err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) msg = "ipv6 tunnel"; err = xfrm6_tunnel_register(&vti_ipv6_handler, AF_INET6); if (err < 0) goto vti_tunnel_ipv6_failed; err = xfrm6_tunnel_register(&vti_ip6ip_handler, AF_INET); if (err < 0) goto vti_tunnel_ip6ip_failed; #endif msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) err = xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); vti_tunnel_ip6ip_failed: err = xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); vti_tunnel_ipv6_failed: #endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); pernet_dev_failed: pr_err("vti6 init: failed to register %s\n", msg); return err; } /** * vti6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); #if IS_REACHABLE(CONFIG_INET6_XFRM_TUNNEL) xfrm6_tunnel_deregister(&vti_ip6ip_handler, AF_INET); xfrm6_tunnel_deregister(&vti_ipv6_handler, AF_INET6); #endif xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); } module_init(vti6_tunnel_init); module_exit(vti6_tunnel_cleanup); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti6"); MODULE_ALIAS_NETDEV("ip6_vti0"); MODULE_AUTHOR("Steffen Klassert"); MODULE_DESCRIPTION("IPv6 virtual tunnel interface"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net> * * Based on the original implementation which is: * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * * Parts of the original code have been moved to arch/x86/vdso/vma.c * * This file implements vsyscall emulation. vsyscalls are a legacy ABI: * Userspace can request certain kernel services by calling fixed * addresses. This concept is problematic: * * - It interferes with ASLR. * - It's awkward to write code that lives in kernel addresses but is * callable by userspace at fixed addresses. * - The whole concept is impossible for 32-bit compat userspace. * - UML cannot easily virtualize a vsyscall. * * As of mid-2014, I believe that there is no new userspace code that * will use a vsyscall if the vDSO is present. I hope that there will * soon be no new userspace code that will ever use a vsyscall. * * The code in this file emulates vsyscalls when notified of a page * fault to a vsyscall address. */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/sched/signal.h> #include <linux/mm_types.h> #include <linux/syscalls.h> #include <linux/ratelimit.h> #include <asm/vsyscall.h> #include <asm/unistd.h> #include <asm/fixmap.h> #include <asm/traps.h> #include <asm/paravirt.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init = #ifdef CONFIG_LEGACY_VSYSCALL_NONE NONE; #elif defined(CONFIG_LEGACY_VSYSCALL_XONLY) XONLY; #else EMULATE; #endif static int __init vsyscall_setup(char *str) { if (str) { if (!strcmp("emulate", str)) vsyscall_mode = EMULATE; else if (!strcmp("xonly", str)) vsyscall_mode = XONLY; else if (!strcmp("none", str)) vsyscall_mode = NONE; else return -EINVAL; return 0; } return -EINVAL; } early_param("vsyscall", vsyscall_setup); static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, const char *message) { if (!show_unhandled_signals) return; printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", level, current->comm, task_pid_nr(current), message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) { int nr; if ((addr & ~0xC00UL) != VSYSCALL_ADDR) return -EINVAL; nr = (addr & 0xC00UL) >> 10; if (nr >= 3) return -EINVAL; return nr; } static bool write_ok_or_segv(unsigned long ptr, size_t size) { /* * XXX: if access_ok, get_user, and put_user handled * sig_on_uaccess_err, this could go away. */ if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; thread->error_code = X86_PF_USER | X86_PF_WRITE; thread->cr2 = ptr; thread->trap_nr = X86_TRAP_PF; force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr); return false; } else { return true; } } bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { struct task_struct *tsk; unsigned long caller; int vsyscall_nr, syscall_nr, tmp; int prev_sig_on_uaccess_err; long ret; unsigned long orig_dx; /* Write faults or kernel-privilege faults never get fixed up. */ if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER) return false; if (!(error_code & X86_PF_INSTR)) { /* Failed vsyscall read */ if (vsyscall_mode == EMULATE) return false; /* * User code tried and failed to read the vsyscall page. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround"); return false; } /* * No point in checking CS -- the only way to get here is a user mode * trap to a high address, which means that we're in 64-bit user code. */ WARN_ON_ONCE(address != regs->ip); if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); return false; } vsyscall_nr = addr_to_vsyscall_nr(address); trace_emulate_vsyscall(vsyscall_nr); if (vsyscall_nr < 0) { warn_bad_vsyscall(KERN_WARNING, regs, "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround"); goto sigsegv; } if (get_user(caller, (unsigned long __user *)regs->sp) != 0) { warn_bad_vsyscall(KERN_WARNING, regs, "vsyscall with bad stack (exploit attempt?)"); goto sigsegv; } tsk = current; /* * Check for access_ok violations and find the syscall nr. * * NULL is a valid user pointer (in the access_ok sense) on 32-bit and * 64-bit, so we don't need to special-case it here. For all the * vsyscalls, NULL means "don't write anything" not "write it at * address 0". */ switch (vsyscall_nr) { case 0: if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) || !write_ok_or_segv(regs->si, sizeof(struct timezone))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_gettimeofday; break; case 1: if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_time; break; case 2: if (!write_ok_or_segv(regs->di, sizeof(unsigned)) || !write_ok_or_segv(regs->si, sizeof(unsigned))) { ret = -EFAULT; goto check_fault; } syscall_nr = __NR_getcpu; break; } /* * Handle seccomp. regs->ip must be the original value. * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst. * * We could optimize the seccomp disabled case, but performance * here doesn't matter. */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); do_exit(SIGSYS); } regs->orig_ax = -1; if (tmp) goto do_ret; /* skip requested */ /* * With a real vsyscall, page faults cause SIGSEGV. We want to * preserve that behavior to make writing exploits harder. */ prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err; current->thread.sig_on_uaccess_err = 1; ret = -EFAULT; switch (vsyscall_nr) { case 0: /* this decodes regs->di and regs->si on its own */ ret = __x64_sys_gettimeofday(regs); break; case 1: /* this decodes regs->di on its own */ ret = __x64_sys_time(regs); break; case 2: /* while we could clobber regs->dx, we didn't in the past... */ orig_dx = regs->dx; regs->dx = 0; /* this decodes regs->di, regs->si and regs->dx on its own */ ret = __x64_sys_getcpu(regs); regs->dx = orig_dx; break; } current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err; check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); /* * If we failed to generate a signal for any reason, * generate one here. (This should be impossible.) */ if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) && !sigismember(&tsk->pending.signal, SIGSEGV))) goto sigsegv; return true; /* Don't emulate the ret. */ } regs->ax = ret; do_ret: /* Emulate a ret instruction. */ regs->ip = caller; regs->sp += 8; return true; sigsegv: force_sig(SIGSEGV); return true; } /* * A pseudo VMA to allow ptrace access for the vsyscall page. This only * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ static const char *gate_vma_name(struct vm_area_struct *vma) { return "[vsyscall]"; } static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; static struct vm_area_struct gate_vma __ro_after_init = { .vm_start = VSYSCALL_ADDR, .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, .vm_flags = VM_READ | VM_EXEC, .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { #ifdef CONFIG_COMPAT if (!mm || mm->context.ia32_compat) return NULL; #endif if (vsyscall_mode == NONE) return NULL; return &gate_vma; } int in_gate_area(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = get_gate_vma(mm); if (!vma) return 0; return (addr >= vma->vm_start) && (addr < vma->vm_end); } /* * Use this when you have no reliable mm, typically from interrupt * context. It is less reliable than using a task's mm and may give * false positives. */ int in_gate_area_no_mm(unsigned long addr) { return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } /* * The VSYSCALL page is the only user-accessible page in the kernel address * range. Normally, the kernel page tables can have _PAGE_USER clear, but * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls * are enabled. * * Some day we may create a "minimal" vsyscall mode in which we emulate * vsyscalls but leave the page not present. If so, we skip calling * this. */ void __init set_vsyscall_pgtable_user_bits(pgd_t *root) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset_pgd(root, VSYSCALL_ADDR); set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); p4d = p4d_offset(pgd, VSYSCALL_ADDR); #if CONFIG_PGTABLE_LEVELS >= 5 set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER)); #endif pud = pud_offset(p4d, VSYSCALL_ADDR); set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); pmd = pmd_offset(pud, VSYSCALL_ADDR); set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER)); } void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); /* * For full emulation, the page needs to exist for real. In * execute-only mode, there is no PTE at all backing the vsyscall * page. */ if (vsyscall_mode == EMULATE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, PAGE_KERNEL_VVAR); set_vsyscall_pgtable_user_bits(swapper_pg_dir); } if (vsyscall_mode == XONLY) gate_vma.vm_flags = VM_EXEC; BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); } |
| 171 171 171 170 984 984 984 5 125 126 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 | // SPDX-License-Identifier: GPL-2.0-only /* net/core/xdp.c * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/bug.h> #include <net/page_pool.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> #include <net/xdp_sock_drv.h> #define REG_STATE_NEW 0x0 #define REG_STATE_REGISTERED 0x1 #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 static DEFINE_IDA(mem_id_pool); static DEFINE_MUTEX(mem_id_lock); #define MEM_ID_MAX 0xFFFE #define MEM_ID_MIN 1 static int mem_id_next = MEM_ID_MIN; static bool mem_id_init; /* false */ static struct rhashtable *mem_id_ht; static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) { const u32 *k = data; const u32 key = *k; BUILD_BUG_ON(sizeof_field(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xdp_mem_allocator *xa = ptr; u32 mem_id = *(u32 *)arg->key; return xa->mem.id != mem_id; } static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), .key_len = sizeof_field(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, .hashfn = xdp_mem_id_hashfn, .obj_cmpfn = xdp_mem_id_cmp, }; static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) { struct xdp_mem_allocator *xa; xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ ida_simple_remove(&mem_id_pool, xa->mem.id); kfree(xa); } static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); } static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; struct rhashtable_iter iter; mutex_lock(&mem_id_lock); rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { if (xa->allocator == allocator) mem_xa_remove(xa); } rhashtable_walk_stop(&iter); } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); } void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; int id = xdp_rxq->mem.id; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; } if (id == 0) return; if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) { rcu_read_lock(); xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ if (xdp_rxq->reg_state == REG_STATE_UNUSED) return; WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; /* Reset mem info to defaults */ xdp_rxq->mem.id = 0; xdp_rxq->mem.type = 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) { memset(xdp_rxq, 0, sizeof(*xdp_rxq)); } /* Returns 0 on success, negative on failure */ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index) { if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); return -EINVAL; } if (xdp_rxq->reg_state == REG_STATE_REGISTERED) { WARN(1, "Missing unregister, handled but fix driver"); xdp_rxq_info_unreg(xdp_rxq); } if (!dev) { WARN(1, "Missing net_device from driver"); return -ENODEV; } /* State either UNREGISTERED or NEW */ xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->reg_state = REG_STATE_UNUSED; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unused); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) { return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); static int __mem_id_init_hash_table(void) { struct rhashtable *rht; int ret; if (unlikely(mem_id_init)) return 0; rht = kzalloc(sizeof(*rht), GFP_KERNEL); if (!rht) return -ENOMEM; ret = rhashtable_init(rht, &mem_id_rht_params); if (ret < 0) { kfree(rht); return ret; } mem_id_ht = rht; smp_mb(); /* mutex lock should provide enough pairing */ mem_id_init = true; return 0; } /* Allocate a cyclic ID that maps to allocator pointer. * See: https://www.kernel.org/doc/html/latest/core-api/idr.html * * Caller must lock mem_id_lock. */ static int __mem_id_cyclic_get(gfp_t gfp) { int retries = 1; int id; again: id = ida_simple_get(&mem_id_pool, mem_id_next, MEM_ID_MAX, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ if (retries--) { mem_id_next = MEM_ID_MIN; goto again; } } return id; /* errno */ } mem_id_next = id + 1; return id; } static bool __is_supported_mem_type(enum xdp_mem_type type) { if (type == MEM_TYPE_PAGE_POOL) return is_page_pool_compiled_in(); if (type >= MEM_TYPE_MAX) return false; return true; } int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return -EFAULT; } if (!__is_supported_mem_type(type)) return -EOPNOTSUPP; xdp_rxq->mem.type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) return -EINVAL; /* Setup time check page_pool req */ return 0; } /* Delay init of rhashtable to save memory if feature isn't used */ if (!mem_id_init) { mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); if (ret < 0) { WARN_ON(1); return ret; } } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) return -ENOMEM; mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); if (id < 0) { errno = id; goto err; } xdp_rxq->mem.id = id; xdp_alloc->mem = xdp_rxq->mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { ida_simple_remove(&mem_id_pool, xdp_rxq->mem.id); xdp_rxq->mem.id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) page_pool_use_xdp_mem(allocator, mem_allocator_disconnect); mutex_unlock(&mem_id_lock); trace_mem_connect(xdp_alloc, xdp_rxq); return 0; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); return errno; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; switch (mem->type) { case MEM_TYPE_PAGE_POOL: rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); if (napi_direct && xdp_return_frame_no_direct()) napi_direct = false; page_pool_put_full_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: page_frag_free(data); break; case MEM_TYPE_PAGE_ORDER0: page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; case MEM_TYPE_XSK_BUFF_POOL: /* NB! Only valid from an xdp_buff! */ xsk_buff_free(xdp); break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); break; } } void xdp_return_frame(struct xdp_frame *xdpf) { __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); void xdp_return_buff(struct xdp_buff *xdp) { __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; struct page *page; rcu_read_lock(); xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); if (xa) page_pool_release_page(xa->page_pool, page); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(__xdp_release_frame); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog) bpf_prog_put(info->prog); info->prog = bpf->prog; info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) { unsigned int metasize, totsize; void *addr, *data_to_copy; struct xdp_frame *xdpf; struct page *page; /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ metasize = xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; if (sizeof(*xdpf) + totsize > PAGE_SIZE) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); xdpf = addr; memset(xdpf, 0, sizeof(*xdpf)); addr += sizeof(*xdpf); data_to_copy = metasize ? xdp->data_meta : xdp->data; memcpy(addr, data_to_copy, totsize); xdpf->data = addr + metasize; xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->frame_sz = PAGE_SIZE; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xsk_buff_free(xdp); return xdpf; } EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); /* Used by XDP_WARN macro, to avoid inlining WARN() in fast-path */ void xdp_warn(const char *msg, const char *func, const int line) { WARN(1, "XDP_WARN: %s(line:%d): %s\n", func, line, msg); }; EXPORT_SYMBOL_GPL(xdp_warn); |
| 226 1119 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/ww_mutex.h> #include <linux/preempt.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 /* * Sequence counters (seqcount_t) * * This is the raw counting mechanism, without any writer protection. * * Write side critical sections must be serialized and non-preemptible. * * If readers can be invoked from hardirq or softirq contexts, * interrupts or bottom halves must also be respectively disabled before * entering the write section. * * This mechanism can't be used if the protected data contains pointers, * as the writer can invalidate a pointer that a reader is following. * * If the write serialization mechanism is one of the common kernel * locking primitives, use a sequence counter with associated lock * (seqcount_LOCKNAME_t) instead. * * If it's desired to automatically handle the sequence counter writer * serialization and non-preemptibility requirements, use a sequential * lock (seqlock_t) instead. * * See Documentation/locking/seqlock.rst */ typedef struct seqcount { unsigned sequence; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } seqcount_t; static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot * disable preemption. It can lead to higher latencies, and the write side * sections will not be able to acquire locks which become sleeping locks * (e.g. spinlock_t). * * To remain preemptible while avoiding a possible livelock caused by the * reader preempting the writer, use a different technique: let the reader * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the * case, acquire then release the associated LOCKNAME writer serialization * lock. This will allow any possibly-preempted writer to make progress * until the end of its writer serialization lock critical section. * * This lock-unlock technique must be implemented for all of PREEMPT_RT * sleeping locks. See Documentation/locking/locktypes.rst */ #if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) #define __SEQ_LOCK(expr) expr #else #define __SEQ_LOCK(expr) #endif /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock); #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex); #define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex); /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockmember: argument for lockdep_assert_held() * @lockbase: associated lock release function (prefix only) * @lock_acquire: associated lock acquisition function (full call) */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \ typedef struct seqcount_##lockname { \ seqcount_t seqcount; \ __SEQ_LOCK(locktype *lock); \ } seqcount_##lockname##_t; \ \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = READ_ONCE(s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lock_acquire); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = READ_ONCE(s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(lockmember)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return READ_ONCE(s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_spin, raw_spin_lock(s->lock)) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s)) #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop((void *)(s)), \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop), \ __seqprop_case((s), ww_mutex, prop)) #define __seqcount_ptr(s) __seqprop(s, ptr) #define __seqcount_sequence(s) __seqprop(s, sequence) #define __seqcount_lock_preemptible(s) __seqprop(s, preemptible) #define __seqcount_assert_lock_held(s) __seqprop(s, assert) /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned seq; \ \ while ((seq = __seqcount_sequence(s)) & 1) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) \ ({ \ unsigned seq = __read_seqcount_begin(s); \ \ smp_rmb(); \ seq; \ }) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(__seqcount_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned seq = __seqcount_sequence(s); \ \ smp_rmb(); \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ seq; \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ __read_seqcount_t_retry(__seqcount_ptr(s), start) static inline int __read_seqcount_t_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ read_seqcount_t_retry(__seqcount_ptr(s), start) static inline int read_seqcount_t_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return __read_seqcount_t_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_begin(s) \ do { \ if (__seqcount_lock_preemptible(s)) \ preempt_disable(); \ \ raw_write_seqcount_t_begin(__seqcount_ptr(s)); \ } while (0) static inline void raw_write_seqcount_t_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_end(s) \ do { \ raw_write_seqcount_t_end(__seqcount_ptr(s)); \ \ if (__seqcount_lock_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void raw_write_seqcount_t_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst */ #define write_seqcount_begin_nested(s, subclass) \ do { \ __seqcount_assert_lock_held(s); \ \ if (__seqcount_lock_preemptible(s)) \ preempt_disable(); \ \ write_seqcount_t_begin_nested(__seqcount_ptr(s), subclass); \ } while (0) static inline void write_seqcount_t_begin_nested(seqcount_t *s, int subclass) { raw_write_seqcount_t_begin(s); seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * write_seqcount_begin opens a write side critical section of the given * seqcount_t. * * Context: seqcount_t write side critical sections must be serialized and * non-preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ __seqcount_assert_lock_held(s); \ \ if (__seqcount_lock_preemptible(s)) \ preempt_disable(); \ \ write_seqcount_t_begin(__seqcount_ptr(s)); \ } while (0) static inline void write_seqcount_t_begin(seqcount_t *s) { write_seqcount_t_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * The write section must've been opened with write_seqcount_begin(). */ #define write_seqcount_end(s) \ do { \ write_seqcount_t_end(__seqcount_ptr(s)); \ \ if (__seqcount_lock_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void write_seqcount_t_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); raw_write_seqcount_t_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before and after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ raw_write_seqcount_t_barrier(__seqcount_ptr(s)) static inline void raw_write_seqcount_t_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ write_seqcount_t_invalidate(__seqcount_ptr(s)) static inline void write_seqcount_t_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { return read_seqcount_retry(&s->seqcount, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * smp_wmb(); // Ensure that the last data[1] update is visible * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[0], ...); * * smp_wmb(); // Ensure that the data[0] update is visible * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[1], ...); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = raw_read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /* * Sequential locks (seqlock_t) * * Sequence counters with an embedded spinlock for writer serialization * and non-preemptibility. * * For more info, see: * - Comments on top of seqcount_t * - Documentation/locking/seqlock.rst */ typedef struct { /* * Make sure that readers don't starve writers on PREEMPT_RT: use * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). */ seqcount_spinlock_t seqcount; spinlock_t lock; } seqlock_t; #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { unsigned ret = read_seqcount_begin(&sl->seqcount); kcsan_atomic_next(0); /* non-raw usage, assume closing read_seqretry() */ kcsan_flat_atomic_begin(); return ret; } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { /* * Assume not nested: read_seqretry() may be called multiple times when * completing read critical section. */ kcsan_flat_atomic_end(); return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use write_seqcount_*t*_begin() * instead of the generic write_seqcount_begin(). This way, no redundant * lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); write_seqcount_t_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) { write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); write_seqcount_t_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) { write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); write_seqcount_t_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) { write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); write_seqcount_t_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { write_seqcount_t_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } #endif /* __LINUX_SEQLOCK_H */ |
| 21 5 506 254 59 332 649 1351 537 107 59 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ ext4_has_feature_quota(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ ext4_has_feature_quota(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\ ext4_has_feature_quota(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 /** * struct ext4_journal_cb_entry - Base structure for callback information. * * This struct is a 'seed' structure for a using with your own callback * structs. If you are using callbacks you must allocate one of these * or another struct of your own definition which has this struct * as it's first element and pass it to ext4_journal_callback_add(). */ struct ext4_journal_cb_entry { /* list information for other callbacks attached to the same handle */ struct list_head jce_list; /* Function to call with this callback structure */ void (*jce_func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int error); /* user data goes here */ }; /** * ext4_journal_callback_add: add a function to call after transaction commit * @handle: active journal transaction handle to register callback on * @func: callback function to call after the transaction has committed: * @sb: superblock of current filesystem for transaction * @jce: returned journal callback data * @rc: journal state at commit (0 = transaction committed properly) * @jce: journal callback data (internal and function private data struct) * * The registered function will be called in the context of the journal thread * after the transaction for which the handle was created has completed. * * No locks are held when the callback function is called, so it is safe to * call blocking functions from within the callback, but the callback should * not block or run for too long, or the filesystem will be blocked waiting for * the next transaction to commit. No journaling functions can be used, or * there is a risk of deadlock. * * There is no guaranteed calling order of multiple registered callbacks on * the same transaction. */ static inline void _ext4_journal_callback_add(handle_t *handle, struct ext4_journal_cb_entry *jce) { /* Add the jce to transaction's private list */ list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list); } static inline void ext4_journal_callback_add(handle_t *handle, void (*func)(struct super_block *sb, struct ext4_journal_cb_entry *jce, int rc), struct ext4_journal_cb_entry *jce) { struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); /* Add the jce to transaction's private list */ jce->jce_func = func; spin_lock(&sbi->s_md_lock); _ext4_journal_callback_add(handle, jce); spin_unlock(&sbi->s_md_lock); } /** * ext4_journal_callback_del: delete a registered callback * @handle: active journal transaction handle on which callback was registered * @jce: registered journal callback entry to unregister * Return true if object was successfully removed */ static inline bool ext4_journal_callback_try_del(handle_t *handle, struct ext4_journal_cb_entry *jce) { bool deleted; struct ext4_sb_info *sbi = EXT4_SB(handle->h_transaction->t_journal->j_private); spin_lock(&sbi->s_md_lock); deleted = !list_empty(&jce->jce_list); list_del_init(&jce->jce_list); spin_unlock(&sbi->s_md_lock); return deleted; } int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct buffer_head *bh); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct buffer_head *bh); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); int __ext4_handle_dirty_super(const char *where, unsigned int line, handle_t *handle, struct super_block *sb); #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, bh) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (bh)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) #define ext4_handle_dirty_super(handle, sb) \ __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_page(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_page(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_mutex for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } #endif /* _EXT4_JBD2_H */ |
| 669 500 499 292 291 292 303 274 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 | // SPDX-License-Identifier: GPL-2.0 /* * Inline encryption support for fscrypt * * Copyright 2019 Google LLC */ /* * With "inline encryption", the block layer handles the decryption/encryption * as part of the bio, instead of the filesystem doing the crypto itself via * crypto API. See Documentation/block/inline-encryption.rst. fscrypt still * provides the key and IV to use. */ #include <linux/blk-crypto.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/keyslot-manager.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/uio.h> #include "fscrypt_private.h" struct fscrypt_blk_crypto_key { struct blk_crypto_key base; int num_devs; struct request_queue *devs[]; }; static int fscrypt_get_num_devices(struct super_block *sb) { if (sb->s_cop->get_num_devices) return sb->s_cop->get_num_devices(sb); return 1; } static void fscrypt_get_devices(struct super_block *sb, int num_devs, struct request_queue **devs) { if (num_devs == 1) devs[0] = bdev_get_queue(sb->s_bdev); else sb->s_cop->get_devices(sb, devs); } static unsigned int fscrypt_get_dun_bytes(const struct fscrypt_info *ci) { struct super_block *sb = ci->ci_inode->i_sb; unsigned int flags = fscrypt_policy_flags(&ci->ci_policy); int ino_bits = 64, lblk_bits = 64; if (flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) return offsetofend(union fscrypt_iv, nonce); if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) return sizeof(__le64); if (flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) return sizeof(__le32); /* Default case: IVs are just the file logical block number */ if (sb->s_cop->get_ino_and_lblk_bits) sb->s_cop->get_ino_and_lblk_bits(sb, &ino_bits, &lblk_bits); return DIV_ROUND_UP(lblk_bits, 8); } /* Enable inline encryption for this file if supported. */ int fscrypt_select_encryption_impl(struct fscrypt_info *ci, bool is_hw_wrapped_key) { const struct inode *inode = ci->ci_inode; struct super_block *sb = inode->i_sb; struct blk_crypto_config crypto_cfg; int num_devs; struct request_queue **devs; int i; /* The file must need contents encryption, not filenames encryption */ if (!S_ISREG(inode->i_mode)) return 0; /* The crypto mode must have a blk-crypto counterpart */ if (ci->ci_mode->blk_crypto_mode == BLK_ENCRYPTION_MODE_INVALID) return 0; /* The filesystem must be mounted with -o inlinecrypt */ if (!(sb->s_flags & SB_INLINECRYPT)) return 0; /* * When a page contains multiple logically contiguous filesystem blocks, * some filesystem code only calls fscrypt_mergeable_bio() for the first * block in the page. This is fine for most of fscrypt's IV generation * strategies, where contiguous blocks imply contiguous IVs. But it * doesn't work with IV_INO_LBLK_32. For now, simply exclude * IV_INO_LBLK_32 with blocksize != PAGE_SIZE from inline encryption. */ if ((fscrypt_policy_flags(&ci->ci_policy) & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) && sb->s_blocksize != PAGE_SIZE) return 0; /* * On all the filesystem's devices, blk-crypto must support the crypto * configuration that the file would use. */ crypto_cfg.crypto_mode = ci->ci_mode->blk_crypto_mode; crypto_cfg.data_unit_size = sb->s_blocksize; crypto_cfg.dun_bytes = fscrypt_get_dun_bytes(ci); crypto_cfg.is_hw_wrapped = is_hw_wrapped_key; num_devs = fscrypt_get_num_devices(sb); devs = kmalloc_array(num_devs, sizeof(*devs), GFP_KERNEL); if (!devs) return -ENOMEM; fscrypt_get_devices(sb, num_devs, devs); for (i = 0; i < num_devs; i++) { if (!blk_crypto_config_supported(devs[i], &crypto_cfg)) goto out_free_devs; } ci->ci_inlinecrypt = true; out_free_devs: kfree(devs); return 0; } int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, const u8 *raw_key, unsigned int raw_key_size, bool is_hw_wrapped, const struct fscrypt_info *ci) { const struct inode *inode = ci->ci_inode; struct super_block *sb = inode->i_sb; enum blk_crypto_mode_num crypto_mode = ci->ci_mode->blk_crypto_mode; int num_devs = fscrypt_get_num_devices(sb); int queue_refs = 0; struct fscrypt_blk_crypto_key *blk_key; int err; int i; blk_key = kzalloc(struct_size(blk_key, devs, num_devs), GFP_KERNEL); if (!blk_key) return -ENOMEM; blk_key->num_devs = num_devs; fscrypt_get_devices(sb, num_devs, blk_key->devs); BUILD_BUG_ON(FSCRYPT_MAX_HW_WRAPPED_KEY_SIZE > BLK_CRYPTO_MAX_WRAPPED_KEY_SIZE); err = blk_crypto_init_key(&blk_key->base, raw_key, raw_key_size, is_hw_wrapped, crypto_mode, fscrypt_get_dun_bytes(ci), sb->s_blocksize); if (err) { fscrypt_err(inode, "error %d initializing blk-crypto key", err); goto fail; } /* * We have to start using blk-crypto on all the filesystem's devices. * We also have to save all the request_queue's for later so that the * key can be evicted from them. This is needed because some keys * aren't destroyed until after the filesystem was already unmounted * (namely, the per-mode keys in struct fscrypt_master_key). */ for (i = 0; i < num_devs; i++) { if (!blk_get_queue(blk_key->devs[i])) { fscrypt_err(inode, "couldn't get request_queue"); err = -EAGAIN; goto fail; } queue_refs++; err = blk_crypto_start_using_key(&blk_key->base, blk_key->devs[i]); if (err) { fscrypt_err(inode, "error %d starting to use blk-crypto", err); goto fail; } } /* * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). * I.e., here we publish ->blk_key with a RELEASE barrier so that * concurrent tasks can ACQUIRE it. Note that this concurrency is only * possible for per-mode keys, not for per-file keys. */ smp_store_release(&prep_key->blk_key, blk_key); return 0; fail: for (i = 0; i < queue_refs; i++) blk_put_queue(blk_key->devs[i]); kfree_sensitive(blk_key); return err; } void fscrypt_destroy_inline_crypt_key(struct fscrypt_prepared_key *prep_key) { struct fscrypt_blk_crypto_key *blk_key = prep_key->blk_key; int i; if (blk_key) { for (i = 0; i < blk_key->num_devs; i++) { blk_crypto_evict_key(blk_key->devs[i], &blk_key->base); blk_put_queue(blk_key->devs[i]); } kfree_sensitive(blk_key); } } int fscrypt_derive_raw_secret(struct super_block *sb, const u8 *wrapped_key, unsigned int wrapped_key_size, u8 *raw_secret, unsigned int raw_secret_size) { struct request_queue *q; q = bdev_get_queue(sb->s_bdev); if (!q->ksm) return -EOPNOTSUPP; return blk_ksm_derive_raw_secret(q->ksm, wrapped_key, wrapped_key_size, raw_secret, raw_secret_size); } bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) { return inode->i_crypt_info->ci_inlinecrypt; } EXPORT_SYMBOL_GPL(__fscrypt_inode_uses_inline_crypto); static void fscrypt_generate_dun(const struct fscrypt_info *ci, u64 lblk_num, u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE]) { union fscrypt_iv iv; int i; fscrypt_generate_iv(&iv, lblk_num, ci); BUILD_BUG_ON(FSCRYPT_MAX_IV_SIZE > BLK_CRYPTO_MAX_IV_SIZE); memset(dun, 0, BLK_CRYPTO_MAX_IV_SIZE); for (i = 0; i < ci->ci_mode->ivsize/sizeof(dun[0]); i++) dun[i] = le64_to_cpu(iv.dun[i]); } /** * fscrypt_set_bio_crypt_ctx() - prepare a file contents bio for inline crypto * @bio: a bio which will eventually be submitted to the file * @inode: the file's inode * @first_lblk: the first file logical block number in the I/O * @gfp_mask: memory allocation flags - these must be a waiting mask so that * bio_crypt_set_ctx can't fail. * * If the contents of the file should be encrypted (or decrypted) with inline * encryption, then assign the appropriate encryption context to the bio. * * Normally the bio should be newly allocated (i.e. no pages added yet), as * otherwise fscrypt_mergeable_bio() won't work as intended. * * The encryption context will be freed automatically when the bio is freed. * * This function also handles setting bi_skip_dm_default_key when needed. */ void fscrypt_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode, u64 first_lblk, gfp_t gfp_mask) { const struct fscrypt_info *ci; u64 dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; if (fscrypt_inode_should_skip_dm_default_key(inode)) bio_set_skip_dm_default_key(bio); if (!fscrypt_inode_uses_inline_crypto(inode)) return; ci = inode->i_crypt_info; fscrypt_generate_dun(ci, first_lblk, dun); bio_crypt_set_ctx(bio, &ci->ci_enc_key.blk_key->base, dun, gfp_mask); } EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx); /* Extract the inode and logical block number from a buffer_head. */ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, const struct inode **inode_ret, u64 *lblk_num_ret) { struct page *page = bh->b_page; const struct address_space *mapping; const struct inode *inode; /* * The ext4 journal (jbd2) can submit a buffer_head it directly created * for a non-pagecache page. fscrypt doesn't care about these. */ mapping = page_mapping(page); if (!mapping) return false; inode = mapping->host; *inode_ret = inode; *lblk_num_ret = ((u64)page->index << (PAGE_SHIFT - inode->i_blkbits)) + (bh_offset(bh) >> inode->i_blkbits); return true; } /** * fscrypt_set_bio_crypt_ctx_bh() - prepare a file contents bio for inline * crypto * @bio: a bio which will eventually be submitted to the file * @first_bh: the first buffer_head for which I/O will be submitted * @gfp_mask: memory allocation flags * * Same as fscrypt_set_bio_crypt_ctx(), except this takes a buffer_head instead * of an inode and block number directly. */ void fscrypt_set_bio_crypt_ctx_bh(struct bio *bio, const struct buffer_head *first_bh, gfp_t gfp_mask) { const struct inode *inode; u64 first_lblk; if (bh_get_inode_and_lblk_num(first_bh, &inode, &first_lblk)) fscrypt_set_bio_crypt_ctx(bio, inode, first_lblk, gfp_mask); } EXPORT_SYMBOL_GPL(fscrypt_set_bio_crypt_ctx_bh); /** * fscrypt_mergeable_bio() - test whether data can be added to a bio * @bio: the bio being built up * @inode: the inode for the next part of the I/O * @next_lblk: the next file logical block number in the I/O * * When building a bio which may contain data which should undergo inline * encryption (or decryption) via fscrypt, filesystems should call this function * to ensure that the resulting bio contains only contiguous data unit numbers. * This will return false if the next part of the I/O cannot be merged with the * bio because either the encryption key would be different or the encryption * data unit numbers would be discontiguous. * * fscrypt_set_bio_crypt_ctx() must have already been called on the bio. * * This function also returns false if the next part of the I/O would need to * have a different value for the bi_skip_dm_default_key flag. * * Return: true iff the I/O is mergeable */ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, u64 next_lblk) { const struct bio_crypt_ctx *bc = bio->bi_crypt_context; u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; if (!!bc != fscrypt_inode_uses_inline_crypto(inode)) return false; if (bio_should_skip_dm_default_key(bio) != fscrypt_inode_should_skip_dm_default_key(inode)) return false; if (!bc) return true; /* * Comparing the key pointers is good enough, as all I/O for each key * uses the same pointer. I.e., there's currently no need to support * merging requests where the keys are the same but the pointers differ. */ if (bc->bc_key != &inode->i_crypt_info->ci_enc_key.blk_key->base) return false; fscrypt_generate_dun(inode->i_crypt_info, next_lblk, next_dun); return bio_crypt_dun_is_contiguous(bc, bio->bi_iter.bi_size, next_dun); } EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio); /** * fscrypt_mergeable_bio_bh() - test whether data can be added to a bio * @bio: the bio being built up * @next_bh: the next buffer_head for which I/O will be submitted * * Same as fscrypt_mergeable_bio(), except this takes a buffer_head instead of * an inode and block number directly. * * Return: true iff the I/O is mergeable */ bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh) { const struct inode *inode; u64 next_lblk; if (!bh_get_inode_and_lblk_num(next_bh, &inode, &next_lblk)) return !bio->bi_crypt_context && !bio_should_skip_dm_default_key(bio); return fscrypt_mergeable_bio(bio, inode, next_lblk); } EXPORT_SYMBOL_GPL(fscrypt_mergeable_bio_bh); /** * fscrypt_dio_supported() - check whether a direct I/O request is unsupported * due to encryption constraints * @iocb: the file and position the I/O is targeting * @iter: the I/O data segment(s) * * Return: true if direct I/O is supported */ bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter) { const struct inode *inode = file_inode(iocb->ki_filp); const unsigned int blocksize = i_blocksize(inode); /* If the file is unencrypted, no veto from us. */ if (!fscrypt_needs_contents_encryption(inode)) return true; /* We only support direct I/O with inline crypto, not fs-layer crypto */ if (!fscrypt_inode_uses_inline_crypto(inode)) return false; /* * Since the granularity of encryption is filesystem blocks, the I/O * must be block aligned -- not just disk sector aligned. */ if (!IS_ALIGNED(iocb->ki_pos | iov_iter_alignment(iter), blocksize)) return false; return true; } EXPORT_SYMBOL_GPL(fscrypt_dio_supported); /** * fscrypt_limit_io_blocks() - limit I/O blocks to avoid discontiguous DUNs * @inode: the file on which I/O is being done * @lblk: the block at which the I/O is being started from * @nr_blocks: the number of blocks we want to submit starting at @pos * * Determine the limit to the number of blocks that can be submitted in the bio * targeting @pos without causing a data unit number (DUN) discontinuity. * * This is normally just @nr_blocks, as normally the DUNs just increment along * with the logical blocks. (Or the file is not encrypted.) * * In rare cases, fscrypt can be using an IV generation method that allows the * DUN to wrap around within logically continuous blocks, and that wraparound * will occur. If this happens, a value less than @nr_blocks will be returned * so that the wraparound doesn't occur in the middle of the bio. * * Return: the actual number of blocks that can be submitted */ u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks) { const struct fscrypt_info *ci = inode->i_crypt_info; u32 dun; if (!fscrypt_inode_uses_inline_crypto(inode)) return nr_blocks; if (nr_blocks <= 1) return nr_blocks; if (!(fscrypt_policy_flags(&ci->ci_policy) & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) return nr_blocks; /* With IV_INO_LBLK_32, the DUN can wrap around from U32_MAX to 0. */ dun = ci->ci_hashed_ino + lblk; return min_t(u64, nr_blocks, (u64)U32_MAX + 1 - dun); } EXPORT_SYMBOL_GPL(fscrypt_limit_io_blocks); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H #include <asm/segment.h> #include <asm/page_types.h> #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ #ifdef __i386__ struct pt_regs { /* * NB: 32-bit x86 CPUs are inconsistent as what happens in the * following cases (where %seg represents a segment register): * * - pushl %seg: some do a 16-bit write and leave the high * bits alone * - movl %seg, [mem]: some do a 16-bit write despite the movl * - IDT entry: some (e.g. 486) will leave the high bits of CS * and (if applicable) SS undefined. * * Fortunately, x86-32 doesn't read the high bits on POP or IRET, * so we can just treat all of the segment registers as 16-bit * values. */ unsigned long bx; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; unsigned long bp; unsigned long ax; unsigned short ds; unsigned short __dsh; unsigned short es; unsigned short __esh; unsigned short fs; unsigned short __fsh; /* On interrupt, gs and __gsh store the vector number. */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; unsigned short __csh; unsigned long flags; unsigned long sp; unsigned short ss; unsigned short __ssh; }; #else /* __i386__ */ struct pt_regs { /* * C ABI says these regs are callee-preserved. They aren't saved on kernel entry * unless syscall needs a complete, fully filled "struct pt_regs". */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; unsigned long r8; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; /* * On syscall entry, this is syscall#. On CPU exception, this is error code. * On hw interrupt, it's IRQ number: */ unsigned long orig_ax; /* Return frame for iretq */ unsigned long ip; unsigned long cs; unsigned long flags; unsigned long sp; unsigned long ss; /* top of stack page */ }; #endif /* !__i386__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif #include <asm/proto.h> struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); static inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the * register set was from protected mode with RPL-3 CS value. This * tricky test checks that with one comparison. * * On x86_64, vm86 mode is mercifully nonexistent, and we don't need * the extra check. */ static __always_inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif } static inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return (regs->flags & X86_VM_MASK); #else return 0; /* No V86 mode support in long mode */ #endif } static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. */ return regs->cs == __USER_CS; #else /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif #else /* !CONFIG_X86_64 */ return false; #endif } /* * Determine whether the register set came from any context that is running in * 64-bit mode. */ static inline bool any_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 return !user_mode(regs) || user_64bit_mode(regs); #else return false; #endif } #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp static inline bool ip_within_syscall_gap(struct pt_regs *regs) { bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); #endif return ret; } #endif static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } static inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } static inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->flags & X86_EFLAGS_IF); } /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); extern const char *regs_query_register_name(unsigned int offset); #define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten. * @offset: offset number of the register. * * regs_get_register returns the value of a register. The @offset is the * offset of the register in struct pt_regs address which specified by @regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) { if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || offset == offsetof(struct pt_regs, ds) || offset == offsetof(struct pt_regs, es) || offset == offsetof(struct pt_regs, fs) || offset == offsetof(struct pt_regs, gs)) { return *(u16 *)((unsigned long)regs + offset); } #endif return *(unsigned long *)((unsigned long)regs + offset); } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns the address of the @n th entry of the * kernel stack which is specified by @regs. If the @n th entry is NOT in * the kernel stack, this returns NULL. */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return addr; else return NULL; } /* To avoid include hell, we can't include uaccess.h */ extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr; unsigned long val; long ret; addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } return 0; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * Note that this chooses most probably assignment, in some case * it can be incorrect. * This is expected to be called from kprobes or ftrace with regs * where the top of stack is the return address. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), offsetof(struct pt_regs, si), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), offsetof(struct pt_regs, r8), offsetof(struct pt_regs, r9), #define NR_REG_ARGUMENTS 6 #endif }; if (n >= NR_REG_ARGUMENTS) { n -= NR_REG_ARGUMENTS - 1; return regs_get_kernel_stack_nth(regs, n); } else return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); #ifdef CONFIG_X86_64 # define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) #else # define do_set_thread_area_64(p, s, t) (0) #endif #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PTRACE_H */ |
| 2 6 3 1 2 1 2 4 2 385 2 2 3 1 2 1 1 2 1 1 12 11 7 1 1 77 1 1 76 16 1 1 1 1 3 1 1 1 1 1 2 1 1 1 1 5 3 2 3 1 2 1 2 1 1 1 4 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 2 2 4 1 1 1 1 2 1260 1032 233 1259 964 1116 1259 31 352 1258 1031 382 385 385 1 384 189 4 384 385 387 198 368 1260 1258 121 134 77 93 3 90 90 89 34 1 33 3 137 4 1 2 133 1 1 1 1 1 8 49 49 46 39 57 6 6 36 16 15 121 101 45 328 33 21 3 1260 1047 216 1032 233 1272 1268 1195 1266 46 1258 11 1272 5 5 1 2 3 4 17 1 16 954 954 819 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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 <asm/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/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/uaccess.h> #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.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 <trace/hooks/sched.h> #include <net/tcp.h> #include <net/busy_poll.h> static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); static void sock_inuse_add(struct net *net, int val); /** * 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_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; /* Maximal space eaten by iovec or ancillary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); EXPORT_SYMBOL(sysctl_optmem_max); int sysctl_tstamp_allow_data __read_mostly = 1; 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 = sk->sk_backlog_rcv(sk, skb); memalloc_noreclaim_restore(noreclaim_flag); return ret; } EXPORT_SYMBOL(__sk_backlog_rcv); static 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); } static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, bool old_timeval) { struct __kernel_sock_timeval tv; 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; } if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; if (tv.tv_sec < 0) { static int warned __read_mostly; *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; } *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); 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) >= 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(struct sock *sk, struct sk_buff *skb) { int err; err = sk_filter(sk, skb); if (err) return err; return __sock_queue_rcv_skb(sk, skb); } EXPORT_SYMBOL(sock_queue_rcv_skb); 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, 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); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); 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 && dst->ops->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; 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; } return sock_bindtoindex(sk, index, true); out: #endif return ret; } static int sock_getbindtodevice(struct sock *sk, char __user *optval, int __user *optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); char devname[IFNAMSIZ]; if (sk->sk_bound_dev_if == 0) { len = 0; goto zero; } ret = -EINVAL; if (len < IFNAMSIZ) goto out; ret = netdev_get_name(net, devname, sk->sk_bound_dev_if); if (ret) goto out; len = strlen(devname) + 1; ret = -EFAULT; if (copy_to_user(optval, devname, len)) goto out; zero: ret = -EFAULT; if (put_user(len, optlen)) goto out; ret = 0; out: #endif return ret; } bool sk_mc_loop(struct sock *sk) { if (dev_recursion_level()) return false; if (!sk) return true; switch (sk->sk_family) { case AF_INET: return inet_sk(sk)->mc_loop; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return inet6_sk(sk)->mc_loop; #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); 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) { lock_sock(sk); sk->sk_priority = priority; release_sock(sk); } 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) sk->sk_sndtimeo = secs * HZ; else 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) { if (val) { sock_valbool_flag(sk, SOCK_TSTAMP_NEW, new); sock_valbool_flag(sk, SOCK_RCVTSTAMPNS, ns); sock_set_flag(sk, SOCK_RCVTSTAMP); sock_enable_timestamp(sk, SOCK_TIMESTAMP); } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); } } 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_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) { 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); /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. */ int sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock_txtime sk_txtime; struct sock *sk = sock->sk; 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; lock_sock(sk); switch (optname) { case SO_DEBUG: if (val && !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_TYPE: case SO_PROTOCOL: case SO_DOMAIN: case SO_ERROR: ret = -ENOPROTOOPT; 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, 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 (!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, sysctl_rmem_max)); break; case SO_RCVBUFFORCE: if (!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_PRIORITY: if ((val >= 0 && val <= 6) || ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) sk->sk_priority = val; else ret = -EPERM; 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 { #if (BITS_PER_LONG == 32) if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ) sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT; else #endif sk->sk_lingertime = (unsigned int)ling.l_linger * HZ; sock_set_flag(sk, SOCK_LINGER); } break; case SO_BSDCOMPAT: break; case SO_PASSCRED: if (valbool) set_bit(SOCK_PASSCRED, &sock->flags); else clear_bit(SOCK_PASSCRED, &sock->flags); break; 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; case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; break; } if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk->sk_protocol == IPPROTO_TCP && sk->sk_type == SOCK_STREAM) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) { ret = -EINVAL; break; } sk->sk_tskey = tcp_sk(sk)->snd_una; } else { sk->sk_tskey = 0; } } if (val & SOF_TIMESTAMPING_OPT_STATS && !(val & SOF_TIMESTAMPING_OPT_TSONLY)) { ret = -EINVAL; break; } 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)); break; case SO_RCVLOWAT: if (val < 0) val = INT_MAX; if (sock->ops->set_rcvlowat) ret = sock->ops->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_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); else clear_bit(SOCK_PASSSEC, &sock->flags); break; case SO_MARK: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; break; } __sock_set_mark(sk, val); 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_PEEK_OFF: if (sock->ops->set_peek_off) ret = sock->ops->set_peek_off(sk, val); else ret = -EOPNOTSUPP; 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; #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) ret = -EPERM; else { if (val < 0) ret = -EINVAL; else WRITE_ONCE(sk->sk_ll_usec, val); } break; #endif case SO_MAX_PACING_RATE: { unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val; if (sizeof(ulval) != sizeof(val) && optlen >= sizeof(ulval) && copy_from_sockptr(&ulval, optval, sizeof(ulval))) { ret = -EFAULT; break; } if (ulval != ~0UL) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); sk->sk_max_pacing_rate = ulval; sk->sk_pacing_rate = min(sk->sk_pacing_rate, ulval); break; } case SO_INCOMING_CPU: WRITE_ONCE(sk->sk_incoming_cpu, 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->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -ENOTSUPP; } else if (sk->sk_family != PF_RDS) { ret = -ENOTSUPP; } 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 && !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { ret = -EPERM; 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; default: ret = -ENOPROTOOPT; break; } release_sock(sk); return ret; } 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(gid_t __user *dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; for (i = 0; i < src->ngroups; i++) if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i)) return -EFAULT; return 0; } int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; 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; } v; int lv = sizeof(int); int len; if (get_user(len, optlen)) 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 = sk->sk_sndbuf; break; case SO_RCVBUF: v.val = 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 = sk->sk_priority; break; case SO_LINGER: lv = sizeof(v.ling); v.ling.l_onoff = sock_flag(sk, SOCK_LINGER); v.ling.l_linger = 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: v.val = sk->sk_tsflags; break; case SO_RCVTIMEO_OLD: case SO_RCVTIMEO_NEW: lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); break; case SO_SNDTIMEO_OLD: case SO_SNDTIMEO_NEW: lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: v.val = 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_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_user(optval, &peercred, len)) return -EFAULT; goto lenout; } 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 put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); ret = groups_to_user((gid_t __user *)optval, cred->group_info); put_cred(cred); if (ret) return ret; goto lenout; } case SO_PEERNAME: { char address[128]; lv = sock->ops->getname(sock, (struct sockaddr *)address, 2); if (lv < 0) return -ENOTCONN; if (lv < len) return -EINVAL; if (copy_to_user(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 = sk->sk_mark; 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 (!sock->ops->set_peek_off) return -EOPNOTSUPP; v.val = 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, (struct sock_filter __user *)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 = sk->sk_ll_usec; break; #endif case SO_MAX_PACING_RATE: if (sizeof(v.ulval) != sizeof(v.val) && len >= sizeof(v.ulval)) { lv = sizeof(v.ulval); v.ulval = sk->sk_max_pacing_rate; } else { /* 32bit version */ v.val = min_t(unsigned long, sk->sk_max_pacing_rate, ~0U); } 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_user(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 = sk->sk_bound_dev_if; 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_user(optval, &v, len)) return -EFAULT; lenout: if (put_user(len, optlen)) 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 temporarly, 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 memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); #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; sk_tx_queue_clear(sk); } 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(net); sock_inuse_add(net, 1); } 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(sock_net(sk)); 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]); 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(sock_net(newsk)); sock_inuse_add(sock_net(newsk), 1); } 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; 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); /* Increment the counter in the same struct proto as the master * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that * is the same as sk->sk_prot->socks, as this field was copied * with memcpy). * * This _changes_ the previous behaviour, where * tcp_create_openreq_child always was incrementing the * equivalent to tcp_prot->socks (inet_sock_nr), so this have * to be taken into account in all callers. -acme */ sk_refcnt_debug_inc(newsk); 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); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; sk->sk_route_caps &= ~sk->sk_route_nocaps; 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 = dst->dev->gso_max_size; max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } sk->sk_gso_max_segs = max_segs; } 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; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { /* * 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); skb->sk = sk; #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) { skb->destructor = sock_edemux; sock_hold(sk); return; } #endif 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() wont 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) { #ifdef CONFIG_TLS_DEVICE /* Drivers depend on in-order delivery for crypto offload, * partial orphan breaks out-of-order-OK logic. */ if (skb->decrypted) return false; #endif 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) { if (sk_is_refcounted(skb->sk)) sock_gen_put(skb->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_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; read_unlock_bh(&sk->sk_callback_lock); 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) > 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) { if ((unsigned int)size <= sysctl_optmem_max && atomic_read(&sk->sk_omem_alloc) + size < sysctl_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 (sk->sk_shutdown & SEND_SHUTDOWN) break; if (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 (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); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); } EXPORT_SYMBOL(sock_alloc_send_skb); int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; switch (cmsg->cmsg_type) { case SO_MARK: if (!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: 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; /* 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, msg, 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) { sk->sk_prot->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 SKB_FRAG_PAGE_ORDER get_order(32768) 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); static 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); 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); spin_unlock_bh(&sk->sk_lock.slock); } /** * 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 */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { struct proto *prot = sk->sk_prot; long allocated = sk_memory_allocated_add(sk, amt); bool charged = true; if (mem_cgroup_sockets_enabled && sk->sk_memcg && !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt))) goto suppress_allocation; /* 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 */ 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; if (!sk_under_memory_pressure(sk)) return 1; 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) 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 (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); return 0; } EXPORT_SYMBOL(__sk_mem_raise_allocated); /** * __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->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT; ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_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_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } EXPORT_SYMBOL(__sk_mem_reduce_allocated); /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { amount >>= SK_MEM_QUANTUM_SHIFT; sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { 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, int flags, bool kern) { 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; int error; /* * The resulting value of "error" is ignored here since we only * need to take action when the file is a socket and testing * "sock" for NULL is sufficient. */ sock = sock_from_file(file, &error); if (sock) { sock_update_netprioidx(&sock->sk->sk_cgrp_data); sock_update_classid(&sock->sk->sk_cgrp_data); } } ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; struct msghdr msg = {.msg_flags = flags}; struct kvec iov; char *kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; res = kernel_sendmsg(sock, &msg, &iov, 1, size); kunmap(page); return res; } EXPORT_SYMBOL(sock_no_sendpage); ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { ssize_t res; struct msghdr msg = {.msg_flags = flags}; struct kvec iov; char *kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size); kunmap(page); return res; } EXPORT_SYMBOL(sock_no_sendpage_locked); /* * 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(sk, SOCK_WAKE_IO, POLL_ERR); rcu_read_unlock(); } void sock_def_readable(struct sock *sk) { struct socket_wq *wq; rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) { int done = 0; trace_android_vh_do_wake_up_sync(&wq->wait, &done); if (done) goto out; wake_up_interruptible_sync_poll(&wq->wait, EPOLLIN | EPOLLPRI | EPOLLRDNORM | EPOLLRDBAND); } out: sk_wake_async(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 ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { 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 */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } 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->f_owner)) 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(struct socket *sock, struct sock *sk) { sk_init_common(sk); sk->sk_send_head = NULL; timer_setup(&sk->sk_timer, NULL, 0); sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; sk->sk_sndbuf = sysctl_wmem_default; sk->sk_state = TCP_CLOSE; 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; sk->sk_uid = SOCK_INODE(sock)->i_uid; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } rwlock_init(&sk->sk_callback_lock); 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->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 = 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); void lock_sock_nested(struct sock *sk, int subclass) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); } 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); /* Warning : release_cb() might need to release sk ownership, * ie call sock_release_ownership(sk) before us. */ if (sk->sk_prot->release_cb) sk->sk_prot->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); /** * lock_sock_fast - fast version of lock_sock * @sk: socket * * This version should be used for very small section, where process wont block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled * * return true if slow path is taken: * * sk_lock.slock unlocked, owned = 1, BH enabled */ bool lock_sock_fast(struct sock *sk) { might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (!sk->sk_lock.owned) /* * Note : We must disable BH */ return false; __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock(&sk->sk_lock.slock); /* * The sk_lock has mutex_lock() semantics here: */ mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); local_bh_enable(); 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 whats 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; return 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 & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &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; return 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); sk_refcnt_debug_release(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->sk_forward_alloc; 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 #define PROTO_INUSE_NR 64 /* should be enough for the first time */ struct prot_inuse { int val[PROTO_INUSE_NR]; }; static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { __this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } EXPORT_SYMBOL_GPL(sock_prot_inuse_add); 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); static void sock_inuse_add(struct net *net, int val) { this_cpu_add(*net->core.sock_inuse, val); } int sock_inuse_get(struct net *net) { int cpu, res = 0; for_each_possible_cpu(cpu) res += *per_cpu_ptr(net->core.sock_inuse, cpu); 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; net->core.sock_inuse = alloc_percpu(int); if (net->core.sock_inuse == NULL) goto out; return 0; out: free_percpu(net->core.prot_inuse); return -ENOMEM; } static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.prot_inuse); free_percpu(net->core.sock_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) { } static void sock_inuse_add(struct net *net, int val) { } #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 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 (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 (prot->twsk_prot != NULL) { prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); if (prot->twsk_prot->twsk_slab_name == NULL) goto out_free_request_sock_slab; prot->twsk_prot->twsk_slab = kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, 0, SLAB_ACCOUNT | prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) 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 && prot->twsk_prot) 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 %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->sendpage), 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 sp 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; return !skb_queue_empty_lockless(&sk->sk_receive_queue) || 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); |
| 66 66 25 25 50 50 20 50 50 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_api.c Packet scheduler API. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * * Rani Assaf <rani@magic.metawire.com> :980802: JIFFIES and CPU clock sources are repaired. * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support * Jamal Hadi Salim <hadi@nortelnetworks.com>: 990601: ingress support */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> #include <linux/slab.h> #include <linux/hashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <trace/events/qdisc.h> /* Short review. ------------- This file consists of two interrelated parts: 1. queueing disciplines manager frontend. 2. traffic classes manager frontend. Generally, queueing discipline ("qdisc") is a black box, which is able to enqueue packets and to dequeue them (when device is ready to send something) in order and at times determined by algorithm hidden in it. qdisc's are divided to two categories: - "queues", which have no internal structure visible from outside. - "schedulers", which split all the packets to "traffic classes", using "packet classifiers" (look at cls_api.c) In turn, classes may have child qdiscs (as rule, queues) attached to them etc. etc. etc. The goal of the routines in this file is to translate information supplied by user in the form of handles to more intelligible for kernel form, to make some sanity checks and part of work, which is common to all qdiscs and to provide rtnetlink notifications. All real intelligent work is done inside qdisc modules. Every discipline has two major routines: enqueue and dequeue. ---dequeue dequeue usually returns a skb to send. It is allowed to return NULL, but it does not mean that queue is empty, it just means that discipline does not want to send anything this time. Queue is really empty if q->q.qlen == 0. For complicated disciplines with multiple queues q->q is not real packet queue, but however q->q.qlen must be valid. ---enqueue enqueue returns 0, if packet was enqueued successfully. If packet (this one or another one) was dropped, it returns not zero error code. NET_XMIT_DROP - this packet dropped Expected action: do not backoff, but wait until queue will clear. NET_XMIT_CN - probably this packet enqueued, but another one dropped. Expected action: backoff or ignore Auxiliary routines: ---peek like dequeue but without removing a packet from the queue ---reset returns qdisc to initial state: purge all buffers, clear all timers, counters (except for statistics) etc. ---init initializes newly created qdisc. ---destroy destroys resources allocated by init and during lifetime of qdisc. ---change changes qdisc parameters. */ /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(qdisc_mod_lock); /************************************************ * Queueing disciplines manipulation. * ************************************************/ /* The list of all installed queueing disciplines. */ static struct Qdisc_ops *qdisc_base; /* Register/unregister queueing discipline */ int register_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int rc = -EEXIST; write_lock(&qdisc_mod_lock); for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (!strcmp(qops->id, q->id)) goto out; if (qops->enqueue == NULL) qops->enqueue = noop_qdisc_ops.enqueue; if (qops->peek == NULL) { if (qops->dequeue == NULL) qops->peek = noop_qdisc_ops.peek; else goto out_einval; } if (qops->dequeue == NULL) qops->dequeue = noop_qdisc_ops.dequeue; if (qops->cl_ops) { const struct Qdisc_class_ops *cops = qops->cl_ops; if (!(cops->find && cops->walk && cops->leaf)) goto out_einval; if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) goto out_einval; } qops->next = NULL; *qp = qops; rc = 0; out: write_unlock(&qdisc_mod_lock); return rc; out_einval: rc = -EINVAL; goto out; } EXPORT_SYMBOL(register_qdisc); int unregister_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int err = -ENOENT; write_lock(&qdisc_mod_lock); for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (q == qops) break; if (q) { *qp = q->next; q->next = NULL; err = 0; } write_unlock(&qdisc_mod_lock); return err; } EXPORT_SYMBOL(unregister_qdisc); /* Get default qdisc if not otherwise specified */ void qdisc_get_default(char *name, size_t len) { read_lock(&qdisc_mod_lock); strlcpy(name, default_qdisc_ops->id, len); read_unlock(&qdisc_mod_lock); } static struct Qdisc_ops *qdisc_lookup_default(const char *name) { struct Qdisc_ops *q = NULL; for (q = qdisc_base; q; q = q->next) { if (!strcmp(name, q->id)) { if (!try_module_get(q->owner)) q = NULL; break; } } return q; } /* Set new default qdisc to use */ int qdisc_set_default(const char *name) { const struct Qdisc_ops *ops; if (!capable(CAP_NET_ADMIN)) return -EPERM; write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); if (!ops) { /* Not found, drop lock and try to load module */ write_unlock(&qdisc_mod_lock); request_module("sch_%s", name); write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); } if (ops) { /* Set new default */ module_put(default_qdisc_ops->owner); default_qdisc_ops = ops; } write_unlock(&qdisc_mod_lock); return ops ? 0 : -ENOENT; } #ifdef CONFIG_NET_SCH_DEFAULT /* Set default value from kernel config */ static int __init sch_default_qdisc(void) { return qdisc_set_default(CONFIG_DEFAULT_NET_SCH); } late_initcall(sch_default_qdisc); #endif /* We know handle. Find qdisc among all qdisc's attached to device * (root qdisc, all its children, children of children etc.) * Note: caller either uses rtnl or rcu_read_lock() */ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) { struct Qdisc *q; if (!qdisc_dev(root)) return (root->handle == handle ? root : NULL); if (!(root->flags & TCQ_F_BUILTIN) && root->handle == handle) return root; hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle, lockdep_rtnl_is_held()) { if (q->handle == handle) return q; } return NULL; } void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); if (invisible) q->flags |= TCQ_F_INVISIBLE; } } EXPORT_SYMBOL(qdisc_hash_add); void qdisc_hash_del(struct Qdisc *q) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { ASSERT_RTNL(); hash_del_rcu(&q->hash); } } EXPORT_SYMBOL(qdisc_hash_del); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; if (!handle) return NULL; q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out; if (dev_ingress_queue(dev)) q = qdisc_match_from_root( dev_ingress_queue(dev)->qdisc_sleeping, handle); out: return q; } struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) { struct netdev_queue *nq; struct Qdisc *q; if (!handle) return NULL; q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); if (q) goto out; nq = dev_ingress_queue_rcu(dev); if (nq) q = qdisc_match_from_root(nq->qdisc_sleeping, handle); out: return q; } static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; const struct Qdisc_class_ops *cops = p->ops->cl_ops; if (cops == NULL) return NULL; cl = cops->find(p, classid); if (cl == 0) return NULL; return cops->leaf(p, cl); } /* Find queueing discipline by name */ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) { struct Qdisc_ops *q = NULL; if (kind) { read_lock(&qdisc_mod_lock); for (q = qdisc_base; q; q = q->next) { if (nla_strcmp(kind, q->id) == 0) { if (!try_module_get(q->owner)) q = NULL; break; } } read_unlock(&qdisc_mod_lock); } return q; } /* The linklayer setting were not transferred from iproute2, in older * versions, and the rate tables lookup systems have been dropped in * the kernel. To keep backward compatible with older iproute2 tc * utils, we detect the linklayer setting by detecting if the rate * table were modified. * * For linklayer ATM table entries, the rate table will be aligned to * 48 bytes, thus some table entries will contain the same value. The * mpu (min packet unit) is also encoded into the old rate table, thus * starting from the mpu, we find low and high table entries for * mapping this cell. If these entries contain the same value, when * the rate tables have been modified for linklayer ATM. * * This is done by rounding mpu to the nearest 48 bytes cell/entry, * and then roundup to the next cell, calc the table entry one below, * and compare. */ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) { int low = roundup(r->mpu, 48); int high = roundup(low+1, 48); int cell_low = low >> r->cell_log; int cell_high = (high >> r->cell_log) - 1; /* rtab is too inaccurate at rates > 100Mbit/s */ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { pr_debug("TC linklayer: Giving up ATM detection\n"); return TC_LINKLAYER_ETHERNET; } if ((cell_high > cell_low) && (cell_high < 256) && (rtab[cell_low] == rtab[cell_high])) { pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", cell_low, cell_high, rtab[cell_high]); return TC_LINKLAYER_ATM; } return TC_LINKLAYER_ETHERNET; } static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack) { struct qdisc_rate_table *rtab; if (tab == NULL || r->rate == 0 || r->cell_log == 0 || r->cell_log >= 32 || nla_len(tab) != TC_RTAB_SIZE) { NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching"); return NULL; } for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) { if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) && !memcmp(&rtab->data, nla_data(tab), 1024)) { rtab->refcnt++; return rtab; } } rtab = kmalloc(sizeof(*rtab), GFP_KERNEL); if (rtab) { rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); if (r->linklayer == TC_LINKLAYER_UNAWARE) r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } else { NL_SET_ERR_MSG(extack, "Failed to allocate new qdisc rate table"); } return rtab; } EXPORT_SYMBOL(qdisc_get_rtab); void qdisc_put_rtab(struct qdisc_rate_table *tab) { struct qdisc_rate_table *rtab, **rtabp; if (!tab || --tab->refcnt) return; for (rtabp = &qdisc_rtab_list; (rtab = *rtabp) != NULL; rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; kfree(rtab); return; } } } EXPORT_SYMBOL(qdisc_put_rtab); static LIST_HEAD(qdisc_stab_list); static const struct nla_policy stab_policy[TCA_STAB_MAX + 1] = { [TCA_STAB_BASE] = { .len = sizeof(struct tc_sizespec) }, [TCA_STAB_DATA] = { .type = NLA_BINARY }, }; static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_STAB_MAX + 1]; struct qdisc_size_table *stab; struct tc_sizespec *s; unsigned int tsize = 0; u16 *tab = NULL; int err; err = nla_parse_nested_deprecated(tb, TCA_STAB_MAX, opt, stab_policy, extack); if (err < 0) return ERR_PTR(err); if (!tb[TCA_STAB_BASE]) { NL_SET_ERR_MSG(extack, "Size table base attribute is missing"); return ERR_PTR(-EINVAL); } s = nla_data(tb[TCA_STAB_BASE]); if (s->tsize > 0) { if (!tb[TCA_STAB_DATA]) { NL_SET_ERR_MSG(extack, "Size table data attribute is missing"); return ERR_PTR(-EINVAL); } tab = nla_data(tb[TCA_STAB_DATA]); tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16); } if (tsize != s->tsize || (!tab && tsize > 0)) { NL_SET_ERR_MSG(extack, "Invalid size of size table"); return ERR_PTR(-EINVAL); } list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) continue; if (tsize > 0 && memcmp(stab->data, tab, tsize * sizeof(u16))) continue; stab->refcnt++; return stab; } if (s->size_log > STAB_SIZE_LOG_MAX || s->cell_log > STAB_SIZE_LOG_MAX) { NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); return ERR_PTR(-EINVAL); } stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); stab->refcnt = 1; stab->szopts = *s; if (tsize > 0) memcpy(stab->data, tab, tsize * sizeof(u16)); list_add_tail(&stab->list, &qdisc_stab_list); return stab; } void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) return; if (--tab->refcnt == 0) { list_del(&tab->list); kfree_rcu(tab, rcu); } } EXPORT_SYMBOL(qdisc_put_stab); static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) goto nla_put_failure; nla_nest_end(skb, nest); return skb->len; nla_put_failure: return -1; } void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) { int pkt_len, slot; pkt_len = skb->len + stab->szopts.overhead; if (unlikely(!stab->szopts.tsize)) goto out; slot = pkt_len + stab->szopts.cell_align; if (unlikely(slot < 0)) slot = 0; slot >>= stab->szopts.cell_log; if (likely(slot < stab->szopts.tsize)) pkt_len = stab->data[slot]; else pkt_len = stab->data[stab->szopts.tsize - 1] * (slot / stab->szopts.tsize) + stab->data[slot % stab->szopts.tsize]; pkt_len <<= stab->szopts.size_log; out: if (unlikely(pkt_len < 1)) pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } EXPORT_SYMBOL(__qdisc_calculate_pkt_len); void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) { if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", txt, qdisc->ops->id, qdisc->handle >> 16); qdisc->flags |= TCQ_F_WARN_NONWC; } } EXPORT_SYMBOL(qdisc_warn_nonwc); static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, timer); rcu_read_lock(); __netif_schedule(qdisc_root(wd->qdisc)); rcu_read_unlock(); return HRTIMER_NORESTART; } void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, clockid_t clockid) { hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED); wd->timer.function = qdisc_watchdog; wd->qdisc = qdisc; } EXPORT_SYMBOL(qdisc_watchdog_init_clockid); void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) { qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC); } EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns) { if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc_root_sleeping(wd->qdisc)->state)) return; if (hrtimer_is_queued(&wd->timer)) { /* If timer is already set in [expires, expires + delta_ns], * do not reprogram it. */ if (wd->last_expires - expires <= delta_ns) return; } wd->last_expires = expires; hrtimer_start_range_ns(&wd->timer, ns_to_ktime(expires), delta_ns, HRTIMER_MODE_ABS_PINNED); } EXPORT_SYMBOL(qdisc_watchdog_schedule_range_ns); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { hrtimer_cancel(&wd->timer); } EXPORT_SYMBOL(qdisc_watchdog_cancel); static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) { struct hlist_head *h; unsigned int i; h = kvmalloc_array(n, sizeof(struct hlist_head), GFP_KERNEL); if (h != NULL) { for (i = 0; i < n; i++) INIT_HLIST_HEAD(&h[i]); } return h; } void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) { struct Qdisc_class_common *cl; struct hlist_node *next; struct hlist_head *nhash, *ohash; unsigned int nsize, nmask, osize; unsigned int i, h; /* Rehash when load factor exceeds 0.75 */ if (clhash->hashelems * 4 <= clhash->hashsize * 3) return; nsize = clhash->hashsize * 2; nmask = nsize - 1; nhash = qdisc_class_hash_alloc(nsize); if (nhash == NULL) return; ohash = clhash->hash; osize = clhash->hashsize; sch_tree_lock(sch); for (i = 0; i < osize; i++) { hlist_for_each_entry_safe(cl, next, &ohash[i], hnode) { h = qdisc_class_hash(cl->classid, nmask); hlist_add_head(&cl->hnode, &nhash[h]); } } clhash->hash = nhash; clhash->hashsize = nsize; clhash->hashmask = nmask; sch_tree_unlock(sch); kvfree(ohash); } EXPORT_SYMBOL(qdisc_class_hash_grow); int qdisc_class_hash_init(struct Qdisc_class_hash *clhash) { unsigned int size = 4; clhash->hash = qdisc_class_hash_alloc(size); if (!clhash->hash) return -ENOMEM; clhash->hashsize = size; clhash->hashmask = size - 1; clhash->hashelems = 0; return 0; } EXPORT_SYMBOL(qdisc_class_hash_init); void qdisc_class_hash_destroy(struct Qdisc_class_hash *clhash) { kvfree(clhash->hash); } EXPORT_SYMBOL(qdisc_class_hash_destroy); void qdisc_class_hash_insert(struct Qdisc_class_hash *clhash, struct Qdisc_class_common *cl) { unsigned int h; INIT_HLIST_NODE(&cl->hnode); h = qdisc_class_hash(cl->classid, clhash->hashmask); hlist_add_head(&cl->hnode, &clhash->hash[h]); clhash->hashelems++; } EXPORT_SYMBOL(qdisc_class_hash_insert); void qdisc_class_hash_remove(struct Qdisc_class_hash *clhash, struct Qdisc_class_common *cl) { hlist_del(&cl->hnode); clhash->hashelems--; } EXPORT_SYMBOL(qdisc_class_hash_remove); /* Allocate an unique handle from space managed by kernel * Possible range is [8000-FFFF]:0000 (0x8000 values) */ static u32 qdisc_alloc_handle(struct net_device *dev) { int i = 0x8000; static u32 autohandle = TC_H_MAKE(0x80000000U, 0); do { autohandle += TC_H_MAKE(0x10000U, 0); if (autohandle == TC_H_MAKE(TC_H_ROOT, 0)) autohandle = TC_H_MAKE(0x80000000U, 0); if (!qdisc_lookup(dev, autohandle)) return autohandle; cond_resched(); } while (--i > 0); return 0; } void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; bool notify; int drops; if (n == 0 && len == 0) return; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { if (TC_H_MAJ(parentid) == TC_H_MAJ(TC_H_INGRESS)) break; if (sch->flags & TCQ_F_NOPARENT) break; /* Notify parent qdisc only if child qdisc becomes empty. * * If child was empty even before update then backlog * counter is screwed and we skip notification because * parent class is already passive. * * If the original child was offloaded then it is allowed * to be seem as empty, so the parent is notified anyway. */ notify = !sch->q.qlen && !WARN_ON_ONCE(!n && !qdisc_is_offloaded); /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; } cops = sch->ops->cl_ops; if (notify && cops->qlen_notify) { cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); } sch->q.qlen -= n; sch->qstats.backlog -= len; __qdisc_qstats_drop(sch, drops); } rcu_read_unlock(); } EXPORT_SYMBOL(qdisc_tree_reduce_backlog); int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type, void *type_data) { struct net_device *dev = qdisc_dev(sch); int err; sch->flags &= ~TCQ_F_OFFLOADED; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return 0; err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); if (err == -EOPNOTSUPP) return 0; if (!err) sch->flags |= TCQ_F_OFFLOADED; return err; } EXPORT_SYMBOL(qdisc_offload_dump_helper); void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack) { bool any_qdisc_is_offloaded; int err; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); /* Don't report error if the graft is part of destroy operation. */ if (!err || !new || new == &noop_qdisc) return; /* Don't report error if the parent, the old child and the new * one are not offloaded. */ any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED; any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED; any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED; if (any_qdisc_is_offloaded) NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); } EXPORT_SYMBOL(qdisc_offload_graft_helper); static void qdisc_offload_graft_root(struct net_device *dev, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct tc_root_qopt_offload graft_offload = { .command = TC_ROOT_GRAFT, .handle = new ? new->handle : 0, .ingress = (new && new->flags & TCQ_F_INGRESS) || (old && old->flags & TCQ_F_INGRESS), }; qdisc_offload_graft_helper(dev, NULL, new, old, TC_SETUP_ROOT_QDISC, &graft_offload, extack); } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event) { struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; struct qdisc_size_table *stab; u32 block_index; __u32 qlen; cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (q->ops->ingress_block_get) { block_index = q->ops->ingress_block_get(q); if (block_index && nla_put_u32(skb, TCA_INGRESS_BLOCK, block_index)) goto nla_put_failure; } if (q->ops->egress_block_get) { block_index = q->ops->egress_block_get(q); if (block_index && nla_put_u32(skb, TCA_EGRESS_BLOCK, block_index)) goto nla_put_failure; } if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) goto nla_put_failure; qlen = qdisc_qlen_sum(q); stab = rtnl_dereference(q->stab); if (stab && qdisc_dump_stab(skb, stab) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0) goto nla_put_failure; if (qdisc_is_percpu_stats(q)) { cpu_bstats = q->cpu_bstats; cpu_qstats = q->cpu_qstats; } if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q), &d, cpu_bstats, &q->bstats) < 0 || gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; } static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) { if (q->flags & TCQ_F_BUILTIN) return true; if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) return true; return false; } static int qdisc_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; } if (skb->len) return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); return -EINVAL; } static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new) { if (new || old) qdisc_notify(net, skb, n, clid, old, new); if (old) qdisc_put(old); } static void qdisc_clear_nolock(struct Qdisc *sch) { sch->flags &= ~TCQ_F_NOLOCK; if (!(sch->flags & TCQ_F_CPUSTATS)) return; free_percpu(sch->cpu_bstats); free_percpu(sch->cpu_qstats); sch->cpu_bstats = NULL; sch->cpu_qstats = NULL; sch->flags &= ~TCQ_F_CPUSTATS; } /* Graft qdisc "new" to class "classid" of qdisc "parent" or * to device "dev". * * When appropriate send a netlink notification using 'skb' * and "n". * * On success, destroy old qdisc. */ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, struct sk_buff *skb, struct nlmsghdr *n, u32 classid, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct Qdisc *q = old; struct net *net = dev_net(dev); if (parent == NULL) { unsigned int i, num_q, ingress; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { num_q = 1; ingress = 1; if (!dev_ingress_queue(dev)) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; } } if (dev->flags & IFF_UP) dev_deactivate(dev); qdisc_offload_graft_root(dev, new, old, extack); if (new && new->ops->attach) goto skip; for (i = 0; i < num_q; i++) { struct netdev_queue *dev_queue = dev_ingress_queue(dev); if (!ingress) dev_queue = netdev_get_tx_queue(dev, i); old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) qdisc_refcount_inc(new); if (!ingress) qdisc_put(old); } skip: if (!ingress) { notify_and_destroy(net, skb, n, classid, rtnl_dereference(dev->qdisc), new); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); if (new && new->ops->attach) new->ops->attach(new); } else { notify_and_destroy(net, skb, n, classid, old, new); } if (dev->flags & IFF_UP) dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; unsigned long cl; int err; /* Only support running class lockless if parent is lockless */ if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK)) qdisc_clear_nolock(new); if (!cops || !cops->graft) return -EOPNOTSUPP; cl = cops->find(parent, classid); if (!cl) { NL_SET_ERR_MSG(extack, "Specified class not found"); return -ENOENT; } err = cops->graft(parent, cl, new, &old, extack); if (err) return err; notify_and_destroy(net, skb, n, classid, old, new); } return 0; } static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { u32 block_index; if (tca[TCA_INGRESS_BLOCK]) { block_index = nla_get_u32(tca[TCA_INGRESS_BLOCK]); if (!block_index) { NL_SET_ERR_MSG(extack, "Ingress block index cannot be 0"); return -EINVAL; } if (!sch->ops->ingress_block_set) { NL_SET_ERR_MSG(extack, "Ingress block sharing is not supported"); return -EOPNOTSUPP; } sch->ops->ingress_block_set(sch, block_index); } if (tca[TCA_EGRESS_BLOCK]) { block_index = nla_get_u32(tca[TCA_EGRESS_BLOCK]); if (!block_index) { NL_SET_ERR_MSG(extack, "Egress block index cannot be 0"); return -EINVAL; } if (!sch->ops->egress_block_set) { NL_SET_ERR_MSG(extack, "Egress block sharing is not supported"); return -EOPNOTSUPP; } sch->ops->egress_block_set(sch, block_index); } return 0; } /* Allocate and initialize new qdisc. Parameters are passed via opt. */ static struct Qdisc *qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, struct Qdisc *p, u32 parent, u32 handle, struct nlattr **tca, int *errp, struct netlink_ext_ack *extack) { int err; struct nlattr *kind = tca[TCA_KIND]; struct Qdisc *sch; struct Qdisc_ops *ops; struct qdisc_size_table *stab; ops = qdisc_lookup_ops(kind); #ifdef CONFIG_MODULES if (ops == NULL && kind != NULL) { char name[IFNAMSIZ]; if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) { /* We dropped the RTNL semaphore in order to * perform the module load. So, even if we * succeeded in loading the module we have to * tell the caller to replay the request. We * indicate this using -EAGAIN. * We replay the request because the device may * go away in the mean time. */ rtnl_unlock(); request_module("sch_%s", name); rtnl_lock(); ops = qdisc_lookup_ops(kind); if (ops != NULL) { /* We will try again qdisc_lookup_ops, * so don't keep a reference. */ module_put(ops->owner); err = -EAGAIN; goto err_out; } } } #endif err = -ENOENT; if (!ops) { NL_SET_ERR_MSG(extack, "Specified qdisc kind is unknown"); goto err_out; } sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { err = PTR_ERR(sch); goto err_out2; } sch->parent = parent; if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); if (handle == 0) { NL_SET_ERR_MSG(extack, "Maximum number of qdisc handles was exceeded"); err = -ENOSPC; goto err_out3; } } if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; /* This exist to keep backward compatible with a userspace * loophole, what allowed userspace to get IFF_NO_QUEUE * facility on older kernels by setting tx_queue_len=0 (prior * to qdisc init), and then forgot to reinit tx_queue_len * before again attaching a qdisc. */ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) { dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } err = qdisc_block_indexes_set(sch, tca, extack); if (err) goto err_out3; if (ops->init) { err = ops->init(sch, tca[TCA_OPTIONS], extack); if (err != 0) goto err_out5; } if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { err = PTR_ERR(stab); goto err_out4; } rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { seqcount_t *running; err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); goto err_out4; } if (sch->parent != TC_H_ROOT && !(sch->flags & TCQ_F_INGRESS) && (!p || !(p->flags & TCQ_F_MQROOT))) running = qdisc_root_sleeping_running(sch); else running = &sch->running; err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, running, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); goto err_out4; } } qdisc_hash_add(sch, false); trace_qdisc_create(ops, dev, parent); return sch; err_out5: /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ if (ops->destroy) ops->destroy(sch); err_out3: dev_put(dev); qdisc_free(sch); err_out2: module_put(ops->owner); err_out: *errp = err; return NULL; err_out4: /* * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. */ qdisc_put_stab(rtnl_dereference(sch->stab)); if (ops->destroy) ops->destroy(sch); goto err_out3; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { if (!sch->ops->change) { NL_SET_ERR_MSG(extack, "Change operation not supported by specified qdisc"); return -EINVAL; } if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); return -EOPNOTSUPP; } err = sch->ops->change(sch, tca[TCA_OPTIONS], extack); if (err) return err; } if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) return PTR_ERR(stab); } ostab = rtnl_dereference(sch->stab); rcu_assign_pointer(sch->stab, stab); qdisc_put_stab(ostab); if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator because change can't be undone. */ if (sch->flags & TCQ_F_MQROOT) goto out; gen_replace_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, qdisc_root_sleeping_running(sch), tca[TCA_RATE]); } out: return 0; } struct check_loop_arg { struct qdisc_walker w; struct Qdisc *p; int depth; }; static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w); static int check_loop(struct Qdisc *q, struct Qdisc *p, int depth) { struct check_loop_arg arg; if (q->ops->cl_ops == NULL) return 0; arg.w.stop = arg.w.skip = arg.w.count = 0; arg.w.fn = check_loop_fn; arg.depth = depth; arg.p = p; q->ops->cl_ops->walk(q, &arg.w); return arg.w.stop ? -ELOOP : 0; } static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) { struct Qdisc *leaf; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct check_loop_arg *arg = (struct check_loop_arg *)w; leaf = cops->leaf(q, cl); if (leaf) { if (leaf == arg->p || arg->depth > 7) return -ELOOP; return check_loop(leaf, arg->p, arg->depth + 1); } return 0; } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, [TCA_DUMP_INVISIBLE] = { .type = NLA_FLAG }, [TCA_CHAIN] = { .type = NLA_U32 }, [TCA_INGRESS_BLOCK] = { .type = NLA_U32 }, [TCA_EGRESS_BLOCK] = { .type = NLA_U32 }, }; /* * Delete/get qdisc. */ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; u32 clid; struct Qdisc *q = NULL; struct Qdisc *p = NULL; int err; if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; clid = tcm->tcm_parent; if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); if (!p) { NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = rtnl_dereference(dev->qdisc); } if (!q) { NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; } } else { q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) { NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified handle"); return -ENOENT; } } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } if (n->nlmsg_type == RTM_DELQDISC) { if (!clid) { NL_SET_ERR_MSG(extack, "Classid cannot be zero"); return -EINVAL; } if (q->handle == 0) { NL_SET_ERR_MSG(extack, "Cannot delete qdisc with handle of zero"); return -ENOENT; } err = qdisc_graft(dev, p, skb, n, clid, NULL, q, extack); if (err != 0) return err; } else { qdisc_notify(net, skb, n, clid, NULL, q); } return 0; } /* * Create/change qdisc. */ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm; struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; u32 clid; struct Qdisc *q, *p; int err; if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; replay: /* Reinit, just in case something touches this. */ err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; tcm = nlmsg_data(n); clid = tcm->tcm_parent; q = p = NULL; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); if (!p) { NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue_create(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = rtnl_dereference(dev->qdisc); } /* It may be default qdisc, ignore it */ if (q && q->handle == 0) q = NULL; if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "NLM_F_REPLACE needed to override"); return -EEXIST; } if (TC_H_MIN(tcm->tcm_handle)) { NL_SET_ERR_MSG(extack, "Invalid minor handle"); return -EINVAL; } q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } qdisc_refcount_inc(q); goto graft; } else { if (!q) goto create_n_graft; /* This magic test requires explanation. * * We know, that some child q is already * attached to this parent and have choice: * either to change it or to create/graft new one. * * 1. We are allowed to create/graft only * if CREATE and REPLACE flags are set. * * 2. If EXCL is set, requestor wanted to say, * that qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. * For now we select create/graft, if * user gave KIND, which does not match existing. */ if ((n->nlmsg_flags & NLM_F_CREATE) && (n->nlmsg_flags & NLM_F_REPLACE) && ((n->nlmsg_flags & NLM_F_EXCL) || (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)))) goto create_n_graft; } } } else { if (!tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Handle cannot be zero"); return -EINVAL; } q = qdisc_lookup(dev, tcm->tcm_handle); } /* Change qdisc parameters */ if (!q) { NL_SET_ERR_MSG(extack, "Specified qdisc not found"); return -ENOENT; } if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot modify"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } err = qdisc_change(q, tca, extack); if (err == 0) qdisc_notify(net, skb, n, clid, NULL, q); return err; create_n_graft: if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), p, tcm->tcm_parent, tcm->tcm_parent, tca, &err, extack); } else { NL_SET_ERR_MSG(extack, "Cannot find ingress queue for specified device"); err = -ENOENT; } } else { struct netdev_queue *dev_queue; if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) dev_queue = p->ops->cl_ops->select_queue(p, tcm); else if (p) dev_queue = p->dev_queue; else dev_queue = netdev_get_tx_queue(dev, 0); q = qdisc_create(dev, dev_queue, p, tcm->tcm_parent, tcm->tcm_handle, tca, &err, extack); } if (q == NULL) { if (err == -EAGAIN) goto replay; return err; } graft: err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) qdisc_put(q); return err; } return 0; } static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, int *q_idx_p, int s_q_idx, bool recur, bool dump_invisible) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; int b; if (!root) return 0; q = root; if (q_idx < s_q_idx) { q_idx++; } else { if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; q_idx++; } /* If dumping singletons, there is no qdisc_dev(root) and the singleton * itself has already been dumped. * * If we've already dumped the top-level (ingress) qdisc above and the global * qdisc hashtable, we don't want to hit it again */ if (!qdisc_dev(root) || !recur) goto out; hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (q_idx < s_q_idx) { q_idx++; continue; } if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; q_idx++; } out: *q_idx_p = q_idx; return ret; done: ret = -1; goto out; } static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; struct nlattr *tca[TCA_MAX + 1]; int err; s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; idx = 0; ASSERT_RTNL(); err = nlmsg_parse_deprecated(nlh, sizeof(struct tcmsg), tca, TCA_MAX, rtm_tca_policy, cb->extack); if (err < 0) return err; for_each_netdev(net, dev) { struct netdev_queue *dev_queue; if (idx < s_idx) goto cont; if (idx > s_idx) s_q_idx = 0; q_idx = 0; if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), skb, cb, &q_idx, s_q_idx, true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx, false, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; cont: idx++; } done: cb->args[0] = idx; cb->args[1] = q_idx; return skb->len; } /************************************************ * Traffic classes manipulation. * ************************************************/ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, unsigned long cl, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = q->handle; tcm->tcm_handle = q->handle; tcm->tcm_info = 0; if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0) goto nla_put_failure; if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; } static int tclass_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, int event) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; int err = 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) { kfree_skb(skb); return -EINVAL; } err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) err = 0; return err; } static int tclass_del_notify(struct net *net, const struct Qdisc_class_ops *cops, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct sk_buff *skb; int err = 0; if (!cops->delete) return -EOPNOTSUPP; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_DELTCLASS) < 0) { kfree_skb(skb); return -EINVAL; } err = cops->delete(q, cl); if (err) { kfree_skb(skb); return err; } err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) err = 0; return err; } #ifdef CONFIG_NET_CLS struct tcf_bind_args { struct tcf_walker w; unsigned long base; unsigned long cl; u32 classid; }; static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) { struct tcf_bind_args *a = (void *)arg; if (tp->ops->bind_class) { struct Qdisc *q = tcf_block_q(tp->chain->block); sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl, q, a->base); sch_tree_unlock(q); } return 0; } struct tc_bind_class_args { struct qdisc_walker w; unsigned long new_cl; u32 portid; u32 clid; }; static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) { struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tcf_block *block; struct tcf_chain *chain; block = cops->tcf_block(q, cl, NULL); if (!block) return 0; for (chain = tcf_get_next_chain(block, NULL); chain; chain = tcf_get_next_chain(block, chain)) { struct tcf_proto *tp; for (tp = tcf_get_next_proto(chain, NULL, true); tp; tp = tcf_get_next_proto(chain, tp, true)) { struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; arg.classid = a->clid; arg.base = cl; arg.cl = a->new_cl; tp->ops->walk(tp, &arg.w, true); } } return 0; } static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tc_bind_class_args args = {}; if (!cops->tcf_block) return; args.portid = portid; args.clid = clid; args.new_cl = new_cl; args.w.fn = tc_bind_class_walker; q->ops->cl_ops->walk(q, &args.w); } #else static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { } #endif static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct Qdisc *q = NULL; const struct Qdisc_class_ops *cops; unsigned long cl = 0; unsigned long new_cl; u32 portid; u32 clid; u32 qid; int err; if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; /* parent == TC_H_UNSPEC - unspecified parent. parent == TC_H_ROOT - class is root, which has no parent. parent == X:0 - parent is root class. parent == X:Y - parent is a node in hierarchy. parent == 0:Y - parent is X:Y, where X:0 is qdisc. handle == 0:0 - generate handle from kernel pool. handle == 0:Y - class is X:Y, where X:0 is qdisc. handle == X:Y - clear. handle == X:0 - root class. */ /* Step 1. Determine qdisc handle X:0 */ portid = tcm->tcm_parent; clid = tcm->tcm_handle; qid = TC_H_MAJ(clid); if (portid != TC_H_ROOT) { u32 qid1 = TC_H_MAJ(portid); if (qid && qid1) { /* If both majors are known, they must be identical. */ if (qid != qid1) return -EINVAL; } else if (qid1) { qid = qid1; } else if (qid == 0) qid = rtnl_dereference(dev->qdisc)->handle; /* Now qid is genuine qdisc handle consistent * both with parent and child. * * TC_H_MAJ(portid) still may be unspecified, complete it now. */ if (portid) portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) qid = rtnl_dereference(dev->qdisc)->handle; } /* OK. Locate qdisc */ q = qdisc_lookup(dev, qid); if (!q) return -ENOENT; /* An check that it supports classes */ cops = q->ops->cl_ops; if (cops == NULL) return -EINVAL; /* Now try to get class */ if (clid == 0) { if (portid == TC_H_ROOT) clid = qid; } else clid = TC_H_MAKE(qid, clid); if (clid) cl = cops->find(q, clid); if (cl == 0) { err = -ENOENT; if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags & NLM_F_CREATE)) goto out; } else { switch (n->nlmsg_type) { case RTM_NEWTCLASS: err = -EEXIST; if (n->nlmsg_flags & NLM_F_EXCL) goto out; break; case RTM_DELTCLASS: err = tclass_del_notify(net, cops, skb, n, q, cl); /* Unbind the class with flilters with 0 */ tc_bind_tclass(q, portid, clid, 0); goto out; case RTM_GETTCLASS: err = tclass_notify(net, skb, n, q, cl, RTM_NEWTCLASS); goto out; default: err = -EINVAL; goto out; } } if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { NL_SET_ERR_MSG(extack, "Shared blocks are not supported for classes"); return -EOPNOTSUPP; } new_cl = cl; err = -EOPNOTSUPP; if (cops->change) err = cops->change(q, clid, portid, tca, &new_cl, extack); if (err == 0) { tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS); /* We just create a new class, need to do reverse binding. */ if (cl != new_cl) tc_bind_tclass(q, portid, clid, new_cl); } out: return err; } struct qdisc_dump_args { struct qdisc_walker w; struct sk_buff *skb; struct netlink_callback *cb; }; static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) { struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg; return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, int *t_p, int s_t) { struct qdisc_dump_args arg; if (tc_qdisc_dump_ignore(q, false) || *t_p < s_t || !q->ops->cl_ops || (tcm->tcm_parent && TC_H_MAJ(tcm->tcm_parent) != q->handle)) { (*t_p)++; return 0; } if (*t_p > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); arg.w.fn = qdisc_class_dump; arg.skb = skb; arg.cb = cb; arg.w.stop = 0; arg.w.skip = cb->args[1]; arg.w.count = 0; q->ops->cl_ops->walk(q, &arg.w); cb->args[1] = arg.w.count; if (arg.w.stop) return -1; (*t_p)++; return 0; } static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; if (!root) return 0; if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent)); if (q && q != root && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; return 0; } hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; } return 0; } static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { struct tcmsg *tcm = nlmsg_data(cb->nlh); struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; struct net_device *dev; int t, s_t; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return 0; dev = dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return 0; s_t = cb->args[0]; t = 0; if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t, false) < 0) goto done; done: cb->args[0] = t; dev_put(dev); return skb->len; } #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { seq_printf(seq, "%08x %08x %08x %08x\n", (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1), 1000000, (u32)NSEC_PER_SEC / hrtimer_resolution); return 0; } static int __net_init psched_net_init(struct net *net) { struct proc_dir_entry *e; e = proc_create_single("psched", 0, net->proc_net, psched_show); if (e == NULL) return -ENOMEM; return 0; } static void __net_exit psched_net_exit(struct net *net) { remove_proc_entry("psched", net->proc_net); } #else static int __net_init psched_net_init(struct net *net) { return 0; } static void __net_exit psched_net_exit(struct net *net) { } #endif static struct pernet_operations psched_net_ops = { .init = psched_net_init, .exit = psched_net_exit, }; static int __init pktsched_init(void) { int err; err = register_pernet_subsys(&psched_net_ops); if (err) { pr_err("pktsched_init: " "cannot initialize per netns operations\n"); return err; } register_qdisc(&pfifo_fast_ops); register_qdisc(&pfifo_qdisc_ops); register_qdisc(&bfifo_qdisc_ops); register_qdisc(&pfifo_head_drop_qdisc_ops); register_qdisc(&mq_qdisc_ops); register_qdisc(&noqueue_qdisc_ops); rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, 0); rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, 0); return 0; } subsys_initcall(pktsched_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAPOPS_H #define _LINUX_SWAPOPS_H #include <linux/radix-tree.h> #include <linux/bug.h> #include <linux/mm_types.h> #ifdef CONFIG_MMU /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in * the low-order bits. * * We arrange the `type' and `offset' fields so that `type' is at the seven * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) pte = pte_swp_clear_uffd_wp(pte); return pte; } /* * Store a type+offset into a swp_entry_t in an arch-independent format */ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } /* * Extract the `type' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline unsigned swp_type(swp_entry_t entry) { return (entry.val >> SWP_TYPE_SHIFT); } /* * Extract the `offset' field from a swp_entry_t. The swp_entry_t is in * arch-independent format */ static inline pgoff_t swp_offset(swp_entry_t entry) { return entry.val & SWP_OFFSET_MASK; } /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { return !pte_none(pte) && !pte_present(pte); } /* * Convert the arch-dependent pte representation of a swp_entry_t into an * arch-independent swp_entry_t. */ static inline swp_entry_t pte_to_swp_entry(pte_t pte) { swp_entry_t arch_entry; pte = pte_swp_clear_flags(pte); arch_entry = __pte_to_swp_entry(pte); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } /* * Convert the arch-independent representation of a swp_entry_t into the * arch-dependent pte representation. */ static inline pte_t swp_entry_to_pte(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pte(arch_entry); } static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, page_to_pfn(page)); } static inline bool is_device_private_entry(swp_entry_t entry) { int type = swp_type(entry); return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } static inline void make_device_private_entry_read(swp_entry_t *entry) { *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); } static inline bool is_write_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) { return swp_offset(entry); } static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return pfn_to_page(swp_offset(entry)); } #else /* CONFIG_DEVICE_PRIVATE */ static inline swp_entry_t make_device_private_entry(struct page *page, bool write) { return swp_entry(0, 0); } static inline void make_device_private_entry_read(swp_entry_t *entry) { } static inline bool is_device_private_entry(swp_entry_t entry) { return false; } static inline bool is_write_device_private_entry(swp_entry_t entry) { return false; } static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) { return 0; } static inline struct page *device_private_entry_to_page(swp_entry_t entry) { return NULL; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { BUG_ON(!PageLocked(compound_head(page))); return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, page_to_pfn(page)); } static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_WRITE); } static inline int is_write_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) { return swp_offset(entry); } static inline struct page *migration_entry_to_page(swp_entry_t entry) { struct page *p = pfn_to_page(swp_offset(entry)); /* * Any use of migration entries may only occur while the * corresponding page is locked */ BUG_ON(!PageLocked(compound_head(p))); return p; } static inline void make_migration_entry_read(swp_entry_t *entry) { *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); } extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte); #else #define make_migration_entry(page, write) swp_entry(0, 0) static inline int is_migration_entry(swp_entry_t swp) { return 0; } static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) { return 0; } static inline struct page *migration_entry_to_page(swp_entry_t entry) { return NULL; } static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte) { } static inline int is_write_migration_entry(swp_entry_t entry) { return 0; } #endif struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new); extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); if (pmd_swp_uffd_wp(pmd)) pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { swp_entry_t arch_entry; arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); return __swp_entry_to_pmd(arch_entry); } static inline int is_pmd_migration_entry(pmd_t pmd) { return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } #else static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); } static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { BUILD_BUG(); } static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { return swp_entry(0, 0); } static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) { return __pmd(0); } static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } #endif #ifdef CONFIG_MEMORY_FAILURE extern atomic_long_t num_poisoned_pages __read_mostly; /* * Support for hardware poisoned pages */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { BUG_ON(!PageLocked(page)); return swp_entry(SWP_HWPOISON, page_to_pfn(page)); } static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); } static inline void num_poisoned_pages_dec(void) { atomic_long_dec(&num_poisoned_pages); } #else static inline swp_entry_t make_hwpoison_entry(struct page *page) { return swp_entry(0, 0); } static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } static inline void num_poisoned_pages_inc(void) { } #endif #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ defined(CONFIG_DEVICE_PRIVATE) static inline int non_swap_entry(swp_entry_t entry) { return swp_type(entry) >= MAX_SWAPFILES; } #else static inline int non_swap_entry(swp_entry_t entry) { return 0; } #endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |
| 66 67 67 67 67 67 67 60 60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu-vm.c - vmalloc area based chunk allocation * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { /* must not be used on pre-mapped chunk */ WARN_ON(chunk->immutable); return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /** * pcpu_get_pages - get temp pages array * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses * should be serialized by pcpu_alloc_mutex. * * RETURNS: * Pointer to temp pages array on success. */ static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } /** * pcpu_free_pages - free pages which were allocated for @chunk * @chunk: chunk pages were allocated for * @pages: array of pages to be freed, indexed by pcpu_page_idx() * @page_start: page index of the first page to be freed * @page_end: page index of the last page to be freed + 1 * * Free pages [@page_start and @page_end) in @pages for all units. * The pages were allocated for @chunk. */ static void pcpu_free_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page = pages[pcpu_page_idx(cpu, i)]; if (page) __free_page(page); } } } /** * pcpu_alloc_pages - allocates pages for @chunk * @chunk: target chunk * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end, gfp_t gfp) { unsigned int cpu, tcpu; int i; gfp |= __GFP_HIGHMEM; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); if (!*pagep) goto err; } } return 0; err: while (--i >= page_start) __free_page(pages[pcpu_page_idx(cpu, i)]); for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; for (i = page_start; i < page_end; i++) __free_page(pages[pcpu_page_idx(tcpu, i)]); } return -ENOMEM; } /** * pcpu_pre_unmap_flush - flush cache prior to unmapping * @chunk: chunk the regions to be flushed belongs to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages in [@page_start,@page_end) of @chunk are about to be * unmapped. Flush cache. As each flushing trial can be very * expensive, issue flush on the whole region at once rather than * doing it for each cpu. This could be an overkill but is more * scalable. */ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vunmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT); } /** * pcpu_unmap_pages - unmap pages out of a pcpu_chunk * @chunk: chunk of interest * @pages: pages array which can be used to pass information to free * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * Corresponding elements in @pages were cleared by the caller and can * be used to carry information to pcpu_free_pages() which will be * called after all unmaps are finished. The caller should call * proper pre/post flush functions. */ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page; page = pcpu_chunk_page(chunk, cpu, i); WARN_ON(!page); pages[pcpu_page_idx(cpu, i)] = page; } __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), page_end - page_start); } } /** * pcpu_post_unmap_tlb_flush - flush TLB after unmapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush * TLB for the regions. This can be skipped if the area is to be * returned to vmalloc as vmalloc will handle TLB flushing lazily. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_tlb_kernel_range( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static int __pcpu_map_pages(unsigned long addr, struct page **pages, int nr_pages) { return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT, PAGE_KERNEL, pages); } /** * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest * @pages: pages array containing pages to be mapped * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * * For each cpu, map pages [@page_start,@page_end) into @chunk. The * caller is responsible for calling pcpu_post_map_flush() after all * mappings are complete. * * This function is responsible for setting up whatever is necessary for * reverse lookup (addr -> chunk). */ static int pcpu_map_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu, tcpu; int i, err; for_each_possible_cpu(cpu) { err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), &pages[pcpu_page_idx(cpu, page_start)], page_end - page_start); if (err < 0) goto err; for (i = page_start; i < page_end; i++) pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], chunk); } return 0; err: for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } /** * pcpu_post_map_flush - flush cache after mapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been mapped. Flush * cache. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } /** * pcpu_populate_chunk - populate and map an area of a pcpu_chunk * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. * * CONTEXT: * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp) { struct page **pages; pages = pcpu_get_pages(); if (!pages) return -ENOMEM; if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { pcpu_free_pages(chunk, pages, page_start, page_end); return -ENOMEM; } pcpu_post_map_flush(chunk, page_start, page_end); return 0; } /** * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk * @chunk: chunk to depopulate * @page_start: the start page * @page_end: the end page * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. * * CONTEXT: * pcpu_alloc_mutex. */ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end) { struct page **pages; /* * If control reaches here, there must have been at least one * successful population attempt so the temp pages array must * be available now. */ pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ pcpu_pre_unmap_flush(chunk, page_start, page_end); pcpu_unmap_pages(chunk, pages, page_start, page_end); /* no need to flush tlb, vmalloc will handle it lazily */ pcpu_free_pages(chunk, pages, page_start, page_end); } static struct pcpu_chunk *pcpu_create_chunk(enum pcpu_chunk_type type, gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; chunk = pcpu_alloc_chunk(type, gfp); if (!chunk) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; } chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(chunk->base_addr); return chunk; } static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; pcpu_stats_chunk_dealloc(); trace_percpu_destroy_chunk(chunk->base_addr); if (chunk->data) pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } static struct page *pcpu_addr_to_page(void *addr) { return vmalloc_to_page(addr); } static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) { /* no extra restriction */ return 0; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" struct debug_req_info { struct ethnl_req_info base; }; struct debug_reply_data { struct ethnl_reply_data base; u32 msg_mask; }; #define DEBUG_REPDATA(__reply_base) \ container_of(__reply_base, struct debug_reply_data, base) const struct nla_policy ethnl_debug_get_policy[] = { [ETHTOOL_A_DEBUG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int debug_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) { struct debug_reply_data *data = DEBUG_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_msglevel) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->msg_mask = dev->ethtool_ops->get_msglevel(dev); ethnl_ops_complete(dev); return 0; } static int debug_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct debug_reply_data *data = DEBUG_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; return ethnl_bitset32_size(&data->msg_mask, NULL, NETIF_MSG_CLASS_COUNT, netif_msg_class_names, compact); } static int debug_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct debug_reply_data *data = DEBUG_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; return ethnl_put_bitset32(skb, ETHTOOL_A_DEBUG_MSGMASK, &data->msg_mask, NULL, NETIF_MSG_CLASS_COUNT, netif_msg_class_names, compact); } const struct ethnl_request_ops ethnl_debug_request_ops = { .request_cmd = ETHTOOL_MSG_DEBUG_GET, .reply_cmd = ETHTOOL_MSG_DEBUG_GET_REPLY, .hdr_attr = ETHTOOL_A_DEBUG_HEADER, .req_info_size = sizeof(struct debug_req_info), .reply_data_size = sizeof(struct debug_reply_data), .prepare_data = debug_prepare_data, .reply_size = debug_reply_size, .fill_reply = debug_fill_reply, }; /* DEBUG_SET */ const struct nla_policy ethnl_debug_set_policy[] = { [ETHTOOL_A_DEBUG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_DEBUG_MSGMASK] = { .type = NLA_NESTED }, }; int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info) { struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; u32 msg_mask; int ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_DEBUG_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_msglevel || !dev->ethtool_ops->set_msglevel) goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; msg_mask = dev->ethtool_ops->get_msglevel(dev); ret = ethnl_update_bitset32(&msg_mask, NETIF_MSG_CLASS_COUNT, tb[ETHTOOL_A_DEBUG_MSGMASK], netif_msg_class_names, info->extack, &mod); if (ret < 0 || !mod) goto out_ops; dev->ethtool_ops->set_msglevel(dev, msg_mask); ethtool_notify(dev, ETHTOOL_MSG_DEBUG_NTF, NULL); out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); out_dev: dev_put(dev); return ret; } |
| 220 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* include/asm-generic/tlb.h * * Generic TLB shootdown code * * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * * Copyright 2011 Red Hat, Inc., Peter Zijlstra */ #ifndef _ASM_GENERIC__TLB_H #define _ASM_GENERIC__TLB_H #include <linux/mmu_notifier.h> #include <linux/swap.h> #include <linux/hugetlb_inline.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> /* * Blindly accessing user memory from NMI context can be dangerous * if we're in the middle of switching the current user task or switching * the loaded mm. */ #ifndef nmi_uaccess_okay # define nmi_uaccess_okay() true #endif #ifdef CONFIG_MMU /* * Generic MMU-gather implementation. * * The mmu_gather data structure is used by the mm code to implement the * correct and efficient ordering of freeing pages and TLB invalidations. * * This correct ordering is: * * 1) unhook page * 2) TLB invalidate page * 3) free page * * That is, we must never free a page before we have ensured there are no live * translations left to it. Otherwise it might be possible to observe (or * worse, change) the page content after it has been reused. * * The mmu_gather API consists of: * * - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather * * Finish in particular will issue a (final) TLB invalidate and free * all (remaining) queued pages. * * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA * * Defaults to flushing at tlb_end_vma() to reset the range; helps when * there's large holes between the VMAs. * * - tlb_remove_table() * * tlb_remove_table() is the basic primitive to free page-table directories * (__p*_free_tlb()). In it's most primitive form it is an alias for * tlb_remove_page() below, for when page directories are pages and have no * additional constraints. * * See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE. * * - tlb_remove_page() / __tlb_remove_page() * - tlb_remove_page_size() / __tlb_remove_page_size() * * __tlb_remove_page_size() is the basic primitive that queues a page for * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a * boolean indicating if the queue is (now) full and a call to * tlb_flush_mmu() is required. * * tlb_remove_page() and tlb_remove_page_size() imply the call to * tlb_flush_mmu() when required and has no return value. * * - tlb_change_page_size() * * call before __tlb_remove_page*() to set the current page-size; implies a * possible tlb_flush_mmu() call. * * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() * * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets * related state, like the range) * * tlb_flush_mmu() - in addition to the above TLB invalidate, also frees * whatever pages are still batched. * * - mmu_gather::fullmm * * A flag set by tlb_gather_mmu() to indicate we're going to free * the entire mm; this allows a number of optimizations. * * - We can ignore tlb_{start,end}_vma(); because we don't * care about ranges. Everything will be shot down. * * - (RISC) architectures that use ASIDs can cycle to a new ASID * and delay the invalidation until ASID space runs out. * * - mmu_gather::need_flush_all * * A flag that can be set by the arch code if it wants to force * flush the entire TLB irrespective of the range. For instance * x86-PAE needs this when changing top-level entries. * * And allows the architecture to provide and implement tlb_flush(): * * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make * use of: * * - mmu_gather::start / mmu_gather::end * * which provides the range that needs to be flushed to cover the pages to * be freed. * * - mmu_gather::freed_tables * * set when we freed page table pages * * - tlb_get_unmap_shift() / tlb_get_unmap_size() * * returns the smallest TLB entry size unmapped in this range. * * If an architecture does not provide tlb_flush() a default implementation * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is * specified, in which case we'll default to flush_tlb_mm(). * * Additionally there are a few opt-in features: * * MMU_GATHER_PAGE_SIZE * * This ensures we call tlb_flush() every time tlb_change_page_size() actually * changes the size and provides mmu_gather::page_size to tlb_flush(). * * This might be useful if your architecture has size specific TLB * invalidation instructions. * * MMU_GATHER_TABLE_FREE * * This provides tlb_remove_table(), to be used instead of tlb_remove_page() * for page directores (__p*_free_tlb()). * * Useful if your architecture has non-page page directories. * * When used, an architecture is expected to provide __tlb_remove_table() * which does the actual freeing of these pages. * * MMU_GATHER_RCU_TABLE_FREE * * Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see * comment below). * * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * * MMU_GATHER_NO_RANGE * * Use this if your architecture lacks an efficient flush_tlb_range(). * * MMU_GATHER_NO_GATHER * * If the option is set the mmu_gather will not track individual pages for * delayed page free anymore. A platform that enables the option needs to * provide its own implementation of the __tlb_remove_page_size() function to * free pages. * * This is useful if your architecture already flushes TLB entries in the * various ptep_get_and_clear() functions. */ #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch { #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE struct rcu_head rcu; #endif unsigned int nr; void *tables[0]; }; #define MAX_TABLE_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *)) extern void tlb_remove_table(struct mmu_gather *tlb, void *table); #else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */ /* * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based * page directories and we can use the normal page batching to free them. */ #define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page)) #endif /* CONFIG_MMU_GATHER_TABLE_FREE */ #ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE /* * This allows an architecture that does not use the linux page-tables for * hardware to skip the TLBI when freeing page tables. */ #ifndef tlb_needs_table_invalidate #define tlb_needs_table_invalidate() (true) #endif #else #ifdef tlb_needs_table_invalidate #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE #endif #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */ #ifndef CONFIG_MMU_GATHER_NO_GATHER /* * If we can't allocate a page to make a big batch of page pointers * to work on, then just handle a few from the on-stack structure. */ #define MMU_GATHER_BUNDLE 8 struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; struct page *pages[0]; }; #define MAX_GATHER_BATCH \ ((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *)) /* * Limit the maximum number of mmu_gather batches to reduce a risk of soft * lockups for non-preemptible kernels on huge machines when a lot of memory * is zapped during unmapping. * 10K pages freed at once should be safe even without a preemption point. */ #define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH) extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); #endif /* * struct mmu_gather is an opaque type used by the mm code for passing around * any data needed by arch specific code for tlb_remove_page. */ struct mmu_gather { struct mm_struct *mm; #ifdef CONFIG_MMU_GATHER_TABLE_FREE struct mmu_table_batch *batch; #endif unsigned long start; unsigned long end; /* * we are in the middle of an operation to clear * a full mm and can make some optimizations */ unsigned int fullmm : 1; /* * we have performed an operation which * requires a complete flush of the tlb */ unsigned int need_flush_all : 1; /* * we have removed page directories */ unsigned int freed_tables : 1; /* * at which levels have we cleared entries? */ unsigned int cleared_ptes : 1; unsigned int cleared_pmds : 1; unsigned int cleared_puds : 1; unsigned int cleared_p4ds : 1; /* * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; unsigned int batch_count; #ifndef CONFIG_MMU_GATHER_NO_GATHER struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; #ifdef CONFIG_MMU_GATHER_PAGE_SIZE unsigned int page_size; #endif #endif }; void tlb_flush_mmu(struct mmu_gather *tlb); static inline void __tlb_adjust_range(struct mmu_gather *tlb, unsigned long address, unsigned int range_size) { tlb->start = min(tlb->start, address); tlb->end = max(tlb->end, address + range_size); } static inline void __tlb_reset_range(struct mmu_gather *tlb) { if (tlb->fullmm) { tlb->start = tlb->end = ~0; } else { tlb->start = TASK_SIZE; tlb->end = 0; } tlb->freed_tables = 0; tlb->cleared_ptes = 0; tlb->cleared_pmds = 0; tlb->cleared_puds = 0; tlb->cleared_p4ds = 0; /* * Do not reset mmu_gather::vma_* fields here, we do not * call into tlb_start_vma() again to set them if there is an * intermediate flush. */ } #ifdef CONFIG_MMU_GATHER_NO_RANGE #if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma) #error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma() #endif /* * When an architecture does not have efficient means of range flushing TLBs * there is no point in doing intermediate flushes on tlb_end_vma() to keep the * range small. We equally don't have to worry about page granularity or other * things. * * All we need to do is issue a full flush for any !0 range. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->end) flush_tlb_mm(tlb->mm); } static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #define tlb_end_vma tlb_end_vma static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush #if defined(tlb_start_vma) || defined(tlb_end_vma) #error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() #endif /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation * use that. */ static inline void tlb_flush(struct mmu_gather *tlb) { if (tlb->fullmm || tlb->need_flush_all) { flush_tlb_mm(tlb->mm); } else if (tlb->end) { struct vm_area_struct vma = { .vm_mm = tlb->mm, .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) | (tlb->vma_huge ? VM_HUGETLB : 0), }; flush_tlb_range(&vma, tlb->start, tlb->end); } } static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * flush_tlb_range() implementations that look at VM_HUGETLB (tile, * mips-4k) flush only large pages. * * flush_tlb_range() implementations that flush I-TLB also flush D-TLB * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing * range. * * We rely on tlb_end_vma() to issue a flush, such that when we reset * these values the batch is empty. */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); } #else static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } #endif #endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* * Anything calling __tlb_adjust_range() also sets at least one of * these bits. */ if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds || tlb->cleared_puds || tlb->cleared_p4ds)) return; tlb_flush(tlb); mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end); __tlb_reset_range(tlb); } static inline void tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) { if (__tlb_remove_page_size(tlb, page, page_size)) tlb_flush_mmu(tlb); } static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page_size(tlb, page, PAGE_SIZE); } /* tlb_remove_page * Similar to __tlb_remove_page but will call tlb_flush_mmu() itself when * required. */ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { return tlb_remove_page_size(tlb, page, PAGE_SIZE); } static inline void tlb_change_page_size(struct mmu_gather *tlb, unsigned int page_size) { #ifdef CONFIG_MMU_GATHER_PAGE_SIZE if (tlb->page_size && tlb->page_size != page_size) { if (!tlb->fullmm && !tlb->need_flush_all) tlb_flush_mmu(tlb); } tlb->page_size = page_size; #endif } static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) { if (tlb->cleared_ptes) return PAGE_SHIFT; if (tlb->cleared_pmds) return PMD_SHIFT; if (tlb->cleared_puds) return PUD_SHIFT; if (tlb->cleared_p4ds) return P4D_SHIFT; return PAGE_SHIFT; } static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) { return 1UL << tlb_get_unmap_shift(tlb); } /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ #ifndef tlb_start_vma static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); flush_cache_range(vma, vma->vm_start, vma->vm_end); } #endif #ifndef tlb_end_vma static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs, * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on * this. */ tlb_flush_mmu_tlbonly(tlb); } #endif /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, * and set corresponding cleared_*. */ static inline void tlb_flush_pte_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_ptes = 1; } static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_pmds = 1; } static inline void tlb_flush_pud_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_puds = 1; } static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, unsigned long address, unsigned long size) { __tlb_adjust_range(tlb, address, size); tlb->cleared_p4ds = 1; } #ifndef __tlb_remove_tlb_entry #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #endif /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * * Record the fact that pte's were really unmapped by updating the range, * so we can later optimise away the tlb invalidate. This helps when * userspace is unmapping already-unmapped pages, which happens quite a lot. */ #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ tlb_flush_pte_range(tlb, address, PAGE_SIZE); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ if (_sz >= P4D_SIZE) \ tlb_flush_p4d_range(tlb, address, _sz); \ else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ else if (_sz >= PMD_SIZE) \ tlb_flush_pmd_range(tlb, address, _sz); \ else \ tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** * tlb_remove_pmd_tlb_entry - remember a pmd mapping for later tlb invalidation * This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pmd_tlb_entry #define __tlb_remove_pmd_tlb_entry(tlb, pmdp, address) do {} while (0) #endif #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE); \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) /** * tlb_remove_pud_tlb_entry - remember a pud mapping for later tlb * invalidation. This is a nop so far, because only x86 needs it. */ #ifndef __tlb_remove_pud_tlb_entry #define __tlb_remove_pud_tlb_entry(tlb, pudp, address) do {} while (0) #endif #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE); \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) /* * For things like page tables caches (ie caching addresses "inside" the * page tables, like x86 does), for legacy reasons, flushing an * individual page had better flush the page table caches behind it. This * is definitely how x86 works, for example. And if you have an * architected non-legacy page table cache (which I'm not aware of * anybody actually doing), you're going to have some architecturally * explicit flushing for that, likely *separate* from a regular TLB entry * flush, and thus you'd need more than just some range expansion.. * * So if we ever find an architecture * that would want something that odd, I think it is up to that * architecture to do its own odd thing, not cause pain for others * http://lkml.kernel.org/r/CA+55aFzBggoXtNXQeng5d_mRoDnaMBE5Y+URs+PHR67nUpMtaw@mail.gmail.com * * For now w.r.t page table cache, mark the range_size as PAGE_SIZE */ #ifndef pte_free_tlb #define pte_free_tlb(tlb, ptep, address) \ do { \ tlb_flush_pmd_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif #ifndef pmd_free_tlb #define pmd_free_tlb(tlb, pmdp, address) \ do { \ tlb_flush_pud_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ tlb_flush_p4d_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ |
| 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM jbd2 #if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_JBD2_H #include <linux/jbd2.h> #include <linux/tracepoint.h> struct transaction_chp_stats_s; struct transaction_run_stats_s; TRACE_EVENT(jbd2_checkpoint, TP_PROTO(journal_t *journal, int result), TP_ARGS(journal, result), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, result ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->result = result; ), TP_printk("dev %d,%d result %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->result) ); DECLARE_EVENT_CLASS(jbd2_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), TP_printk("dev %d,%d transaction %d sync %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit) ); DEFINE_EVENT(jbd2_commit, jbd2_start_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_locking, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_flushing, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_logging, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_drop_transaction, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); TRACE_EVENT(jbd2_end_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) __field( int, head ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; __entry->head = journal->j_tail_sequence; ), TP_printk("dev %d,%d transaction %d sync %d head %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit, __entry->head) ); TRACE_EVENT(jbd2_submit_inode_data, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); DECLARE_EVENT_CLASS(jbd2_handle_start_class, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, requested_blocks) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->requested_blocks = requested_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u " "requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_start, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_restart, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); TRACE_EVENT(jbd2_handle_extend, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int buffer_credits, int requested_blocks), TP_ARGS(dev, tid, type, line_no, buffer_credits, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, buffer_credits ) __field( int, requested_blocks) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->buffer_credits = buffer_credits; __entry->requested_blocks = requested_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u " "buffer_credits %d requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->buffer_credits, __entry->requested_blocks) ); TRACE_EVENT(jbd2_handle_stats, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int interval, int sync, int requested_blocks, int dirtied_blocks), TP_ARGS(dev, tid, type, line_no, interval, sync, requested_blocks, dirtied_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, interval ) __field( int, sync ) __field( int, requested_blocks) __field( int, dirtied_blocks ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->interval = interval; __entry->sync = sync; __entry->requested_blocks = requested_blocks; __entry->dirtied_blocks = dirtied_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u interval %d " "sync %d requested_blocks %d dirtied_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->interval, __entry->sync, __entry->requested_blocks, __entry->dirtied_blocks) ); TRACE_EVENT(jbd2_run_stats, TP_PROTO(dev_t dev, unsigned long tid, struct transaction_run_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, wait ) __field( unsigned long, request_delay ) __field( unsigned long, running ) __field( unsigned long, locked ) __field( unsigned long, flushing ) __field( unsigned long, logging ) __field( __u32, handle_count ) __field( __u32, blocks ) __field( __u32, blocks_logged ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->wait = stats->rs_wait; __entry->request_delay = stats->rs_request_delay; __entry->running = stats->rs_running; __entry->locked = stats->rs_locked; __entry->flushing = stats->rs_flushing; __entry->logging = stats->rs_logging; __entry->handle_count = stats->rs_handle_count; __entry->blocks = stats->rs_blocks; __entry->blocks_logged = stats->rs_blocks_logged; ), TP_printk("dev %d,%d tid %lu wait %u request_delay %u running %u " "locked %u flushing %u logging %u handle_count %u " "blocks %u blocks_logged %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->wait), jiffies_to_msecs(__entry->request_delay), jiffies_to_msecs(__entry->running), jiffies_to_msecs(__entry->locked), jiffies_to_msecs(__entry->flushing), jiffies_to_msecs(__entry->logging), __entry->handle_count, __entry->blocks, __entry->blocks_logged) ); TRACE_EVENT(jbd2_checkpoint_stats, TP_PROTO(dev_t dev, unsigned long tid, struct transaction_chp_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, chp_time ) __field( __u32, forced_to_close ) __field( __u32, written ) __field( __u32, dropped ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->chp_time = stats->cs_chp_time; __entry->forced_to_close= stats->cs_forced_to_close; __entry->written = stats->cs_written; __entry->dropped = stats->cs_dropped; ), TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " "written %u dropped %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), __entry->forced_to_close, __entry->written, __entry->dropped) ); TRACE_EVENT(jbd2_update_log_tail, TP_PROTO(journal_t *journal, tid_t first_tid, unsigned long block_nr, unsigned long freed), TP_ARGS(journal, first_tid, block_nr, freed), TP_STRUCT__entry( __field( dev_t, dev ) __field( tid_t, tail_sequence ) __field( tid_t, first_tid ) __field(unsigned long, block_nr ) __field(unsigned long, freed ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->tail_sequence = journal->j_tail_sequence; __entry->first_tid = first_tid; __entry->block_nr = block_nr; __entry->freed = freed; ), TP_printk("dev %d,%d from %u to %u offset %lu freed %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tail_sequence, __entry->first_tid, __entry->block_nr, __entry->freed) ); TRACE_EVENT(jbd2_write_superblock, TP_PROTO(journal_t *journal, int write_op), TP_ARGS(journal, write_op), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, write_op ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->write_op = write_op; ), TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->write_op) ); TRACE_EVENT(jbd2_lock_buffer_stall, TP_PROTO(dev_t dev, unsigned long stall_ms), TP_ARGS(dev, stall_ms), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, stall_ms ) ), TP_fast_assign( __entry->dev = dev; __entry->stall_ms = stall_ms; ), TP_printk("dev %d,%d stall_ms %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->stall_ms) ); #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 819 372 447 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 | // SPDX-License-Identifier: GPL-2.0 #include <linux/sysctl.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/xfrm.h> static void __net_init __xfrm_sysctl_init(struct net *net) { net->xfrm.sysctl_aevent_etime = XFRM_AE_ETIME; net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE; net->xfrm.sysctl_larval_drop = 1; net->xfrm.sysctl_acq_expires = 30; } #ifdef CONFIG_SYSCTL static struct ctl_table xfrm_table[] = { { .procname = "xfrm_aevent_etime", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec }, { .procname = "xfrm_aevent_rseqth", .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec }, { .procname = "xfrm_larval_drop", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "xfrm_acq_expires", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, {} }; int __net_init xfrm_sysctl_init(struct net *net) { struct ctl_table *table; __xfrm_sysctl_init(net); table = kmemdup(xfrm_table, sizeof(xfrm_table), GFP_KERNEL); if (!table) goto out_kmemdup; table[0].data = &net->xfrm.sysctl_aevent_etime; table[1].data = &net->xfrm.sysctl_aevent_rseqth; table[2].data = &net->xfrm.sysctl_larval_drop; table[3].data = &net->xfrm.sysctl_acq_expires; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table[0].procname = NULL; net->xfrm.sysctl_hdr = register_net_sysctl(net, "net/core", table); if (!net->xfrm.sysctl_hdr) goto out_register; return 0; out_register: kfree(table); out_kmemdup: return -ENOMEM; } void __net_exit xfrm_sysctl_fini(struct net *net) { struct ctl_table *table; table = net->xfrm.sysctl_hdr->ctl_table_arg; unregister_net_sysctl_table(net->xfrm.sysctl_hdr); kfree(table); } #else int __net_init xfrm_sysctl_init(struct net *net) { __xfrm_sysctl_init(net); return 0; } #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Manage a process's keyrings * * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/user.h> #include <linux/keyctl.h> #include <linux/fs.h> #include <linux/err.h> #include <linux/mutex.h> #include <linux/security.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> #include <linux/init_task.h> #include <keys/request_key_auth-type.h> #include "internal.h" /* Session keyring create vs join semaphore */ static DEFINE_MUTEX(key_session_mutex); /* The root user's tracking struct */ struct key_user root_key_user = { .usage = REFCOUNT_INIT(3), .cons_lock = __MUTEX_INITIALIZER(root_key_user.cons_lock), .lock = __SPIN_LOCK_UNLOCKED(root_key_user.lock), .nkeys = ATOMIC_INIT(2), .nikeys = ATOMIC_INIT(2), .uid = GLOBAL_ROOT_UID, }; /* * Get or create a user register keyring. */ static struct key *get_user_register(struct user_namespace *user_ns) { struct key *reg_keyring = READ_ONCE(user_ns->user_keyring_register); if (reg_keyring) return reg_keyring; down_write(&user_ns->keyring_sem); /* Make sure there's a register keyring. It gets owned by the * user_namespace's owner. */ reg_keyring = user_ns->user_keyring_register; if (!reg_keyring) { reg_keyring = keyring_alloc(".user_reg", user_ns->owner, INVALID_GID, &init_cred, KEY_POS_WRITE | KEY_POS_SEARCH | KEY_USR_VIEW | KEY_USR_READ, 0, NULL, NULL); if (!IS_ERR(reg_keyring)) smp_store_release(&user_ns->user_keyring_register, reg_keyring); } up_write(&user_ns->keyring_sem); /* We don't return a ref since the keyring is pinned by the user_ns */ return reg_keyring; } /* * Look up the user and user session keyrings for the current process's UID, * creating them if they don't exist. */ int look_up_user_keyrings(struct key **_user_keyring, struct key **_user_session_keyring) { const struct cred *cred = current_cred(); struct user_namespace *user_ns = current_user_ns(); struct key *reg_keyring, *uid_keyring, *session_keyring; key_perm_t user_keyring_perm; key_ref_t uid_keyring_r, session_keyring_r; uid_t uid = from_kuid(user_ns, cred->user->uid); char buf[20]; int ret; user_keyring_perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL; kenter("%u", uid); reg_keyring = get_user_register(user_ns); if (IS_ERR(reg_keyring)) return PTR_ERR(reg_keyring); down_write(&user_ns->keyring_sem); ret = 0; /* Get the user keyring. Note that there may be one in existence * already as it may have been pinned by a session, but the user_struct * pointing to it may have been destroyed by setuid. */ snprintf(buf, sizeof(buf), "_uid.%u", uid); uid_keyring_r = keyring_search(make_key_ref(reg_keyring, true), &key_type_keyring, buf, false); kdebug("_uid %p", uid_keyring_r); if (uid_keyring_r == ERR_PTR(-EAGAIN)) { uid_keyring = keyring_alloc(buf, cred->user->uid, INVALID_GID, cred, user_keyring_perm, KEY_ALLOC_UID_KEYRING | KEY_ALLOC_IN_QUOTA, NULL, reg_keyring); if (IS_ERR(uid_keyring)) { ret = PTR_ERR(uid_keyring); goto error; } } else if (IS_ERR(uid_keyring_r)) { ret = PTR_ERR(uid_keyring_r); goto error; } else { uid_keyring = key_ref_to_ptr(uid_keyring_r); } /* Get a default session keyring (which might also exist already) */ snprintf(buf, sizeof(buf), "_uid_ses.%u", uid); session_keyring_r = keyring_search(make_key_ref(reg_keyring, true), &key_type_keyring, buf, false); kdebug("_uid_ses %p", session_keyring_r); if (session_keyring_r == ERR_PTR(-EAGAIN)) { session_keyring = keyring_alloc(buf, cred->user->uid, INVALID_GID, cred, user_keyring_perm, KEY_ALLOC_UID_KEYRING | KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(session_keyring)) { ret = PTR_ERR(session_keyring); goto error_release; } /* We install a link from the user session keyring to * the user keyring. */ ret = key_link(session_keyring, uid_keyring); if (ret < 0) goto error_release_session; /* And only then link the user-session keyring to the * register. */ ret = key_link(reg_keyring, session_keyring); if (ret < 0) goto error_release_session; } else if (IS_ERR(session_keyring_r)) { ret = PTR_ERR(session_keyring_r); goto error_release; } else { session_keyring = key_ref_to_ptr(session_keyring_r); } up_write(&user_ns->keyring_sem); if (_user_session_keyring) *_user_session_keyring = session_keyring; else key_put(session_keyring); if (_user_keyring) *_user_keyring = uid_keyring; else key_put(uid_keyring); kleave(" = 0"); return 0; error_release_session: key_put(session_keyring); error_release: key_put(uid_keyring); error: up_write(&user_ns->keyring_sem); kleave(" = %d", ret); return ret; } /* * Get the user session keyring if it exists, but don't create it if it * doesn't. */ struct key *get_user_session_keyring_rcu(const struct cred *cred) { struct key *reg_keyring = READ_ONCE(cred->user_ns->user_keyring_register); key_ref_t session_keyring_r; char buf[20]; struct keyring_search_context ctx = { .index_key.type = &key_type_keyring, .index_key.description = buf, .cred = cred, .match_data.cmp = key_default_cmp, .match_data.raw_data = buf, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = KEYRING_SEARCH_DO_STATE_CHECK, }; if (!reg_keyring) return NULL; ctx.index_key.desc_len = snprintf(buf, sizeof(buf), "_uid_ses.%u", from_kuid(cred->user_ns, cred->user->uid)); session_keyring_r = keyring_search_rcu(make_key_ref(reg_keyring, true), &ctx); if (IS_ERR(session_keyring_r)) return NULL; return key_ref_to_ptr(session_keyring_r); } /* * Install a thread keyring to the given credentials struct if it didn't have * one already. This is allowed to overrun the quota. * * Return: 0 if a thread keyring is now present; -errno on failure. */ int install_thread_keyring_to_cred(struct cred *new) { struct key *keyring; if (new->thread_keyring) return 0; keyring = keyring_alloc("_tid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, KEY_ALLOC_QUOTA_OVERRUN, NULL, NULL); if (IS_ERR(keyring)) return PTR_ERR(keyring); new->thread_keyring = keyring; return 0; } /* * Install a thread keyring to the current task if it didn't have one already. * * Return: 0 if a thread keyring is now present; -errno on failure. */ static int install_thread_keyring(void) { struct cred *new; int ret; new = prepare_creds(); if (!new) return -ENOMEM; ret = install_thread_keyring_to_cred(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); } /* * Install a process keyring to the given credentials struct if it didn't have * one already. This is allowed to overrun the quota. * * Return: 0 if a process keyring is now present; -errno on failure. */ int install_process_keyring_to_cred(struct cred *new) { struct key *keyring; if (new->process_keyring) return 0; keyring = keyring_alloc("_pid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, KEY_ALLOC_QUOTA_OVERRUN, NULL, NULL); if (IS_ERR(keyring)) return PTR_ERR(keyring); new->process_keyring = keyring; return 0; } /* * Install a process keyring to the current task if it didn't have one already. * * Return: 0 if a process keyring is now present; -errno on failure. */ static int install_process_keyring(void) { struct cred *new; int ret; new = prepare_creds(); if (!new) return -ENOMEM; ret = install_process_keyring_to_cred(new); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); } /* * Install the given keyring as the session keyring of the given credentials * struct, replacing the existing one if any. If the given keyring is NULL, * then install a new anonymous session keyring. * @cred can not be in use by any task yet. * * Return: 0 on success; -errno on failure. */ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) { unsigned long flags; struct key *old; might_sleep(); /* create an empty session keyring */ if (!keyring) { flags = KEY_ALLOC_QUOTA_OVERRUN; if (cred->session_keyring) flags = KEY_ALLOC_IN_QUOTA; keyring = keyring_alloc("_ses", cred->uid, cred->gid, cred, KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ, flags, NULL, NULL); if (IS_ERR(keyring)) return PTR_ERR(keyring); } else { __key_get(keyring); } /* install the keyring */ old = cred->session_keyring; cred->session_keyring = keyring; if (old) key_put(old); return 0; } /* * Install the given keyring as the session keyring of the current task, * replacing the existing one if any. If the given keyring is NULL, then * install a new anonymous session keyring. * * Return: 0 on success; -errno on failure. */ static int install_session_keyring(struct key *keyring) { struct cred *new; int ret; new = prepare_creds(); if (!new) return -ENOMEM; ret = install_session_keyring_to_cred(new, keyring); if (ret < 0) { abort_creds(new); return ret; } return commit_creds(new); } /* * Handle the fsuid changing. */ void key_fsuid_changed(struct cred *new_cred) { /* update the ownership of the thread keyring */ if (new_cred->thread_keyring) { down_write(&new_cred->thread_keyring->sem); new_cred->thread_keyring->uid = new_cred->fsuid; up_write(&new_cred->thread_keyring->sem); } } /* * Handle the fsgid changing. */ void key_fsgid_changed(struct cred *new_cred) { /* update the ownership of the thread keyring */ if (new_cred->thread_keyring) { down_write(&new_cred->thread_keyring->sem); new_cred->thread_keyring->gid = new_cred->fsgid; up_write(&new_cred->thread_keyring->sem); } } /* * Search the process keyrings attached to the supplied cred for the first * matching key under RCU conditions (the caller must be holding the RCU read * lock). * * The search criteria are the type and the match function. The description is * given to the match function as a parameter, but doesn't otherwise influence * the search. Typically the match function will compare the description * parameter to the key's description. * * This can only search keyrings that grant Search permission to the supplied * credentials. Keyrings linked to searched keyrings will also be searched if * they grant Search permission too. Keys can only be found if they grant * Search permission to the credentials. * * Returns a pointer to the key with the key usage count incremented if * successful, -EAGAIN if we didn't find any matching key or -ENOKEY if we only * matched negative keys. * * In the case of a successful return, the possession attribute is set on the * returned key reference. */ key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx) { struct key *user_session; key_ref_t key_ref, ret, err; const struct cred *cred = ctx->cred; /* we want to return -EAGAIN or -ENOKEY if any of the keyrings were * searchable, but we failed to find a key or we found a negative key; * otherwise we want to return a sample error (probably -EACCES) if * none of the keyrings were searchable * * in terms of priority: success > -ENOKEY > -EAGAIN > other error */ key_ref = NULL; ret = NULL; err = ERR_PTR(-EAGAIN); /* search the thread keyring first */ if (cred->thread_keyring) { key_ref = keyring_search_rcu( make_key_ref(cred->thread_keyring, 1), ctx); if (!IS_ERR(key_ref)) goto found; switch (PTR_ERR(key_ref)) { case -EAGAIN: /* no key */ case -ENOKEY: /* negative key */ ret = key_ref; break; default: err = key_ref; break; } } /* search the process keyring second */ if (cred->process_keyring) { key_ref = keyring_search_rcu( make_key_ref(cred->process_keyring, 1), ctx); if (!IS_ERR(key_ref)) goto found; switch (PTR_ERR(key_ref)) { case -EAGAIN: /* no key */ if (ret) break; fallthrough; case -ENOKEY: /* negative key */ ret = key_ref; break; default: err = key_ref; break; } } /* search the session keyring */ if (cred->session_keyring) { key_ref = keyring_search_rcu( make_key_ref(cred->session_keyring, 1), ctx); if (!IS_ERR(key_ref)) goto found; switch (PTR_ERR(key_ref)) { case -EAGAIN: /* no key */ if (ret) break; fallthrough; case -ENOKEY: /* negative key */ ret = key_ref; break; default: err = key_ref; break; } } /* or search the user-session keyring */ else if ((user_session = get_user_session_keyring_rcu(cred))) { key_ref = keyring_search_rcu(make_key_ref(user_session, 1), ctx); key_put(user_session); if (!IS_ERR(key_ref)) goto found; switch (PTR_ERR(key_ref)) { case -EAGAIN: /* no key */ if (ret) break; fallthrough; case -ENOKEY: /* negative key */ ret = key_ref; break; default: err = key_ref; break; } } /* no key - decide on the error we're going to go for */ key_ref = ret ? ret : err; found: return key_ref; } /* * Search the process keyrings attached to the supplied cred for the first * matching key in the manner of search_my_process_keyrings(), but also search * the keys attached to the assumed authorisation key using its credentials if * one is available. * * The caller must be holding the RCU read lock. * * Return same as search_cred_keyrings_rcu(). */ key_ref_t search_process_keyrings_rcu(struct keyring_search_context *ctx) { struct request_key_auth *rka; key_ref_t key_ref, ret = ERR_PTR(-EACCES), err; key_ref = search_cred_keyrings_rcu(ctx); if (!IS_ERR(key_ref)) goto found; err = key_ref; /* if this process has an instantiation authorisation key, then we also * search the keyrings of the process mentioned there * - we don't permit access to request_key auth keys via this method */ if (ctx->cred->request_key_auth && ctx->cred == current_cred() && ctx->index_key.type != &key_type_request_key_auth ) { const struct cred *cred = ctx->cred; if (key_validate(cred->request_key_auth) == 0) { rka = ctx->cred->request_key_auth->payload.data[0]; //// was search_process_keyrings() [ie. recursive] ctx->cred = rka->cred; key_ref = search_cred_keyrings_rcu(ctx); ctx->cred = cred; if (!IS_ERR(key_ref)) goto found; ret = key_ref; } } /* no key - decide on the error we're going to go for */ if (err == ERR_PTR(-ENOKEY) || ret == ERR_PTR(-ENOKEY)) key_ref = ERR_PTR(-ENOKEY); else if (err == ERR_PTR(-EACCES)) key_ref = ret; else key_ref = err; found: return key_ref; } /* * See if the key we're looking at is the target key. */ bool lookup_user_key_possessed(const struct key *key, const struct key_match_data *match_data) { return key == match_data->raw_data; } /* * Look up a key ID given us by userspace with a given permissions mask to get * the key it refers to. * * Flags can be passed to request that special keyrings be created if referred * to directly, to permit partially constructed keys to be found and to skip * validity and permission checks on the found key. * * Returns a pointer to the key with an incremented usage count if successful; * -EINVAL if the key ID is invalid; -ENOKEY if the key ID does not correspond * to a key or the best found key was a negative key; -EKEYREVOKED or * -EKEYEXPIRED if the best found key was revoked or expired; -EACCES if the * found key doesn't grant the requested permit or the LSM denied access to it; * or -ENOMEM if a special keyring couldn't be created. * * In the case of a successful return, the possession attribute is set on the * returned key reference. */ key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags, enum key_need_perm need_perm) { struct keyring_search_context ctx = { .match_data.cmp = lookup_user_key_possessed, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_RECURSE), }; struct request_key_auth *rka; struct key *key, *user_session; key_ref_t key_ref, skey_ref; int ret; try_again: ctx.cred = get_current_cred(); key_ref = ERR_PTR(-ENOKEY); switch (id) { case KEY_SPEC_THREAD_KEYRING: if (!ctx.cred->thread_keyring) { if (!(lflags & KEY_LOOKUP_CREATE)) goto error; ret = install_thread_keyring(); if (ret < 0) { key_ref = ERR_PTR(ret); goto error; } goto reget_creds; } key = ctx.cred->thread_keyring; __key_get(key); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_PROCESS_KEYRING: if (!ctx.cred->process_keyring) { if (!(lflags & KEY_LOOKUP_CREATE)) goto error; ret = install_process_keyring(); if (ret < 0) { key_ref = ERR_PTR(ret); goto error; } goto reget_creds; } key = ctx.cred->process_keyring; __key_get(key); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_SESSION_KEYRING: if (!ctx.cred->session_keyring) { /* always install a session keyring upon access if one * doesn't exist yet */ ret = look_up_user_keyrings(NULL, &user_session); if (ret < 0) goto error; if (lflags & KEY_LOOKUP_CREATE) ret = join_session_keyring(NULL); else ret = install_session_keyring(user_session); key_put(user_session); if (ret < 0) goto error; goto reget_creds; } else if (test_bit(KEY_FLAG_UID_KEYRING, &ctx.cred->session_keyring->flags) && lflags & KEY_LOOKUP_CREATE) { ret = join_session_keyring(NULL); if (ret < 0) goto error; goto reget_creds; } key = ctx.cred->session_keyring; __key_get(key); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_USER_KEYRING: ret = look_up_user_keyrings(&key, NULL); if (ret < 0) goto error; key_ref = make_key_ref(key, 1); break; case KEY_SPEC_USER_SESSION_KEYRING: ret = look_up_user_keyrings(NULL, &key); if (ret < 0) goto error; key_ref = make_key_ref(key, 1); break; case KEY_SPEC_GROUP_KEYRING: /* group keyrings are not yet supported */ key_ref = ERR_PTR(-EINVAL); goto error; case KEY_SPEC_REQKEY_AUTH_KEY: key = ctx.cred->request_key_auth; if (!key) goto error; __key_get(key); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_REQUESTOR_KEYRING: if (!ctx.cred->request_key_auth) goto error; down_read(&ctx.cred->request_key_auth->sem); if (test_bit(KEY_FLAG_REVOKED, &ctx.cred->request_key_auth->flags)) { key_ref = ERR_PTR(-EKEYREVOKED); key = NULL; } else { rka = ctx.cred->request_key_auth->payload.data[0]; key = rka->dest_keyring; __key_get(key); } up_read(&ctx.cred->request_key_auth->sem); if (!key) goto error; key_ref = make_key_ref(key, 1); break; default: key_ref = ERR_PTR(-EINVAL); if (id < 1) goto error; key = key_lookup(id); if (IS_ERR(key)) { key_ref = ERR_CAST(key); goto error; } key_ref = make_key_ref(key, 0); /* check to see if we possess the key */ ctx.index_key = key->index_key; ctx.match_data.raw_data = key; kdebug("check possessed"); rcu_read_lock(); skey_ref = search_process_keyrings_rcu(&ctx); rcu_read_unlock(); kdebug("possessed=%p", skey_ref); if (!IS_ERR(skey_ref)) { key_put(key); key_ref = skey_ref; } break; } /* unlink does not use the nominated key in any way, so can skip all * the permission checks as it is only concerned with the keyring */ if (need_perm != KEY_NEED_UNLINK) { if (!(lflags & KEY_LOOKUP_PARTIAL)) { ret = wait_for_key_construction(key, true); switch (ret) { case -ERESTARTSYS: goto invalid_key; default: if (need_perm != KEY_AUTHTOKEN_OVERRIDE && need_perm != KEY_DEFER_PERM_CHECK) goto invalid_key; case 0: break; } } else if (need_perm != KEY_DEFER_PERM_CHECK) { ret = key_validate(key); if (ret < 0) goto invalid_key; } ret = -EIO; if (!(lflags & KEY_LOOKUP_PARTIAL) && key_read_state(key) == KEY_IS_UNINSTANTIATED) goto invalid_key; } /* check the permissions */ ret = key_task_permission(key_ref, ctx.cred, need_perm); if (ret < 0) goto invalid_key; key->last_used_at = ktime_get_real_seconds(); error: put_cred(ctx.cred); return key_ref; invalid_key: key_ref_put(key_ref); key_ref = ERR_PTR(ret); goto error; /* if we attempted to install a keyring, then it may have caused new * creds to be installed */ reget_creds: put_cred(ctx.cred); goto try_again; } EXPORT_SYMBOL(lookup_user_key); /* * Join the named keyring as the session keyring if possible else attempt to * create a new one of that name and join that. * * If the name is NULL, an empty anonymous keyring will be installed as the * session keyring. * * Named session keyrings are joined with a semaphore held to prevent the * keyrings from going away whilst the attempt is made to going them and also * to prevent a race in creating compatible session keyrings. */ long join_session_keyring(const char *name) { const struct cred *old; struct cred *new; struct key *keyring; long ret, serial; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); /* if no name is provided, install an anonymous keyring */ if (!name) { ret = install_session_keyring_to_cred(new, NULL); if (ret < 0) goto error; serial = new->session_keyring->serial; ret = commit_creds(new); if (ret == 0) ret = serial; goto okay; } /* allow the user to join or create a named keyring */ mutex_lock(&key_session_mutex); /* look for an existing keyring of this name */ keyring = find_keyring_by_name(name, false); if (PTR_ERR(keyring) == -ENOKEY) { /* not found - try and create a new one */ keyring = keyring_alloc( name, old->uid, old->gid, old, KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_LINK, KEY_ALLOC_IN_QUOTA, NULL, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto error2; } } else if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto error2; } else if (keyring == new->session_keyring) { ret = 0; goto error3; } /* we've got a keyring - now to install it */ ret = install_session_keyring_to_cred(new, keyring); if (ret < 0) goto error3; commit_creds(new); mutex_unlock(&key_session_mutex); ret = keyring->serial; key_put(keyring); okay: return ret; error3: key_put(keyring); error2: mutex_unlock(&key_session_mutex); error: abort_creds(new); return ret; } /* * Replace a process's session keyring on behalf of one of its children when * the target process is about to resume userspace execution. */ void key_change_session_keyring(struct callback_head *twork) { const struct cred *old = current_cred(); struct cred *new = container_of(twork, struct cred, rcu); if (unlikely(current->flags & PF_EXITING)) { put_cred(new); return; } new-> uid = old-> uid; new-> euid = old-> euid; new-> suid = old-> suid; new->fsuid = old->fsuid; new-> gid = old-> gid; new-> egid = old-> egid; new-> sgid = old-> sgid; new->fsgid = old->fsgid; new->user = get_uid(old->user); new->user_ns = get_user_ns(old->user_ns); new->group_info = get_group_info(old->group_info); new->securebits = old->securebits; new->cap_inheritable = old->cap_inheritable; new->cap_permitted = old->cap_permitted; new->cap_effective = old->cap_effective; new->cap_ambient = old->cap_ambient; new->cap_bset = old->cap_bset; new->jit_keyring = old->jit_keyring; new->thread_keyring = key_get(old->thread_keyring); new->process_keyring = key_get(old->process_keyring); security_transfer_creds(new, old); commit_creds(new); } /* * Make sure that root's user and user-session keyrings exist. */ static int __init init_root_keyring(void) { return look_up_user_keyrings(NULL, NULL); } late_initcall(init_root_keyring); |
| 43 43 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 | // SPDX-License-Identifier: GPL-2.0 #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/export.h> #include <net/net_namespace.h> #include <net/fib_notifier.h> #include <net/netns/ipv4.h> #include <net/ip_fib.h> int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { ASSERT_RTNL(); info->family = AF_INET; net->ipv4.fib_seq++; return call_fib_notifiers(net, event_type, info); } static unsigned int fib4_seq_read(struct net *net) { ASSERT_RTNL(); return net->ipv4.fib_seq + fib4_rules_seq_read(net); } static int fib4_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { int err; err = fib4_rules_dump(net, nb, extack); if (err) return err; return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { .family = AF_INET, .fib_seq_read = fib4_seq_read, .fib_dump = fib4_dump, .owner = THIS_MODULE, }; int __net_init fib4_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.fib_seq = 0; ops = fib_notifier_ops_register(&fib4_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.notifier_ops = ops; return 0; } void __net_exit fib4_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.notifier_ops); } |
| 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 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth address family and sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/stringify.h> #include <linux/sched/signal.h> #include <asm/ioctls.h> #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> #include "leds.h" #include "selftest.h" /* Bluetooth sockets */ #define BT_MAX_PROTO 8 static const struct net_proto_family *bt_proto[BT_MAX_PROTO]; static DEFINE_RWLOCK(bt_proto_lock); static struct lock_class_key bt_lock_key[BT_MAX_PROTO]; static const char *const bt_key_strings[BT_MAX_PROTO] = { "sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP", "sk_lock-AF_BLUETOOTH-BTPROTO_HCI", "sk_lock-AF_BLUETOOTH-BTPROTO_SCO", "sk_lock-AF_BLUETOOTH-BTPROTO_RFCOMM", "sk_lock-AF_BLUETOOTH-BTPROTO_BNEP", "sk_lock-AF_BLUETOOTH-BTPROTO_CMTP", "sk_lock-AF_BLUETOOTH-BTPROTO_HIDP", "sk_lock-AF_BLUETOOTH-BTPROTO_AVDTP", }; static struct lock_class_key bt_slock_key[BT_MAX_PROTO]; static const char *const bt_slock_key_strings[BT_MAX_PROTO] = { "slock-AF_BLUETOOTH-BTPROTO_L2CAP", "slock-AF_BLUETOOTH-BTPROTO_HCI", "slock-AF_BLUETOOTH-BTPROTO_SCO", "slock-AF_BLUETOOTH-BTPROTO_RFCOMM", "slock-AF_BLUETOOTH-BTPROTO_BNEP", "slock-AF_BLUETOOTH-BTPROTO_CMTP", "slock-AF_BLUETOOTH-BTPROTO_HIDP", "slock-AF_BLUETOOTH-BTPROTO_AVDTP", }; void bt_sock_reclassify_lock(struct sock *sk, int proto) { BUG_ON(!sk); BUG_ON(!sock_allow_reclassification(sk)); sock_lock_init_class_and_name(sk, bt_slock_key_strings[proto], &bt_slock_key[proto], bt_key_strings[proto], &bt_lock_key[proto]); } EXPORT_SYMBOL(bt_sock_reclassify_lock); int bt_sock_register(int proto, const struct net_proto_family *ops) { int err = 0; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; write_lock(&bt_proto_lock); if (bt_proto[proto]) err = -EEXIST; else bt_proto[proto] = ops; write_unlock(&bt_proto_lock); return err; } EXPORT_SYMBOL(bt_sock_register); void bt_sock_unregister(int proto) { if (proto < 0 || proto >= BT_MAX_PROTO) return; write_lock(&bt_proto_lock); bt_proto[proto] = NULL; write_unlock(&bt_proto_lock); } EXPORT_SYMBOL(bt_sock_unregister); static int bt_sock_create(struct net *net, struct socket *sock, int proto, int kern) { int err; if (net != &init_net) return -EAFNOSUPPORT; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; if (!bt_proto[proto]) request_module("bt-proto-%d", proto); err = -EPROTONOSUPPORT; read_lock(&bt_proto_lock); if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { err = bt_proto[proto]->create(net, sock, proto, kern); if (!err) bt_sock_reclassify_lock(sock->sk, proto); module_put(bt_proto[proto]->owner); } read_unlock(&bt_proto_lock); return err; } void bt_sock_link(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_add_node(sk, &l->head); write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_link); void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_del_node_init(sk); write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_unlink); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); if (bh) bh_lock_sock_nested(sk); else lock_sock_nested(sk, SINGLE_DEPTH_NESTING); list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; if (bh) bh_unlock_sock(sk); else release_sock(sk); sk_acceptq_added(parent); } EXPORT_SYMBOL(bt_accept_enqueue); /* Calling function must hold the sk lock. * bt_sk(sk)->parent must be non-NULL meaning sk is in the parent list. */ void bt_accept_unlink(struct sock *sk) { BT_DBG("sk %p state %d", sk, sk->sk_state); list_del_init(&bt_sk(sk)->accept_q); sk_acceptq_removed(bt_sk(sk)->parent); bt_sk(sk)->parent = NULL; sock_put(sk); } EXPORT_SYMBOL(bt_accept_unlink); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) { struct bt_sock *s, *n; struct sock *sk; BT_DBG("parent %p", parent); restart: list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; /* Prevent early freeing of sk due to unlink and sock_kill */ sock_hold(sk); lock_sock(sk); /* Check sk has not already been unlinked via * bt_accept_unlink() due to serialisation caused by sk locking */ if (!bt_sk(sk)->parent) { BT_DBG("sk %p, already unlinked", sk); release_sock(sk); sock_put(sk); /* Restart the loop as sk is no longer in the list * and also avoid a potential infinite loop because * list_for_each_entry_safe() is not thread safe. */ goto restart; } /* sk is safely in the parent list so reduce reference count */ sock_put(sk); /* FIXME: Is this check still needed */ if (sk->sk_state == BT_CLOSED) { bt_accept_unlink(sk); release_sock(sk); continue; } if (sk->sk_state == BT_CONNECTED || !newsock || test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) { bt_accept_unlink(sk); if (newsock) sock_graft(sk, newsock); release_sock(sk); return sk; } release_sock(sk); } return NULL; } EXPORT_SYMBOL(bt_accept_dequeue); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct sk_buff *skb; size_t copied; size_t skblen; int err; BT_DBG("sock %p sk %p len %zu", sock, sk, len); if (flags & MSG_OOB) return -EOPNOTSUPP; skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) return 0; return err; } skblen = skb->len; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err == 0) { sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name && bt_sk(sk)->skb_msg_name) bt_sk(sk)->skb_msg_name(skb, msg->msg_name, &msg->msg_namelen); if (bt_sk(sk)->skb_put_cmsg) bt_sk(sk)->skb_put_cmsg(skb, msg, sk); } skb_free_datagram(sk, skb); if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; } EXPORT_SYMBOL(bt_sock_recvmsg); static long bt_sock_data_wait(struct sock *sk, long timeo) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(sk_sleep(sk), &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (!skb_queue_empty(&sk->sk_receive_queue)) break; if (sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN)) break; if (signal_pending(current) || !timeo) break; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return timeo; } int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int err = 0; size_t target, copied = 0; long timeo; if (flags & MSG_OOB) return -EOPNOTSUPP; BT_DBG("sk %p size %zu", sk, size); lock_sock(sk); target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb; int chunk; skb = skb_dequeue(&sk->sk_receive_queue); if (!skb) { if (copied >= target) break; err = sock_error(sk); if (err) break; if (sk->sk_shutdown & RCV_SHUTDOWN) break; err = -EAGAIN; if (!timeo) break; timeo = bt_sock_data_wait(sk, timeo); if (signal_pending(current)) { err = sock_intr_errno(timeo); goto out; } continue; } chunk = min_t(unsigned int, skb->len, size); if (skb_copy_datagram_msg(skb, 0, msg, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); if (!copied) copied = -EFAULT; break; } copied += chunk; size -= chunk; sock_recv_ts_and_drops(msg, sk, skb); if (!(flags & MSG_PEEK)) { int skb_len = skb_headlen(skb); if (chunk <= skb_len) { __skb_pull(skb, chunk); } else { struct sk_buff *frag; __skb_pull(skb, skb_len); chunk -= skb_len; skb_walk_frags(skb, frag) { if (chunk <= frag->len) { /* Pulling partial data */ skb->len -= chunk; skb->data_len -= chunk; __skb_pull(frag, chunk); break; } else if (frag->len) { /* Pulling all frag data */ chunk -= frag->len; skb->len -= frag->len; skb->data_len -= frag->len; __skb_pull(frag, frag->len); } } } if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); break; } kfree_skb(skb); } else { /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); break; } } while (size); out: release_sock(sk); return copied ? : err; } EXPORT_SYMBOL(bt_sock_stream_recvmsg); static inline __poll_t bt_accept_poll(struct sock *parent) { struct bt_sock *s, *n; struct sock *sk; list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; if (sk->sk_state == BT_CONNECTED || (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && sk->sk_state == BT_CONNECT2)) return EPOLLIN | EPOLLRDNORM; } return 0; } __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask = 0; poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) mask |= EPOLLHUP; if (sk->sk_state == BT_CONNECT || sk->sk_state == BT_CONNECT2 || sk->sk_state == BT_CONFIG) return mask; if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } EXPORT_SYMBOL(bt_sock_poll); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; struct sk_buff *skb; long amount; int err; BT_DBG("sk %p cmd %x arg %lx", sk, cmd, arg); switch (cmd) { case TIOCOUTQ: if (sk->sk_state == BT_LISTEN) return -EINVAL; amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; err = put_user(amount, (int __user *) arg); break; case TIOCINQ: if (sk->sk_state == BT_LISTEN) return -EINVAL; lock_sock(sk); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; release_sock(sk); err = put_user(amount, (int __user *) arg); break; default: err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(bt_sock_ioctl); /* This function expects the sk lock to be held when called */ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) { DECLARE_WAITQUEUE(wait, current); int err = 0; BT_DBG("sk %p", sk); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (sk->sk_state != state) { if (!timeo) { err = -EINPROGRESS; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_state); /* This function expects the sk lock to be held when called */ int bt_sock_wait_ready(struct sock *sk, unsigned long flags) { DECLARE_WAITQUEUE(wait, current); unsigned long timeo; int err = 0; BT_DBG("sk %p", sk); timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags)) { if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_ready); #ifdef CONFIG_PROC_FS static void *bt_seq_start(struct seq_file *seq, loff_t *pos) __acquires(seq->private->l->lock) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); read_lock(&l->lock); return seq_hlist_start_head(&l->head, *pos); } static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); return seq_hlist_next(v, &l->head, pos); } static void bt_seq_stop(struct seq_file *seq, void *v) __releases(seq->private->l->lock) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); read_unlock(&l->lock); } static int bt_seq_show(struct seq_file *seq, void *v) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); if (v == SEQ_START_TOKEN) { seq_puts(seq ,"sk RefCnt Rmem Wmem User Inode Parent"); if (l->custom_seq_show) { seq_putc(seq, ' '); l->custom_seq_show(seq, v); } seq_putc(seq, '\n'); } else { struct sock *sk = sk_entry(v); struct bt_sock *bt = bt_sk(sk); seq_printf(seq, "%pK %-6d %-6u %-6u %-6u %-6lu %-6lu", sk, refcount_read(&sk->sk_refcnt), sk_rmem_alloc_get(sk), sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), bt->parent? sock_i_ino(bt->parent): 0LU); if (l->custom_seq_show) { seq_putc(seq, ' '); l->custom_seq_show(seq, v); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations bt_seq_ops = { .start = bt_seq_start, .next = bt_seq_next, .stop = bt_seq_stop, .show = bt_seq_show, }; int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (* seq_show)(struct seq_file *, void *)) { sk_list->custom_seq_show = seq_show; if (!proc_create_seq_data(name, 0, net->proc_net, &bt_seq_ops, sk_list)) return -ENOMEM; return 0; } void bt_procfs_cleanup(struct net *net, const char *name) { remove_proc_entry(name, net->proc_net); } #else int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (* seq_show)(struct seq_file *, void *)) { return 0; } void bt_procfs_cleanup(struct net *net, const char *name) { } #endif EXPORT_SYMBOL(bt_procfs_init); EXPORT_SYMBOL(bt_procfs_cleanup); static const struct net_proto_family bt_sock_family_ops = { .owner = THIS_MODULE, .family = PF_BLUETOOTH, .create = bt_sock_create, }; struct dentry *bt_debugfs; EXPORT_SYMBOL_GPL(bt_debugfs); #define VERSION __stringify(BT_SUBSYS_VERSION) "." \ __stringify(BT_SUBSYS_REVISION) static int __init bt_init(void) { int err; sock_skb_cb_check_size(sizeof(struct bt_skb_cb)); BT_INFO("Core ver %s", VERSION); err = bt_selftest(); if (err < 0) return err; bt_debugfs = debugfs_create_dir("bluetooth", NULL); bt_leds_init(); err = bt_sysfs_init(); if (err < 0) return err; err = sock_register(&bt_sock_family_ops); if (err) goto cleanup_sysfs; BT_INFO("HCI device and connection manager initialized"); err = hci_sock_init(); if (err) goto unregister_socket; err = l2cap_init(); if (err) goto cleanup_socket; err = sco_init(); if (err) goto cleanup_cap; err = mgmt_init(); if (err) goto cleanup_sco; return 0; cleanup_sco: sco_exit(); cleanup_cap: l2cap_exit(); cleanup_socket: hci_sock_cleanup(); unregister_socket: sock_unregister(PF_BLUETOOTH); cleanup_sysfs: bt_sysfs_cleanup(); return err; } static void __exit bt_exit(void) { mgmt_exit(); sco_exit(); l2cap_exit(); hci_sock_cleanup(); sock_unregister(PF_BLUETOOTH); bt_sysfs_cleanup(); bt_leds_cleanup(); debugfs_remove_recursive(bt_debugfs); } subsys_initcall(bt_init); module_exit(bt_exit); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth Core ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_BLUETOOTH); |
| 5 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/export.h> #include <linux/mm.h> #include <linux/utsname.h> #include <linux/mman.h> #include <linux/reboot.h> #include <linux/prctl.h> #include <linux/highuid.h> #include <linux/fs.h> #include <linux/kmod.h> #include <linux/perf_event.h> #include <linux/resource.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/capability.h> #include <linux/device.h> #include <linux/key.h> #include <linux/times.h> #include <linux/posix-timers.h> #include <linux/security.h> #include <linux/dcookies.h> #include <linux/suspend.h> #include <linux/tty.h> #include <linux/signal.h> #include <linux/cn_proc.h> #include <linux/getcpu.h> #include <linux/task_io_accounting_ops.h> #include <linux/seccomp.h> #include <linux/cpu.h> #include <linux/personality.h> #include <linux/ptrace.h> #include <linux/fs_struct.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/version.h> #include <linux/ctype.h> #include <linux/mm.h> #include <linux/mempolicy.h> #include <linux/compat.h> #include <linux/syscalls.h> #include <linux/kprobes.h> #include <linux/user_namespace.h> #include <linux/time_namespace.h> #include <linux/binfmts.h> #include <linux/sched.h> #include <linux/sched/autogroup.h> #include <linux/sched/loadavg.h> #include <linux/sched/stat.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> #include <linux/nospec.h> #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> #include "uid16.h" #include <trace/hooks/sys.h> #ifndef SET_UNALIGN_CTL # define SET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef GET_UNALIGN_CTL # define GET_UNALIGN_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEMU_CTL # define SET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEMU_CTL # define GET_FPEMU_CTL(a, b) (-EINVAL) #endif #ifndef SET_FPEXC_CTL # define SET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a, b) (-EINVAL) #endif #ifndef GET_ENDIAN # define GET_ENDIAN(a, b) (-EINVAL) #endif #ifndef SET_ENDIAN # define SET_ENDIAN(a, b) (-EINVAL) #endif #ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif #ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif #ifndef SVE_SET_VL # define SVE_SET_VL(a) (-EINVAL) #endif #ifndef SVE_GET_VL # define SVE_GET_VL() (-EINVAL) #endif #ifndef PAC_RESET_KEYS # define PAC_RESET_KEYS(a, b) (-EINVAL) #endif #ifndef PAC_SET_ENABLED_KEYS # define PAC_SET_ENABLED_KEYS(a, b, c) (-EINVAL) #endif #ifndef PAC_GET_ENABLED_KEYS # define PAC_GET_ENABLED_KEYS(a) (-EINVAL) #endif #ifndef SET_TAGGED_ADDR_CTRL # define SET_TAGGED_ADDR_CTRL(a) (-EINVAL) #endif #ifndef GET_TAGGED_ADDR_CTRL # define GET_TAGGED_ADDR_CTRL() (-EINVAL) #endif /* * this is where the system-wide overflow UID and GID are defined, for * architectures that now have 32-bit UID/GID but didn't in the past */ int overflowuid = DEFAULT_OVERFLOWUID; int overflowgid = DEFAULT_OVERFLOWGID; EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); /* * the same as above, but for filesystems which can only store a 16-bit * UID and GID. as such, this is needed on all architectures */ int fs_overflowuid = DEFAULT_FS_OVERFLOWUID; int fs_overflowgid = DEFAULT_FS_OVERFLOWGID; EXPORT_SYMBOL(fs_overflowuid); EXPORT_SYMBOL(fs_overflowgid); /* * Returns true if current's euid is same as p's uid or euid, * or has CAP_SYS_NICE to p's user_ns. * * Called with rcu_read_lock, creds are safe */ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) return true; if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) return true; return false; } /* * set the priority of a task * - the caller must hold the RCU read lock */ static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; if (!set_one_prio_perm(p)) { error = -EPERM; goto out; } if (niceval < task_nice(p) && !can_nice(p, niceval)) { error = -EACCES; goto out; } no_nice = security_task_setnice(p, niceval); if (no_nice) { error = no_nice; goto out; } if (error == -ESRCH) error = 0; set_user_nice(p, niceval); out: return error; } SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; if (niceval < MIN_NICE) niceval = MIN_NICE; if (niceval > MAX_NICE) niceval = MAX_NICE; rcu_read_lock(); read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } do_each_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) error = set_one_prio(p, niceval, error); } while_each_thread(g, p); if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; } out_unlock: read_unlock(&tasklist_lock); rcu_read_unlock(); out: return error; } /* * Ugh. To avoid negative return values, "getpriority()" will * not return the normal nice-value, but a negated value that * has been offset by 20 (ie it returns 40..1 instead of -20..19) * to stay compatible. */ SYSCALL_DEFINE2(getpriority, int, which, int, who) { struct task_struct *g, *p; struct user_struct *user; const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; kuid_t uid; if (which > PRIO_USER || which < PRIO_PROCESS) return -EINVAL; rcu_read_lock(); read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } do_each_thread(g, p) { if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } } while_each_thread(g, p); if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; } out_unlock: read_unlock(&tasklist_lock); rcu_read_unlock(); return retval; } /* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) * * If you set the real gid at all, or set the effective gid to a value not * equal to the real gid, then the saved gid is set to the new effective gid. * * This makes it possible for a setgid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setregid() will be * 100% compatible with BSD. A program which uses just setgid() will be * 100% compatible with POSIX with saved IDs. * * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ #ifdef CONFIG_MULTIUSER long __sys_setregid(gid_t rgid, gid_t egid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (rgid != (gid_t) -1) { if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = krgid; else goto error; } if (egid != (gid_t) -1) { if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || ns_capable_setid(old->user_ns, CAP_SETGID)) new->egid = kegid; else goto error; } if (rgid != (gid_t) -1 || (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) new->sgid = new->egid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RE); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { return __sys_setregid(rgid, egid); } /* * setgid() is implemented like SysV w/ SAVED_IDS * * SMP: Same implicit races as above. */ long __sys_setgid(gid_t gid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETGID)) new->gid = new->egid = new->sgid = new->fsgid = kgid; else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) new->egid = new->fsgid = kgid; else goto error; retval = security_task_fix_setgid(new, old, LSM_SETID_ID); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setgid, gid_t, gid) { return __sys_setgid(gid); } /* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) { struct user_struct *new_user; new_user = alloc_uid(new->uid); if (!new_user) return -EAGAIN; /* * We don't fail in case of NPROC limit excess here because too many * poorly written programs don't check set*uid() return code, assuming * it never fails if called by root. We may still enforce NPROC limit * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && new_user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; free_uid(new->user); new->user = new_user; return 0; } /* * Unprivileged users may change the real uid to the effective uid * or vice versa. (BSD-style) * * If you set the real uid at all, or set the effective uid to a value not * equal to the real uid, then the saved uid is set to the new effective uid. * * This makes it possible for a setuid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setreuid() will be * 100% compatible with BSD. A program which uses just setuid() will be * 100% compatible with POSIX with saved IDs. */ long __sys_setreuid(uid_t ruid, uid_t euid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (euid != (uid_t) -1) { new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && !ns_capable_setid(old->user_ns, CAP_SETUID)) goto error; } if (!uid_eq(new->uid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } if (ruid != (uid_t) -1 || (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) new->suid = new->euid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { return __sys_setreuid(ruid, euid); } /* * setuid() is implemented like SysV with SAVED_IDS * * Note that SAVED_ID's is deficient in that a setuid root program * like sendmail, for example, cannot set its uid to be a normal * user and then switch back, because if you're root, setuid() sets * the saved uid too. If you don't like this, blame the bright people * in the POSIX committee and/or USG. Note that the BSD-style setreuid() * will allow a root program to temporarily drop privileges and be able to * regain them by swapping the real and effective uid. */ long __sys_setuid(uid_t uid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (ns_capable_setid(old->user_ns, CAP_SETUID)) { new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { goto error; } new->fsuid = new->euid = kuid; retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE1(setuid, uid_t, uid) { return __sys_setuid(uid); } /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kuid_t kruid, keuid, ksuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); ksuid = make_kuid(ns, suid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (!ns_capable_setid(old->user_ns, CAP_SETUID)) { if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) goto error; if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) goto error; if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) goto error; } if (ruid != (uid_t) -1) { new->uid = kruid; if (!uid_eq(kruid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } if (euid != (uid_t) -1) new->euid = keuid; if (suid != (uid_t) -1) new->suid = ksuid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { return __sys_setresuid(ruid, euid, suid); } SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; uid_t ruid, euid, suid; ruid = from_kuid_munged(cred->user_ns, cred->uid); euid = from_kuid_munged(cred->user_ns, cred->euid); suid = from_kuid_munged(cred->user_ns, cred->suid); retval = put_user(ruid, ruidp); if (!retval) { retval = put_user(euid, euidp); if (!retval) return put_user(suid, suidp); } return retval; } /* * Same as above, but for rgid, egid, sgid. */ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) { struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; kgid_t krgid, kegid, ksgid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); ksgid = make_kgid(ns, sgid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); retval = -EPERM; if (!ns_capable_setid(old->user_ns, CAP_SETGID)) { if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) goto error; if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) goto error; if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) goto error; } if (rgid != (gid_t) -1) new->gid = krgid; if (egid != (gid_t) -1) new->egid = kegid; if (sgid != (gid_t) -1) new->sgid = ksgid; new->fsgid = new->egid; retval = security_task_fix_setgid(new, old, LSM_SETID_RES); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { return __sys_setresgid(rgid, egid, sgid); } SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; gid_t rgid, egid, sgid; rgid = from_kgid_munged(cred->user_ns, cred->gid); egid = from_kgid_munged(cred->user_ns, cred->egid); sgid = from_kgid_munged(cred->user_ns, cred->sgid); retval = put_user(rgid, rgidp); if (!retval) { retval = put_user(egid, egidp); if (!retval) retval = put_user(sgid, sgidp); } return retval; } /* * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This * is used for "access()" and for the NFS daemon (letting nfsd stay at * whatever uid it wants to). It normally shadows "euid", except when * explicitly set by setfsuid() or for access.. */ long __sys_setfsuid(uid_t uid) { const struct cred *old; struct cred *new; uid_t old_fsuid; kuid_t kuid; old = current_cred(); old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); kuid = make_kuid(old->user_ns, uid); if (!uid_valid(kuid)) return old_fsuid; new = prepare_creds(); if (!new) return old_fsuid; if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || ns_capable_setid(old->user_ns, CAP_SETUID)) { if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsuid; change_okay: commit_creds(new); return old_fsuid; } SYSCALL_DEFINE1(setfsuid, uid_t, uid) { return __sys_setfsuid(uid); } /* * Samma pÃ¥ svenska.. */ long __sys_setfsgid(gid_t gid) { const struct cred *old; struct cred *new; gid_t old_fsgid; kgid_t kgid; old = current_cred(); old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); kgid = make_kgid(old->user_ns, gid); if (!gid_valid(kgid)) return old_fsgid; new = prepare_creds(); if (!new) return old_fsgid; if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || ns_capable_setid(old->user_ns, CAP_SETGID)) { if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; if (security_task_fix_setgid(new,old,LSM_SETID_FS) == 0) goto change_okay; } } abort_creds(new); return old_fsgid; change_okay: commit_creds(new); return old_fsgid; } SYSCALL_DEFINE1(setfsgid, gid_t, gid) { return __sys_setfsgid(gid); } #endif /* CONFIG_MULTIUSER */ /** * sys_getpid - return the thread group id of the current process * * Note, despite the name, this returns the tgid not the pid. The tgid and * the pid are identical unless CLONE_THREAD was specified on clone() in * which case the tgid is the same in all threads of the same group. * * This is SMP safe as current->tgid does not change. */ SYSCALL_DEFINE0(getpid) { return task_tgid_vnr(current); } /* Thread ID - the internal kernel "pid" */ SYSCALL_DEFINE0(gettid) { return task_pid_vnr(current); } /* * Accessing ->real_parent is not SMP-safe, it could * change from under us. However, we can use a stale * value of ->real_parent under rcu_read_lock(), see * release_task()->call_rcu(delayed_put_task_struct). */ SYSCALL_DEFINE0(getppid) { int pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_egid()); } static void do_sys_times(struct tms *tms) { u64 tgutime, tgstime, cutime, cstime; thread_group_cputime_adjusted(current, &tgutime, &tgstime); cutime = current->signal->cutime; cstime = current->signal->cstime; tms->tms_utime = nsec_to_clock_t(tgutime); tms->tms_stime = nsec_to_clock_t(tgstime); tms->tms_cutime = nsec_to_clock_t(cutime); tms->tms_cstime = nsec_to_clock_t(cstime); } SYSCALL_DEFINE1(times, struct tms __user *, tbuf) { if (tbuf) { struct tms tmp; do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } force_successful_syscall_return(); return (long) jiffies_64_to_clock_t(get_jiffies_64()); } #ifdef CONFIG_COMPAT static compat_clock_t clock_t_to_compat_clock_t(clock_t x) { return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); } COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) { if (tbuf) { struct tms tms; struct compat_tms tmp; do_sys_times(&tms); /* Convert our struct tms to the compat version. */ tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } force_successful_syscall_return(); return compat_jiffies_to_clock_t(jiffies); } #endif /* * This needs some heavy checking ... * I just haven't the stomach for it. I also don't fully * understand sessions/pgrp etc. Let somebody who does explain it. * * OK, I think I have the protection semantics right.... this is really * only important on a multi-user system anyway, to make sure one user * can't send a signal to a process owned by another. -TYT, 12/12/91 * * !PF_FORKNOEXEC check to conform completely to POSIX. */ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) { struct task_struct *p; struct task_struct *group_leader = current->group_leader; struct pid *pgrp; int err; if (!pid) pid = task_pid_vnr(group_leader); if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; rcu_read_lock(); /* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM */ write_lock_irq(&tasklist_lock); err = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; if (same_thread_group(p->real_parent, group_leader)) { err = -EPERM; if (task_session(p) != task_session(group_leader)) goto out; err = -EACCES; if (!(p->flags & PF_FORKNOEXEC)) goto out; } else { err = -ESRCH; if (p != group_leader) goto out; } err = -EPERM; if (p->signal->leader) goto out; pgrp = task_pid(p); if (pgid != pid) { struct task_struct *g; pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); if (!g || task_session(g) != task_session(group_leader)) goto out; } err = security_task_setpgid(p, pgid); if (err) goto out; if (task_pgrp(p) != pgrp) change_pid(p, PIDTYPE_PGID, pgrp); err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); rcu_read_unlock(); return err; } static int do_getpgid(pid_t pid) { struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); if (!pid) grp = task_pgrp(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; grp = task_pgrp(p); if (!grp) goto out; retval = security_task_getpgid(p); if (retval) goto out; } retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; } SYSCALL_DEFINE1(getpgid, pid_t, pid) { return do_getpgid(pid); } #ifdef __ARCH_WANT_SYS_GETPGRP SYSCALL_DEFINE0(getpgrp) { return do_getpgid(0); } #endif SYSCALL_DEFINE1(getsid, pid_t, pid) { struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); if (!pid) sid = task_session(current); else { retval = -ESRCH; p = find_task_by_vpid(pid); if (!p) goto out; sid = task_session(p); if (!sid) goto out; retval = security_task_getsid(p); if (retval) goto out; } retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; } static void set_special_pids(struct pid *pid) { struct task_struct *curr = current->group_leader; if (task_session(curr) != pid) change_pid(curr, PIDTYPE_SID, pid); if (task_pgrp(curr) != pid) change_pid(curr, PIDTYPE_PGID, pid); } int ksys_setsid(void) { struct task_struct *group_leader = current->group_leader; struct pid *sid = task_pid(group_leader); pid_t session = pid_vnr(sid); int err = -EPERM; write_lock_irq(&tasklist_lock); /* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; /* Fail if a process group id already exists that equals the * proposed session id. */ if (pid_task(sid, PIDTYPE_PGID)) goto out; group_leader->signal->leader = 1; set_special_pids(sid); proc_clear_tty(group_leader); err = session; out: write_unlock_irq(&tasklist_lock); if (err > 0) { proc_sid_connector(group_leader); sched_autogroup_create_attach(group_leader); } return err; } SYSCALL_DEFINE0(setsid) { return ksys_setsid(); } DECLARE_RWSEM(uts_sem); #ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ (personality(current->personality) == PER_LINUX32 && \ copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif /* * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 * And we map 4.x and later versions to 2.6.60+x, so 4.0/5.0/6.0/... would be * 2.6.60. */ static int override_release(char __user *release, size_t len) { int ret = 0; if (current->personality & UNAME26) { const char *rest = UTS_RELEASE; char buf[65] = { 0 }; int ndots = 0; unsigned v; size_t copy; while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; copy = clamp_t(size_t, len, 1, sizeof(buf)); copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); } return ret; } SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) { struct new_utsname tmp; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } #ifdef __ARCH_WANT_SYS_OLD_UNAME /* * Old cruft */ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) { struct old_utsname tmp; if (!name) return -EFAULT; down_read(&uts_sem); memcpy(&tmp, utsname(), sizeof(tmp)); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; } SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { struct oldold_utsname tmp; if (!name) return -EFAULT; memset(&tmp, 0, sizeof(tmp)); down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); memcpy(&tmp.release, &utsname()->release, __OLD_UTS_LEN); memcpy(&tmp.version, &utsname()->version, __OLD_UTS_LEN); memcpy(&tmp.machine, &utsname()->machine, __OLD_UTS_LEN); up_read(&uts_sem); if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; if (override_architecture(name)) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; return 0; } #endif SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; down_write(&uts_sem); u = utsname(); memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); errno = 0; uts_proc_notify(UTS_PROC_HOSTNAME); up_write(&uts_sem); } return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) { int i; struct new_utsname *u; char tmp[__NEW_UTS_LEN + 1]; if (len < 0) return -EINVAL; down_read(&uts_sem); u = utsname(); i = 1 + strlen(u->nodename); if (i > len) i = len; memcpy(tmp, u->nodename, i); up_read(&uts_sem); if (copy_to_user(name, tmp, i)) return -EFAULT; return 0; } #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) { int errno; char tmp[__NEW_UTS_LEN]; if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { struct new_utsname *u; down_write(&uts_sem); u = utsname(); memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); errno = 0; uts_proc_notify(UTS_PROC_DOMAINNAME); up_write(&uts_sem); } return errno; } SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit value; int ret; ret = do_prlimit(current, resource, NULL, &value); if (!ret) ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0; return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; struct compat_rlimit r32; if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit))) return -EFAULT; if (r32.rlim_cur == COMPAT_RLIM_INFINITY) r.rlim_cur = RLIM_INFINITY; else r.rlim_cur = r32.rlim_cur; if (r32.rlim_max == COMPAT_RLIM_INFINITY) r.rlim_max = RLIM_INFINITY; else r.rlim_max = r32.rlim_max; return do_prlimit(current, resource, &r, NULL); } COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; ret = do_prlimit(current, resource, NULL, &r); if (!ret) { struct compat_rlimit r32; if (r.rlim_cur > COMPAT_RLIM_INFINITY) r32.rlim_cur = COMPAT_RLIM_INFINITY; else r32.rlim_cur = r.rlim_cur; if (r.rlim_max > COMPAT_RLIM_INFINITY) r32.rlim_max = COMPAT_RLIM_INFINITY; else r32.rlim_max = r.rlim_max; if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit))) return -EFAULT; } return ret; } #endif #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit x; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); if (x.rlim_cur > 0x7FFFFFFF) x.rlim_cur = 0x7FFFFFFF; if (x.rlim_max > 0x7FFFFFFF) x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; if (resource >= RLIM_NLIMITS) return -EINVAL; resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); if (r.rlim_cur > 0x7FFFFFFF) r.rlim_cur = 0x7FFFFFFF; if (r.rlim_max > 0x7FFFFFFF) r.rlim_max = 0x7FFFFFFF; if (put_user(r.rlim_cur, &rlim->rlim_cur) || put_user(r.rlim_max, &rlim->rlim_max)) return -EFAULT; return 0; } #endif #endif static inline bool rlim64_is_infinity(__u64 rlim64) { #if BITS_PER_LONG < 64 return rlim64 >= ULONG_MAX; #else return rlim64 == RLIM64_INFINITY; #endif } static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64) { if (rlim->rlim_cur == RLIM_INFINITY) rlim64->rlim_cur = RLIM64_INFINITY; else rlim64->rlim_cur = rlim->rlim_cur; if (rlim->rlim_max == RLIM_INFINITY) rlim64->rlim_max = RLIM64_INFINITY; else rlim64->rlim_max = rlim->rlim_max; } static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) { if (rlim64_is_infinity(rlim64->rlim_cur)) rlim->rlim_cur = RLIM_INFINITY; else rlim->rlim_cur = (unsigned long)rlim64->rlim_cur; if (rlim64_is_infinity(rlim64->rlim_max)) rlim->rlim_max = RLIM_INFINITY; else rlim->rlim_max = (unsigned long)rlim64->rlim_max; } /* make sure you are allowed to change @tsk limits before calling this */ int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) { struct rlimit *rlim; int retval = 0; if (resource >= RLIM_NLIMITS) return -EINVAL; if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; if (resource == RLIMIT_NOFILE && new_rlim->rlim_max > sysctl_nr_open) return -EPERM; } /* protect tsk->signal and tsk->sighand from disappearing */ read_lock(&tasklist_lock); if (!tsk->sighand) { retval = -ESRCH; goto out; } rlim = tsk->signal->rlim + resource; task_lock(tsk->group_leader); if (new_rlim) { /* Keep the capable check against init_user_ns until cgroups can contain all limits */ if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; if (!retval) retval = security_task_setrlimit(tsk, resource, new_rlim); } if (!retval) { if (old_rlim) *old_rlim = *rlim; if (new_rlim) *rlim = *new_rlim; } task_unlock(tsk->group_leader); /* * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not * infite. In case of RLIM_INFINITY the posix CPU timer code * ignores the rlimit. */ if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY && IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(tsk, new_rlim->rlim_cur); out: read_unlock(&tasklist_lock); return retval; } /* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task, unsigned int flags) { const struct cred *cred = current_cred(), *tcred; bool id_match; if (current == task) return 0; tcred = __task_cred(task); id_match = (uid_eq(cred->uid, tcred->euid) && uid_eq(cred->uid, tcred->suid) && uid_eq(cred->uid, tcred->uid) && gid_eq(cred->gid, tcred->egid) && gid_eq(cred->gid, tcred->sgid) && gid_eq(cred->gid, tcred->gid)); if (!id_match && !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return -EPERM; return security_task_prlimit(cred, tcred, flags); } SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim) { struct rlimit64 old64, new64; struct rlimit old, new; struct task_struct *tsk; unsigned int checkflags = 0; int ret; if (old_rlim) checkflags |= LSM_PRLIMIT_READ; if (new_rlim) { if (copy_from_user(&new64, new_rlim, sizeof(new64))) return -EFAULT; rlim64_to_rlim(&new64, &new); checkflags |= LSM_PRLIMIT_WRITE; } rcu_read_lock(); tsk = pid ? find_task_by_vpid(pid) : current; if (!tsk) { rcu_read_unlock(); return -ESRCH; } ret = check_prlimit_permission(tsk, checkflags); if (ret) { rcu_read_unlock(); return ret; } get_task_struct(tsk); rcu_read_unlock(); ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL, old_rlim ? &old : NULL); if (!ret && old_rlim) { rlim_to_rlim64(&old, &old64); if (copy_to_user(old_rlim, &old64, sizeof(old64))) ret = -EFAULT; } put_task_struct(tsk); return ret; } SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; return do_prlimit(current, resource, &new_rlim, NULL); } /* * It would make sense to put struct rusage in the task_struct, * except that would make the task_struct be *really big*. After * task_struct gets moved into malloc'ed memory, it would * make sense to do this. It will make moving the rest of the information * a lot simpler! (Which we're not doing right now because we're not * measuring them yet). * * When sampling multiple threads for RUSAGE_SELF, under SMP we might have * races with threads incrementing their own counters. But since word * reads are atomic, we either get new values or old values and we don't * care which for the sums. We always take the siglock to protect reading * the c* fields from p->signal from races with exit.c updating those * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. * * Locking: * We need to take the siglock for CHILDEREN, SELF and BOTH * for the cases current multithreaded, non-current single threaded * non-current multithreaded. Thread traversal is now safe with * the siglock held. * Strictly speaking, we donot need to take the siglock if we are current and * single threaded, as no one else can take our signal_struct away, no one * else can reap the children to update signal->c* counters, and no one else * can race with the signal-> fields. If we do not take any lock, the * signal-> fields could be read out of order while another thread was just * exiting. So we should place a read memory barrier when we avoid the lock. * On the writer side, write memory barrier is implied in __exit_signal * as __exit_signal releases the siglock spinlock after updating the signal-> * fields. But we don't do this yet to keep things simple. * */ static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; r->ru_inblock += task_io_get_inblock(t); r->ru_oublock += task_io_get_oublock(t); } void getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; u64 tgutime, tgstime, utime, stime; unsigned long maxrss = 0; memset((char *)r, 0, sizeof (*r)); utime = stime = 0; if (who == RUSAGE_THREAD) { task_cputime_adjusted(current, &utime, &stime); accumulate_thread_rusage(p, r); maxrss = p->signal->maxrss; goto out; } if (!lock_task_sighand(p, &flags)) return; switch (who) { case RUSAGE_BOTH: case RUSAGE_CHILDREN: utime = p->signal->cutime; stime = p->signal->cstime; r->ru_nvcsw = p->signal->cnvcsw; r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; r->ru_inblock = p->signal->cinblock; r->ru_oublock = p->signal->coublock; maxrss = p->signal->cmaxrss; if (who == RUSAGE_CHILDREN) break; fallthrough; case RUSAGE_SELF: thread_group_cputime_adjusted(p, &tgutime, &tgstime); utime += tgutime; stime += tgstime; r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; r->ru_majflt += p->signal->maj_flt; r->ru_inblock += p->signal->inblock; r->ru_oublock += p->signal->oublock; if (maxrss < p->signal->maxrss) maxrss = p->signal->maxrss; t = p; do { accumulate_thread_rusage(t, r); } while_each_thread(p, t); break; default: BUG(); } unlock_task_sighand(p, &flags); out: r->ru_utime = ns_to_kernel_old_timeval(utime); r->ru_stime = ns_to_kernel_old_timeval(stime); if (who != RUSAGE_CHILDREN) { struct mm_struct *mm = get_task_mm(p); if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } } r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ } SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif SYSCALL_DEFINE1(umask, int, mask) { mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { struct fd exe; struct file *old_exe, *exe_file; struct inode *inode; int err; exe = fdget(fd); if (!exe.file) return -EBADF; inode = file_inode(exe.file); /* * Because the original mm->exe_file points to executable file, make * sure that this one is executable as well, to avoid breaking an * overall picture. */ err = -EACCES; if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path)) goto exit; err = inode_permission(inode, MAY_EXEC); if (err) goto exit; /* * Forbid mm->exe_file change if old file still mapped. */ exe_file = get_mm_exe_file(mm); err = -EBUSY; if (exe_file) { struct vm_area_struct *vma; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &exe_file->f_path)) goto exit_err; } mmap_read_unlock(mm); fput(exe_file); } err = 0; /* set the new file, lockless */ get_file(exe.file); old_exe = xchg(&mm->exe_file, exe.file); if (old_exe) fput(old_exe); exit: fdput(exe); return err; exit_err: mmap_read_unlock(mm); fput(exe_file); goto exit; } /* * Check arithmetic relations of passed addresses. * * WARNING: we don't require any capability here so be very careful * in what is allowed for modification from userspace. */ static int validate_prctl_map_addr(struct prctl_mm_map *prctl_map) { unsigned long mmap_max_addr = TASK_SIZE; int error = -EINVAL, i; static const unsigned char offsets[] = { offsetof(struct prctl_mm_map, start_code), offsetof(struct prctl_mm_map, end_code), offsetof(struct prctl_mm_map, start_data), offsetof(struct prctl_mm_map, end_data), offsetof(struct prctl_mm_map, start_brk), offsetof(struct prctl_mm_map, brk), offsetof(struct prctl_mm_map, start_stack), offsetof(struct prctl_mm_map, arg_start), offsetof(struct prctl_mm_map, arg_end), offsetof(struct prctl_mm_map, env_start), offsetof(struct prctl_mm_map, env_end), }; /* * Make sure the members are not somewhere outside * of allowed address space. */ for (i = 0; i < ARRAY_SIZE(offsets); i++) { u64 val = *(u64 *)((char *)prctl_map + offsets[i]); if ((unsigned long)val >= mmap_max_addr || (unsigned long)val < mmap_min_addr) goto out; } /* * Make sure the pairs are ordered. */ #define __prctl_check_order(__m1, __op, __m2) \ ((unsigned long)prctl_map->__m1 __op \ (unsigned long)prctl_map->__m2) ? 0 : -EINVAL error = __prctl_check_order(start_code, <, end_code); error |= __prctl_check_order(start_data,<=, end_data); error |= __prctl_check_order(start_brk, <=, brk); error |= __prctl_check_order(arg_start, <=, arg_end); error |= __prctl_check_order(env_start, <=, env_end); if (error) goto out; #undef __prctl_check_order error = -EINVAL; /* * Neither we should allow to override limits if they set. */ if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, prctl_map->start_brk, prctl_map->end_data, prctl_map->start_data)) goto out; error = 0; out: return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) { struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; unsigned long user_auxv[AT_VECTOR_SIZE]; struct mm_struct *mm = current->mm; int error; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); if (opt == PR_SET_MM_MAP_SIZE) return put_user((unsigned int)sizeof(prctl_map), (unsigned int __user *)addr); if (data_size != sizeof(prctl_map)) return -EINVAL; if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) return -EFAULT; error = validate_prctl_map_addr(&prctl_map); if (error) return error; if (prctl_map.auxv_size) { /* * Someone is trying to cheat the auxv vector. */ if (!prctl_map.auxv || prctl_map.auxv_size > sizeof(mm->saved_auxv)) return -EINVAL; memset(user_auxv, 0, sizeof(user_auxv)); if (copy_from_user(user_auxv, (const void __user *)prctl_map.auxv, prctl_map.auxv_size)) return -EFAULT; /* Last entry must be AT_NULL as specification requires */ user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } if (prctl_map.exe_fd != (u32)-1) { /* * Check if the current user is checkpoint/restore capable. * At the time of this writing, it checks for CAP_SYS_ADMIN * or CAP_CHECKPOINT_RESTORE. * Note that a user with access to ptrace can masquerade an * arbitrary program as any executable, even setuid ones. * This may have implications in the tomoyo subsystem. */ if (!checkpoint_restore_ns_capable(current_user_ns())) return -EPERM; error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); if (error) return error; } /* * arg_lock protects concurent updates but we still need mmap_lock for * read to exclude races with sys_brk. */ mmap_read_lock(mm); /* * We don't validate if these members are pointing to * real present VMAs because application may have correspond * VMAs already unmapped and kernel uses these members for statistics * output in procfs mostly, except * * - @start_brk/@brk which are used in do_brk_flags but kernel lookups * for VMAs when updating these memvers so anything wrong written * here cause kernel to swear at userspace program but won't lead * to any problem in kernel itself */ spin_lock(&mm->arg_lock); mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; spin_unlock(&mm->arg_lock); /* * Note this update of @saved_auxv is lockless thus * if someone reads this member in procfs while we're * updating -- it may get partly updated results. It's * known and acceptable trade off: we leave it as is to * not introduce additional locks here making the kernel * more complex. */ if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); mmap_read_unlock(mm); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, unsigned long len) { /* * This doesn't move the auxiliary vector itself since it's pinned to * mm_struct, but it permits filling the vector with new values. It's * up to the caller to provide sane values here, otherwise userspace * tools which use this vector might be unhappy. */ unsigned long user_auxv[AT_VECTOR_SIZE]; if (len > sizeof(user_auxv)) return -EINVAL; if (copy_from_user(user_auxv, (const void __user *)addr, len)) return -EFAULT; /* Make sure the last entry is always AT_NULL */ user_auxv[AT_VECTOR_SIZE - 2] = 0; user_auxv[AT_VECTOR_SIZE - 1] = 0; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); task_lock(current); memcpy(mm->saved_auxv, user_auxv, len); task_unlock(current); return 0; } static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { struct mm_struct *mm = current->mm; struct prctl_mm_map prctl_map = { .auxv = NULL, .auxv_size = 0, .exe_fd = -1, }; struct vm_area_struct *vma; int error; if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && opt != PR_SET_MM_MAP && opt != PR_SET_MM_MAP_SIZE))) return -EINVAL; #ifdef CONFIG_CHECKPOINT_RESTORE if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) return prctl_set_mm_map(opt, (const void __user *)addr, arg4); #endif if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); if (opt == PR_SET_MM_AUXV) return prctl_set_auxv(mm, addr, arg4); if (addr >= TASK_SIZE || addr < mmap_min_addr) return -EINVAL; error = -EINVAL; /* * arg_lock protects concurent updates of arg boundaries, we need * mmap_lock for a) concurrent sys_brk, b) finding VMA for addr * validation. */ mmap_read_lock(mm); vma = find_vma(mm, addr); spin_lock(&mm->arg_lock); prctl_map.start_code = mm->start_code; prctl_map.end_code = mm->end_code; prctl_map.start_data = mm->start_data; prctl_map.end_data = mm->end_data; prctl_map.start_brk = mm->start_brk; prctl_map.brk = mm->brk; prctl_map.start_stack = mm->start_stack; prctl_map.arg_start = mm->arg_start; prctl_map.arg_end = mm->arg_end; prctl_map.env_start = mm->env_start; prctl_map.env_end = mm->env_end; switch (opt) { case PR_SET_MM_START_CODE: prctl_map.start_code = addr; break; case PR_SET_MM_END_CODE: prctl_map.end_code = addr; break; case PR_SET_MM_START_DATA: prctl_map.start_data = addr; break; case PR_SET_MM_END_DATA: prctl_map.end_data = addr; break; case PR_SET_MM_START_STACK: prctl_map.start_stack = addr; break; case PR_SET_MM_START_BRK: prctl_map.start_brk = addr; break; case PR_SET_MM_BRK: prctl_map.brk = addr; break; case PR_SET_MM_ARG_START: prctl_map.arg_start = addr; break; case PR_SET_MM_ARG_END: prctl_map.arg_end = addr; break; case PR_SET_MM_ENV_START: prctl_map.env_start = addr; break; case PR_SET_MM_ENV_END: prctl_map.env_end = addr; break; default: goto out; } error = validate_prctl_map_addr(&prctl_map); if (error) goto out; switch (opt) { /* * If command line arguments and environment * are placed somewhere else on stack, we can * set them up here, ARG_START/END to setup * command line argumets and ENV_START/END * for environment. */ case PR_SET_MM_START_STACK: case PR_SET_MM_ARG_START: case PR_SET_MM_ARG_END: case PR_SET_MM_ENV_START: case PR_SET_MM_ENV_END: if (!vma) { error = -EFAULT; goto out; } } mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; error = 0; out: spin_unlock(&mm->arg_lock); mmap_read_unlock(mm); return error; } #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return put_user(me->clear_child_tid, tid_addr); } #else static int prctl_get_tid_address(struct task_struct *me, int __user * __user *tid_addr) { return -EINVAL; } #endif static int propagate_has_child_subreaper(struct task_struct *p, void *data) { /* * If task has has_child_subreaper - all its decendants * already have these flag too and new decendants will * inherit it on fork, skip them. * * If we've found child_reaper - skip descendants in * it's subtree as they will never get out pidns. */ if (p->signal->has_child_subreaper || is_child_reaper(task_pid(p))) return 0; p->signal->has_child_subreaper = 1; return 1; } int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) { return -EINVAL; } int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, unsigned long ctrl) { return -EINVAL; } #ifdef CONFIG_MMU static int prctl_update_vma_anon_name(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, const char __user *name_addr) { struct mm_struct *mm = vma->vm_mm; int error = 0; pgoff_t pgoff; if (name_addr == vma_get_anon_name(vma)) { *prev = vma; goto out; } pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, name_addr); if (*prev) { vma = *prev; goto success; } *prev = vma; if (start != vma->vm_start) { error = split_vma(mm, vma, start, 1); if (error) goto out; } if (end != vma->vm_end) { error = split_vma(mm, vma, end, 0); if (error) goto out; } success: if (!vma->vm_file) vma->anon_name = name_addr; out: if (error == -ENOMEM) error = -EAGAIN; return error; } static int prctl_set_vma_anon_name(unsigned long start, unsigned long end, unsigned long arg) { unsigned long tmp; struct vm_area_struct *vma, *prev; int unmapped_error = 0; int error = -EINVAL; /* * If the interval [start,end) covers some unmapped address * ranges, just ignore them, but return -ENOMEM at the end. * - this matches the handling in madvise. */ vma = find_vma_prev(current->mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; for (;;) { /* Still start < end. */ error = -ENOMEM; if (!vma) return error; /* Here start < (end|vma->vm_end). */ if (start < vma->vm_start) { unmapped_error = -ENOMEM; start = vma->vm_start; if (start >= end) return error; } /* Here vma->vm_start <= start < (end|vma->vm_end) */ tmp = vma->vm_end; if (end < tmp) tmp = end; /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ error = prctl_update_vma_anon_name(vma, &prev, start, tmp, (const char __user *)arg); if (error) return error; start = tmp; if (prev && start < prev->vm_end) start = prev->vm_end; error = unmapped_error; if (start >= end) return error; if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_lock */ vma = find_vma(current->mm, start); } } static int prctl_set_vma(unsigned long opt, unsigned long start, unsigned long len_in, unsigned long arg) { struct mm_struct *mm = current->mm; int error; unsigned long len; unsigned long end; if (start & ~PAGE_MASK) return -EINVAL; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); switch (opt) { case PR_SET_VMA_ANON_NAME: error = prctl_set_vma_anon_name(start, end, arg); break; default: error = -EINVAL; } mmap_write_unlock(mm); return error; } #else /* CONFIG_MMU */ static int prctl_set_vma(unsigned long opt, unsigned long start, unsigned long len_in, unsigned long arg) { return -EINVAL; } #endif #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) return error; error = 0; switch (option) { case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; break; } me->pdeath_signal = arg2; break; case PR_GET_PDEATHSIG: error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { error = -EINVAL; break; } set_dumpable(me->mm, arg2); break; case PR_SET_UNALIGN: error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; break; case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; break; case PR_SET_NAME: comm[sizeof(me->comm) - 1] = 0; if (strncpy_from_user(comm, (char __user *)arg2, sizeof(me->comm) - 1) < 0) return -EFAULT; set_task_comm(me, comm); proc_comm_connector(me); break; case PR_GET_NAME: get_task_comm(comm, me); if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) return -EFAULT; break; case PR_GET_ENDIAN: error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: error = prctl_get_seccomp(); break; case PR_SET_SECCOMP: error = prctl_set_seccomp(arg2, (char __user *)arg3); break; case PR_GET_TSC: error = GET_TSC_CTL(arg2); break; case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; case PR_TASK_PERF_EVENTS_DISABLE: error = perf_event_task_disable(); break; case PR_TASK_PERF_EVENTS_ENABLE: error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: if (current->timer_slack_ns > ULONG_MAX) error = ULONG_MAX; else error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (arg2 <= 0) current->timer_slack_ns = current->default_timer_slack_ns; else current->timer_slack_ns = arg2; break; case PR_MCE_KILL: if (arg4 | arg5) return -EINVAL; switch (arg2) { case PR_MCE_KILL_CLEAR: if (arg3 != 0) return -EINVAL; current->flags &= ~PF_MCE_PROCESS; break; case PR_MCE_KILL_SET: current->flags |= PF_MCE_PROCESS; if (arg3 == PR_MCE_KILL_EARLY) current->flags |= PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_LATE) current->flags &= ~PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_DEFAULT) current->flags &= ~(PF_MCE_EARLY|PF_MCE_PROCESS); else return -EINVAL; break; default: return -EINVAL; } break; case PR_MCE_KILL_GET: if (arg2 | arg3 | arg4 | arg5) return -EINVAL; if (current->flags & PF_MCE_PROCESS) error = (current->flags & PF_MCE_EARLY) ? PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; else error = PR_MCE_KILL_DEFAULT; break; case PR_SET_MM: error = prctl_set_mm(arg2, arg3, arg4, arg5); break; case PR_GET_TID_ADDRESS: error = prctl_get_tid_address(me, (int __user * __user *)arg2); break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; if (!arg2) break; walk_process_tree(me, propagate_has_child_subreaper, NULL); break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, (int __user *)arg2); break; case PR_SET_NO_NEW_PRIVS: if (arg2 != 1 || arg3 || arg4 || arg5) return -EINVAL; task_set_no_new_privs(current); break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return task_no_new_privs(current) ? 1 : 0; case PR_GET_THP_DISABLE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags); break; case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; if (mmap_write_lock_killable(me->mm)) return -EINTR; if (arg2) set_bit(MMF_DISABLE_THP, &me->mm->flags); else clear_bit(MMF_DISABLE_THP, &me->mm->flags); mmap_write_unlock(me->mm); break; case PR_MPX_ENABLE_MANAGEMENT: case PR_MPX_DISABLE_MANAGEMENT: /* No longer implemented: */ return -EINVAL; case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; case PR_SVE_SET_VL: error = SVE_SET_VL(arg2); break; case PR_SVE_GET_VL: error = SVE_GET_VL(); break; case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_get(me, arg2); break; case PR_SET_SPECULATION_CTRL: if (arg4 || arg5) return -EINVAL; error = arch_prctl_spec_ctrl_set(me, arg2, arg3); break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) return -EINVAL; error = PAC_RESET_KEYS(me, arg2); break; case PR_PAC_SET_ENABLED_KEYS: if (arg4 || arg5) return -EINVAL; error = PAC_SET_ENABLED_KEYS(me, arg2, arg3); break; case PR_PAC_GET_ENABLED_KEYS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = PAC_GET_ENABLED_KEYS(me); break; case PR_SET_TAGGED_ADDR_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; error = SET_TAGGED_ADDR_CTRL(arg2); break; case PR_GET_TAGGED_ADDR_CTRL: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = GET_TAGGED_ADDR_CTRL(); break; case PR_SET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg3 || arg4 || arg5) return -EINVAL; if (arg2 == 1) current->flags |= PR_IO_FLUSHER; else if (!arg2) current->flags &= ~PR_IO_FLUSHER; else return -EINVAL; break; case PR_GET_IO_FLUSHER: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER; break; default: error = -EINVAL; break; } trace_android_vh_syscall_prctl_finished(option, me); return error; } SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, struct getcpu_cache __user *, unused) { int err = 0; int cpu = raw_smp_processor_id(); if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); return err ? -EFAULT : 0; } /** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill */ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; struct timespec64 tp; memset(info, 0, sizeof(struct sysinfo)); ktime_get_boottime_ts64(&tp); timens_add_boottime(&tp); info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); info->procs = nr_threads; si_meminfo(info); si_swapinfo(info); /* * If the sum of all the available memory (i.e. ram + swap) * is less than can be stored in a 32 bit unsigned long then * we can be binary compatible with 2.2.x kernels. If not, * well, in that case 2.2.x was broken anyways... * * -Erik Andersen <andersee@debian.org> */ mem_total = info->totalram + info->totalswap; if (mem_total < info->totalram || mem_total < info->totalswap) goto out; bitcount = 0; mem_unit = info->mem_unit; while (mem_unit > 1) { bitcount++; mem_unit >>= 1; sav_total = mem_total; mem_total <<= 1; if (mem_total < sav_total) goto out; } /* * If mem_total did not overflow, multiply all memory values by * info->mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ info->mem_unit = 1; info->totalram <<= bitcount; info->freeram <<= bitcount; info->sharedram <<= bitcount; info->bufferram <<= bitcount; info->totalswap <<= bitcount; info->freeswap <<= bitcount; info->totalhigh <<= bitcount; info->freehigh <<= bitcount; out: return 0; } SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) { struct sysinfo val; do_sysinfo(&val); if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_sysinfo { s32 uptime; u32 loads[3]; u32 totalram; u32 freeram; u32 sharedram; u32 bufferram; u32 totalswap; u32 freeswap; u16 procs; u16 pad; u32 totalhigh; u32 freehigh; u32 mem_unit; char _f[20-2*sizeof(u32)-sizeof(int)]; }; COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) { struct sysinfo s; struct compat_sysinfo s_32; do_sysinfo(&s); /* Check to see if any memory value is too large for 32-bit and scale * down if needed */ if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { int bitcount = 0; while (s.mem_unit < PAGE_SIZE) { s.mem_unit <<= 1; bitcount++; } s.totalram >>= bitcount; s.freeram >>= bitcount; s.sharedram >>= bitcount; s.bufferram >>= bitcount; s.totalswap >>= bitcount; s.freeswap >>= bitcount; s.totalhigh >>= bitcount; s.freehigh >>= bitcount; } memset(&s_32, 0, sizeof(s_32)); s_32.uptime = s.uptime; s_32.loads[0] = s.loads[0]; s_32.loads[1] = s.loads[1]; s_32.loads[2] = s.loads[2]; s_32.totalram = s.totalram; s_32.freeram = s.freeram; s_32.sharedram = s.sharedram; s_32.bufferram = s.bufferram; s_32.totalswap = s.totalswap; s_32.freeswap = s.freeswap; s_32.procs = s.procs; s_32.totalhigh = s.totalhigh; s_32.freehigh = s.freehigh; s_32.mem_unit = s.mem_unit; if (copy_to_user(info, &s_32, sizeof(s_32))) return -EFAULT; return 0; } #endif /* CONFIG_COMPAT */ |
| 109 121 120 673 672 331 33 673 672 673 673 673 110 672 673 672 673 673 672 665 11 595 325 673 325 673 605 127 664 668 6 618 2 600 672 672 519 1036 482 1037 1037 1038 567 614 1037 482 932 226 226 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001 */ /* * This handles all read/write requests to block devices */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kernel_stat.h> #include <linux/string.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/task_io_accounting_ops.h> #include <linux/fault-inject.h> #include <linux/list_sort.h> #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> #include <linux/blk-cgroup.h> #include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> #include <linux/psi.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-pm.h" #include "blk-rq-qos.h" struct dentry *blk_debugfs_root; EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_queue); EXPORT_TRACEPOINT_SYMBOL_GPL(block_getrq); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_issue); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_merge); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_requeue); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_complete); DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd */ static struct workqueue_struct *kblockd_workqueue; /** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); /** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); /** * blk_queue_flag_test_and_set - atomically test and set a queue flag * @flag: flag to be set * @q: request queue * * Returns the previous value of @flag - 0 if the flag was not set and 1 if * the flag was already set. */ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) { return test_and_set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = ktime_get_ns(); rq->part = NULL; blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), REQ_OP_NAME(SCSI_OUT), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT), }; #undef REQ_OP_NAME /** * blk_op_str - Return string XXX in the REQ_OP_XXX. * @op: REQ_OP_XXX. * * Description: Centralize block layer function to convert REQ_OP_XXX into * string format. Useful in the debugging and tracing bio or request. For * invalid REQ_OP_XXX it returns string "UNKNOWN". */ inline const char *blk_op_str(unsigned int op) { const char *op_str = "UNKNOWN"; if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op]; return op_str; } EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; const char *name; } blk_errors[] = { [BLK_STS_OK] = { 0, "" }, [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, [BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" }, [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, /* zone device specific errors */ [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; blk_status_t errno_to_blk_status(int errno) { int i; for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; } return BLK_STS_IOERR; } EXPORT_SYMBOL_GPL(errno_to_blk_status); int blk_status_to_errno(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno; } EXPORT_SYMBOL_GPL(blk_status_to_errno); static void print_req_error(struct request *req, blk_status_t status, const char *caller) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return; printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", caller, blk_errors[idx].name, req->rq_disk ? req->rq_disk->disk_name : "?", blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)), req->cmd_flags & ~REQ_OP_MASK, req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, blk_status_t error) { if (error) bio->bi_status = error; if (unlikely(rq->rq_flags & RQF_QUIET)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, nbytes); if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. */ if (bio->bi_iter.bi_size) bio->bi_status = BLK_STS_IOERR; else bio->bi_iter.bi_sector = rq->__sector; } /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->rq_disk ? rq->rq_disk->disk_name : "?", (unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); /** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */ void blk_set_pm_only(struct request_queue *q) { atomic_inc(&q->pm_only); } EXPORT_SYMBOL_GPL(blk_set_pm_only); void blk_clear_pm_only(struct request_queue *q) { int pm_only; pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_clear_pm_only); /** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue kobject. When this reaches 0 * we'll have blk_release_queue() called. * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } EXPORT_SYMBOL(blk_put_queue); void blk_set_queue_dying(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_DYING, q); /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ blk_freeze_queue_start(q); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_set_queue_dying); /** * blk_cleanup_queue - shutdown a request queue * @q: request queue to shutdown * * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and * put it. All future requests will be failed immediately with -ENODEV. * * Context: can sleep */ void blk_cleanup_queue(struct request_queue *q) { /* cannot be called from atomic context */ might_sleep(); WARN_ON_ONCE(blk_queue_registered(q)); /* mark @q DYING, no new request or merges will be allowed afterwards */ blk_set_queue_dying(q); blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); /* * Drain all requests queued before DYING marking. Set DEAD flag to * prevent that blk_mq_run_hw_queues() accesses the hardware queues * after draining finished. */ blk_freeze_queue(q); rq_qos_exit(q); blk_queue_flag_set(QUEUE_FLAG_DEAD, q); /* for synchronous bio-based driver finish in-flight integrity i/o */ blk_flush_integrity(); /* @q won't process any more request, flush async actions */ del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); blk_sync_queue(q); if (queue_is_mq(q)) blk_mq_exit_queue(q); /* * In theory, request pool of sched_tags belongs to request queue. * However, the current implementation requires tag_set for freeing * requests, so free the pool now. * * Queue has become frozen, there can't be any in-queue requests, so * it is safe to free requests now. */ mutex_lock(&q->sysfs_lock); if (q->elevator) blk_mq_sched_free_requests(q); mutex_unlock(&q->sysfs_lock); percpu_ref_exit(&q->q_usage_counter); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; while (true) { bool success = false; rcu_read_lock(); if (percpu_ref_tryget_live(&q->q_usage_counter)) { /* * The code that increments the pm_only counter is * responsible for ensuring that that counter is * globally visible before the queue is unfrozen. */ if (pm || !blk_queue_pm_only(q)) { success = true; } else { percpu_ref_put(&q->q_usage_counter); } } rcu_read_unlock(); if (success) return 0; if (flags & BLK_MQ_REQ_NOWAIT) return -EBUSY; /* * read pair of barrier in blk_freeze_queue_start(), * we need to order reading __PERCPU_REF_DEAD flag of * .q_usage_counter and reading .mq_freeze_depth or * queue dying flag, otherwise the following wait may * never return if the two reads are reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && (pm || (blk_pm_request_resume(q), !blk_queue_pm_only(q)))) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } } static inline int bio_queue_enter(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; bool nowait = bio->bi_opf & REQ_NOWAIT; int ret; ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0); if (unlikely(ret)) { if (nowait && !blk_queue_dying(q)) bio_wouldblock_error(bio); else bio_io_error(bio); } return ret; } void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); } static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); wake_up_all(&q->mq_freeze_wq); } static void blk_rq_timed_out_timer(struct timer_list *t) { struct request_queue *q = from_timer(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } static void blk_timeout_work(struct work_struct *work) { } struct request_queue *blk_alloc_queue(int node_id) { struct request_queue *q; int ret; q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return NULL; q->last_merge = NULL; q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL); if (q->id < 0) goto fail_q; ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (ret) goto fail_id; q->backing_dev_info = bdi_alloc(node_id); if (!q->backing_dev_info) goto fail_split; q->stats = blk_alloc_queue_stats(); if (!q->stats) goto fail_stats; q->node = node_id; atomic_set(&q->nr_active_requests_shared_sbitmap, 0); timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); #endif kobject_init(&q->kobj, &blk_queue_ktype); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) goto fail_bdi; if (blkcg_init_queue(q)) goto fail_ref; blk_queue_dma_alignment(q, 511); blk_set_default_limits(&q->limits); q->nr_requests = BLKDEV_MAX_RQ; return q; fail_ref: percpu_ref_exit(&q->q_usage_counter); fail_bdi: blk_free_queue_stats(q->stats); fail_stats: bdi_put(q->backing_dev_info); fail_split: bioset_exit(&q->bio_split); fail_id: ida_simple_remove(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } EXPORT_SYMBOL(blk_alloc_queue); /** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */ bool blk_get_queue(struct request_queue *q) { if (likely(!blk_queue_dying(q))) { __blk_get_queue(q); return true; } return false; } EXPORT_SYMBOL(blk_get_queue); /** * blk_get_request - allocate a request * @q: request queue to allocate a request for * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. */ struct request *blk_get_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct request *req; WARN_ON_ONCE(op & REQ_NOWAIT); WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); req = blk_mq_alloc_request(q, op, flags); if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) q->mq_ops->initialize_rq_fn(req); return req; } EXPORT_SYMBOL(blk_get_request); void blk_put_request(struct request *req) { blk_mq_free_request(req); } EXPORT_SYMBOL(blk_put_request); static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; pr_info_ratelimited("attempt to access beyond end of device\n" "%s: rw=%d, want=%llu, limit=%llu\n", bio_devname(bio, b), bio->bi_opf, bio_end_sector(bio), maxsector); } #ifdef CONFIG_FAIL_MAKE_REQUEST static DECLARE_FAULT_ATTR(fail_make_request); static int __init setup_fail_make_request(char *str) { return setup_fault_attr(&fail_make_request, str); } __setup("fail_make_request=", setup_fail_make_request); static bool should_fail_request(struct hd_struct *part, unsigned int bytes) { return part->make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool should_fail_request(struct hd_struct *part, unsigned int bytes) { return false; } #endif /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) { const int op = bio_op(bio); if (part->policy && op_is_write(op)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; WARN_ONCE(1, "Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false; } return false; } static noinline int should_fail_bio(struct bio *bio) { if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) return -EIO; return 0; } ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); /* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) { unsigned int nr_sectors = bio_sectors(bio); if (nr_sectors && maxsector && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { handle_bad_sector(bio, maxsector); return -EIO; } return 0; } /* * Remap block n of partition p to block n+start(p) of the disk. */ static inline int blk_partition_remap(struct bio *bio) { struct hd_struct *p; int ret = -EIO; rcu_read_lock(); p = __disk_get_part(bio->bi_disk, bio->bi_partno); if (unlikely(!p)) goto out; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) goto out; if (unlikely(bio_check_ro(bio, p))) goto out; if (bio_sectors(bio)) { if (bio_check_eod(bio, part_nr_sects_read(p))) goto out; bio->bi_iter.bi_sector += p->start_sect; trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), bio->bi_iter.bi_sector - p->start_sect); } bio->bi_partno = 0; ret = 0; out: rcu_read_unlock(); return ret; } /* * Check write append to a zoned block device. */ static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { sector_t pos = bio->bi_iter.bi_sector; int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ if (!blk_queue_is_zoned(q)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ if (pos & (blk_queue_zone_sectors(q) - 1) || !blk_queue_zone_is_seq(q, pos)) return BLK_STS_IOERR; /* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR; /* Make sure the BIO is small enough and will not get split */ if (nr_sectors > q->limits.max_zone_append_sectors) return BLK_STS_IOERR; bio->bi_opf |= REQ_NOMERGE; return BLK_STS_OK; } static noinline_for_stack bool submit_bio_checks(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; blk_status_t status = BLK_STS_IOERR; struct blk_plug *plug; might_sleep(); plug = blk_mq_plug(q, bio); if (plug && plug->nowait) bio->bi_opf |= REQ_NOWAIT; /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) goto not_supported; if (should_fail_bio(bio)) goto end_io; if (bio->bi_partno) { if (unlikely(blk_partition_remap(bio))) goto end_io; } else { if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; } /* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf) && !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) bio->bi_opf &= ~REQ_HIPRI; switch (bio_op(bio)) { case REQ_OP_DISCARD: if (!blk_queue_discard(q)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!blk_queue_secure_erase(q)) goto not_supported; break; case REQ_OP_WRITE_SAME: if (!q->limits.max_write_same_sectors) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; case REQ_OP_ZONE_RESET_ALL: if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q)) goto not_supported; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; default: break; } /* * Various block parts want %current->io_context, so allocate it up * front rather than dealing with lots of pain to allocate it only * where needed. This may fail and the block layer knows how to live * with it. */ if (unlikely(!current->io_context)) create_task_io_context(current, GFP_ATOMIC, q->node); if (blk_throtl_bio(bio)) return false; blk_cgroup_bio_start(bio); blkcg_bio_issue_init(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(q, bio); /* Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); } return true; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); return false; } static blk_qc_t __submit_bio(struct bio *bio) { struct gendisk *disk = bio->bi_disk; blk_qc_t ret = BLK_QC_T_NONE; if (blk_crypto_bio_prep(&bio)) { if (!disk->fops->submit_bio) return blk_mq_submit_bio(bio); ret = disk->fops->submit_bio(bio); } blk_queue_exit(disk->queue); return ret; } /* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio of the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio_bio, but that haven't been processed yet. */ static blk_qc_t __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; blk_qc_t ret = BLK_QC_T_NONE; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; do { struct request_queue *q = bio->bi_disk->queue; struct bio_list lower, same; if (unlikely(bio_queue_enter(bio) != 0)) continue; /* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); ret = __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bio->bi_disk->queue) bio_list_add(&same, bio); else bio_list_add(&lower, bio); /* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; return ret; } static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; blk_qc_t ret = BLK_QC_T_NONE; current->bio_list = bio_list; do { struct gendisk *disk = bio->bi_disk; if (unlikely(bio_queue_enter(bio) != 0)) continue; if (!blk_crypto_bio_prep(&bio)) { blk_queue_exit(disk->queue); ret = BLK_QC_T_NONE; continue; } ret = blk_mq_submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; return ret; } /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */ blk_qc_t submit_bio_noacct(struct bio *bio) { if (!submit_bio_checks(bio)) return BLK_QC_T_NONE; /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submited by a ->submit_bio method while * it is active, and then process them after it returned. */ if (current->bio_list) { bio_list_add(¤t->bio_list[0], bio); return BLK_QC_T_NONE; } if (!bio->bi_disk->fops->submit_bio) return __submit_bio_noacct_mq(bio); return __submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio_noacct); /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be send to the device described by the bi_disk and bi_partno fields. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has * been called. */ blk_qc_t submit_bio(struct bio *bio) { if (blkcg_punt_bio_submit(bio)) return BLK_QC_T_NONE; /* * If it's a regular read/write or a barrier with data attached, * go through the normal accounting stuff before submission. */ if (bio_has_data(bio)) { unsigned int count; if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) count = queue_logical_block_size(bio->bi_disk->queue) >> 9; else count = bio_sectors(bio); if (op_is_write(bio_op(bio))) { count_vm_events(PGPGOUT, count); } else { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } if (unlikely(block_dump)) { char b[BDEVNAME_SIZE]; printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", current->comm, task_pid_nr(current), op_is_write(bio_op(bio)) ? "WRITE" : "READ", (unsigned long long)bio->bi_iter.bi_sector, bio_devname(bio, b), count); } } /* * If we're reading data that is part of the userspace workingset, count * submission time as memory stall. When the device is congested, or * the submitting cgroup IO-throttled, submission can be a significant * part of overall IO time. */ if (unlikely(bio_op(bio) == REQ_OP_READ && bio_flagged(bio, BIO_WORKINGSET))) { unsigned long pflags; blk_qc_t ret; psi_memstall_enter(&pflags); ret = submit_bio_noacct(bio); psi_memstall_leave(&pflags); return ret; } return submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** * blk_cloned_rq_check_limits - Helper function to check a cloned request * for the new queue limits * @q: the queue * @rq: the request being checked * * Description: * @rq may have been made based on weaker limitations of upper-level queues * in request stacking drivers, and it may violate the limitation of @q. * Since the block layer and the underlying device driver trust @rq * after it is inserted to @q, it should be checked against @q before * the insertion using this generic function. * * Request stacking drivers like request-based dm may change the queue * limits when retrying requests on other queues. Those requests need * to be checked against the new queue limits again during dispatch. */ static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q, struct request *rq) { unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * queue's settings related to segment counting like q->bounce_pfn * may differ from that of other stacking queues. * Recalculate it to check the request correctly on this queue's * limitation. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > queue_max_segments(q)) { printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n", __func__, rq->nr_phys_segments, queue_max_segments(q)); return BLK_STS_IOERR; } return BLK_STS_OK; } /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @q: the queue to submit the request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { blk_status_t ret; ret = blk_cloned_rq_check_limits(q, rq); if (ret != BLK_STS_OK) return ret; if (rq->rq_disk && should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) return BLK_STS_IOERR; if (blk_queue_io_stat(q)) blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ return blk_mq_request_issue_directly(rq, true); } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_err_bytes - determine number of bytes till the next failure boundary * @rq: request to examine * * Description: * A request could be merge of IOs which require different failure * handling. This function determines the number of bytes which * can be failed from the beginning of the request without * crossing into area which need to be retried further. * * Return: * The number of bytes to fail. */ unsigned int blk_rq_err_bytes(const struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; unsigned int bytes = 0; struct bio *bio; if (!(rq->rq_flags & RQF_MIXED_MERGE)) return blk_rq_bytes(rq); /* * Currently the only 'mixing' which can happen is between * different fastfail types. We can safely fail portions * which have all the failfast bits that the first one has - * the ones which are at least as eager to fail as the first * one. */ for (bio = rq->bio; bio; bio = bio->bi_next) { if ((bio->bi_opf & ff) != ff) break; bytes += bio->bi_iter.bi_size; } /* this could lead to infinite loop */ BUG_ON(blk_rq_bytes(rq) && !bytes); return bytes; } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) { unsigned long stamp; again: stamp = READ_ONCE(part->stamp); if (unlikely(stamp != now)) { if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->partno) { part = &part_to_disk(part)->part0; goto again; } } static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; part_stat_lock(); part = req->part; part_stat_add(part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } void blk_account_io_done(struct request *req, u64 now) { /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the * containing request is enough. */ if (req->part && blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; part_stat_lock(); part = req->part; update_io_ticks(part, jiffies, true); part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); hd_struct_put(part); } } void blk_account_io_start(struct request *rq) { if (!blk_do_io_stat(rq)) return; rq->part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); part_stat_lock(); update_io_ticks(rq->part, jiffies, false); part_stat_unlock(); } static unsigned long __part_start_io_acct(struct hd_struct *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); part_stat_lock(); update_io_ticks(part, now, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); return now; } unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, struct bio *bio) { *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio)); } EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { return __part_start_io_acct(&disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); static void __part_end_io_acct(struct hd_struct *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); update_io_ticks(part, now, true); part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); } void part_end_io_acct(struct hd_struct *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); hd_struct_put(part); } EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { __part_end_io_acct(&disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); /** * blk_update_request - Special helper function for request stacking drivers * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * This special helper function is only for request stacking drivers * (e.g. request-based dm) so that they can handle partial completion. * Actual device drivers should use blk_mq_end_request instead. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both * blk_rq_bytes() and in blk_update_request(). * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { int total_bytes; trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes); if (!req->bio) return false; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) req->q->integrity.profile->complete_fn(req, nr_bytes); #endif if (unlikely(error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET))) print_req_error(req, error, __func__); blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (bio_bytes == bio->bi_iter.bi_size) req->bio = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); req_bio_endio(req, bio, bio_bytes, error); total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE /** * rq_flush_dcache_pages - Helper function to flush all pages in a request * @rq: the request to be flushed * * Description: * Flush all pages in @rq. */ void rq_flush_dcache_pages(struct request *rq) { struct req_iterator iter; struct bio_vec bvec; rq_for_each_segment(bvec, rq, iter) flush_dcache_page(bvec.bv_page); } EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); #endif /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */ int blk_lld_busy(struct request_queue *q) { if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; } EXPORT_SYMBOL_GPL(blk_lld_busy); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio, *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_clone_fast(bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) goto free_and_out; if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } bio = NULL; } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: if (bio) bio_put(bio); blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); int kblockd_schedule_work(struct work_struct *work) { return queue_work(kblockd_workqueue, work); } EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */ void blk_start_plug(struct blk_plug *plug) { struct task_struct *tsk = current; /* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return; INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); plug->rq_count = 0; plug->multiple_queues = false; plug->nowait = false; /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug; } EXPORT_SYMBOL(blk_start_plug); static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } } } struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size) { struct blk_plug *plug = current->plug; struct blk_plug_cb *cb; if (!plug) return NULL; list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb; /* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb; } EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { flush_plug_callbacks(plug, from_schedule); if (!list_empty(&plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); } /** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */ void blk_finish_plug(struct blk_plug *plug) { if (plug != current->plug) return; blk_flush_plug_list(plug, false); current->plug = NULL; } EXPORT_SYMBOL(blk_finish_plug); void blk_io_schedule(void) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) io_schedule_timeout(timeout); else io_schedule(); } EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n"); blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); blk_debugfs_root = debugfs_create_dir("block", NULL); 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MLD_H #define LINUX_MLD_H #include <linux/in6.h> #include <linux/icmpv6.h> /* MLDv1 Query/Report/Done */ struct mld_msg { struct icmp6hdr mld_hdr; struct in6_addr mld_mca; }; #define mld_type mld_hdr.icmp6_type #define mld_code mld_hdr.icmp6_code #define mld_cksum mld_hdr.icmp6_cksum #define mld_maxdelay mld_hdr.icmp6_maxdelay #define mld_reserved mld_hdr.icmp6_dataun.un_data16[1] /* Multicast Listener Discovery version 2 headers */ /* MLDv2 Report */ struct mld2_grec { __u8 grec_type; __u8 grec_auxwords; __be16 grec_nsrcs; struct in6_addr grec_mca; struct in6_addr grec_src[]; }; struct mld2_report { struct icmp6hdr mld2r_hdr; struct mld2_grec mld2r_grec[]; }; #define mld2r_type mld2r_hdr.icmp6_type #define mld2r_resv1 mld2r_hdr.icmp6_code #define mld2r_cksum mld2r_hdr.icmp6_cksum #define mld2r_resv2 mld2r_hdr.icmp6_dataun.un_data16[0] #define mld2r_ngrec mld2r_hdr.icmp6_dataun.un_data16[1] /* MLDv2 Query */ struct mld2_query { struct icmp6hdr mld2q_hdr; struct in6_addr mld2q_mca; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 mld2q_qrv:3, mld2q_suppress:1, mld2q_resv2:4; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 mld2q_resv2:4, mld2q_suppress:1, mld2q_qrv:3; #else #error "Please fix <asm/byteorder.h>" #endif __u8 mld2q_qqic; __be16 mld2q_nsrcs; struct in6_addr mld2q_srcs[]; }; #define mld2q_type mld2q_hdr.icmp6_type #define mld2q_code mld2q_hdr.icmp6_code #define mld2q_cksum mld2q_hdr.icmp6_cksum #define mld2q_mrc mld2q_hdr.icmp6_maxdelay #define mld2q_resv1 mld2q_hdr.icmp6_dataun.un_data16[1] /* RFC3810, 5.1.3. Maximum Response Code: * * If Maximum Response Code >= 32768, Maximum Response Code represents a * floating-point value as follows: * * 0 1 2 3 4 5 6 7 8 9 A B C D E F * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ #define MLDV2_MRC_EXP(value) (((value) >> 12) & 0x0007) #define MLDV2_MRC_MAN(value) ((value) & 0x0fff) /* RFC3810, 5.1.9. QQIC (Querier's Query Interval Code): * * If QQIC >= 128, QQIC represents a floating-point value as follows: * * 0 1 2 3 4 5 6 7 * +-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+ */ #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) #define MLD_EXP_MIN_LIMIT 32768UL #define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) { /* RFC3810, 5.1.3. Maximum Response Code */ unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); if (mc_mrc < MLD_EXP_MIN_LIMIT) { ret = mc_mrc; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_MRC_EXP(mc_mrc); mc_man = MLDV2_MRC_MAN(mc_mrc); ret = (mc_man | 0x1000) << (mc_exp + 3); } return ret; } #endif |
| 3 2 1 3 822 821 1 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { bool is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { if (!net_eq(sock_net(sk), net)) continue; if (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) goto found; continue; } goto found; } sk = NULL; found: return sk; } EXPORT_SYMBOL_GPL(__raw_v6_lookup); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmp6hdr _hdr; const struct icmp6hdr *hdr; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; return (data[type >> 5] & (1U << (type & 31))) != 0; } return 1; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; bool delivered = false; __u8 hash; struct net *net; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (!sk) goto out; net = dev_net(skb->dev); sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); while (sk) { int filtered; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) { nf_reset_ct(clone); rawv6_rcv(sk, clone); } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; return raw_sk != NULL; } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!np->recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (np->recverr || harderr) { sk->sk_err = err; sk->sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; const struct in6_addr *saddr, *daddr; struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; daddr = &ip6h->daddr; net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, inet6_iif(skb), inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); } } read_unlock(&raw_v6_hashinfo.lock); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* hdrincl should be READ_ONCE(inet->hdrincl) * but READ_ONCE() doesn't work with bit fields. * Doing this indirectly yields the same result. */ hdrincl = inet->hdrincl; hdrincl = READ_ONCE(hdrincl); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; fl6.flowi6_mark = ipc6.sockc.mark; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, sockptr_t optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_sk(sk)->hdrincl = !!val; return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_sk(sk)->hdrincl; break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) val = -1; else val = rp->offset; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; fallthrough; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { 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); } default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_ioctl(sk, cmd, (void __user *)arg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); } static void raw6_destroy(struct sock *sk) { lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); inet6_destroy_sock(sk); } static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; break; case IPPROTO_MH: rp->checksum = 1; rp->offset = 4; break; default: break; } return 0; } struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, .recvmsg = rawv6_recvmsg, .bind = rawv6_bind, .backlog_rcv = rawv6_rcv_skb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { struct sock *sp = v; __u16 srcp = inet_sk(sp)->inet_num; ip6_dgram_sock_seq_show(seq, v, srcp, 0, raw_seq_private(seq)->bucket); } return 0; } static const struct seq_operations raw6_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw6_seq_show, }; static int __net_init raw6_init_net(struct net *net) { if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops, sizeof(struct raw_iter_state), &raw_v6_hashinfo)) return -ENOMEM; return 0; } static void __net_exit raw6_exit_net(struct net *net) { remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, }; int __init raw6_proc_init(void) { return register_pernet_subsys(&raw6_net_ops); } void raw6_proc_exit(void) { unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw rawv6_protosw = { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; int __init rawv6_init(void) { return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) { inet6_unregister_protosw(&rawv6_protosw); } |
| 8 1 2 1 158 1051 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Linux Socket Filter Data Structures */ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ #include <stdarg.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/capability.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <crypto/sha.h> #include <net/sch_generic.h> #include <asm/byteorder.h> #include <uapi/linux/filter.h> #include <uapi/linux/bpf.h> struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; struct ctl_table; struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */ #define BPF_REG_ARG1 BPF_REG_1 #define BPF_REG_ARG2 BPF_REG_2 #define BPF_REG_ARG3 BPF_REG_3 #define BPF_REG_ARG4 BPF_REG_4 #define BPF_REG_ARG5 BPF_REG_5 #define BPF_REG_CTX BPF_REG_6 #define BPF_REG_FP BPF_REG_10 /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 #define BPF_REG_TMP BPF_REG_2 /* scratch reg */ #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) #define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Speculative Store Bypass */ #define BPF_NOSPEC 0xc0 /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */ #define BPF_SYM_ELF_TYPE 't' /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ #define BPF_ALU64_REG(OP, DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_ALU32_REG(OP, DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM(OP, DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_ALU32_IMM(OP, DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ #define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 }) static inline bool insn_is_zext(const struct bpf_insn *insn) { return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) #define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ #define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ #define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Memory load, dst_reg = *(uint *) (src_reg + off16) */ #define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */ #define BPF_STX_XADD(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ #define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 }) /* Relative call */ #define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT }) /* Function call */ #define BPF_CAST_CALL(x) \ ((u64 (*)(u64, u64, u64, u64, u64))(x)) #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((FUNC) - __bpf_call_base) }) /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) /* Program exit */ #define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Speculation barrier */ #define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K)) #define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \ }) #define bpf_size_to_bytes(bpf_size) \ ({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \ }) #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ }) #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) #define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) #define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) #define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) #define __BPF_REG_0(...) __BPF_PAD(5) #define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) #define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) #define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) #define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) #define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) #define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) #define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) #define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a #define __BPF_V void #define __BPF_N #define __BPF_DECL_ARGS(t, a) t a #define __BPF_DECL_REGS(t, a) u64 a #define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define BPF_CALL_0(name, ...) BPF_CALL_x(0, name, __VA_ARGS__) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, name, __VA_ARGS__) #define BPF_CALL_2(name, ...) BPF_CALL_x(2, name, __VA_ARGS__) #define BPF_CALL_3(name, ...) BPF_CALL_x(3, name, __VA_ARGS__) #define BPF_CALL_4(name, ...) BPF_CALL_x(4, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 #if BITS_PER_LONG == 64 # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #else # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 #endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; struct sock_fprog_kern { u16 len; struct sock_filter *filter; }; /* Some arches need doubleword alignment for their instructions and/or data */ #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { u32 pages; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); /* Instructions for interpreter */ struct sock_filter insns[0]; struct bpf_insn insnsi[]; }; struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); #define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ u32 __ret; \ cant_migrate(); \ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ struct bpf_prog_stats *__stats; \ u64 __start = sched_clock(); \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ __stats = this_cpu_ptr(prog->aux->stats); \ u64_stats_update_begin(&__stats->syncp); \ __stats->cnt++; \ __stats->nsecs += sched_clock() - __start; \ u64_stats_update_end(&__stats->syncp); \ } else { \ __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ } \ __ret; }) #define BPF_PROG_RUN(prog, ctx) \ __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) /* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. * * For non RT enabled kernels migrate_disable/enable() maps to * preempt_disable/enable(), i.e. it disables also preemption. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) { u32 ret; migrate_disable(); ret = __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func); migrate_enable(); return ret; } #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end; }; struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; }; }; struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; struct bpf_map *map; u32 kern_flags; struct bpf_nh_params nh; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; *saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb); } /* Restore data saved by bpf_compute_data_pointers(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; cb->data_end = saved_data_end; } static inline u8 *bpf_skb_cb(struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); } res = BPF_PROG_RUN(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u32 res; migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res; } static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { /* Caller needs to hold rcu_read_lock() (!), otherwise program * can be released while still running, or map elements could be * freed early while still having concurrent users. XDP fastpath * already takes rcu_read_lock() when fetching the program, so * it's not necessary here anymore. */ return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); } static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) { /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC; } static inline u32 bpf_ctx_off_adjust_machine(u32 size) { const u32 size_machine = sizeof(unsigned long); if (size > size_machine && size % size_machine == 0) size = size_machine; return size; } static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { return size <= size_default && (size & (size - 1)) == 0; } static inline u8 bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN return access_off; #else return size_default - (access_off + size); #endif } #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); set_memory_ro((unsigned long)fp, fp->pages); } #endif } static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); set_memory_ro((unsigned long)hdr, hdr->pages); set_memory_x((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) { unsigned long real_start = (unsigned long)fp->bpf_func; unsigned long addr = real_start & PAGE_MASK; return (void *)addr; } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { return sk_filter_trim_cap(sk, skb, 1); } struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); void bpf_prog_free_linfo(struct bpf_prog *prog); void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); void bpf_prog_free_jited_linfo(struct bpf_prog *prog); void bpf_prog_free_unused_jited_linfo(struct bpf_prog *prog); struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { __bpf_prog_free(fp); } typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen); int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); void bpf_clear_redirect_map(struct bpf_map *map); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { unsigned int len; if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE; return 0; } /* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); void xdp_do_flush(void); /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as * it is no longer only flushing maps. Keep this define for compatibility * until all drivers are updated - do not use xdp_do_flush_map() in new code! */ #define xdp_do_flush_map xdp_do_flush void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, u32 hash) { return NULL; } #endif #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } static inline bool bpf_jit_is_ebpf(void) { # ifdef CONFIG_HAVE_EBPF_JIT return true; # else return false; # endif } static inline bool ebpf_jit_enabled(void) { return bpf_jit_enable && bpf_jit_is_ebpf(); } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && capable(CAP_SYS_ADMIN)) return false; return true; } static inline bool bpf_jit_kallsyms_enabled(void) { /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true; return false; } const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { const char *ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; return ret; } void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ static inline bool ebpf_jit_enabled(void) { return false; } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { return false; } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } static inline int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { return -ENOTSUPP; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } static inline bool bpf_jit_kallsyms_enabled(void) { return false; } static inline const char * __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { return NULL; } static inline bool is_bpf_text_address(unsigned long addr) { return false; } static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { return NULL; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) { switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false; default: return true; } } static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: #define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; } } void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size); static inline void *bpf_load_pointer(const struct sk_buff *skb, int k, unsigned int size, void *buffer) { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); return bpf_internal_load_pointer_neg_helper(skb, k, size); } static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ }; struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */ }; struct bpf_sysctl_kern { struct ctl_table_header *head; struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; s32 retval; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; bool no_reuseport; }; extern struct static_key_false bpf_sk_lookup_enabled; /* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */ #define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #if IS_ENABLED(CONFIG_IPV6) static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* __LINUX_FILTER_H__ */ |
| 819 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xt_hashlimit - Netfilter module to limit the number of packets per time * separately for each hashbucket (sourceip/sourceport/dstip/dstport) * * (C) 2003-2004 by Harald Welte <laforge@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> * Copyright © CC Computer Consultants GmbH, 2007 - 2008 * * Development of this code was funded by Astaro AG, http://www.astaro.com/ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/random.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/mm.h> #include <linux/in.h> #include <linux/ip.h> #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) #include <linux/ipv6.h> #include <net/ipv6.h> #endif #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/mutex.h> #include <linux/kernel.h> #include <linux/refcount.h> #include <uapi/linux/netfilter/xt_hashlimit.h> #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ XT_HASHLIMIT_RATE_MATCH) MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: per hash-bucket rate-limit match"); MODULE_ALIAS("ipt_hashlimit"); MODULE_ALIAS("ip6t_hashlimit"); struct hashlimit_net { struct hlist_head htables; struct proc_dir_entry *ipt_hashlimit; struct proc_dir_entry *ip6t_hashlimit; }; static unsigned int hashlimit_net_id; static inline struct hashlimit_net *hashlimit_pernet(struct net *net) { return net_generic(net, hashlimit_net_id); } /* need to declare this at the top */ static const struct seq_operations dl_seq_ops_v2; static const struct seq_operations dl_seq_ops_v1; static const struct seq_operations dl_seq_ops; /* hash table crap */ struct dsthash_dst { union { struct { __be32 src; __be32 dst; } ip; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) struct { __be32 src[4]; __be32 dst[4]; } ip6; #endif }; __be16 src_port; __be16 dst_port; }; struct dsthash_ent { /* static / read-only parts in the beginning */ struct hlist_node node; struct dsthash_dst dst; /* modified structure members in the end */ spinlock_t lock; unsigned long expires; /* precalculated expiry time */ struct { unsigned long prev; /* last modification */ union { struct { u_int64_t credit; u_int64_t credit_cap; u_int64_t cost; }; struct { u_int32_t interval, prev_window; u_int64_t current_rate; u_int64_t rate; int64_t burst; }; }; } rateinfo; struct rcu_head rcu; }; struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ refcount_t use; u_int8_t family; bool rnd_initialized; struct hashlimit_cfg3 cfg; /* config */ /* used internally */ spinlock_t lock; /* lock for list_head */ u_int32_t rnd; /* random seed for hash */ unsigned int count; /* number entries in table */ struct delayed_work gc_work; /* seq_file stuff */ struct proc_dir_entry *pde; const char *name; struct net *net; struct hlist_head hash[]; /* hashtable itself */ }; static int cfg_copy(struct hashlimit_cfg3 *to, const void *from, int revision) { if (revision == 1) { struct hashlimit_cfg1 *cfg = (struct hashlimit_cfg1 *)from; to->mode = cfg->mode; to->avg = cfg->avg; to->burst = cfg->burst; to->size = cfg->size; to->max = cfg->max; to->gc_interval = cfg->gc_interval; to->expire = cfg->expire; to->srcmask = cfg->srcmask; to->dstmask = cfg->dstmask; } else if (revision == 2) { struct hashlimit_cfg2 *cfg = (struct hashlimit_cfg2 *)from; to->mode = cfg->mode; to->avg = cfg->avg; to->burst = cfg->burst; to->size = cfg->size; to->max = cfg->max; to->gc_interval = cfg->gc_interval; to->expire = cfg->expire; to->srcmask = cfg->srcmask; to->dstmask = cfg->dstmask; } else if (revision == 3) { memcpy(to, from, sizeof(struct hashlimit_cfg3)); } else { return -EINVAL; } return 0; } static DEFINE_MUTEX(hashlimit_mutex); /* protects htables list */ static struct kmem_cache *hashlimit_cachep __read_mostly; static inline bool dst_cmp(const struct dsthash_ent *ent, const struct dsthash_dst *b) { return !memcmp(&ent->dst, b, sizeof(ent->dst)); } static u_int32_t hash_dst(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst) { u_int32_t hash = jhash2((const u32 *)dst, sizeof(*dst)/sizeof(u32), ht->rnd); /* * Instead of returning hash % ht->cfg.size (implying a divide) * we return the high 32 bits of the (hash * ht->cfg.size) that will * give results between [0 and cfg.size-1] and same hash distribution, * but using a multiply, less expensive than a divide */ return reciprocal_scale(hash, ht->cfg.size); } static struct dsthash_ent * dsthash_find(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst) { struct dsthash_ent *ent; u_int32_t hash = hash_dst(ht, dst); if (!hlist_empty(&ht->hash[hash])) { hlist_for_each_entry_rcu(ent, &ht->hash[hash], node) if (dst_cmp(ent, dst)) { spin_lock(&ent->lock); return ent; } } return NULL; } /* allocate dsthash_ent, initialize dst, put in htable and lock it */ static struct dsthash_ent * dsthash_alloc_init(struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst, bool *race) { struct dsthash_ent *ent; spin_lock(&ht->lock); /* Two or more packets may race to create the same entry in the * hashtable, double check if this packet lost race. */ ent = dsthash_find(ht, dst); if (ent != NULL) { spin_unlock(&ht->lock); *race = true; return ent; } /* initialize hash with random val at the time we allocate * the first hashtable entry */ if (unlikely(!ht->rnd_initialized)) { get_random_bytes(&ht->rnd, sizeof(ht->rnd)); ht->rnd_initialized = true; } if (ht->cfg.max && ht->count >= ht->cfg.max) { /* FIXME: do something. question is what.. */ net_err_ratelimited("max count of %u reached\n", ht->cfg.max); ent = NULL; } else ent = kmem_cache_alloc(hashlimit_cachep, GFP_ATOMIC); if (ent) { memcpy(&ent->dst, dst, sizeof(ent->dst)); spin_lock_init(&ent->lock); spin_lock(&ent->lock); hlist_add_head_rcu(&ent->node, &ht->hash[hash_dst(ht, dst)]); ht->count++; } spin_unlock(&ht->lock); return ent; } static void dsthash_free_rcu(struct rcu_head *head) { struct dsthash_ent *ent = container_of(head, struct dsthash_ent, rcu); kmem_cache_free(hashlimit_cachep, ent); } static inline void dsthash_free(struct xt_hashlimit_htable *ht, struct dsthash_ent *ent) { hlist_del_rcu(&ent->node); call_rcu(&ent->rcu, dsthash_free_rcu); ht->count--; } static void htable_gc(struct work_struct *work); static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, const char *name, u_int8_t family, struct xt_hashlimit_htable **out_hinfo, int revision) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; const struct seq_operations *ops; unsigned int size, i; unsigned long nr_pages = totalram_pages(); int ret; if (cfg->size) { size = cfg->size; } else { size = (nr_pages << PAGE_SHIFT) / 16384 / sizeof(struct hlist_head); if (nr_pages > 1024 * 1024 * 1024 / PAGE_SIZE) size = 8192; if (size < 16) size = 16; } /* FIXME: don't use vmalloc() here or anywhere else -HW */ hinfo = vmalloc(struct_size(hinfo, hash, size)); if (hinfo == NULL) return -ENOMEM; *out_hinfo = hinfo; /* copy match config into hashtable config */ ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3); if (ret) { vfree(hinfo); return ret; } hinfo->cfg.size = size; if (hinfo->cfg.max == 0) hinfo->cfg.max = 8 * hinfo->cfg.size; else if (hinfo->cfg.max < hinfo->cfg.size) hinfo->cfg.max = hinfo->cfg.size; for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; hinfo->name = kstrdup(name, GFP_KERNEL); if (!hinfo->name) { vfree(hinfo); return -ENOMEM; } spin_lock_init(&hinfo->lock); switch (revision) { case 1: ops = &dl_seq_ops_v1; break; case 2: ops = &dl_seq_ops_v2; break; default: ops = &dl_seq_ops; } hinfo->pde = proc_create_seq_data(name, 0, (family == NFPROTO_IPV4) ? hashlimit_net->ipt_hashlimit : hashlimit_net->ip6t_hashlimit, ops, hinfo); if (hinfo->pde == NULL) { kfree(hinfo->name); vfree(hinfo); return -ENOMEM; } hinfo->net = net; INIT_DEFERRABLE_WORK(&hinfo->gc_work, htable_gc); queue_delayed_work(system_power_efficient_wq, &hinfo->gc_work, msecs_to_jiffies(hinfo->cfg.gc_interval)); hlist_add_head(&hinfo->node, &hashlimit_net->htables); return 0; } static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select_all) { unsigned int i; for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; struct hlist_node *n; spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if (time_after_eq(jiffies, dh->expires) || select_all) dsthash_free(ht, dh); } spin_unlock_bh(&ht->lock); cond_resched(); } } static void htable_gc(struct work_struct *work) { struct xt_hashlimit_htable *ht; ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); htable_selective_cleanup(ht, false); queue_delayed_work(system_power_efficient_wq, &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); } static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(hinfo->net); struct proc_dir_entry *parent; if (hinfo->family == NFPROTO_IPV4) parent = hashlimit_net->ipt_hashlimit; else parent = hashlimit_net->ip6t_hashlimit; if (parent != NULL) remove_proc_entry(hinfo->name, parent); } static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { refcount_inc(&hinfo->use); return hinfo; } } return NULL; } static void htable_put(struct xt_hashlimit_htable *hinfo) { if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); htable_remove_proc_entry(hinfo); mutex_unlock(&hashlimit_mutex); cancel_delayed_work_sync(&hinfo->gc_work); htable_selective_cleanup(hinfo, true); kfree(hinfo->name); vfree(hinfo); } } /* The algorithm used is the Simple Token Bucket Filter (TBF) * see net/sched/sch_tbf.c in the linux source tree */ /* Rusty: This is my (non-mathematically-inclined) understanding of this algorithm. The `average rate' in jiffies becomes your initial amount of credit `credit' and the most credit you can ever have `credit_cap'. The `peak rate' becomes the cost of passing the test, `cost'. `prev' tracks the last packet hit: you gain one credit per jiffy. If you get credit balance more than this, the extra credit is discarded. Every time the match passes, you lose `cost' credits; if you don't have that many, the test fails. See Alexey's formal explanation in net/sched/sch_tbf.c. To get the maximum range, we multiply by this factor (ie. you get N credits per jiffy). We want to allow a rate as low as 1 per day (slowest userspace tool allows), which means CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie. */ #define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24)) #define MAX_CPJ (0xFFFFFFFFFFFFFFFFULL / (HZ*60*60*24)) /* Repeated shift and or gives us all 1s, final shift and add 1 gives * us the power of 2 below the theoretical max, so GCC simply does a * shift. */ #define _POW2_BELOW2(x) ((x)|((x)>>1)) #define _POW2_BELOW4(x) (_POW2_BELOW2(x)|_POW2_BELOW2((x)>>2)) #define _POW2_BELOW8(x) (_POW2_BELOW4(x)|_POW2_BELOW4((x)>>4)) #define _POW2_BELOW16(x) (_POW2_BELOW8(x)|_POW2_BELOW8((x)>>8)) #define _POW2_BELOW32(x) (_POW2_BELOW16(x)|_POW2_BELOW16((x)>>16)) #define _POW2_BELOW64(x) (_POW2_BELOW32(x)|_POW2_BELOW32((x)>>32)) #define POW2_BELOW32(x) ((_POW2_BELOW32(x)>>1) + 1) #define POW2_BELOW64(x) ((_POW2_BELOW64(x)>>1) + 1) #define CREDITS_PER_JIFFY POW2_BELOW64(MAX_CPJ) #define CREDITS_PER_JIFFY_v1 POW2_BELOW32(MAX_CPJ_v1) /* in byte mode, the lowest possible rate is one packet/second. * credit_cap is used as a counter that tells us how many times we can * refill the "credits available" counter when it becomes empty. */ #define MAX_CPJ_BYTES (0xFFFFFFFF / HZ) #define CREDITS_PER_JIFFY_BYTES POW2_BELOW32(MAX_CPJ_BYTES) static u32 xt_hashlimit_len_to_chunks(u32 len) { return (len >> XT_HASHLIMIT_BYTE_SHIFT) + 1; } /* Precision saver. */ static u64 user2credits(u64 user, int revision) { u64 scale = (revision == 1) ? XT_HASHLIMIT_SCALE : XT_HASHLIMIT_SCALE_v2; u64 cpj = (revision == 1) ? CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; /* Avoid overflow: divide the constant operands first */ if (scale >= HZ * cpj) return div64_u64(user, div64_u64(scale, HZ * cpj)); return user * div64_u64(HZ * cpj, scale); } static u32 user2credits_byte(u32 user) { u64 us = user; us *= HZ * CREDITS_PER_JIFFY_BYTES; return (u32) (us >> 32); } static u64 user2rate(u64 user) { if (user != 0) { return div64_u64(XT_HASHLIMIT_SCALE_v2, user); } else { pr_info_ratelimited("invalid rate from userspace: %llu\n", user); return 0; } } static u64 user2rate_bytes(u32 user) { u64 r; r = user ? U32_MAX / user : U32_MAX; return (r - 1) << XT_HASHLIMIT_BYTE_SHIFT; } static void rateinfo_recalc(struct dsthash_ent *dh, unsigned long now, u32 mode, int revision) { unsigned long delta = now - dh->rateinfo.prev; u64 cap, cpj; if (delta == 0) return; if (revision >= 3 && mode & XT_HASHLIMIT_RATE_MATCH) { u64 interval = dh->rateinfo.interval * HZ; if (delta < interval) return; dh->rateinfo.prev = now; dh->rateinfo.prev_window = ((dh->rateinfo.current_rate * interval) > (delta * dh->rateinfo.rate)); dh->rateinfo.current_rate = 0; return; } dh->rateinfo.prev = now; if (mode & XT_HASHLIMIT_BYTES) { u64 tmp = dh->rateinfo.credit; dh->rateinfo.credit += CREDITS_PER_JIFFY_BYTES * delta; cap = CREDITS_PER_JIFFY_BYTES * HZ; if (tmp >= dh->rateinfo.credit) {/* overflow */ dh->rateinfo.credit = cap; return; } } else { cpj = (revision == 1) ? CREDITS_PER_JIFFY_v1 : CREDITS_PER_JIFFY; dh->rateinfo.credit += delta * cpj; cap = dh->rateinfo.credit_cap; } if (dh->rateinfo.credit > cap) dh->rateinfo.credit = cap; } static void rateinfo_init(struct dsthash_ent *dh, struct xt_hashlimit_htable *hinfo, int revision) { dh->rateinfo.prev = jiffies; if (revision >= 3 && hinfo->cfg.mode & XT_HASHLIMIT_RATE_MATCH) { dh->rateinfo.prev_window = 0; dh->rateinfo.current_rate = 0; if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { dh->rateinfo.rate = user2rate_bytes((u32)hinfo->cfg.avg); if (hinfo->cfg.burst) dh->rateinfo.burst = hinfo->cfg.burst * dh->rateinfo.rate; else dh->rateinfo.burst = dh->rateinfo.rate; } else { dh->rateinfo.rate = user2rate(hinfo->cfg.avg); dh->rateinfo.burst = hinfo->cfg.burst + dh->rateinfo.rate; } dh->rateinfo.interval = hinfo->cfg.interval; } else if (hinfo->cfg.mode & XT_HASHLIMIT_BYTES) { dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; dh->rateinfo.cost = user2credits_byte(hinfo->cfg.avg); dh->rateinfo.credit_cap = hinfo->cfg.burst; } else { dh->rateinfo.credit = user2credits(hinfo->cfg.avg * hinfo->cfg.burst, revision); dh->rateinfo.cost = user2credits(hinfo->cfg.avg, revision); dh->rateinfo.credit_cap = dh->rateinfo.credit; } } static inline __be32 maskl(__be32 a, unsigned int l) { return l ? htonl(ntohl(a) & ~0 << (32 - l)) : 0; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static void hashlimit_ipv6_mask(__be32 *i, unsigned int p) { switch (p) { case 0 ... 31: i[0] = maskl(i[0], p); i[1] = i[2] = i[3] = 0; break; case 32 ... 63: i[1] = maskl(i[1], p - 32); i[2] = i[3] = 0; break; case 64 ... 95: i[2] = maskl(i[2], p - 64); i[3] = 0; break; case 96 ... 127: i[3] = maskl(i[3], p - 96); break; case 128: break; } } #endif static int hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo, struct dsthash_dst *dst, const struct sk_buff *skb, unsigned int protoff) { __be16 _ports[2], *ports; u8 nexthdr; int poff; memset(dst, 0, sizeof(*dst)); switch (hinfo->family) { case NFPROTO_IPV4: if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) dst->ip.dst = maskl(ip_hdr(skb)->daddr, hinfo->cfg.dstmask); if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_SIP) dst->ip.src = maskl(ip_hdr(skb)->saddr, hinfo->cfg.srcmask); if (!(hinfo->cfg.mode & (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT))) return 0; nexthdr = ip_hdr(skb)->protocol; break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: { __be16 frag_off; if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) { memcpy(&dst->ip6.dst, &ipv6_hdr(skb)->daddr, sizeof(dst->ip6.dst)); hashlimit_ipv6_mask(dst->ip6.dst, hinfo->cfg.dstmask); } if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_SIP) { memcpy(&dst->ip6.src, &ipv6_hdr(skb)->saddr, sizeof(dst->ip6.src)); hashlimit_ipv6_mask(dst->ip6.src, hinfo->cfg.srcmask); } if (!(hinfo->cfg.mode & (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT))) return 0; nexthdr = ipv6_hdr(skb)->nexthdr; protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off); if ((int)protoff < 0) return -1; break; } #endif default: BUG(); return 0; } poff = proto_ports_offset(nexthdr); if (poff >= 0) { ports = skb_header_pointer(skb, protoff + poff, sizeof(_ports), &_ports); } else { _ports[0] = _ports[1] = 0; ports = _ports; } if (!ports) return -1; if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_SPT) dst->src_port = ports[0]; if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DPT) dst->dst_port = ports[1]; return 0; } static u32 hashlimit_byte_cost(unsigned int len, struct dsthash_ent *dh) { u64 tmp = xt_hashlimit_len_to_chunks(len); tmp = tmp * dh->rateinfo.cost; if (unlikely(tmp > CREDITS_PER_JIFFY_BYTES * HZ)) tmp = CREDITS_PER_JIFFY_BYTES * HZ; if (dh->rateinfo.credit < tmp && dh->rateinfo.credit_cap) { dh->rateinfo.credit_cap--; dh->rateinfo.credit = CREDITS_PER_JIFFY_BYTES * HZ; } return (u32) tmp; } static bool hashlimit_mt_common(const struct sk_buff *skb, struct xt_action_param *par, struct xt_hashlimit_htable *hinfo, const struct hashlimit_cfg3 *cfg, int revision) { unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; bool race = false; u64 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) goto hotdrop; local_bh_disable(); dh = dsthash_find(hinfo, &dst); if (dh == NULL) { dh = dsthash_alloc_init(hinfo, &dst, &race); if (dh == NULL) { local_bh_enable(); goto hotdrop; } else if (race) { /* Already got an entry, update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } else { dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); rateinfo_init(dh, hinfo, revision); } } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); rateinfo_recalc(dh, now, hinfo->cfg.mode, revision); } if (cfg->mode & XT_HASHLIMIT_RATE_MATCH) { cost = (cfg->mode & XT_HASHLIMIT_BYTES) ? skb->len : 1; dh->rateinfo.current_rate += cost; if (!dh->rateinfo.prev_window && (dh->rateinfo.current_rate <= dh->rateinfo.burst)) { spin_unlock(&dh->lock); local_bh_enable(); return !(cfg->mode & XT_HASHLIMIT_INVERT); } else { goto overlimit; } } if (cfg->mode & XT_HASHLIMIT_BYTES) cost = hashlimit_byte_cost(skb->len, dh); else cost = dh->rateinfo.cost; if (dh->rateinfo.credit >= cost) { /* below the limit */ dh->rateinfo.credit -= cost; spin_unlock(&dh->lock); local_bh_enable(); return !(cfg->mode & XT_HASHLIMIT_INVERT); } overlimit: spin_unlock(&dh->lock); local_bh_enable(); /* default match is underlimit - so over the limit, we need to invert */ return cfg->mode & XT_HASHLIMIT_INVERT; hotdrop: par->hotdrop = true; return false; } static bool hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); if (ret) return ret; return hashlimit_mt_common(skb, par, hinfo, &cfg, 1); } static bool hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); if (ret) return ret; return hashlimit_mt_common(skb, par, hinfo, &cfg, 2); } static bool hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; struct xt_hashlimit_htable *hinfo = info->hinfo; return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } #define HASHLIMIT_MAX_SIZE 1048576 static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, const char *name, int revision) { struct net *net = par->net; int ret; if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; if (cfg->size > HASHLIMIT_MAX_SIZE) { cfg->size = HASHLIMIT_MAX_SIZE; pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); } if (cfg->max > HASHLIMIT_MAX_SIZE) { cfg->max = HASHLIMIT_MAX_SIZE; pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; } else { if (cfg->srcmask > 128 || cfg->dstmask > 128) return -EINVAL; } if (cfg->mode & ~XT_HASHLIMIT_ALL) { pr_info_ratelimited("Unknown mode mask %X, kernel too old?\n", cfg->mode); return -EINVAL; } /* Check for overflow. */ if (revision >= 3 && cfg->mode & XT_HASHLIMIT_RATE_MATCH) { if (cfg->avg == 0 || cfg->avg > U32_MAX) { pr_info_ratelimited("invalid rate\n"); return -ERANGE; } if (cfg->interval == 0) { pr_info_ratelimited("invalid interval\n"); return -EINVAL; } } else if (cfg->mode & XT_HASHLIMIT_BYTES) { if (user2credits_byte(cfg->avg) == 0) { pr_info_ratelimited("overflow, rate too high: %llu\n", cfg->avg); return -EINVAL; } } else if (cfg->burst == 0 || user2credits(cfg->avg * cfg->burst, revision) < user2credits(cfg->avg, revision)) { pr_info_ratelimited("overflow, try lower: %llu/%llu\n", cfg->avg, cfg->burst); return -ERANGE; } mutex_lock(&hashlimit_mutex); *hinfo = htable_find_get(net, name, par->family); if (*hinfo == NULL) { ret = htable_create(net, cfg, name, par->family, hinfo, revision); if (ret < 0) { mutex_unlock(&hashlimit_mutex); return ret; } } mutex_unlock(&hashlimit_mutex); return 0; } static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo1 *info = par->matchinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = xt_check_proc_name(info->name, sizeof(info->name)); if (ret) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); if (ret) return ret; return hashlimit_mt_check_common(par, &info->hinfo, &cfg, info->name, 1); } static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo2 *info = par->matchinfo; struct hashlimit_cfg3 cfg = {}; int ret; ret = xt_check_proc_name(info->name, sizeof(info->name)); if (ret) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); if (ret) return ret; return hashlimit_mt_check_common(par, &info->hinfo, &cfg, info->name, 2); } static int hashlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_hashlimit_mtinfo3 *info = par->matchinfo; int ret; ret = xt_check_proc_name(info->name, sizeof(info->name)); if (ret) return ret; return hashlimit_mt_check_common(par, &info->hinfo, &info->cfg, info->name, 3); } static void hashlimit_mt_destroy_v2(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo2 *info = par->matchinfo; htable_put(info->hinfo); } static void hashlimit_mt_destroy_v1(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo1 *info = par->matchinfo; htable_put(info->hinfo); } static void hashlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_hashlimit_mtinfo3 *info = par->matchinfo; htable_put(info->hinfo); } static struct xt_match hashlimit_mt_reg[] __read_mostly = { { .name = "hashlimit", .revision = 1, .family = NFPROTO_IPV4, .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo), .checkentry = hashlimit_mt_check_v1, .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV4, .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), .checkentry = hashlimit_mt_check_v2, .destroy = hashlimit_mt_destroy_v2, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 3, .family = NFPROTO_IPV4, .match = hashlimit_mt, .matchsize = sizeof(struct xt_hashlimit_mtinfo3), .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "hashlimit", .revision = 1, .family = NFPROTO_IPV6, .match = hashlimit_mt_v1, .matchsize = sizeof(struct xt_hashlimit_mtinfo1), .usersize = offsetof(struct xt_hashlimit_mtinfo1, hinfo), .checkentry = hashlimit_mt_check_v1, .destroy = hashlimit_mt_destroy_v1, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 2, .family = NFPROTO_IPV6, .match = hashlimit_mt_v2, .matchsize = sizeof(struct xt_hashlimit_mtinfo2), .usersize = offsetof(struct xt_hashlimit_mtinfo2, hinfo), .checkentry = hashlimit_mt_check_v2, .destroy = hashlimit_mt_destroy_v2, .me = THIS_MODULE, }, { .name = "hashlimit", .revision = 3, .family = NFPROTO_IPV6, .match = hashlimit_mt, .matchsize = sizeof(struct xt_hashlimit_mtinfo3), .usersize = offsetof(struct xt_hashlimit_mtinfo3, hinfo), .checkentry = hashlimit_mt_check, .destroy = hashlimit_mt_destroy, .me = THIS_MODULE, }, #endif }; /* PROC stuff */ static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); if (*pos >= htable->cfg.size) return NULL; bucket = kmalloc(sizeof(unsigned int), GFP_ATOMIC); if (!bucket) return ERR_PTR(-ENOMEM); *bucket = *pos; return bucket; } static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); if (*pos >= htable->cfg.size) { kfree(v); return NULL; } return bucket; } static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) kfree(bucket); spin_unlock_bh(&htable->lock); } static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { switch (family) { case NFPROTO_IPV4: seq_printf(s, "%ld %pI4:%u->%pI4:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip.src, ntohs(ent->dst.src_port), &ent->dst.ip.dst, ntohs(ent->dst.dst_port), ent->rateinfo.credit, ent->rateinfo.credit_cap, ent->rateinfo.cost); break; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) case NFPROTO_IPV6: seq_printf(s, "%ld %pI6:%u->%pI6:%u %llu %llu %llu\n", (long)(ent->expires - jiffies)/HZ, &ent->dst.ip6.src, ntohs(ent->dst.src_port), &ent->dst.ip6.dst, ntohs(ent->dst.dst_port), ent->rateinfo.credit, ent->rateinfo.credit_cap, ent->rateinfo.cost); break; #endif default: BUG(); } } static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ rateinfo_recalc(ent, jiffies, ht->cfg.mode, 2); dl_seq_print(ent, family, s); spin_unlock(&ent->lock); return seq_has_overflowed(s); } static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ rateinfo_recalc(ent, jiffies, ht->cfg.mode, 1); dl_seq_print(ent, family, s); spin_unlock(&ent->lock); return seq_has_overflowed(s); } static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ rateinfo_recalc(ent, jiffies, ht->cfg.mode, 3); dl_seq_print(ent, family, s); spin_unlock(&ent->lock); return seq_has_overflowed(s); } static int dl_seq_show_v2(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show_v2(ent, htable->family, s)) return -1; } return 0; } static int dl_seq_show_v1(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show_v1(ent, htable->family, s)) return -1; } return 0; } static int dl_seq_show(struct seq_file *s, void *v) { struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; if (!hlist_empty(&htable->hash[*bucket])) { hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show(ent, htable->family, s)) return -1; } return 0; } static const struct seq_operations dl_seq_ops_v1 = { .start = dl_seq_start, .next = dl_seq_next, .stop = dl_seq_stop, .show = dl_seq_show_v1 }; static const struct seq_operations dl_seq_ops_v2 = { .start = dl_seq_start, .next = dl_seq_next, .stop = dl_seq_stop, .show = dl_seq_show_v2 }; static const struct seq_operations dl_seq_ops = { .start = dl_seq_start, .next = dl_seq_next, .stop = dl_seq_stop, .show = dl_seq_show }; static int __net_init hashlimit_proc_net_init(struct net *net) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); hashlimit_net->ipt_hashlimit = proc_mkdir("ipt_hashlimit", net->proc_net); if (!hashlimit_net->ipt_hashlimit) return -ENOMEM; #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net); if (!hashlimit_net->ip6t_hashlimit) { remove_proc_entry("ipt_hashlimit", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit hashlimit_proc_net_exit(struct net *net) { struct xt_hashlimit_htable *hinfo; struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); /* hashlimit_net_exit() is called before hashlimit_mt_destroy(). * Make sure that the parent ipt_hashlimit and ip6t_hashlimit proc * entries is empty before trying to remove it. */ mutex_lock(&hashlimit_mutex); hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) htable_remove_proc_entry(hinfo); hashlimit_net->ipt_hashlimit = NULL; hashlimit_net->ip6t_hashlimit = NULL; mutex_unlock(&hashlimit_mutex); remove_proc_entry("ipt_hashlimit", net->proc_net); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) remove_proc_entry("ip6t_hashlimit", net->proc_net); #endif } static int __net_init hashlimit_net_init(struct net *net) { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); INIT_HLIST_HEAD(&hashlimit_net->htables); return hashlimit_proc_net_init(net); } static void __net_exit hashlimit_net_exit(struct net *net) { hashlimit_proc_net_exit(net); } static struct pernet_operations hashlimit_net_ops = { .init = hashlimit_net_init, .exit = hashlimit_net_exit, .id = &hashlimit_net_id, .size = sizeof(struct hashlimit_net), }; static int __init hashlimit_mt_init(void) { int err; err = register_pernet_subsys(&hashlimit_net_ops); if (err < 0) return err; err = xt_register_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); if (err < 0) goto err1; err = -ENOMEM; hashlimit_cachep = kmem_cache_create("xt_hashlimit", sizeof(struct dsthash_ent), 0, 0, NULL); if (!hashlimit_cachep) { pr_warn("unable to create slab cache\n"); goto err2; } return 0; err2: xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); err1: unregister_pernet_subsys(&hashlimit_net_ops); return err; } static void __exit hashlimit_mt_exit(void) { xt_unregister_matches(hashlimit_mt_reg, ARRAY_SIZE(hashlimit_mt_reg)); unregister_pernet_subsys(&hashlimit_net_ops); rcu_barrier(); kmem_cache_destroy(hashlimit_cachep); } module_init(hashlimit_mt_init); module_exit(hashlimit_mt_exit); |
| 3 1 9 496 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> #ifdef CONFIG_SET_FS /* * Force the uaccess routines to be wired up for actual userspace access, * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone * using force_uaccess_end below. */ static inline mm_segment_t force_uaccess_begin(void) { mm_segment_t fs = get_fs(); set_fs(USER_DS); return fs; } static inline void force_uaccess_end(mm_segment_t oldfs) { set_fs(oldfs); } #else /* CONFIG_SET_FS */ typedef struct { /* empty dummy */ } mm_segment_t; #ifndef TASK_SIZE_MAX #define TASK_SIZE_MAX TASK_SIZE #endif #define uaccess_kernel() (false) #define user_addr_max() (TASK_SIZE_MAX) static inline mm_segment_t force_uaccess_begin(void) { return (mm_segment_t) { }; } static inline void force_uaccess_end(mm_segment_t oldfs) { } #endif /* CONFIG_SET_FS */ /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } #ifdef INLINE_COPY_FROM_USER static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } #else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (likely(check_copy_size(to, n, false))) n = _copy_from_user(to, from, n); return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (likely(check_copy_size(from, n, true))) n = _copy_to_user(to, from, n); return n; } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(to, n) && access_ok(from, n)) n = raw_copy_in_user(to, from, n); return n; } #endif #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 2 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | /* 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 of the Internet Protocol. * * Version: @(#)in.h 1.0.1 04/21/93 * * Authors: Original taken from the GNU Project <netinet/in.h> file. * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IN_H #define _LINUX_IN_H #include <linux/errno.h> #include <uapi/linux/in.h> static inline int proto_ports_offset(int proto) { switch (proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_DCCP: case IPPROTO_ESP: /* SPI */ case IPPROTO_SCTP: case IPPROTO_UDPLITE: return 0; case IPPROTO_AH: /* SPI */ return 4; default: return -EINVAL; } } static inline bool ipv4_is_loopback(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x7f000000); } static inline bool ipv4_is_multicast(__be32 addr) { return (addr & htonl(0xf0000000)) == htonl(0xe0000000); } static inline bool ipv4_is_local_multicast(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xe0000000); } static inline bool ipv4_is_lbcast(__be32 addr) { /* limited broadcast */ return addr == htonl(INADDR_BROADCAST); } static inline bool ipv4_is_all_snoopers(__be32 addr) { return addr == htonl(INADDR_ALLSNOOPERS_GROUP); } static inline bool ipv4_is_zeronet(__be32 addr) { return (addr == 0); } /* Special-Use IPv4 Addresses (RFC3330) */ static inline bool ipv4_is_private_10(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x0a000000); } static inline bool ipv4_is_private_172(__be32 addr) { return (addr & htonl(0xfff00000)) == htonl(0xac100000); } static inline bool ipv4_is_private_192(__be32 addr) { return (addr & htonl(0xffff0000)) == htonl(0xc0a80000); } static inline bool ipv4_is_linklocal_169(__be32 addr) { return (addr & htonl(0xffff0000)) == htonl(0xa9fe0000); } static inline bool ipv4_is_anycast_6to4(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xc0586300); } static inline bool ipv4_is_test_192(__be32 addr) { return (addr & htonl(0xffffff00)) == htonl(0xc0000200); } static inline bool ipv4_is_test_198(__be32 addr) { return (addr & htonl(0xfffe0000)) == htonl(0xc6120000); } #endif /* _LINUX_IN_H */ |
| 91 91 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KERNEL_PRINTK__ #define __KERNEL_PRINTK__ #include <stdarg.h> #include <linux/init.h> #include <linux/kern_levels.h> #include <linux/linkage.h> #include <linux/cache.h> #include <linux/ratelimit_types.h> extern const char linux_banner[]; extern const char linux_proc_banner[]; extern int oops_in_progress; /* If set, an oops, panic(), BUG() or die() is in progress */ #define PRINTK_MAX_SINGLE_HEADER_LEN 2 static inline int printk_get_level(const char *buffer) { if (buffer[0] == KERN_SOH_ASCII && buffer[1]) { switch (buffer[1]) { case '0' ... '7': case 'c': /* KERN_CONT */ return buffer[1]; } } return 0; } static inline const char *printk_skip_level(const char *buffer) { if (printk_get_level(buffer)) return buffer + 2; return buffer; } static inline const char *printk_skip_headers(const char *buffer) { while (printk_get_level(buffer)) buffer = printk_skip_level(buffer); return buffer; } #define CONSOLE_EXT_LOG_MAX 8192 /* printk's without a loglevel use this.. */ #define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ #define CONSOLE_LOGLEVEL_MIN 1 /* Minimum loglevel we let people use */ #define CONSOLE_LOGLEVEL_DEBUG 10 /* issue debug messages */ #define CONSOLE_LOGLEVEL_MOTORMOUTH 15 /* You can't shut this one up */ /* * Default used to be hard-coded at 7, quiet used to be hardcoded at 4, * we're now allowing both to be set from kernel config. */ #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT #define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET extern int console_printk[]; #define console_loglevel (console_printk[0]) #define default_message_loglevel (console_printk[1]) #define minimum_console_loglevel (console_printk[2]) #define default_console_loglevel (console_printk[3]) static inline void console_silent(void) { console_loglevel = CONSOLE_LOGLEVEL_SILENT; } static inline void console_verbose(void) { if (console_loglevel) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 extern char devkmsg_log_str[]; struct ctl_table; extern int suppress_printk; struct va_format { const char *fmt; va_list *va; }; /* * FW_BUG * Add this to a message where you are sure the firmware is buggy or behaves * really stupid or out of spec. Be aware that the responsible BIOS developer * should be able to fix this issue or at least get a concrete idea of the * problem by reading your message without the need of looking at the kernel * code. * * Use it for definite and high priority BIOS bugs. * * FW_WARN * Use it for not that clear (e.g. could the kernel messed up things already?) * and medium priority BIOS bugs. * * FW_INFO * Use this one if you want to tell the user or vendor about something * suspicious, but generally harmless related to the firmware. * * Use it for information or very low priority BIOS bugs. */ #define FW_BUG "[Firmware Bug]: " #define FW_WARN "[Firmware Warn]: " #define FW_INFO "[Firmware Info]: " /* * HW_ERR * Add this to a message for hardware errors, so that user can report * it to hardware vendor instead of LKML or software vendor. */ #define HW_ERR "[Hardware Error]: " /* * DEPRECATED * Add this to a message whenever you want to warn user space about the use * of a deprecated aspect of an API so they can stop using it */ #define DEPRECATED "[Deprecated]: " /* * Dummy printk for disabled debugging statements to use whilst maintaining * gcc's format checking. */ #define no_printk(fmt, ...) \ ({ \ if (0) \ printk(fmt, ##__VA_ARGS__); \ 0; \ }) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) void early_printk(const char *fmt, ...); #else static inline __printf(1, 2) __cold void early_printk(const char *s, ...) { } #endif #ifdef CONFIG_PRINTK_NMI extern void printk_nmi_enter(void); extern void printk_nmi_exit(void); extern void printk_nmi_direct_enter(void); extern void printk_nmi_direct_exit(void); #else static inline void printk_nmi_enter(void) { } static inline void printk_nmi_exit(void) { } static inline void printk_nmi_direct_enter(void) { } static inline void printk_nmi_direct_exit(void) { } #endif /* PRINTK_NMI */ struct dev_printk_info; #ifdef CONFIG_PRINTK asmlinkage __printf(4, 0) int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args); asmlinkage __printf(1, 0) int vprintk(const char *fmt, va_list args); asmlinkage __printf(1, 2) __cold int printk(const char *fmt, ...); /* * Special printk facility for scheduler/timekeeping use only, _DO_NOT_USE_ ! */ __printf(1, 2) __cold int printk_deferred(const char *fmt, ...); /* * Please don't use printk_ratelimit(), because it shares ratelimiting state * with all other unrelated printk_ratelimit() callsites. Instead use * printk_ratelimited() or plain old __ratelimit(). */ extern int __printk_ratelimit(const char *func); #define printk_ratelimit() __printk_ratelimit(__func__) extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec); extern int printk_delay_msec; extern int dmesg_restrict; extern int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos); extern void wake_up_klogd(void); char *log_buf_addr_get(void); u32 log_buf_len_get(void); void log_buf_vmcoreinfo_setup(void); void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; extern void printk_safe_flush(void); extern void printk_safe_flush_on_panic(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) { return 0; } static inline __printf(1, 2) __cold int printk(const char *s, ...) { return 0; } static inline __printf(1, 2) __cold int printk_deferred(const char *s, ...) { return 0; } static inline int printk_ratelimit(void) { return 0; } static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msec) { return false; } static inline void wake_up_klogd(void) { } static inline char *log_buf_addr_get(void) { return NULL; } static inline u32 log_buf_len_get(void) { return 0; } static inline void log_buf_vmcoreinfo_setup(void) { } static inline void setup_log_buf(int early) { } static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...) { } static inline void dump_stack_print_info(const char *log_lvl) { } static inline void show_regs_print_info(const char *log_lvl) { } static inline void dump_stack_lvl(const char *log_lvl) { } static inline void dump_stack(void) { } static inline void printk_safe_flush(void) { } static inline void printk_safe_flush_on_panic(void) { } #endif extern int kptr_restrict; /** * pr_fmt - used by the pr_*() macros to generate the printk format string * @fmt: format string passed from a pr_*() macro * * This macro can be used to generate a unified format string for pr_*() * macros. A common use is to prefix all pr_*() messages in a file with a common * string. For example, defining this at the top of a source file: * * #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt * * would prefix all pr_info, pr_emerg... messages in the file with the module * name. */ #ifndef pr_fmt #define pr_fmt(fmt) fmt #endif /** * pr_emerg - Print an emergency-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_EMERG loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_emerg(fmt, ...) \ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) /** * pr_alert - Print an alert-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ALERT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_alert(fmt, ...) \ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_crit - Print a critical-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CRIT loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_crit(fmt, ...) \ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) /** * pr_err - Print an error-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_ERR loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_err(fmt, ...) \ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) /** * pr_warn - Print a warning-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_WARNING loglevel. It uses pr_fmt() * to generate the format string. */ #define pr_warn(fmt, ...) \ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) /** * pr_notice - Print a notice-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_NOTICE loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_notice(fmt, ...) \ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) /** * pr_info - Print an info-level message * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_INFO loglevel. It uses pr_fmt() to * generate the format string. */ #define pr_info(fmt, ...) \ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /** * pr_cont - Continues a previous log message in the same line. * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_CONT loglevel. It should only be * used when continuing a log message with no newline ('\n') enclosed. Otherwise * it defaults back to KERN_DEFAULT loglevel. */ #define pr_cont(fmt, ...) \ printk(KERN_CONT fmt, ##__VA_ARGS__) /** * pr_devel - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to a printk with KERN_DEBUG loglevel if DEBUG is * defined. Otherwise it does nothing. * * It uses pr_fmt() to generate the format string. */ #ifdef DEBUG #define pr_devel(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #include <linux/dynamic_debug.h> /** * pr_debug - Print a debug-level message conditionally * @fmt: format string * @...: arguments for the format string * * This macro expands to dynamic_pr_debug() if CONFIG_DYNAMIC_DEBUG is * set. Otherwise, if DEBUG is defined, it's equivalent to a printk with * KERN_DEBUG loglevel. If DEBUG is not defined it does nothing. * * It uses pr_fmt() to generate the format string (dynamic_pr_debug() uses * pr_fmt() internally). */ #define pr_debug(fmt, ...) \ dynamic_pr_debug(fmt, ##__VA_ARGS__) #elif defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * Print a one-time message (analogous to WARN_ONCE() et al): */ #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ ({ \ static bool __section(".data.once") __print_once; \ bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ __print_once = true; \ printk(fmt, ##__VA_ARGS__); \ } \ unlikely(__ret_print_once); \ }) #define printk_deferred_once(fmt, ...) \ ({ \ static bool __section(".data.once") __print_once; \ bool __ret_print_once = !__print_once; \ \ if (!__print_once) { \ __print_once = true; \ printk_deferred(fmt, ##__VA_ARGS__); \ } \ unlikely(__ret_print_once); \ }) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_once(fmt, ...) \ printk_once(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_once(fmt, ...) \ printk_once(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_once(fmt, ...) \ printk_once(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_once(fmt, ...) \ printk_once(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_once(fmt, ...) \ printk_once(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_once(fmt, ...) \ printk_once(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_once(fmt, ...) \ printk_once(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_once, don't do that... */ #if defined(DEBUG) #define pr_devel_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(DEBUG) #define pr_debug_once(fmt, ...) \ printk_once(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_once(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* * ratelimited messages with local ratelimit_state, * no local ratelimit_state used in the !PRINTK case */ #ifdef CONFIG_PRINTK #define printk_ratelimited(fmt, ...) \ ({ \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ printk(fmt, ##__VA_ARGS__); \ }) #else #define printk_ratelimited(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) #endif #define pr_emerg_ratelimited(fmt, ...) \ printk_ratelimited(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) #define pr_alert_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) #define pr_crit_ratelimited(fmt, ...) \ printk_ratelimited(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) #define pr_err_ratelimited(fmt, ...) \ printk_ratelimited(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) #define pr_warn_ratelimited(fmt, ...) \ printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) #define pr_notice_ratelimited(fmt, ...) \ printk_ratelimited(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) #define pr_info_ratelimited(fmt, ...) \ printk_ratelimited(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* no pr_cont_ratelimited, don't do that... */ #if defined(DEBUG) #define pr_devel_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_devel_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif /* If you are writing a driver, please use dev_dbg instead */ #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) /* descriptor check is first to prevent flooding with "callbacks suppressed" */ #define pr_debug_ratelimited(fmt, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ __ratelimit(&_rs)) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define pr_debug_ratelimited(fmt, ...) \ printk_ratelimited(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #else #define pr_debug_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif extern const struct file_operations kmsg_fops; enum { DUMP_PREFIX_NONE, DUMP_PREFIX_ADDRESS, DUMP_PREFIX_OFFSET }; extern int hex_dump_to_buffer(const void *buf, size_t len, int rowsize, int groupsize, char *linebuf, size_t linebuflen, bool ascii); #ifdef CONFIG_PRINTK extern void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); #else static inline void print_hex_dump(const char *level, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, const void *buf, size_t len) { } #endif #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #elif defined(DEBUG) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) #else static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii) { } #endif /** * print_hex_dump_bytes - shorthand form of print_hex_dump() with default params * @prefix_str: string to prefix each line with; * caller supplies trailing spaces for alignment if desired * @prefix_type: controls whether prefix of an offset, address, or none * is printed (%DUMP_PREFIX_OFFSET, %DUMP_PREFIX_ADDRESS, %DUMP_PREFIX_NONE) * @buf: data blob to dump * @len: number of bytes in the @buf * * Calls print_hex_dump(), with log level of KERN_DEBUG, * rowsize of 16, groupsize of 1, and ASCII output included. */ #define print_hex_dump_bytes(prefix_str, prefix_type, buf, len) \ print_hex_dump_debug(prefix_str, prefix_type, 16, 1, buf, len, true) #endif |
| 1183 1184 819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "TEE" target extension for Xtables * Copyright © Sebastian Claßen, 2007 * Jan Engelhardt, 2007-2010 * * based on ipt_ROUTE.c from Cédric de Launois * <delaunois@info.ucl.be> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/route.h> #include <linux/netfilter/x_tables.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/route.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #include <net/netfilter/ipv6/nf_dup_ipv6.h> #include <linux/netfilter/xt_TEE.h> struct xt_tee_priv { struct list_head list; struct xt_tee_tginfo *tginfo; int oif; }; static unsigned int tee_net_id __read_mostly; static const union nf_inet_addr tee_zero_address; struct tee_net { struct list_head priv_list; /* lock protects the priv_list */ struct mutex lock; }; static unsigned int tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv4(xt_net(par), skb, xt_hooknum(par), &info->gw.in, oif); return XT_CONTINUE; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv6(xt_net(par), skb, xt_hooknum(par), &info->gw.in6, oif); return XT_CONTINUE; } #endif static int tee_netdev_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 tee_net *tn = net_generic(net, tee_net_id); struct xt_tee_priv *priv; mutex_lock(&tn->lock); list_for_each_entry(priv, &tn->priv_list, list) { switch (event) { case NETDEV_REGISTER: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; break; case NETDEV_UNREGISTER: if (dev->ifindex == priv->oif) priv->oif = -1; break; case NETDEV_CHANGENAME: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; else if (dev->ifindex == priv->oif) priv->oif = -1; break; } } mutex_unlock(&tn->lock); return NOTIFY_DONE; } static int tee_tg_check(const struct xt_tgchk_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; struct xt_tee_priv *priv; /* 0.0.0.0 and :: not allowed */ if (memcmp(&info->gw, &tee_zero_address, sizeof(tee_zero_address)) == 0) return -EINVAL; if (info->oif[0]) { struct net_device *dev; if (info->oif[sizeof(info->oif)-1] != '\0') return -EINVAL; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) return -ENOMEM; priv->tginfo = info; priv->oif = -1; info->priv = priv; dev = dev_get_by_name(par->net, info->oif); if (dev) { priv->oif = dev->ifindex; dev_put(dev); } mutex_lock(&tn->lock); list_add(&priv->list, &tn->priv_list); mutex_unlock(&tn->lock); } else info->priv = NULL; static_key_slow_inc(&xt_tee_enabled); return 0; } static void tee_tg_destroy(const struct xt_tgdtor_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; if (info->priv) { mutex_lock(&tn->lock); list_del(&info->priv->list); mutex_unlock(&tn->lock); kfree(info->priv); } static_key_slow_dec(&xt_tee_enabled); } static struct xt_target tee_tg_reg[] __read_mostly = { { .name = "TEE", .revision = 1, .family = NFPROTO_IPV4, .target = tee_tg4, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "TEE", .revision = 1, .family = NFPROTO_IPV6, .target = tee_tg6, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __net_init tee_net_init(struct net *net) { struct tee_net *tn = net_generic(net, tee_net_id); INIT_LIST_HEAD(&tn->priv_list); mutex_init(&tn->lock); return 0; } static struct pernet_operations tee_net_ops = { .init = tee_net_init, .id = &tee_net_id, .size = sizeof(struct tee_net), }; static struct notifier_block tee_netdev_notifier = { .notifier_call = tee_netdev_event, }; static int __init tee_tg_init(void) { int ret; ret = register_pernet_subsys(&tee_net_ops); if (ret < 0) return ret; ret = xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); if (ret < 0) goto cleanup_subsys; ret = register_netdevice_notifier(&tee_netdev_notifier); if (ret < 0) goto unregister_targets; return 0; unregister_targets: xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); cleanup_subsys: unregister_pernet_subsys(&tee_net_ops); return ret; } static void __exit tee_tg_exit(void) { unregister_netdevice_notifier(&tee_netdev_notifier); xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); unregister_pernet_subsys(&tee_net_ops); } module_init(tee_tg_init); module_exit(tee_tg_exit); MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: Reroute packet copy"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_TEE"); MODULE_ALIAS("ip6t_TEE"); |
| 1184 1178 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2007-2012 Siemens AG * * Written by: * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Sergey Lapin <slapin@ossfans.org> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/netdevice.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/ieee802154.h> #include <net/nl802154.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/cfg802154.h> #include "ieee802154_i.h" #include "driver-ops.h" int mac802154_wpan_update_llsec(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; int rc = 0; if (ops->llsec) { struct ieee802154_llsec_params params; int changed = 0; params.pan_id = wpan_dev->pan_id; changed |= IEEE802154_LLSEC_PARAM_PAN_ID; params.hwaddr = wpan_dev->extended_addr; changed |= IEEE802154_LLSEC_PARAM_HWADDR; rc = ops->llsec->set_params(dev, ¶ms, changed); } return rc; } static int mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct sockaddr_ieee802154 *sa = (struct sockaddr_ieee802154 *)&ifr->ifr_addr; int err = -ENOIOCTLCMD; if (cmd != SIOCGIFADDR && cmd != SIOCSIFADDR) return err; rtnl_lock(); switch (cmd) { case SIOCGIFADDR: { u16 pan_id, short_addr; pan_id = le16_to_cpu(wpan_dev->pan_id); short_addr = le16_to_cpu(wpan_dev->short_addr); if (pan_id == IEEE802154_PANID_BROADCAST || short_addr == IEEE802154_ADDR_BROADCAST) { err = -EADDRNOTAVAIL; break; } sa->family = AF_IEEE802154; sa->addr.addr_type = IEEE802154_ADDR_SHORT; sa->addr.pan_id = pan_id; sa->addr.short_addr = short_addr; err = 0; break; } case SIOCSIFADDR: if (netif_running(dev)) { rtnl_unlock(); return -EBUSY; } dev_warn(&dev->dev, "Using DEBUGing ioctl SIOCSIFADDR isn't recommended!\n"); if (sa->family != AF_IEEE802154 || sa->addr.addr_type != IEEE802154_ADDR_SHORT || sa->addr.pan_id == IEEE802154_PANID_BROADCAST || sa->addr.short_addr == IEEE802154_ADDR_BROADCAST || sa->addr.short_addr == IEEE802154_ADDR_UNDEF) { err = -EINVAL; break; } wpan_dev->pan_id = cpu_to_le16(sa->addr.pan_id); wpan_dev->short_addr = cpu_to_le16(sa->addr.short_addr); err = mac802154_wpan_update_llsec(dev); break; } rtnl_unlock(); return err; } static int mac802154_wpan_mac_addr(struct net_device *dev, void *p) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct sockaddr *addr = p; __le64 extended_addr; if (netif_running(dev)) return -EBUSY; /* lowpan need to be down for update * SLAAC address after ifup */ if (sdata->wpan_dev.lowpan_dev) { if (netif_running(sdata->wpan_dev.lowpan_dev)) return -EBUSY; } ieee802154_be64_to_le64(&extended_addr, addr->sa_data); if (!ieee802154_is_valid_extended_unicast_addr(extended_addr)) return -EINVAL; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); sdata->wpan_dev.extended_addr = extended_addr; /* update lowpan interface mac address when * wpan mac has been changed */ if (sdata->wpan_dev.lowpan_dev) memcpy(sdata->wpan_dev.lowpan_dev->dev_addr, dev->dev_addr, dev->addr_len); return mac802154_wpan_update_llsec(dev); } static int ieee802154_setup_hw(struct ieee802154_sub_if_data *sdata) { struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { ret = drv_set_promiscuous_mode(local, wpan_dev->promiscuous_mode); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_AFILT) { ret = drv_set_pan_id(local, wpan_dev->pan_id); if (ret < 0) return ret; ret = drv_set_extended_addr(local, wpan_dev->extended_addr); if (ret < 0) return ret; ret = drv_set_short_addr(local, wpan_dev->short_addr); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_LBT) { ret = drv_set_lbt_mode(local, wpan_dev->lbt); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { ret = drv_set_csma_params(local, wpan_dev->min_be, wpan_dev->max_be, wpan_dev->csma_retries); if (ret < 0) return ret; } if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) { ret = drv_set_max_frame_retries(local, wpan_dev->frame_retries); if (ret < 0) return ret; } return 0; } static int mac802154_slave_open(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; int res; ASSERT_RTNL(); set_bit(SDATA_STATE_RUNNING, &sdata->state); if (!local->open_count) { res = ieee802154_setup_hw(sdata); if (res) goto err; res = drv_start(local); if (res) goto err; } local->open_count++; netif_start_queue(dev); return 0; err: /* might already be clear but that doesn't matter */ clear_bit(SDATA_STATE_RUNNING, &sdata->state); return res; } static int ieee802154_check_mac_settings(struct ieee802154_local *local, struct wpan_dev *wpan_dev, struct wpan_dev *nwpan_dev) { ASSERT_RTNL(); if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { if (wpan_dev->promiscuous_mode != nwpan_dev->promiscuous_mode) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_AFILT) { if (wpan_dev->pan_id != nwpan_dev->pan_id || wpan_dev->short_addr != nwpan_dev->short_addr || wpan_dev->extended_addr != nwpan_dev->extended_addr) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_CSMA_PARAMS) { if (wpan_dev->min_be != nwpan_dev->min_be || wpan_dev->max_be != nwpan_dev->max_be || wpan_dev->csma_retries != nwpan_dev->csma_retries) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_FRAME_RETRIES) { if (wpan_dev->frame_retries != nwpan_dev->frame_retries) return -EBUSY; } if (local->hw.flags & IEEE802154_HW_LBT) { if (wpan_dev->lbt != nwpan_dev->lbt) return -EBUSY; } return 0; } static int ieee802154_check_concurrent_iface(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype iftype) { struct ieee802154_local *local = sdata->local; struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_sub_if_data *nsdata; /* we hold the RTNL here so can safely walk the list */ list_for_each_entry(nsdata, &local->interfaces, list) { if (nsdata != sdata && ieee802154_sdata_running(nsdata)) { int ret; /* TODO currently we don't support multiple node types * we need to run skb_clone at rx path. Check if there * exist really an use case if we need to support * multiple node types at the same time. */ if (wpan_dev->iftype == NL802154_IFTYPE_NODE && nsdata->wpan_dev.iftype == NL802154_IFTYPE_NODE) return -EBUSY; /* check all phy mac sublayer settings are the same. * We have only one phy, different values makes trouble. */ ret = ieee802154_check_mac_settings(local, wpan_dev, &nsdata->wpan_dev); if (ret < 0) return ret; } } return 0; } static int mac802154_wpan_open(struct net_device *dev) { int rc; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; rc = ieee802154_check_concurrent_iface(sdata, wpan_dev->iftype); if (rc < 0) return rc; return mac802154_slave_open(dev); } static int mac802154_slave_close(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; ASSERT_RTNL(); netif_stop_queue(dev); local->open_count--; clear_bit(SDATA_STATE_RUNNING, &sdata->state); if (!local->open_count) ieee802154_stop_device(local); return 0; } static int mac802154_set_header_security(struct ieee802154_sub_if_data *sdata, struct ieee802154_hdr *hdr, const struct ieee802154_mac_cb *cb) { struct ieee802154_llsec_params params; u8 level; mac802154_llsec_get_params(&sdata->sec, ¶ms); if (!params.enabled && cb->secen_override && cb->secen) return -EINVAL; if (!params.enabled || (cb->secen_override && !cb->secen) || !params.out_level) return 0; if (cb->seclevel_override && !cb->seclevel) return -EINVAL; level = cb->seclevel_override ? cb->seclevel : params.out_level; hdr->fc.security_enabled = 1; hdr->sec.level = level; hdr->sec.key_id_mode = params.out_key.mode; if (params.out_key.mode == IEEE802154_SCF_KEY_SHORT_INDEX) hdr->sec.short_src = params.out_key.short_source; else if (params.out_key.mode == IEEE802154_SCF_KEY_HW_INDEX) hdr->sec.extended_src = params.out_key.extended_source; hdr->sec.key_id = params.out_key.id; return 0; } static int ieee802154_header_create(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, const struct ieee802154_addr *saddr, unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_mac_cb *cb = mac_cb(skb); int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); hdr.fc.type = cb->type; hdr.fc.security_enabled = cb->secen; hdr.fc.ack_request = cb->ackreq; hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; if (mac802154_set_header_security(sdata, &hdr, cb) < 0) return -EINVAL; if (!saddr) { if (wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST) || wpan_dev->short_addr == cpu_to_le16(IEEE802154_ADDR_UNDEF) || wpan_dev->pan_id == cpu_to_le16(IEEE802154_PANID_BROADCAST)) { hdr.source.mode = IEEE802154_ADDR_LONG; hdr.source.extended_addr = wpan_dev->extended_addr; } else { hdr.source.mode = IEEE802154_ADDR_SHORT; hdr.source.short_addr = wpan_dev->short_addr; } hdr.source.pan_id = wpan_dev->pan_id; } else { hdr.source = *(const struct ieee802154_addr *)saddr; } hdr.dest = *(const struct ieee802154_addr *)daddr; hlen = ieee802154_hdr_push(skb, &hdr); if (hlen < 0) return -EINVAL; skb_reset_mac_header(skb); skb->mac_len = hlen; if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; } static const struct wpan_dev_header_ops ieee802154_header_ops = { .create = ieee802154_header_create, }; /* This header create functionality assumes a 8 byte array for * source and destination pointer at maximum. To adapt this for * the 802.15.4 dataframe header we use extended address handling * here only and intra pan connection. fc fields are mostly fallback * handling. For provide dev_hard_header for dgram sockets. */ static int mac802154_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { struct ieee802154_hdr hdr; struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct ieee802154_mac_cb cb = { }; int hlen; if (!daddr) return -EINVAL; memset(&hdr.fc, 0, sizeof(hdr.fc)); hdr.fc.type = IEEE802154_FC_TYPE_DATA; hdr.fc.ack_request = wpan_dev->ackreq; hdr.seq = atomic_inc_return(&dev->ieee802154_ptr->dsn) & 0xFF; /* TODO currently a workaround to give zero cb block to set * security parameters defaults according MIB. */ if (mac802154_set_header_security(sdata, &hdr, &cb) < 0) return -EINVAL; hdr.dest.pan_id = wpan_dev->pan_id; hdr.dest.mode = IEEE802154_ADDR_LONG; ieee802154_be64_to_le64(&hdr.dest.extended_addr, daddr); hdr.source.pan_id = hdr.dest.pan_id; hdr.source.mode = IEEE802154_ADDR_LONG; if (!saddr) hdr.source.extended_addr = wpan_dev->extended_addr; else ieee802154_be64_to_le64(&hdr.source.extended_addr, saddr); hlen = ieee802154_hdr_push(skb, &hdr); if (hlen < 0) return -EINVAL; skb_reset_mac_header(skb); skb->mac_len = hlen; if (len > ieee802154_max_payload(&hdr)) return -EMSGSIZE; return hlen; } static int mac802154_header_parse(const struct sk_buff *skb, unsigned char *haddr) { struct ieee802154_hdr hdr; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) { pr_debug("malformed packet\n"); return 0; } if (hdr.source.mode == IEEE802154_ADDR_LONG) { ieee802154_le64_to_be64(haddr, &hdr.source.extended_addr); return IEEE802154_EXTENDED_ADDR_LEN; } return 0; } static const struct header_ops mac802154_header_ops = { .create = mac802154_header_create, .parse = mac802154_header_parse, }; static const struct net_device_ops mac802154_wpan_ops = { .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = ieee802154_subif_start_xmit, .ndo_do_ioctl = mac802154_wpan_ioctl, .ndo_set_mac_address = mac802154_wpan_mac_addr, }; static const struct net_device_ops mac802154_monitor_ops = { .ndo_open = mac802154_wpan_open, .ndo_stop = mac802154_slave_close, .ndo_start_xmit = ieee802154_monitor_start_xmit, }; static void mac802154_wpan_free(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); mac802154_llsec_destroy(&sdata->sec); } static void ieee802154_if_setup(struct net_device *dev) { dev->addr_len = IEEE802154_EXTENDED_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_EXTENDED_ADDR_LEN); /* Let hard_header_len set to IEEE802154_MIN_HEADER_LEN. AF_PACKET * will not send frames without any payload, but ack frames * has no payload, so substract one that we can send a 3 bytes * frame. The xmit callback assumes at least a hard header where two * bytes fc and sequence field are set. */ dev->hard_header_len = IEEE802154_MIN_HEADER_LEN - 1; /* The auth_tag header is for security and places in private payload * room of mac frame which stucks between payload and FCS field. */ dev->needed_tailroom = IEEE802154_MAX_AUTH_TAG_LEN + IEEE802154_FCS_LEN; /* The mtu size is the payload without mac header in this case. * We have a dynamic length header with a minimum header length * which is hard_header_len. In this case we let mtu to the size * of maximum payload which is IEEE802154_MTU - IEEE802154_FCS_LEN - * hard_header_len. The FCS which is set by hardware or ndo_start_xmit * and the minimum mac header which can be evaluated inside driver * layer. The rest of mac header will be part of payload if greater * than hard_header_len. */ dev->mtu = IEEE802154_MTU - IEEE802154_FCS_LEN - dev->hard_header_len; dev->tx_queue_len = 300; dev->flags = IFF_NOARP | IFF_BROADCAST; } static int ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, enum nl802154_iftype type) { struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; u8 tmp; /* set some type-dependent values */ sdata->wpan_dev.iftype = type; get_random_bytes(&tmp, sizeof(tmp)); atomic_set(&wpan_dev->bsn, tmp); get_random_bytes(&tmp, sizeof(tmp)); atomic_set(&wpan_dev->dsn, tmp); /* defaults per 802.15.4-2011 */ wpan_dev->min_be = 3; wpan_dev->max_be = 5; wpan_dev->csma_retries = 4; wpan_dev->frame_retries = 3; wpan_dev->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); wpan_dev->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); switch (type) { case NL802154_IFTYPE_NODE: ieee802154_be64_to_le64(&wpan_dev->extended_addr, sdata->dev->dev_addr); sdata->dev->header_ops = &mac802154_header_ops; sdata->dev->needs_free_netdev = true; sdata->dev->priv_destructor = mac802154_wpan_free; sdata->dev->netdev_ops = &mac802154_wpan_ops; sdata->dev->ml_priv = &mac802154_mlme_wpan; wpan_dev->promiscuous_mode = false; wpan_dev->header_ops = &ieee802154_header_ops; mutex_init(&sdata->sec_mtx); mac802154_llsec_init(&sdata->sec); ret = mac802154_wpan_update_llsec(sdata->dev); if (ret < 0) return ret; break; case NL802154_IFTYPE_MONITOR: sdata->dev->needs_free_netdev = true; sdata->dev->netdev_ops = &mac802154_monitor_ops; wpan_dev->promiscuous_mode = true; break; default: BUG(); } return 0; } struct net_device * ieee802154_if_add(struct ieee802154_local *local, const char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { struct net_device *ndev = NULL; struct ieee802154_sub_if_data *sdata = NULL; int ret = -ENOMEM; ASSERT_RTNL(); ndev = alloc_netdev(sizeof(*sdata), name, name_assign_type, ieee802154_if_setup); if (!ndev) return ERR_PTR(-ENOMEM); ndev->needed_headroom = local->hw.extra_tx_headroom + IEEE802154_MAX_HEADER_LEN; ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) goto err; ieee802154_le64_to_be64(ndev->perm_addr, &local->hw.phy->perm_extended_addr); switch (type) { case NL802154_IFTYPE_NODE: ndev->type = ARPHRD_IEEE802154; if (ieee802154_is_valid_extended_unicast_addr(extended_addr)) ieee802154_le64_to_be64(ndev->dev_addr, &extended_addr); else memcpy(ndev->dev_addr, ndev->perm_addr, IEEE802154_EXTENDED_ADDR_LEN); break; case NL802154_IFTYPE_MONITOR: ndev->type = ARPHRD_IEEE802154_MONITOR; break; default: ret = -EINVAL; goto err; } /* TODO check this */ SET_NETDEV_DEV(ndev, &local->phy->dev); dev_net_set(ndev, wpan_phy_net(local->hw.phy)); sdata = netdev_priv(ndev); ndev->ieee802154_ptr = &sdata->wpan_dev; memcpy(sdata->name, ndev->name, IFNAMSIZ); sdata->dev = ndev; sdata->wpan_dev.wpan_phy = local->hw.phy; sdata->local = local; /* setup type-dependent data */ ret = ieee802154_setup_sdata(sdata, type); if (ret) goto err; ret = register_netdevice(ndev); if (ret < 0) goto err; mutex_lock(&local->iflist_mtx); list_add_tail_rcu(&sdata->list, &local->interfaces); mutex_unlock(&local->iflist_mtx); return ndev; err: free_netdev(ndev); return ERR_PTR(ret); } void ieee802154_if_remove(struct ieee802154_sub_if_data *sdata) { ASSERT_RTNL(); mutex_lock(&sdata->local->iflist_mtx); list_del_rcu(&sdata->list); mutex_unlock(&sdata->local->iflist_mtx); synchronize_rcu(); unregister_netdevice(sdata->dev); } void ieee802154_remove_interfaces(struct ieee802154_local *local) { struct ieee802154_sub_if_data *sdata, *tmp; mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { list_del(&sdata->list); unregister_netdevice(sdata->dev); } mutex_unlock(&local->iflist_mtx); } static int netdev_notify(struct notifier_block *nb, unsigned long state, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ieee802154_sub_if_data *sdata; if (state != NETDEV_CHANGENAME) return NOTIFY_DONE; if (!dev->ieee802154_ptr || !dev->ieee802154_ptr->wpan_phy) return NOTIFY_DONE; if (dev->ieee802154_ptr->wpan_phy->privid != mac802154_wpan_phy_privid) return NOTIFY_DONE; sdata = IEEE802154_DEV_TO_SUB_IF(dev); memcpy(sdata->name, dev->name, IFNAMSIZ); return NOTIFY_OK; } static struct notifier_block mac802154_netdev_notifier = { .notifier_call = netdev_notify, }; int ieee802154_iface_init(void) { return register_netdevice_notifier(&mac802154_netdev_notifier); } void ieee802154_iface_exit(void) { unregister_netdevice_notifier(&mac802154_netdev_notifier); } |
| 70 10 110 878 3 12 12 42 37 42 46 46 9 11 42 94 77 1269 5 51 1 2 51 7 134 333 4 72 3 70 3 203 228 259 124 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the AF_INET socket handler. * * Version: @(#)sock.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche <flla@stud.uni-sb.de> * * Fixes: * Alan Cox : Volatiles in skbuff pointers. See * skbuff comments. May be overdone, * better to prove they can be removed * than the reverse. * Alan Cox : Added a zapped field for tcp to note * a socket is reset and must stay shut up * Alan Cox : New fields for options * Pauline Middelink : identd support * Alan Cox : Eliminate low level recv/recvfrom * David S. Miller : New socket lookup architecture. * Steve Whitehouse: Default routines for sock_ops * Arnaldo C. Melo : removed net_pinfo, tp_pinfo and made * protinfo be just a void pointer, as the * protocol specific parts were moved to * respective headers and ipv4/v6, etc now * use private slabcaches for its socks * Pedro Hortas : New flags field for socket options */ #ifndef _SOCK_H #define _SOCK_H #include <linux/hardirq.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/timer.h> #include <linux/cache.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* struct sk_buff */ #include <linux/mm.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/page_counter.h> #include <linux/memcontrol.h> #include <linux/static_key.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/cgroup-defs.h> #include <linux/rbtree.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/l3mdev.h> #include <linux/android_kabi.h> #include <linux/android_vendor.h> /* * This structure really needs to be cleaned up. * Most of it is for TCP, and not used by any of * the other protocols. */ /* Define this to get the SOCK_DBG debugging facility. */ #define SOCK_DEBUGGING #ifdef SOCK_DEBUGGING #define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \ printk(KERN_DEBUG msg); } while (0) #else /* Validate arguments and do nothing */ static inline __printf(2, 3) void SOCK_DEBUG(const struct sock *sk, const char *msg, ...) { } #endif /* This is the per-socket lock. The spinlock provides a synchronization * between user contexts and software interrupt processing, whereas the * mini-semaphore synchronizes multiple users amongst themselves. */ typedef struct { spinlock_t slock; int owned; wait_queue_head_t wq; /* * We express the mutex-alike socket_lock semantics * to the lock validator by explicitly managing * the slock as a lock variant (in addition to * the slock itself): */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } socket_lock_t; struct sock; struct proto; struct net; typedef __u32 __bitwise __portpair; typedef __u64 __bitwise __addrpair; /** * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket * @skc_v6_daddr: IPV6 destination address * @skc_v6_rcv_saddr: IPV6 source address * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection * @skc_rx_queue_mapping: rx queue number for this connection * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @skc_listener: connection request listener socket (aka rsk_listener) * [union with @skc_flags] * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) * [union with @skc_incoming_cpu] * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header * for struct sock and struct inet_timewait_sock. */ struct sock_common { /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned * address on 64bit arches : cf INET_MATCH() */ union { __addrpair skc_addrpair; struct { __be32 skc_daddr; __be32 skc_rcv_saddr; }; }; union { unsigned int skc_hash; __u16 skc_u16hashes[2]; }; /* skc_dport && skc_num must be grouped as well */ union { __portpair skc_portpair; struct { __be16 skc_dport; __u16 skc_num; }; }; unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse:4; unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; struct hlist_node skc_portaddr_node; }; struct proto *skc_prot; possible_net_t skc_net; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr skc_v6_daddr; struct in6_addr skc_v6_rcv_saddr; #endif atomic64_t skc_cookie; /* following fields are padding to force * offset(struct sock, sk_refcnt) == 128 on 64bit arches * assuming IPV6 is enabled. We use this padding differently * for different kind of 'sockets' */ union { unsigned long skc_flags; struct sock *skc_listener; /* request_sock */ struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */ }; /* * fields between dontcopy_begin/dontcopy_end * are not copied in sock_copy() */ /* private: */ int skc_dontcopy_begin[0]; /* public: */ union { struct hlist_node skc_node; struct hlist_nulls_node skc_nulls_node; }; unsigned short skc_tx_queue_mapping; #ifdef CONFIG_XPS unsigned short skc_rx_queue_mapping; #endif union { int skc_incoming_cpu; u32 skc_rcv_wnd; u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */ }; refcount_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; union { u32 skc_rxhash; u32 skc_window_clamp; u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */ }; /* public: */ }; struct bpf_local_storage; /** * struct sock - network layer representation of sockets * @__sk_common: shared layout with inet_timewait_sock * @sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_kern_sock: True if sock is using kernel lock classes * @sk_rcvbuf: size of receive buffer in bytes * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags * @sk_write_queue: Packet sending queue * @sk_omem_alloc: "o" is "option" or "other" * @sk_wmem_queued: persistent queue size * @sk_forward_alloc: space allocated forward * @sk_napi_id: id of the last napi context to receive data for sk * @sk_ll_usec: usecs to busypoll when there is no data * @sk_allocation: allocation mode * @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler) * @sk_pacing_status: Pacing status (requested, handled by sch_fq) * @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE) * @sk_sndbuf: size of send buffer in bytes * @__sk_flags_offset: empty field used to determine location of bitfield * @sk_padding: unused element for alignment * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) * @sk_route_forced_caps: static, forced route capabilities * (set in tcp_init_sock()) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, * IPV6_ADDRFORM for instance) * @sk_err: last error * @sk_err_soft: errors that don't cause failure but are the cause of a * persistent failure not just 'timed out' * @sk_drops: raw/udp drops counter * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING socket options * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags */ struct sock { /* * Now struct inet_timewait_sock also uses sock_common, so please just * don't add nothing before this first member (__sk_common) --acme */ struct sock_common __sk_common; #define sk_node __sk_common.skc_node #define sk_nulls_node __sk_common.skc_nulls_node #define sk_refcnt __sk_common.skc_refcnt #define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping #ifdef CONFIG_XPS #define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping #endif #define sk_dontcopy_begin __sk_common.skc_dontcopy_begin #define sk_dontcopy_end __sk_common.skc_dontcopy_end #define sk_hash __sk_common.skc_hash #define sk_portpair __sk_common.skc_portpair #define sk_num __sk_common.skc_num #define sk_dport __sk_common.skc_dport #define sk_addrpair __sk_common.skc_addrpair #define sk_daddr __sk_common.skc_daddr #define sk_rcv_saddr __sk_common.skc_rcv_saddr #define sk_family __sk_common.skc_family #define sk_state __sk_common.skc_state #define sk_reuse __sk_common.skc_reuse #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot #define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie #define sk_incoming_cpu __sk_common.skc_incoming_cpu #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash socket_lock_t sk_lock; atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; struct sk_buff *sk_rx_skb_cache; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with * the per-socket spinlock held and requires low latency * access. Therefore we special case it's implementation. * Note : rmem_alloc is in this structure to fill a hole * on 64bit arches, not because its logically part of * backlog. */ struct { atomic_t rmem_alloc; int len; struct sk_buff *head; struct sk_buff *tail; } sk_backlog; #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_ll_usec; /* ===== mostly read cache line ===== */ unsigned int sk_napi_id; #endif int sk_rcvbuf; struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; /* private: */ struct socket_wq *sk_wq_raw; /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif struct dst_entry *sk_rx_dst; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; int sk_sndbuf; /* ===== cache line for TX ===== */ int sk_wmem_queued; refcount_t sk_wmem_alloc; unsigned long sk_tsq_flags; union { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; struct sk_buff *sk_tx_skb_cache; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; __u32 sk_dst_pending_confirm; u32 sk_pacing_status; /* see enum sk_pacing */ long sk_sndtimeo; struct timer_list sk_timer; __u32 sk_priority; __u32 sk_mark; unsigned long sk_pacing_rate; /* bytes per second */ unsigned long sk_max_pacing_rate; struct page_frag sk_frag; netdev_features_t sk_route_caps; netdev_features_t sk_route_nocaps; netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; __u32 sk_txhash; /* * Because of non atomicity rules, all * changes are protected by socket lock. */ u8 sk_padding : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, sk_userlocks : 4; u8 sk_pacing_shift; u16 sk_type; u16 sk_protocol; u16 sk_gso_max_segs; unsigned long sk_lingertime; struct proto *sk_prot_creator; rwlock_t sk_callback_lock; int sk_err, sk_err_soft; u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; #if IS_ENABLED(CONFIG_DEBUG_SPINLOCK) || IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC) spinlock_t sk_peer_lock; #else /* sk_peer_lock is in the ANDROID_KABI_RESERVE(1) field below */ #endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, sk_txtime_report_errors : 1, sk_txtime_unused : 6; struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY void *sk_security; #endif struct sock_cgroup_data sk_cgrp_data; struct mem_cgroup *sk_memcg; void (*sk_state_change)(struct sock *sk); void (*sk_data_ready)(struct sock *sk); void (*sk_write_space)(struct sock *sk); void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, struct net_device *dev, struct sk_buff *skb); #endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; #ifdef CONFIG_BPF_SYSCALL struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; #if IS_ENABLED(CONFIG_DEBUG_SPINLOCK) || IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC) ANDROID_KABI_RESERVE(1); #else ANDROID_KABI_USE(1, spinlock_t sk_peer_lock); #endif ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); ANDROID_KABI_RESERVE(5); ANDROID_KABI_RESERVE(6); ANDROID_KABI_RESERVE(7); ANDROID_KABI_RESERVE(8); ANDROID_OEM_DATA(1); }; enum sk_pacing { SK_PACING_NONE = 0, SK_PACING_NEEDED = 1, SK_PACING_FQ = 2, }; /* Pointer stored in sk_user_data might not be suitable for copying * when cloning the socket. For instance, it can point to a reference * counted object. sk_user_data bottom bit is set if pointer must not * be copied. */ #define SK_USER_DATA_NOCOPY 1UL #define SK_USER_DATA_BPF 2UL /* Managed by BPF */ #define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied * @sk: socket */ static inline bool sk_user_data_is_nocopy(const struct sock *sk) { return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); } #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) #define rcu_dereference_sk_user_data(sk) \ ({ \ void *__tmp = rcu_dereference(__sk_user_data((sk))); \ (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \ }) #define rcu_assign_sk_user_data(sk, ptr) \ ({ \ uintptr_t __tmp = (uintptr_t)(ptr); \ WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), __tmp); \ }) #define rcu_assign_sk_user_data_nocopy(sk, ptr) \ ({ \ uintptr_t __tmp = (uintptr_t)(ptr); \ WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), \ __tmp | SK_USER_DATA_NOCOPY); \ }) /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE * on a socket means that the socket will reuse everybody else's port * without looking at the other's sk_reuse value. */ #define SK_NO_REUSE 0 #define SK_CAN_REUSE 1 #define SK_FORCE_REUSE 2 int sk_set_peek_off(struct sock *sk, int val); static inline int sk_peek_offset(struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); } return 0; } static inline void sk_peek_offset_bwd(struct sock *sk, int val) { s32 off = READ_ONCE(sk->sk_peek_off); if (unlikely(off >= 0)) { off = max_t(s32, off - val, 0); WRITE_ONCE(sk->sk_peek_off, off); } } static inline void sk_peek_offset_fwd(struct sock *sk, int val) { sk_peek_offset_bwd(sk, -val); } /* * Hashed lists helper routines */ static inline struct sock *sk_entry(const struct hlist_node *node) { return hlist_entry(node, struct sock, sk_node); } static inline struct sock *__sk_head(const struct hlist_head *head) { return hlist_entry(head->first, struct sock, sk_node); } static inline struct sock *sk_head(const struct hlist_head *head) { return hlist_empty(head) ? NULL : __sk_head(head); } static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_entry(head->first, struct sock, sk_nulls_node); } static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head) { return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head); } static inline struct sock *sk_next(const struct sock *sk) { return hlist_entry_safe(sk->sk_node.next, struct sock, sk_node); } static inline struct sock *sk_nulls_next(const struct sock *sk) { return (!is_a_nulls(sk->sk_nulls_node.next)) ? hlist_nulls_entry(sk->sk_nulls_node.next, struct sock, sk_nulls_node) : NULL; } static inline bool sk_unhashed(const struct sock *sk) { return hlist_unhashed(&sk->sk_node); } static inline bool sk_hashed(const struct sock *sk) { return !sk_unhashed(sk); } static inline void sk_node_init(struct hlist_node *node) { node->pprev = NULL; } static inline void sk_nulls_node_init(struct hlist_nulls_node *node) { node->pprev = NULL; } static inline void __sk_del_node(struct sock *sk) { __hlist_del(&sk->sk_node); } /* NB: equivalent to hlist_del_init_rcu */ static inline bool __sk_del_node_init(struct sock *sk) { if (sk_hashed(sk)) { __sk_del_node(sk); sk_node_init(&sk->sk_node); return true; } return false; } /* Grab socket reference count. This operation is valid only when sk is ALREADY grabbed f.e. it is found in hash table or a list and the lookup is made under lock preventing hash table modifications. */ static __always_inline void sock_hold(struct sock *sk) { refcount_inc(&sk->sk_refcnt); } /* Ungrab socket in the context, which assumes that socket refcnt cannot hit zero, f.e. it is true in context of any socketcall. */ static __always_inline void __sock_put(struct sock *sk) { refcount_dec(&sk->sk_refcnt); } static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) static inline bool __sk_nulls_del_node_init_rcu(struct sock *sk) { if (sk_hashed(sk)) { hlist_nulls_del_init_rcu(&sk->sk_nulls_node); return true; } return false; } static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); if (rc) { /* paranoid for a while -acme */ WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } return rc; } static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); } static inline void sk_add_node(struct sock *sk, struct hlist_head *list) { sock_hold(sk); __sk_add_node(sk, list); } static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&sk->sk_node, list); else hlist_add_head_rcu(&sk->sk_node, list); } static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list) { sock_hold(sk); hlist_add_tail_rcu(&sk->sk_node, list); } static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) { hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); __sk_nulls_add_node_rcu(sk, list); } static inline void __sk_del_bind_node(struct sock *sk) { __hlist_del(&sk->sk_bind_node); } static inline void sk_add_bind_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_bind_node, list); } #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ hlist_for_each_entry_rcu(__sk, list, sk_node) #define sk_nulls_for_each(__sk, node, list) \ hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) #define sk_nulls_for_each_rcu(__sk, node, list) \ hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) #define sk_for_each_from(__sk) \ hlist_for_each_entry_from(__sk, sk_node) #define sk_nulls_for_each_from(__sk, node) \ if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \ hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node) #define sk_for_each_safe(__sk, tmp, list) \ hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @offset: offset of hlist_node within the struct. * */ #define sk_for_each_entry_offset_rcu(tpos, pos, head, offset) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos != NULL && \ ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) static inline struct user_namespace *sk_user_ns(struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from * userspace. */ return sk->sk_socket->file->f_cred->user_ns; } /* Sock flags */ enum sock_flags { SOCK_DEAD, SOCK_DONE, SOCK_URGINLINE, SOCK_KEEPOPEN, SOCK_LINGER, SOCK_DESTROY, SOCK_BROADCAST, SOCK_TIMESTAMP, SOCK_ZAPPED, SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG, /* %SO_DEBUG setting */ SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */ SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_RX_SOFTWARE, /* %SOF_TIMESTAMPING_RX_SOFTWARE */ SOCK_FASYNC, /* fasync() active */ SOCK_RXQ_OVFL, SOCK_ZEROCOPY, /* buffers from userspace */ SOCK_WIFI_STATUS, /* push wifi status to userspace */ SOCK_NOFCS, /* Tell NIC not to do the Ethernet FCS. * Will use last 4 bytes of packet sent from * user-space instead. */ SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */ SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) { nsk->sk_flags = osk->sk_flags; } static inline void sock_set_flag(struct sock *sk, enum sock_flags flag) { __set_bit(flag, &sk->sk_flags); } static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag) { __clear_bit(flag, &sk->sk_flags); } static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, int valbool) { if (valbool) sock_set_flag(sk, bit); else sock_reset_flag(sk, bit); } static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) { return test_bit(flag, &sk->sk_flags); } #ifdef CONFIG_NET DECLARE_STATIC_KEY_FALSE(memalloc_socks_key); static inline int sk_memalloc_socks(void) { return static_branch_unlikely(&memalloc_socks_key); } void __receive_sock(struct file *file); #else static inline int sk_memalloc_socks(void) { return 0; } static inline void __receive_sock(struct file *file) { } #endif static inline gfp_t sk_gfp_mask(const struct sock *sk, gfp_t gfp_mask) { return gfp_mask | (sk->sk_allocation & __GFP_MEMALLOC); } static inline void sk_acceptq_removed(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog - 1); } static inline void sk_acceptq_added(struct sock *sk) { WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); } /* * Compute minimal free write space needed to queue new packets. */ static inline int sk_stream_min_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_wmem_queued) >> 1; } static inline int sk_stream_wspace(const struct sock *sk) { return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); } static inline void sk_wmem_queued_add(struct sock *sk, int val) { WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); } void sk_stream_write_space(struct sock *sk); /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ skb_dst_force(skb); if (!sk->sk_backlog.tail) WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb; WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; } /* * Take into account size of receive queue and backlog queue * Do not take into account this skb truesize, * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, unsigned int limit) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); return qsize > limit; } /* The per-socket spinlock must be held here. */ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb, unsigned int limit) { if (sk_rcvqueues_full(sk, limit)) return -ENOBUFS; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) return -ENOMEM; __sk_add_backlog(sk, skb); sk->sk_backlog.len += skb->truesize; return 0; } int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); return sk->sk_backlog_rcv(sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) { int cpu = raw_smp_processor_id(); if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu)) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } static inline void sock_rps_record_flow_hash(__u32 hash) { #ifdef CONFIG_RPS struct rps_sock_flow_table *sock_flow_table; rcu_read_lock(); sock_flow_table = rcu_dereference(rps_sock_flow_table); rps_record_sock_flow(sock_flow_table, hash); rcu_read_unlock(); #endif } static inline void sock_rps_record_flow(const struct sock *sk) { #ifdef CONFIG_RPS if (static_branch_unlikely(&rfs_needed)) { /* Reading sk->sk_rxhash might incur an expensive cache line * miss. * * TCP_ESTABLISHED does cover almost all states where RFS * might be useful, and is cheaper [1] than testing : * IPv4: inet_sk(sk)->inet_daddr * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) * OR an additional socket flag * [1] : sk_state and sk_prot are in the same cache line. */ if (sk->sk_state == TCP_ESTABLISHED) sock_rps_record_flow_hash(sk->sk_rxhash); } #endif } static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_RPS if (unlikely(sk->sk_rxhash != skb->hash)) sk->sk_rxhash = skb->hash; #endif } static inline void sock_rps_reset_rxhash(struct sock *sk) { #ifdef CONFIG_RPS sk->sk_rxhash = 0; #endif } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ ({ int __rc; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ *(__timeo) = wait_woken(__wait, \ TASK_INTERRUPTIBLE, \ *(__timeo)); \ } \ sched_annotate_sleep(); \ lock_sock(__sk); \ __rc = __condition; \ __rc; \ }) int sk_stream_wait_connect(struct sock *sk, long *timeo_p); int sk_stream_wait_memory(struct sock *sk, long *timeo_p); void sk_stream_wait_close(struct sock *sk, long timeo_p); int sk_stream_error(struct sock *sk, int flags, int err); void sk_stream_kill_queues(struct sock *sk); void sk_set_memalloc(struct sock *sk); void sk_clear_memalloc(struct sock *sk); void __sk_flush_backlog(struct sock *sk); static inline bool sk_flush_backlog(struct sock *sk) { if (unlikely(READ_ONCE(sk->sk_backlog.tail))) { __sk_flush_backlog(sk); return true; } return false; } int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb); struct request_sock_ops; struct timewait_sock_ops; struct inet_hashinfo; struct raw_hashinfo; struct smc_hashinfo; struct module; /* * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes * un-modified. Special care is taken when initializing object to zero. */ static inline void sk_prot_clear_nulls(struct sock *sk, int size) { if (offsetof(struct sock, sk_node.next) != 0) memset(sk, 0, offsetof(struct sock, sk_node.next)); memset(&sk->sk_node.pprev, 0, size - offsetof(struct sock, sk_node.pprev)); } /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface */ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*connect)(struct sock *sk, struct sockaddr *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); struct sock * (*accept)(struct sock *sk, int flags, int *err, bool kern); int (*ioctl)(struct sock *sk, int cmd, unsigned long arg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct sock *sk, int level, int optname, char __user *optval, int __user *option); void (*keepalive)(struct sock *sk, int valbool); #ifdef CONFIG_COMPAT int (*compat_ioctl)(struct sock *sk, unsigned int cmd, unsigned long arg); #endif int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); /* Keeping track of sockets in use */ #ifdef CONFIG_PROC_FS unsigned int inuse_idx; #endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*stream_memory_read)(const struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long *memory_pressure; long *sysctl_mem; int *sysctl_wmem; int *sysctl_rmem; u32 sysctl_wmem_offset; u32 sysctl_rmem_offset; int max_header; bool no_autobind; struct kmem_cache *slab; unsigned int obj_size; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ unsigned int usersize; /* Usercopy region size */ struct percpu_counter *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; union { struct inet_hashinfo *hashinfo; struct udp_table *udp_table; struct raw_hashinfo *raw_hash; struct smc_hashinfo *smc_hash; } h; struct module *owner; char name[32]; struct list_head node; #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif int (*diag_destroy)(struct sock *sk, int err); } __randomize_layout; int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); int sock_load_diag_module(int family, int protocol); #ifdef SOCK_REFCNT_DEBUG static inline void sk_refcnt_debug_inc(struct sock *sk) { atomic_inc(&sk->sk_prot->socks); } static inline void sk_refcnt_debug_dec(struct sock *sk) { atomic_dec(&sk->sk_prot->socks); printk(KERN_DEBUG "%s socket %p released, %d are still alive\n", sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks)); } static inline void sk_refcnt_debug_release(const struct sock *sk) { if (refcount_read(&sk->sk_refcnt) != 1) printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n", sk->sk_prot->name, sk, refcount_read(&sk->sk_refcnt)); } #else /* SOCK_REFCNT_DEBUG */ #define sk_refcnt_debug_inc(sk) do { } while (0) #define sk_refcnt_debug_dec(sk) do { } while (0) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; return sk->sk_prot->stream_memory_free ? sk->sk_prot->stream_memory_free(sk, wake) : true; } static inline bool sk_stream_memory_free(const struct sock *sk) { return __sk_stream_memory_free(sk, 0); } static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && __sk_stream_memory_free(sk, wake); } static inline bool sk_stream_is_writeable(const struct sock *sk) { return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, struct cgroup *ancestor) { #ifdef CONFIG_SOCK_CGROUP_DATA return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), ancestor); #else return -ENOTSUPP; #endif } static inline bool sk_has_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure != NULL; } static inline bool sk_under_memory_pressure(const struct sock *sk) { if (!sk->sk_prot->memory_pressure) return false; if (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) return true; return !!*sk->sk_prot->memory_pressure; } static inline long sk_memory_allocated(const struct sock *sk) { return atomic_long_read(sk->sk_prot->memory_allocated); } static inline long sk_memory_allocated_add(struct sock *sk, int amt) { return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { atomic_long_sub(amt, sk->sk_prot->memory_allocated); } static inline void sk_sockets_allocated_dec(struct sock *sk) { percpu_counter_dec(sk->sk_prot->sockets_allocated); } static inline void sk_sockets_allocated_inc(struct sock *sk) { percpu_counter_inc(sk->sk_prot->sockets_allocated); } static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); } static inline int proto_sockets_allocated_sum_positive(struct proto *prot) { return percpu_counter_sum_positive(prot->sockets_allocated); } static inline long proto_memory_allocated(struct proto *prot) { return atomic_long_read(prot->memory_allocated); } static inline bool proto_memory_pressure(struct proto *prot) { if (!prot->memory_pressure) return false; return !!*prot->memory_pressure; } #ifdef CONFIG_PROC_FS /* Called with local bh disabled */ void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc) { } #endif /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); return sk->sk_prot->hash(sk); } /* About 10 seconds */ #define SOCK_DESTROY_TIME (10*HZ) /* Sockets 0-1023 can't be bound to unless you are superuser */ #define PROT_SOCK 1024 #define SHUTDOWN_MASK 3 #define RCV_SHUTDOWN 1 #define SEND_SHUTDOWN 2 #define SOCK_SNDBUF_LOCK 1 #define SOCK_RCVBUF_LOCK 2 #define SOCK_BINDADDR_LOCK 4 #define SOCK_BINDPORT_LOCK 8 struct socket_alloc { struct socket socket; struct inode vfs_inode; }; static inline struct socket *SOCKET_I(struct inode *inode) { return &container_of(inode, struct socket_alloc, vfs_inode)->socket; } static inline struct inode *SOCK_INODE(struct socket *socket) { return &container_of(socket, struct socket_alloc, socket)->vfs_inode; } /* * Functions for memory accounting */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind); int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); /* We used to have PAGE_SIZE here, but systems with 64KB pages * do not necessarily have 16x time more memory than 4KB ones. */ #define SK_MEM_QUANTUM 4096 #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 /* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]); #if PAGE_SIZE > SK_MEM_QUANTUM val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; #elif PAGE_SIZE < SK_MEM_QUANTUM val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; #endif return val; } static inline int sk_mem_pages(int amt) { return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; } static inline bool sk_has_account(struct sock *sk) { /* return true if protocol supports memory accounting */ return !!sk->sk_prot->memory_allocated; } static inline bool sk_wmem_schedule(struct sock *sk, int size) { if (!sk_has_account(sk)) return true; return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { if (!sk_has_account(sk)) return true; return size <= sk->sk_forward_alloc || __sk_mem_schedule(sk, size, SK_MEM_RECV) || skb_pfmemalloc(skb); } static inline void sk_mem_reclaim(struct sock *sk) { if (!sk_has_account(sk)) return; if (sk->sk_forward_alloc >= SK_MEM_QUANTUM) __sk_mem_reclaim(sk, sk->sk_forward_alloc); } static inline void sk_mem_reclaim_partial(struct sock *sk) { if (!sk_has_account(sk)) return; if (sk->sk_forward_alloc > SK_MEM_QUANTUM) __sk_mem_reclaim(sk, sk->sk_forward_alloc - 1); } static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk->sk_forward_alloc -= size; } static inline void sk_mem_uncharge(struct sock *sk, int size) { if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; /* Avoid a possible overflow. * TCP send queues can make this happen, if sk_mem_reclaim() * is not called and more than 2 GBytes are released at once. * * If we reach 2 MBytes, reclaim 1 MBytes right now, there is * no need to hold that much forward allocation anyway. */ if (unlikely(sk->sk_forward_alloc >= 1 << 21)) __sk_mem_reclaim(sk, 1 << 20); } DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && !sk->sk_tx_skb_cache && !skb_cloned(skb)) { skb_ext_reset(skb); skb_zcopy_clear(skb, true); sk->sk_tx_skb_cache = skb; return; } __kfree_skb(skb); } static inline void sock_release_ownership(struct sock *sk) { if (sk->sk_lock.owned) { sk->sk_lock.owned = 0; /* The sk_lock has mutex_unlock() semantics: */ mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } } /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. * * Mark both the sk_lock and the sk_lock.slock as a * per-address-family lock class. */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0) #ifdef CONFIG_LOCKDEP static inline bool lockdep_sock_is_held(const struct sock *sk) { return lockdep_is_held(&sk->sk_lock) || lockdep_is_held(&sk->sk_lock.slock); } #endif void lock_sock_nested(struct sock *sk, int subclass); static inline void lock_sock(struct sock *sk) { lock_sock_nested(sk, 0); } void __release_sock(struct sock *sk); void release_sock(struct sock *sk); /* BH context may only use the following locking interface. */ #define bh_lock_sock(__sk) spin_lock(&((__sk)->sk_lock.slock)) #define bh_lock_sock_nested(__sk) \ spin_lock_nested(&((__sk)->sk_lock.slock), \ SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) bool lock_sock_fast(struct sock *sk); /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket * @slow: slow mode * * fast unlock socket for user context. * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) { if (slow) release_sock(sk); else spin_unlock_bh(&sk->sk_lock.slock); } /* Used by processes to "lock" a socket state, so that * interrupts and bottom half handlers won't change it * from under us. It essentially blocks any incoming * packets, so that we won't get any new data or any * packets that change the state of the socket. * * While locked, BH processing will add new packets to * the backlog queue. This queue is processed by the * owner of the socket lock right before it is released. * * Since ~2.3.5 it is also exclusive sleep lock serializing * accesses from user process context. */ static inline void sock_owned_by_me(const struct sock *sk) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks); #endif } static inline bool sock_owned_by_user(const struct sock *sk) { sock_owned_by_me(sk); return sk->sk_lock.owned; } static inline bool sock_owned_by_user_nocheck(const struct sock *sk) { return sk->sk_lock.owned; } /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); void sk_free(struct sock *sk); void sk_destruct(struct sock *sk); struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); void sk_free_unlock_clone(struct sock *sk); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); void sock_pfree(struct sk_buff *skb); #else #define sock_edemux sock_efree #endif int sock_setsockopt(struct socket *sock, int level, int op, sockptr_t optval, unsigned int optlen); int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode); 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); void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); struct sockcm_cookie { u64 transmit_time; u32 mark; u16 tsflags; }; static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; } int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); /* * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ int sock_no_bind(struct socket *, struct sockaddr *, int); int sock_no_connect(struct socket *, struct sockaddr *, int, int); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); int sock_no_shutdown(struct socket *, int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); /* * Functions to fill in entries in struct proto_ops when a protocol * uses the inet style. */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); int sock_common_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int sock_common_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); void sk_common_release(struct sock *sk); /* * Default socket callbacks and setup code */ /* Initialise core socket variables */ void sock_init_data(struct socket *sock, struct sock *sk); /* * Socket reference counting postulates. * * * Each user of socket SHOULD hold a reference count. * * Each access point to socket (an hash table bucket, reference from a list, * running timer, skb in flight MUST hold a reference count. * * When reference count hits 0, it means it will never increase back. * * When reference count hits 0, it means that no references from * outside exist to this socket and current process on current CPU * is last user and may/should destroy this socket. * * sk_free is called from any context: process, BH, IRQ. When * it is called, socket has no references from outside -> sk_free * may release descendant resources allocated by the socket, but * to the time when it is called, socket is NOT referenced by any * hash tables, lists etc. * * Packets, delivered from outside (from network or from another process) * and enqueued on receive/error queues SHOULD NOT grab reference count, * when they sit in queue. Otherwise, packets will leak to hole, when * socket is looked up by one cpu and unhasing is made by another CPU. * It is true for udp/raw, netlink (leak to receive and error queues), tcp * (leak to backlog). Packet socket does all the processing inside * BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets * use separate SMP lock, so that they are prone too. */ /* Ungrab socket and destroy it, if it was the last reference. */ static inline void sock_put(struct sock *sk) { if (refcount_dec_and_test(&sk->sk_refcnt)) sk_free(sk); } /* Generic version of sock_put(), dealing with all sockets * (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...) */ void sock_gen_put(struct sock *sk); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted); static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) { return __sk_receive_skb(sk, skb, nested, 1, true); } static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) { /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; sk->sk_tx_queue_mapping = tx_queue; } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; } static inline int sk_tx_queue_get(const struct sock *sk) { if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) return sk->sk_tx_queue_mapping; return -1; } static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_XPS if (skb_rx_queue_recorded(skb)) { u16 rx_queue = skb_get_rx_queue(skb); if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING)) return; sk->sk_rx_queue_mapping = rx_queue; } #endif } static inline void sk_rx_queue_clear(struct sock *sk) { #ifdef CONFIG_XPS sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING; #endif } #ifdef CONFIG_XPS static inline int sk_rx_queue_get(const struct sock *sk) { if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING) return sk->sk_rx_queue_mapping; return -1; } #endif static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk->sk_socket = sock; } static inline wait_queue_head_t *sk_sleep(struct sock *sk) { BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0); return &rcu_dereference_raw(sk->sk_wq)->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, * we do not release it in this function, because protocol * probably wants some additional cleanups or even continuing * to work with this socket (TCP). */ static inline void sock_orphan(struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { WARN_ON(parent->sk); write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } kuid_t sock_i_uid(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { return sk ? sk->sk_uid : make_kuid(net->user_ns, 0); } static inline u32 net_tx_rndhash(void) { u32 v = prandom_u32(); return v ?: 1; } static inline void sk_set_txhash(struct sock *sk) { /* This pairs with READ_ONCE() in skb_set_hash_from_sk() */ WRITE_ONCE(sk->sk_txhash, net_tx_rndhash()); } static inline bool sk_rethink_txhash(struct sock *sk) { if (sk->sk_txhash) { sk_set_txhash(sk); return true; } return false; } static inline struct dst_entry * __sk_dst_get(struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, lockdep_sock_is_held(sk)); } static inline struct dst_entry * sk_dst_get(struct sock *sk) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(sk->sk_dst_cache); if (dst && !atomic_inc_not_zero(&dst->__refcnt)) dst = NULL; rcu_read_unlock(); return dst; } static inline void __dst_negative_advice(struct sock *sk) { struct dst_entry *ndst, *dst = __sk_dst_get(sk); if (dst && dst->ops->negative_advice) { ndst = dst->ops->negative_advice(dst); if (ndst != dst) { rcu_assign_pointer(sk->sk_dst_cache, ndst); sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; } } } static inline void dst_negative_advice(struct sock *sk) { sk_rethink_txhash(sk); __dst_negative_advice(sk); } static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); sk->sk_dst_pending_confirm = 0; old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void __sk_dst_reset(struct sock *sk) { __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { sk_dst_set(sk, NULL); } struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie); static inline void sk_dst_confirm(struct sock *sk) { if (!READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 1); } static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); } } bool sk_mc_loop(struct sock *sk); static inline bool sk_can_gso(const struct sock *sk) { return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type); } void sk_setup_caps(struct sock *sk, struct dst_entry *dst); static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) { sk->sk_route_nocaps |= flags; sk->sk_route_caps &= ~flags; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, char *to, int copy, int offset) { if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, copy, &csum, from)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, offset); } else if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) return -EFAULT; return 0; } static inline int skb_add_data_nocache(struct sock *sk, struct sk_buff *skb, struct iov_iter *from, int copy) { int err, offset = skb->len; err = skb_do_copy_data_nocache(sk, skb, from, skb_put(skb, copy), copy, offset); if (err) __skb_trim(skb, offset); return err; } static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *from, struct sk_buff *skb, struct page *page, int off, int copy) { int err; err = skb_do_copy_data_nocache(sk, skb, from, page_address(page) + off, copy, skb->len); if (err) return err; skb->len += copy; skb->data_len += copy; skb->truesize += copy; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } /** * sk_wmem_alloc_get - returns write allocations * @sk: socket * * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) - 1; } /** * sk_rmem_alloc_get - returns read allocations * @sk: socket * * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { return atomic_read(&sk->sk_rmem_alloc); } /** * sk_has_allocations - check if allocations are outstanding * @sk: socket * * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk); } /** * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths:: * * CPU1 CPU2 * sys_select receive packet * ... ... * __add_wait_queue update tp->rcv_nxt * ... ... * tp->rcv_nxt check sock_def_readable * ... { * schedule rcu_read_lock(); * wq = rcu_dereference(sk->sk_wq); * if (wq && waitqueue_active(&wq->wait)) * wake_up_interruptible(&wq->wait) * ... * } * * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 * could then endup calling schedule and sleep forever if there are no more * data on the socket. * */ static inline bool skwq_has_sleeper(struct socket_wq *wq) { return wq && wq_has_sleeper(&wq->wait); } /** * sock_poll_wait - place memory barrier behind the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table * * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { if (!poll_does_not_wait(p)) { poll_wait(filp, &sock->wq.wait, p); /* We need to be sure we are in sync with the * socket flags modification. * * This memory barrier is paired in the wq_has_sleeper. */ smp_mb(); } } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) { /* This pairs with WRITE_ONCE() in sk_set_txhash() */ u32 txhash = READ_ONCE(sk->sk_txhash); if (txhash) { skb->l4_hash = 1; skb->hash = txhash; } } void skb_set_owner_w(struct sk_buff *skb, struct sock *sk); /* * Queue a received datagram if it will fit. Stream and sequenced * protocols can't normally use this as they need to fit buffers in * and play with them. * * Inlined as it's very short and called for pretty much every * packet ever received. */ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = sock_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static inline __must_check bool skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) { if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { skb_orphan(skb); skb->destructor = sock_efree; skb->sk = sk; return true; } return false; } void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); void sk_stop_timer(struct sock *sk, struct timer_list *timer); void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); /* * Recover an error report and clear atomically */ static inline int sock_error(struct sock *sk) { int err; /* Avoid an atomic operation for the common case. * This is racy since another cpu/thread can change sk_err under us. */ if (likely(data_race(!sk->sk_err))) return 0; err = xchg(&sk->sk_err, 0); return -err; } static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { amt = sk->sk_sndbuf - refcount_read(&sk->sk_wmem_alloc); if (amt < 0) amt = 0; } return amt; } /* Note: * We use sk->sk_wq_raw, from contexts knowing this * pointer is not NULL and cannot disappear/change. */ static inline void sk_set_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; set_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_clear_bit(int nr, struct sock *sk) { if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) && !sock_flag(sk, SOCK_FASYNC)) return; clear_bit(nr, &sk->sk_wq_raw->flags); } static inline void sk_wake_async(const struct sock *sk, int how, int band) { if (sock_flag(sk, SOCK_FASYNC)) { rcu_read_lock(); sock_wake_async(rcu_dereference(sk->sk_wq), how, band); rcu_read_unlock(); } } /* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might * need sizeof(sk_buff) + MTU + padding, unless net driver perform copybreak. * Note: for send buffers, TCP works better if we can build two skbs at * minimum. */ #define TCP_SKB_MIN_TRUESIZE (2048 + SKB_DATA_ALIGN(sizeof(struct sk_buff))) #define SOCK_MIN_SNDBUF (TCP_SKB_MIN_TRUESIZE * 2) #define SOCK_MIN_RCVBUF TCP_SKB_MIN_TRUESIZE static inline void sk_stream_moderate_sndbuf(struct sock *sk) { u32 val; if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); } struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, bool force_schedule); /** * sk_page_frag - return an appropriate page_frag * @sk: socket * * Use the per task page_frag instead of the per socket one for * optimization when we know that we're in process context and own * everything that's associated with %current. * * Both direct reclaim and page faults can nest inside other * socket operations and end up recursing into sk_page_frag() * while it's already in use: explicitly avoid task page_frag * usage if the caller is potentially doing any of them. * This assumes that page fault handlers use the GFP_NOFS flags. * * Return: a per task page_frag if context allows that, * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { if ((sk->sk_allocation & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC | __GFP_FS)) == (__GFP_DIRECT_RECLAIM | __GFP_FS)) return ¤t->task_frag; return &sk->sk_frag; } bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); } static inline gfp_t gfp_any(void) { return in_softirq() ? GFP_ATOMIC : GFP_KERNEL; } static inline long sock_rcvtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_rcvtimeo; } static inline long sock_sndtimeo(const struct sock *sk, bool noblock) { return noblock ? 0 : sk->sk_sndtimeo; } static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); return v ?: 1; } /* Alas, with timeout socket operations are not restartable. * Compare this to poll(). */ static inline int sock_intr_errno(long timeo) { return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR; } struct sock_skb_cb { u32 dropcount; }; /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its * alignement guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) #define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ SOCK_SKB_CB_OFFSET)) #define sock_skb_cb_check_size(size) \ BUILD_BUG_ON((size) > SOCK_SKB_CB_OFFSET) static inline void sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) { SOCK_SKB_CB(skb)->dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? atomic_read(&sk->sk_drops) : 0; } static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) { int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); atomic_add(segs, &sk->sk_drops); } static inline ktime_t sock_read_timestamp(struct sock *sk) { #if BITS_PER_LONG==32 unsigned int seq; ktime_t kt; do { seq = read_seqbegin(&sk->sk_stamp_seq); kt = sk->sk_stamp; } while (read_seqretry(&sk->sk_stamp_seq, seq)); return kt; #else return READ_ONCE(sk->sk_stamp); #endif } static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) { #if BITS_PER_LONG==32 write_seqlock(&sk->sk_stamp_seq); sk->sk_stamp = kt; write_sequnlock(&sk->sk_stamp_seq); #else WRITE_ONCE(sk->sk_stamp, kt); #endif } void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { ktime_t kt = skb->tstamp; struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); /* * generate control messages if * - receive time stamping in software requested * - software time stamp available and wanted * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid) __sock_recv_wifi_status(msg, sk, skb); } void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_RCVTSTAMP)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) __sock_recv_ts_and_drops(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) sock_write_timestamp(sk, 0); } void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); /** * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @tsflags: timestamping flags to use * @tx_flags: completed with instructions for time stamping * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, __u8 *tx_flags, __u32 *tskey) { if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) *tskey = sk->sk_tskey++; } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, __u8 *tx_flags) { _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); } static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) { _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, &skb_shinfo(skb)->tskey); } DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (static_branch_unlikely(&tcp_rx_skb_cache_key) && !sk->sk_rx_skb_cache) { sk->sk_rx_skb_cache = skb; skb_orphan(skb); return; } __kfree_skb(skb); } static inline struct net *sock_net(const struct sock *sk) { return read_pnet(&sk->sk_net); } static inline void sock_net_set(struct sock *sk, struct net *net) { write_pnet(&sk->sk_net, net); } static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { #ifdef CONFIG_INET return skb->destructor == sock_pfree; #else return false; #endif /* CONFIG_INET */ } /* This helper checks if a socket is a full socket, * ie _not_ a timewait or request socket. */ static inline bool sk_fullsock(const struct sock *sk) { return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } static inline bool sk_is_refcounted(struct sock *sk) { /* Only full sockets have sk->sk_flags. */ return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE); } /** * skb_steal_sock - steal a socket from an sk_buff * @skb: sk_buff to steal the socket from * @refcounted: is set to true if the socket is reference-counted */ static inline struct sock * skb_steal_sock(struct sk_buff *skb, bool *refcounted) { if (skb->sk) { struct sock *sk = skb->sk; *refcounted = true; if (skb_sk_is_prefetched(skb)) *refcounted = sk_is_refcounted(sk); skb->destructor = NULL; skb->sk = NULL; return sk; } *refcounted = false; return NULL; } /* Checks if this SKB belongs to an HW offloaded socket * and whether any SW fallbacks are required based on dev. * Check decrypted mark in case skb_orphan() cleared socket. */ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) { #ifdef CONFIG_SOCK_VALIDATE_XMIT struct sock *sk = skb->sk; if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) { skb = sk->sk_validate_xmit_skb(sk, dev, skb); #ifdef CONFIG_TLS_DEVICE } else if (unlikely(skb->decrypted)) { pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n"); kfree_skb(skb); skb = NULL; #endif } #endif return skb; } /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) */ static inline bool sk_listener(const struct sock *sk) { return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); } void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type); bool sk_ns_capable(const struct sock *sk, struct user_namespace *user_ns, int cap); bool sk_capable(const struct sock *sk, int cap); bool sk_net_capable(const struct sock *sk, int cap); void sk_get_meminfo(const struct sock *sk, u32 *meminfo); /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance * not depend upon such differences. */ #define _SK_MEM_PACKETS 256 #define _SK_MEM_OVERHEAD SKB_TRUESIZE(256) #define SK_WMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) extern __u32 sysctl_wmem_max; extern __u32 sysctl_rmem_max; extern int sysctl_tstamp_allow_data; extern int sysctl_optmem_max; extern __u32 sysctl_wmem_default; extern __u32 sysctl_rmem_default; #define SKB_FRAG_PAGE_ORDER get_order(32768) DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_wmem ? */ if (proto->sysctl_wmem_offset) return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset); return *proto->sysctl_wmem; } static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto) { /* Does this proto have per netns sysctl_rmem ? */ if (proto->sysctl_rmem_offset) return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset); return *proto->sysctl_rmem; } /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) * Some wifi drivers need to tweak it to get more chunks. * They can use this helper from their ndo_start_xmit() */ static inline void sk_pacing_shift_update(struct sock *sk, int val) { if (!sk || !sk_fullsock(sk) || READ_ONCE(sk->sk_pacing_shift) == val) return; WRITE_ONCE(sk->sk_pacing_shift, val); } /* if a socket is bound to a device, check that the given device * index is either the same or that the socket is bound to an L3 * master device and the given device index is also enslaved to * that L3 master */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { int mdif; if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); if (mdif && mdif == sk->sk_bound_dev_if) return true; return false; } void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); void sock_set_priority(struct sock *sk, u32 priority); void sock_set_rcvbuf(struct sock *sk, int val); void sock_set_mark(struct sock *sk, u32 val); void sock_set_reuseaddr(struct sock *sk); void sock_set_reuseport(struct sock *sk); void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); #endif /* _SOCK_H */ |
| 1066 181 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* 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 <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.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 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_INVALID, }; extern int is_audit_feature_set(int which); 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[]; extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* 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_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_getcwd(void); 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_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_getcwd(void) { if (unlikely(audit_context())) __audit_getcwd(); } 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_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); 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_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(unsigned int response) { if (!audit_dummy_context()) __audit_fanotify(response); } 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_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_getcwd(void) { } 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_log_kern_module(char *name) { } static inline void audit_fanotify(unsigned int response) { } 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 |
| 84 91 19 39 89 72 7 7 86 90 90 91 90 91 91 91 91 91 90 91 91 7 2 2 89 89 90 9 91 91 91 91 91 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/irqflags.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" /** * DOC: printk_ringbuffer overview * * Data Structure * -------------- * The printk_ringbuffer is made up of 3 internal ringbuffers: * * desc_ring * A ring of descriptors and their meta data (such as sequence number, * timestamp, loglevel, etc.) as well as internal state information about * the record and logical positions specifying where in the other * ringbuffer the text strings are located. * * text_data_ring * A ring of data blocks. A data block consists of an unsigned long * integer (ID) that maps to a desc_ring index followed by the text * string of the record. * * The internal state information of a descriptor is the key element to allow * readers and writers to locklessly synchronize access to the data. * * Implementation * -------------- * * Descriptor Ring * ~~~~~~~~~~~~~~~ * The descriptor ring is an array of descriptors. A descriptor contains * essential meta data to track the data of a printk record using * blk_lpos structs pointing to associated text data blocks (see * "Data Rings" below). Each descriptor is assigned an ID that maps * directly to index values of the descriptor array and has a state. The ID * and the state are bitwise combined into a single descriptor field named * @state_var, allowing ID and state to be synchronously and atomically * updated. * * Descriptors have four states: * * reserved * A writer is modifying the record. * * committed * The record and all its data are written. A writer can reopen the * descriptor (transitioning it back to reserved), but in the committed * state the data is consistent. * * finalized * The record and all its data are complete and available for reading. A * writer cannot reopen the descriptor. * * reusable * The record exists, but its text and/or meta data may no longer be * available. * * Querying the @state_var of a record requires providing the ID of the * descriptor to query. This can yield a possible fifth (pseudo) state: * * miss * The descriptor being queried has an unexpected ID. * * The descriptor ring has a @tail_id that contains the ID of the oldest * descriptor and @head_id that contains the ID of the newest descriptor. * * When a new descriptor should be created (and the ring is full), the tail * descriptor is invalidated by first transitioning to the reusable state and * then invalidating all tail data blocks up to and including the data blocks * associated with the tail descriptor (for the text ring). Then * @tail_id is advanced, followed by advancing @head_id. And finally the * @state_var of the new descriptor is initialized to the new ID and reserved * state. * * The @tail_id can only be advanced if the new @tail_id would be in the * committed or reusable queried state. This makes it possible that a valid * sequence number of the tail is always available. * * Descriptor Finalization * ~~~~~~~~~~~~~~~~~~~~~~~ * When a writer calls the commit function prb_commit(), record data is * fully stored and is consistent within the ringbuffer. However, a writer can * reopen that record, claiming exclusive access (as with prb_reserve()), and * modify that record. When finished, the writer must again commit the record. * * In order for a record to be made available to readers (and also become * recyclable for writers), it must be finalized. A finalized record cannot be * reopened and can never become "unfinalized". Record finalization can occur * in three different scenarios: * * 1) A writer can simultaneously commit and finalize its record by calling * prb_final_commit() instead of prb_commit(). * * 2) When a new record is reserved and the previous record has been * committed via prb_commit(), that previous record is automatically * finalized. * * 3) When a record is committed via prb_commit() and a newer record * already exists, the record being committed is automatically finalized. * * Data Ring * ~~~~~~~~~ * The text data ring is a byte array composed of data blocks. Data blocks are * referenced by blk_lpos structs that point to the logical position of the * beginning of a data block and the beginning of the next adjacent data * block. Logical positions are mapped directly to index values of the byte * array ringbuffer. * * Each data block consists of an ID followed by the writer data. The ID is * the identifier of a descriptor that is associated with the data block. A * given data block is considered valid if all of the following conditions * are met: * * 1) The descriptor associated with the data block is in the committed * or finalized queried state. * * 2) The blk_lpos struct within the descriptor associated with the data * block references back to the same data block. * * 3) The data block is within the head/tail logical position range. * * If the writer data of a data block would extend beyond the end of the * byte array, only the ID of the data block is stored at the logical * position and the full data block (ID and writer data) is stored at the * beginning of the byte array. The referencing blk_lpos will point to the * ID before the wrap and the next data block will be at the logical * position adjacent the full data block after the wrap. * * Data rings have a @tail_lpos that points to the beginning of the oldest * data block and a @head_lpos that points to the logical position of the * next (not yet existing) data block. * * When a new data block should be created (and the ring is full), tail data * blocks will first be invalidated by putting their associated descriptors * into the reusable state and then pushing the @tail_lpos forward beyond * them. Then the @head_lpos is pushed forward and is associated with a new * descriptor. If a data block is not valid, the @tail_lpos cannot be * advanced beyond it. * * Info Array * ~~~~~~~~~~ * The general meta data of printk records are stored in printk_info structs, * stored in an array with the same number of elements as the descriptor ring. * Each info corresponds to the descriptor of the same index in the * descriptor ring. Info validity is confirmed by evaluating the corresponding * descriptor before and after loading the info. * * Usage * ----- * Here are some simple examples demonstrating writers and readers. For the * examples a global ringbuffer (test_rb) is available (which is not the * actual ringbuffer used by printk):: * * DEFINE_PRINTKRB(test_rb, 15, 5); * * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of * 1 MiB (2 ^ (15 + 5)) for text data. * * Sample writer code:: * * const char *textstr = "message text"; * struct prb_reserved_entry e; * struct printk_record r; * * // specify how much to allocate * prb_rec_init_wr(&r, strlen(textstr) + 1); * * if (prb_reserve(&e, &test_rb, &r)) { * snprintf(r.text_buf, r.text_buf_size, "%s", textstr); * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit and finalize the record * prb_final_commit(&e); * } * * Note that additional writer functions are available to extend a record * after it has been committed but not yet finalized. This can be done as * long as no new records have been reserved and the caller is the same. * * Sample writer code (record extending):: * * // alternate rest of previous example * * r.info->text_len = strlen(textstr); * r.info->ts_nsec = local_clock(); * r.info->caller_id = printk_caller_id(); * * // commit the record (but do not finalize yet) * prb_commit(&e); * } * * ... * * // specify additional 5 bytes text space to extend * prb_rec_init_wr(&r, 5); * * // try to extend, but only if it does not exceed 32 bytes * if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id()), 32) { * snprintf(&r.text_buf[r.info->text_len], * r.text_buf_size - r.info->text_len, "hello"); * * r.info->text_len += 5; * * // commit and finalize the record * prb_final_commit(&e); * } * * Sample reader code:: * * struct printk_info info; * struct printk_record r; * char text_buf[32]; * u64 seq; * * prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf)); * * prb_for_each_record(0, &test_rb, &seq, &r) { * if (info.seq != seq) * pr_warn("lost %llu records\n", info.seq - seq); * * if (info.text_len > r.text_buf_size) { * pr_warn("record %llu text truncated\n", info.seq); * text_buf[r.text_buf_size - 1] = 0; * } * * pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec, * &text_buf[0]); * } * * Note that additional less convenient reader functions are available to * allow complex record access. * * ABA Issues * ~~~~~~~~~~ * To help avoid ABA issues, descriptors are referenced by IDs (array index * values combined with tagged bits counting array wraps) and data blocks are * referenced by logical positions (array index values combined with tagged * bits counting array wraps). However, on 32-bit systems the number of * tagged bits is relatively small such that an ABA incident is (at least * theoretically) possible. For example, if 4 million maximally sized (1KiB) * printk messages were to occur in NMI context on a 32-bit system, the * interrupted context would not be able to recognize that the 32-bit integer * completely wrapped and thus represents a different data block than the one * the interrupted context expects. * * To help combat this possibility, additional state checking is performed * (such as using cmpxchg() even though set() would suffice). These extra * checks are commented as such and will hopefully catch any ABA issue that * a 32-bit system might experience. * * Memory Barriers * ~~~~~~~~~~~~~~~ * Multiple memory barriers are used. To simplify proving correctness and * generating litmus tests, lines of code related to memory barriers * (loads, stores, and the associated memory barriers) are labeled:: * * LMM(function:letter) * * Comments reference the labels using only the "function:letter" part. * * The memory barrier pairs and their ordering are: * * desc_reserve:D / desc_reserve:B * push descriptor tail (id), then push descriptor head (id) * * desc_reserve:D / data_push_tail:B * push data tail (lpos), then set new descriptor reserved (state) * * desc_reserve:D / desc_push_tail:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:D / prb_first_seq:C * push descriptor tail (id), then set new descriptor reserved (state) * * desc_reserve:F / desc_read:D * set new descriptor id and reserved (state), then allow writer changes * * data_alloc:A (or data_realloc:A) / desc_read:D * set old descriptor reusable (state), then modify new data block area * * data_alloc:A (or data_realloc:A) / data_push_tail:B * push data tail (lpos), then modify new data block area * * _prb_commit:B / desc_read:B * store writer changes, then set new descriptor committed (state) * * desc_reopen_last:A / _prb_commit:B * set descriptor reserved (state), then read descriptor data * * _prb_commit:B / desc_reserve:D * set new descriptor committed (state), then check descriptor head (id) * * data_push_tail:D / data_push_tail:A * set descriptor reusable (state), then push data tail (lpos) * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) #define DATA_SIZE_MASK(data_ring) (DATA_SIZE(data_ring) - 1) #define DESCS_COUNT(desc_ring) _DESCS_COUNT((desc_ring)->count_bits) #define DESCS_COUNT_MASK(desc_ring) (DESCS_COUNT(desc_ring) - 1) /* Determine the data array index from a logical position. */ #define DATA_INDEX(data_ring, lpos) ((lpos) & DATA_SIZE_MASK(data_ring)) /* Determine the desc array index from an ID or sequence number. */ #define DESC_INDEX(desc_ring, n) ((n) & DESCS_COUNT_MASK(desc_ring)) /* Determine how many times the data array has wrapped. */ #define DATA_WRAPS(data_ring, lpos) ((lpos) >> (data_ring)->size_bits) /* Determine if a logical position refers to a data-less block. */ #define LPOS_DATALESS(lpos) ((lpos) & 1UL) #define BLK_DATALESS(blk) (LPOS_DATALESS((blk)->begin) && \ LPOS_DATALESS((blk)->next)) /* Get the logical position at index 0 of the current wrap. */ #define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \ ((lpos) & ~DATA_SIZE_MASK(data_ring)) /* Get the ID for the same index of the previous wrap as the given ID. */ #define DESC_ID_PREV_WRAP(desc_ring, id) \ DESC_ID((id) - DESCS_COUNT(desc_ring)) /* * A data block: mapped directly to the beginning of the data block area * specified as a logical position within the data ring. * * @id: the ID of the associated descriptor * @data: the writer data * * Note that the size of a data block is only known by its associated * descriptor. */ struct prb_data_block { unsigned long id; char data[]; }; /* * Return the descriptor associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->descs[DESC_INDEX(desc_ring, n)]; } /* * Return the printk_info associated with @n. @n can be either a * descriptor ID or a sequence number. */ static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n) { return &desc_ring->infos[DESC_INDEX(desc_ring, n)]; } static struct prb_data_block *to_block(struct prb_data_ring *data_ring, unsigned long begin_lpos) { return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)]; } /* * Increase the data size to account for data block meta data plus any * padding so that the adjacent data block is aligned on the ID size. */ static unsigned int to_blk_size(unsigned int size) { struct prb_data_block *db = NULL; size += sizeof(*db); size = ALIGN(size, sizeof(db->id)); return size; } /* * Sanity checker for reserve size. The ringbuffer code assumes that a data * block does not exceed the maximum possible size that could fit within the * ringbuffer. This function provides that basic size check so that the * assumption is safe. */ static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size) { struct prb_data_block *db = NULL; if (size == 0) return true; /* * Ensure the alignment padded size could possibly fit in the data * array. The largest possible data block must still leave room for * at least the ID of the next block. */ size = to_blk_size(size); if (size > DATA_SIZE(data_ring) - sizeof(db->id)) return false; return true; } /* Query the state of a descriptor. */ static enum desc_state get_desc_state(unsigned long id, unsigned long state_val) { if (id != DESC_ID(state_val)) return desc_miss; return DESC_STATE(state_val); } /* * Get a copy of a specified descriptor and return its queried state. If the * descriptor is in an inconsistent state (miss or reserved), the caller can * only expect the descriptor's @state_var field to be valid. * * The sequence number and caller_id can be optionally retrieved. Like all * non-state_var data, they are only valid if the descriptor is in a * consistent state. */ static enum desc_state desc_read(struct prb_desc_ring *desc_ring, unsigned long id, struct prb_desc *desc_out, u64 *seq_out, u32 *caller_id_out) { struct printk_info *info = to_info(desc_ring, id); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; enum desc_state d_state; unsigned long state_val; /* Check the descriptor state. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */ d_state = get_desc_state(id, state_val); if (d_state == desc_miss || d_state == desc_reserved) { /* * The descriptor is in an inconsistent state. Set at least * @state_var so that the caller can see the details of * the inconsistent state. */ goto out; } /* * Guarantee the state is loaded before copying the descriptor * content. This avoids copying obsolete descriptor content that might * not apply to the descriptor state. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_read:A reads from _prb_commit:B, then desc_read:C reads * from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * RMB from desc_read:A to desc_read:C */ smp_rmb(); /* LMM(desc_read:B) */ /* * Copy the descriptor data. The data is not valid until the * state has been re-checked. A memcpy() for all of @desc * cannot be used because of the atomic_t @state_var field. */ if (desc_out) { memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos, sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */ } if (seq_out) *seq_out = info->seq; /* also part of desc_read:C */ if (caller_id_out) *caller_id_out = info->caller_id; /* also part of desc_read:C */ /* * 1. Guarantee the descriptor content is loaded before re-checking * the state. This avoids reading an obsolete descriptor state * that may not apply to the copied content. This pairs with * desc_reserve:F. * * Memory barrier involvement: * * If desc_read:C reads from desc_reserve:G, then desc_read:E * reads from desc_reserve:F. * * Relies on: * * WMB from desc_reserve:F to desc_reserve:G * matching * RMB from desc_read:C to desc_read:E * * 2. Guarantee the record data is loaded before re-checking the * state. This avoids reading an obsolete descriptor state that may * not apply to the copied data. This pairs with data_alloc:A and * data_realloc:A. * * Memory barrier involvement: * * If copy_data:A reads from data_alloc:B, then desc_read:E * reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_alloc:B * matching * RMB from desc_read:C to desc_read:E * * Note: desc_make_reusable:A and data_alloc:B can be different * CPUs. However, the data_alloc:B CPU (which performs the * full memory barrier) must have previously seen * desc_make_reusable:A. */ smp_rmb(); /* LMM(desc_read:D) */ /* * The data has been copied. Return the current descriptor state, * which may have changed since the load above. */ state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */ d_state = get_desc_state(id, state_val); out: if (desc_out) atomic_long_set(&desc_out->state_var, state_val); return d_state; } /* * Take a specified descriptor out of the finalized state by attempting * the transition from finalized to reusable. Either this context or some * other context will have been successful. */ static void desc_make_reusable(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long val_finalized = DESC_SV(id, desc_finalized); unsigned long val_reusable = DESC_SV(id, desc_reusable); struct prb_desc *desc = to_desc(desc_ring, id); atomic_long_t *state_var = &desc->state_var; atomic_long_cmpxchg_relaxed(state_var, val_finalized, val_reusable); /* LMM(desc_make_reusable:A) */ } /* * Given the text data ring, put the associated descriptor of each * data block from @lpos_begin until @lpos_end into the reusable state. * * If there is any problem making the associated descriptor reusable, either * the descriptor has not yet been finalized or another writer context has * already pushed the tail lpos past the problematic data block. Regardless, * on error the caller can re-load the tail lpos to determine the situation. */ static bool data_make_reusable(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned long lpos_begin, unsigned long lpos_end, unsigned long *lpos_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct prb_data_block *blk; enum desc_state d_state; struct prb_desc desc; struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos; unsigned long id; /* Loop until @lpos_begin has advanced to or beyond @lpos_end. */ while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) { blk = to_block(data_ring, lpos_begin); /* * Load the block ID from the data block. This is a data race * against a writer that may have newly reserved this data * area. If the loaded value matches a valid descriptor ID, * the blk_lpos of that descriptor will be checked to make * sure it points back to this data block. If the check fails, * the data area has been recycled by another writer. */ id = blk->id; /* LMM(data_make_reusable:A) */ d_state = desc_read(desc_ring, id, &desc, NULL, NULL); /* LMM(data_make_reusable:B) */ switch (d_state) { case desc_miss: case desc_reserved: case desc_committed: return false; case desc_finalized: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; desc_make_reusable(desc_ring, id); break; case desc_reusable: /* * This data block is invalid if the descriptor * does not point back to it. */ if (blk_lpos->begin != lpos_begin) return false; break; } /* Advance @lpos_begin to the next data block. */ lpos_begin = blk_lpos->next; } *lpos_out = lpos_begin; return true; } /* * Advance the data ring tail to at least @lpos. This function puts * descriptors into the reusable state if the tail is pushed beyond * their associated data block. */ static bool data_push_tail(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned long lpos) { unsigned long tail_lpos_new; unsigned long tail_lpos; unsigned long next_lpos; /* If @lpos is from a data-less block, there is nothing to do. */ if (LPOS_DATALESS(lpos)) return true; /* * Any descriptor states that have transitioned to reusable due to the * data tail being pushed to this loaded value will be visible to this * CPU. This pairs with data_push_tail:D. * * Memory barrier involvement: * * If data_push_tail:A reads from data_push_tail:D, then this CPU can * see desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to data_push_tail:D * matches * READFROM from data_push_tail:D to data_push_tail:A * thus * READFROM from desc_make_reusable:A to this CPU */ tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */ /* * Loop until the tail lpos is at or beyond @lpos. This condition * may already be satisfied, resulting in no full memory barrier * from data_push_tail:D being performed. However, since this CPU * sees the new tail lpos, any descriptor states that transitioned to * the reusable state must already be visible. */ while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) { /* * Make all descriptors reusable that are associated with * data blocks before @lpos. */ if (!data_make_reusable(rb, data_ring, tail_lpos, lpos, &next_lpos)) { /* * 1. Guarantee the block ID loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled data area causing the tail lpos to * have been previously pushed. This pairs with * data_alloc:A and data_realloc:A. * * Memory barrier involvement: * * If data_make_reusable:A reads from data_alloc:B, * then data_push_tail:C reads from * data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to data_alloc:B * matching * RMB from data_make_reusable:A to * data_push_tail:C * * Note: data_push_tail:D and data_alloc:B can be * different CPUs. However, the data_alloc:B * CPU (which performs the full memory * barrier) must have previously seen * data_push_tail:D. * * 2. Guarantee the descriptor state loaded in * data_make_reusable() is performed before * reloading the tail lpos. The failed * data_make_reusable() may be due to a newly * recycled descriptor causing the tail lpos to * have been previously pushed. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If data_make_reusable:B reads from * desc_reserve:F, then data_push_tail:C reads * from data_push_tail:D. * * Relies on: * * MB from data_push_tail:D to desc_reserve:F * matching * RMB from data_make_reusable:B to * data_push_tail:C * * Note: data_push_tail:D and desc_reserve:F can * be different CPUs. However, the * desc_reserve:F CPU (which performs the * full memory barrier) must have previously * seen data_push_tail:D. */ smp_rmb(); /* LMM(data_push_tail:B) */ tail_lpos_new = atomic_long_read(&data_ring->tail_lpos ); /* LMM(data_push_tail:C) */ if (tail_lpos_new == tail_lpos) return false; /* Another CPU pushed the tail. Try again. */ tail_lpos = tail_lpos_new; continue; } /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail lpos. A full * memory barrier is needed since other CPUs may have made * the descriptor states reusable. This pairs with * data_push_tail:A. */ if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos, next_lpos)) { /* LMM(data_push_tail:D) */ break; } } return true; } /* * Advance the desc ring tail. This function advances the tail by one * descriptor, thus invalidating the oldest descriptor. Before advancing * the tail, the tail descriptor is made reusable and all data blocks up to * and including the descriptor's data block are invalidated (i.e. the data * ring tail is pushed past the data block of the descriptor being made * reusable). */ static bool desc_push_tail(struct printk_ringbuffer *rb, unsigned long tail_id) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL); switch (d_state) { case desc_miss: /* * If the ID is exactly 1 wrap behind the expected, it is * in the process of being reserved by another writer and * must be considered reserved. */ if (DESC_ID(atomic_long_read(&desc.state_var)) == DESC_ID_PREV_WRAP(desc_ring, tail_id)) { return false; } /* * The ID has changed. Another writer must have pushed the * tail and recycled the descriptor already. Success is * returned because the caller is only interested in the * specified tail being pushed, which it was. */ return true; case desc_reserved: case desc_committed: return false; case desc_finalized: desc_make_reusable(desc_ring, tail_id); break; case desc_reusable: break; } /* * Data blocks must be invalidated before their associated * descriptor can be made available for recycling. Invalidating * them later is not possible because there is no way to trust * data blocks once their associated descriptor is gone. */ if (!data_push_tail(rb, &rb->text_data_ring, desc.text_blk_lpos.next)) return false; /* * Check the next descriptor after @tail_id before pushing the tail * to it because the tail must always be in a finalized or reusable * state. The implementation of prb_first_seq() relies on this. * * A successful read implies that the next descriptor is less than or * equal to @head_id so there is no risk of pushing the tail past the * head. */ d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc, NULL, NULL); /* LMM(desc_push_tail:A) */ if (d_state == desc_finalized || d_state == desc_reusable) { /* * Guarantee any descriptor states that have transitioned to * reusable are stored before pushing the tail ID. This allows * verifying the recycled descriptor state. A full memory * barrier is needed since other CPUs may have made the * descriptor states reusable. This pairs with desc_reserve:D. */ atomic_long_cmpxchg(&desc_ring->tail_id, tail_id, DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */ } else { /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail ID in the * case that the descriptor has been recycled. This pairs * with desc_reserve:D. * * Memory barrier involvement: * * If desc_push_tail:A reads from desc_reserve:F, then * desc_push_tail:D reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB from desc_push_tail:A to desc_push_tail:D * * Note: desc_push_tail:B and desc_reserve:F can be different * CPUs. However, the desc_reserve:F CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_push_tail:C) */ /* * Re-check the tail ID. The descriptor following @tail_id is * not in an allowed tail state. But if the tail has since * been moved by another CPU, then it does not matter. */ if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */ return false; } return true; } /* Reserve a new descriptor, invalidating the oldest if necessary. */ static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out) { struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val; unsigned long id_prev_wrap; struct prb_desc *desc; unsigned long head_id; unsigned long id; head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */ do { id = DESC_ID(head_id + 1); id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id); /* * Guarantee the head ID is read before reading the tail ID. * Since the tail ID is updated before the head ID, this * guarantees that @id_prev_wrap is never ahead of the tail * ID. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If desc_reserve:A reads from desc_reserve:D, then * desc_reserve:C reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:D * matching * RMB from desc_reserve:A to desc_reserve:C * * Note: desc_push_tail:B and desc_reserve:D can be different * CPUs. However, the desc_reserve:D CPU (which performs * the full memory barrier) must have previously seen * desc_push_tail:B. */ smp_rmb(); /* LMM(desc_reserve:B) */ if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id )) { /* LMM(desc_reserve:C) */ /* * Make space for the new descriptor by * advancing the tail. */ if (!desc_push_tail(rb, id_prev_wrap)) return false; } /* * 1. Guarantee the tail ID is read before validating the * recycled descriptor state. A read memory barrier is * sufficient for this. This pairs with desc_push_tail:B. * * Memory barrier involvement: * * If desc_reserve:C reads from desc_push_tail:B, then * desc_reserve:E reads from desc_make_reusable:A. * * Relies on: * * MB from desc_make_reusable:A to desc_push_tail:B * matching * RMB from desc_reserve:C to desc_reserve:E * * Note: desc_make_reusable:A and desc_push_tail:B can be * different CPUs. However, the desc_push_tail:B CPU * (which performs the full memory barrier) must have * previously seen desc_make_reusable:A. * * 2. Guarantee the tail ID is stored before storing the head * ID. This pairs with desc_reserve:B. * * 3. Guarantee any data ring tail changes are stored before * recycling the descriptor. Data ring tail changes can * happen via desc_push_tail()->data_push_tail(). A full * memory barrier is needed since another CPU may have * pushed the data ring tails. This pairs with * data_push_tail:B. * * 4. Guarantee a new tail ID is stored before recycling the * descriptor. A full memory barrier is needed since * another CPU may have pushed the tail ID. This pairs * with desc_push_tail:C and this also pairs with * prb_first_seq:C. * * 5. Guarantee the head ID is stored before trying to * finalize the previous descriptor. This pairs with * _prb_commit:B. */ } while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id, id)); /* LMM(desc_reserve:D) */ desc = to_desc(desc_ring, id); /* * If the descriptor has been recycled, verify the old state val. * See "ABA Issues" about why this verification is performed. */ prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */ if (prev_state_val && get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) { WARN_ON_ONCE(1); return false; } /* * Assign the descriptor a new ID and set its state to reserved. * See "ABA Issues" about why cmpxchg() instead of set() is used. * * Guarantee the new descriptor ID and state is stored before making * any other changes. A write memory barrier is sufficient for this. * This pairs with desc_read:D. */ if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */ WARN_ON_ONCE(1); return false; } /* Now data in @desc can be modified: LMM(desc_reserve:G) */ *id_out = id; return true; } /* Determine the end of a data block. */ static unsigned long get_next_lpos(struct prb_data_ring *data_ring, unsigned long lpos, unsigned int size) { unsigned long begin_lpos; unsigned long next_lpos; begin_lpos = lpos; next_lpos = lpos + size; /* First check if the data block does not wrap. */ if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos)) return next_lpos; /* Wrapping data blocks store their data at the beginning. */ return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size); } /* * Allocate a new data block, invalidating the oldest data block(s) * if necessary. This function also associates the data block with * a specified descriptor. */ static char *data_alloc(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_block *blk; unsigned long begin_lpos; unsigned long next_lpos; if (size == 0) { /* Specify a data-less block. */ blk_lpos->begin = NO_LPOS; blk_lpos->next = NO_LPOS; return NULL; } size = to_blk_size(size); begin_lpos = atomic_long_read(&data_ring->head_lpos); do { next_lpos = get_next_lpos(data_ring, begin_lpos, size); if (!data_push_tail(rb, data_ring, next_lpos - DATA_SIZE(data_ring))) { /* Failed to allocate, specify a data-less block. */ blk_lpos->begin = FAILED_LPOS; blk_lpos->next = FAILED_LPOS; return NULL; } /* * 1. Guarantee any descriptor states that have transitioned * to reusable are stored before modifying the newly * allocated data area. A full memory barrier is needed * since other CPUs may have made the descriptor states * reusable. See data_push_tail:A about why the reusable * states are visible. This pairs with desc_read:D. * * 2. Guarantee any updated tail lpos is stored before * modifying the newly allocated data area. Another CPU may * be in data_make_reusable() and is reading a block ID * from this area. data_make_reusable() can handle reading * a garbage block ID value, but then it must be able to * load a new tail lpos. A full memory barrier is needed * since other CPUs may have updated the tail lpos. This * pairs with data_push_tail:B. */ } while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos, next_lpos)); /* LMM(data_alloc:A) */ blk = to_block(data_ring, begin_lpos); blk->id = id; /* LMM(data_alloc:B) */ if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) { /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; } blk_lpos->begin = begin_lpos; blk_lpos->next = next_lpos; return &blk->data[0]; } /* * Try to resize an existing data block associated with the descriptor * specified by @id. If the resized data block should become wrapped, it * copies the old data to the new data block. If @size yields a data block * with the same or less size, the data block is left as is. * * Fail if this is not the last allocated data block or if there is not * enough space or it is not possible make enough space. * * Return a pointer to the beginning of the entire data buffer or NULL on * failure. */ static char *data_realloc(struct printk_ringbuffer *rb, struct prb_data_ring *data_ring, unsigned int size, struct prb_data_blk_lpos *blk_lpos, unsigned long id) { struct prb_data_block *blk; unsigned long head_lpos; unsigned long next_lpos; bool wrapped; /* Reallocation only works if @blk_lpos is the newest data block. */ head_lpos = atomic_long_read(&data_ring->head_lpos); if (head_lpos != blk_lpos->next) return NULL; /* Keep track if @blk_lpos was a wrapping data block. */ wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next)); size = to_blk_size(size); next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size); /* If the data block does not increase, there is nothing to do. */ if (head_lpos - next_lpos < DATA_SIZE(data_ring)) { if (wrapped) blk = to_block(data_ring, 0); else blk = to_block(data_ring, blk_lpos->begin); return &blk->data[0]; } if (!data_push_tail(rb, data_ring, next_lpos - DATA_SIZE(data_ring))) return NULL; /* The memory barrier involvement is the same as data_alloc:A. */ if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos, next_lpos)) { /* LMM(data_realloc:A) */ return NULL; } blk = to_block(data_ring, blk_lpos->begin); if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) { struct prb_data_block *old_blk = blk; /* Wrapping data blocks store their data at the beginning. */ blk = to_block(data_ring, 0); /* * Store the ID on the wrapped block for consistency. * The printk_ringbuffer does not actually use it. */ blk->id = id; if (!wrapped) { /* * Since the allocated space is now in the newly * created wrapping data block, copy the content * from the old data block. */ memcpy(&blk->data[0], &old_blk->data[0], (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id)); } } blk_lpos->next = next_lpos; return &blk->data[0]; } /* Return the number of bytes used by a data block. */ static unsigned int space_used(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos) { /* Data-less blocks take no space. */ if (BLK_DATALESS(blk_lpos)) return 0; if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) { /* Data block does not wrap. */ return (DATA_INDEX(data_ring, blk_lpos->next) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * For wrapping data blocks, the trailing (wasted) space is * also counted. */ return (DATA_INDEX(data_ring, blk_lpos->next) + DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin)); } /* * Given @blk_lpos, return a pointer to the writer data from the data block * and calculate the size of the data part. A NULL pointer is returned if * @blk_lpos specifies values that could never be legal. * * This function (used by readers) performs strict validation on the lpos * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static const char *get_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, unsigned int *data_size) { struct prb_data_block *db; /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { if (blk_lpos->begin == NO_LPOS && blk_lpos->next == NO_LPOS) { *data_size = 0; return ""; } return NULL; } /* Regular data block: @begin less than @next and in same wrap. */ if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) && blk_lpos->begin < blk_lpos->next) { db = to_block(data_ring, blk_lpos->begin); *data_size = blk_lpos->next - blk_lpos->begin; /* Wrapping data block: @begin is one wrap behind @next. */ } else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) == DATA_WRAPS(data_ring, blk_lpos->next)) { db = to_block(data_ring, 0); *data_size = DATA_INDEX(data_ring, blk_lpos->next); /* Illegal block description. */ } else { WARN_ON_ONCE(1); return NULL; } /* A valid data block will always be aligned to the ID size. */ if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) || WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) { return NULL; } /* A valid data block will always have at least an ID. */ if (WARN_ON_ONCE(*data_size < sizeof(db->id))) return NULL; /* Subtract block ID space from size to reflect data size. */ *data_size -= sizeof(db->id); return &db->data[0]; } /* * Attempt to transition the newest descriptor from committed back to reserved * so that the record can be modified by a writer again. This is only possible * if the descriptor is not yet finalized and the provided @caller_id matches. */ static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring, u32 caller_id, unsigned long *id_out) { unsigned long prev_state_val; enum desc_state d_state; struct prb_desc desc; struct prb_desc *d; unsigned long id; u32 cid; id = atomic_long_read(&desc_ring->head_id); /* * To reduce unnecessarily reopening, first check if the descriptor * state and caller ID are correct. */ d_state = desc_read(desc_ring, id, &desc, NULL, &cid); if (d_state != desc_committed || cid != caller_id) return NULL; d = to_desc(desc_ring, id); prev_state_val = DESC_SV(id, desc_committed); /* * Guarantee the reserved state is stored before reading any * record data. A full memory barrier is needed because @state_var * modification is followed by reading. This pairs with _prb_commit:B. * * Memory barrier involvement: * * If desc_reopen_last:A reads from _prb_commit:B, then * prb_reserve_in_last:A reads from _prb_commit:A. * * Relies on: * * WMB from _prb_commit:A to _prb_commit:B * matching * MB If desc_reopen_last:A to prb_reserve_in_last:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */ return NULL; } *id_out = id; return d; } /** * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer * used by the newest record. * * @e: The entry structure to setup. * @rb: The ringbuffer to re-reserve and extend data in. * @r: The record structure to allocate buffers for. * @caller_id: The caller ID of the caller (reserving writer). * @max_size: Fail if the extended size would be greater than this. * * This is the public function available to writers to re-reserve and extend * data. * * The writer specifies the text size to extend (not the new total size) by * setting the @text_buf_size field of @r. To ensure proper initialization * of @r, prb_rec_init_wr() should be used. * * This function will fail if @caller_id does not match the caller ID of the * newest record. In that case the caller must reserve new data using * prb_reserve(). * * Context: Any context. Disables local interrupts on success. * Return: true if text data could be extended, otherwise false. * * On success: * * - @r->text_buf points to the beginning of the entire text buffer. * * - @r->text_buf_size is set to the new total size of the buffer. * * - @r->info is not touched so that @r->info->text_len could be used * to append the text. * * - prb_record_text_space() can be used on @e to query the new * actually used space. * * Important: All @r->info fields will already be set with the current values * for the record. I.e. @r->info->text_len will be less than * @text_buf_size. Writers can use @r->info->text_len to know * where concatenation begins and writers should update * @r->info->text_len after concatenating. */ bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; unsigned int data_size; struct prb_desc *d; unsigned long id; local_irq_save(e->irqflags); /* Transition the newest descriptor back to the reserved state. */ d = desc_reopen_last(desc_ring, caller_id, &id); if (!d) { local_irq_restore(e->irqflags); goto fail_reopen; } /* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */ info = to_info(desc_ring, id); /* * Set the @e fields here so that prb_commit() can be used if * anything fails from now on. */ e->rb = rb; e->id = id; /* * desc_reopen_last() checked the caller_id, but there was no * exclusive access at that point. The descriptor may have * changed since then. */ if (caller_id != info->caller_id) goto fail; if (BLK_DATALESS(&d->text_blk_lpos)) { if (WARN_ON_ONCE(info->text_len != 0)) { pr_warn_once("wrong text_len value (%hu, expecting 0)\n", info->text_len); info->text_len = 0; } if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_alloc(rb, &rb->text_data_ring, r->text_buf_size, &d->text_blk_lpos, id); } else { if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size)) goto fail; /* * Increase the buffer size to include the original size. If * the meta data (@text_len) is not sane, use the full data * block size. */ if (WARN_ON_ONCE(info->text_len > data_size)) { pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n", info->text_len, data_size); info->text_len = data_size; } r->text_buf_size += info->text_len; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; if (r->text_buf_size > max_size) goto fail; r->text_buf = data_realloc(rb, &rb->text_data_ring, r->text_buf_size, &d->text_blk_lpos, id); } if (r->text_buf_size && !r->text_buf) goto fail; r->info = info; e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: prb_commit(e); /* prb_commit() re-enabled interrupts. */ fail_reopen: /* Make it clear to the caller that the re-reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ static void desc_make_final(struct prb_desc_ring *desc_ring, unsigned long id) { unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); atomic_long_cmpxchg_relaxed(&d->state_var, prev_state_val, DESC_SV(id, desc_finalized)); /* LMM(desc_make_final:A) */ /* Best effort to remember the last finalized @id. */ atomic_long_set(&desc_ring->last_finalized_id, id); } /** * prb_reserve() - Reserve space in the ringbuffer. * * @e: The entry structure to setup. * @rb: The ringbuffer to reserve data in. * @r: The record structure to allocate buffers for. * * This is the public function available to writers to reserve data. * * The writer specifies the text size to reserve by setting the * @text_buf_size field of @r. To ensure proper initialization of @r, * prb_rec_init_wr() should be used. * * Context: Any context. Disables local interrupts on success. * Return: true if at least text data could be allocated, otherwise false. * * On success, the fields @info and @text_buf of @r will be set by this * function and should be filled in by the writer before committing. Also * on success, prb_record_text_space() can be used on @e to query the actual * space used for the text data block. * * Important: @info->text_len needs to be set correctly by the writer in * order for data to be readable and/or extended. Its value * is initialized to 0. */ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info; struct prb_desc *d; unsigned long id; u64 seq; if (!data_check_size(&rb->text_data_ring, r->text_buf_size)) goto fail; /* * Descriptors in the reserved state act as blockers to all further * reservations once the desc_ring has fully wrapped. Disable * interrupts during the reserve/commit window in order to minimize * the likelihood of this happening. */ local_irq_save(e->irqflags); if (!desc_reserve(rb, &id)) { /* Descriptor reservation failures are tracked. */ atomic_long_inc(&rb->fail); local_irq_restore(e->irqflags); goto fail; } d = to_desc(desc_ring, id); info = to_info(desc_ring, id); /* * All @info fields (except @seq) are cleared and must be filled in * by the writer. Save @seq before clearing because it is used to * determine the new sequence number. */ seq = info->seq; memset(info, 0, sizeof(*info)); /* * Set the @e fields here so that prb_commit() can be used if * text data allocation fails. */ e->rb = rb; e->id = id; /* * Initialize the sequence number if it has "never been set". * Otherwise just increment it by a full wrap. * * @seq is considered "never been set" if it has a value of 0, * _except_ for @infos[0], which was specially setup by the ringbuffer * initializer and therefore is always considered as set. * * See the "Bootstrap" comment block in printk_ringbuffer.h for * details about how the initializer bootstraps the descriptors. */ if (seq == 0 && DESC_INDEX(desc_ring, id) != 0) info->seq = DESC_INDEX(desc_ring, id); else info->seq = seq + DESCS_COUNT(desc_ring); /* * New data is about to be reserved. Once that happens, previous * descriptors are no longer able to be extended. Finalize the * previous descriptor now so that it can be made available to * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) desc_make_final(desc_ring, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, &rb->text_data_ring, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ if (r->text_buf_size && !r->text_buf) { prb_commit(e); /* prb_commit() re-enabled interrupts. */ goto fail; } r->info = info; /* Record full text space used by record. */ e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos); return true; fail: /* Make it clear to the caller that the reserve failed. */ memset(r, 0, sizeof(*r)); return false; } /* Commit the data (possibly finalizing it) and restore interrupts. */ static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; struct prb_desc *d = to_desc(desc_ring, e->id); unsigned long prev_state_val = DESC_SV(e->id, desc_reserved); /* Now the writer has finished all writing: LMM(_prb_commit:A) */ /* * Set the descriptor as committed. See "ABA Issues" about why * cmpxchg() instead of set() is used. * * 1 Guarantee all record data is stored before the descriptor state * is stored as committed. A write memory barrier is sufficient * for this. This pairs with desc_read:B and desc_reopen_last:A. * * 2. Guarantee the descriptor state is stored as committed before * re-checking the head ID in order to possibly finalize this * descriptor. This pairs with desc_reserve:D. * * Memory barrier involvement: * * If prb_commit:A reads from desc_reserve:D, then * desc_make_final:A reads from _prb_commit:B. * * Relies on: * * MB _prb_commit:B to prb_commit:A * matching * MB desc_reserve:D to desc_make_final:A */ if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val, DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */ WARN_ON_ONCE(1); } /* Restore interrupts, the reserve/commit window is finished. */ local_irq_restore(e->irqflags); } /** * prb_commit() - Commit (previously reserved) data to the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit data. * * Note that the data is not yet available to readers until it is finalized. * Finalizing happens automatically when space for the next record is * reserved. * * See prb_final_commit() for a version of this function that finalizes * immediately. * * Context: Any context. Enables local interrupts. */ void prb_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; unsigned long head_id; _prb_commit(e, desc_committed); /* * If this descriptor is no longer the head (i.e. a new record has * been allocated), extending the data for this record is no longer * allowed and therefore it must be finalized. */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) desc_make_final(desc_ring, e->id); } /** * prb_final_commit() - Commit and finalize (previously reserved) data to * the ringbuffer. * * @e: The entry containing the reserved data information. * * This is the public function available to writers to commit+finalize data. * * By finalizing, the data is made immediately available to readers. * * This function should only be used if there are no intentions of extending * this data using prb_reserve_in_last(). * * Context: Any context. Enables local interrupts. */ void prb_final_commit(struct prb_reserved_entry *e) { struct prb_desc_ring *desc_ring = &e->rb->desc_ring; _prb_commit(e, desc_finalized); /* Best effort to remember the last finalized @id. */ atomic_long_set(&desc_ring->last_finalized_id, e->id); } /* * Count the number of lines in provided text. All text has at least 1 line * (even if @text_size is 0). Each '\n' processed is counted as an additional * line. */ static unsigned int count_lines(const char *text, unsigned int text_size) { unsigned int next_size = text_size; unsigned int line_count = 1; const char *next = text; while (next_size) { next = memchr(next, '\n', next_size); if (!next) break; line_count++; next++; next_size = text_size - (next - text); } return line_count; } /* * Given @blk_lpos, copy an expected @len of data into the provided buffer. * If @line_count is provided, count the number of lines in the data. * * This function (used by readers) performs strict validation on the data * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is * triggered if an internal error is detected. */ static bool copy_data(struct prb_data_ring *data_ring, struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf, unsigned int buf_size, unsigned int *line_count) { unsigned int data_size; const char *data; /* Caller might not want any data. */ if ((!buf || !buf_size) && !line_count) return true; data = get_data(data_ring, blk_lpos, &data_size); if (!data) return false; /* * Actual cannot be less than expected. It can be more than expected * because of the trailing alignment padding. * * Note that invalid @len values can occur because the caller loads * the value during an allowed data race. */ if (data_size < (unsigned int)len) return false; /* Caller interested in the line count? */ if (line_count) *line_count = count_lines(data, len); /* Caller interested in the data content? */ if (!buf || !buf_size) return true; data_size = min_t(u16, buf_size, len); memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */ return true; } /* * This is an extended version of desc_read(). It gets a copy of a specified * descriptor. However, it also verifies that the record is finalized and has * the sequence number @seq. On success, 0 is returned. * * Error return values: * -EINVAL: A finalized record with sequence number @seq does not exist. * -ENOENT: A finalized record with sequence number @seq exists, but its data * is not available. This is a valid record, so readers should * continue with the next record. */ static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring, unsigned long id, u64 seq, struct prb_desc *desc_out) { struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos; enum desc_state d_state; u64 s; d_state = desc_read(desc_ring, id, desc_out, &s, NULL); /* * An unexpected @id (desc_miss) or @seq mismatch means the record * does not exist. A descriptor in the reserved or committed state * means the record does not yet exist for the reader. */ if (d_state == desc_miss || d_state == desc_reserved || d_state == desc_committed || s != seq) { return -EINVAL; } /* * A descriptor in the reusable state may no longer have its data * available; report it as existing but with lost data. Or the record * may actually be a record with lost data. */ if (d_state == desc_reusable || (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) { return -ENOENT; } return 0; } /* * Copy the ringbuffer data from the record with @seq to the provided * @r buffer. On success, 0 is returned. * * See desc_read_finalized_seq() for error return values. */ static int prb_read(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r, unsigned int *line_count) { struct prb_desc_ring *desc_ring = &rb->desc_ring; struct printk_info *info = to_info(desc_ring, seq); struct prb_desc *rdesc = to_desc(desc_ring, seq); atomic_long_t *state_var = &rdesc->state_var; struct prb_desc desc; unsigned long id; int err; /* Extract the ID, used to specify the descriptor to read. */ id = DESC_ID(atomic_long_read(state_var)); /* Get a local copy of the correct descriptor (if available). */ err = desc_read_finalized_seq(desc_ring, id, seq, &desc); /* * If @r is NULL, the caller is only interested in the availability * of the record. */ if (err || !r) return err; /* If requested, copy meta data. */ if (r->info) memcpy(r->info, info, sizeof(*(r->info))); /* Copy text data. If it fails, this is a data-less record. */ if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len, r->text_buf, r->text_buf_size, line_count)) { return -ENOENT; } /* Ensure the record is still finalized and has the same @seq. */ return desc_read_finalized_seq(desc_ring, id, seq, &desc); } /* Get the sequence number of the tail descriptor. */ static u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; struct prb_desc desc; unsigned long id; u64 seq; for (;;) { id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */ d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */ /* * This loop will not be infinite because the tail is * _always_ in the finalized or reusable state. */ if (d_state == desc_finalized || d_state == desc_reusable) break; /* * Guarantee the last state load from desc_read() is before * reloading @tail_id in order to see a new tail in the case * that the descriptor has been recycled. This pairs with * desc_reserve:D. * * Memory barrier involvement: * * If prb_first_seq:B reads from desc_reserve:F, then * prb_first_seq:A reads from desc_push_tail:B. * * Relies on: * * MB from desc_push_tail:B to desc_reserve:F * matching * RMB prb_first_seq:B to prb_first_seq:A */ smp_rmb(); /* LMM(prb_first_seq:C) */ } return seq; } /* * Non-blocking read of a record. Updates @seq to the last finalized record * (which may have no data available). * * See the description of prb_read_valid() and prb_read_valid_info() * for details. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) { u64 tail_seq; int err; while ((err = prb_read(rb, *seq, r, line_count))) { tail_seq = prb_first_seq(rb); if (*seq < tail_seq) { /* * Behind the tail. Catch up and try again. This * can happen for -ENOENT and -EINVAL cases. */ *seq = tail_seq; } else if (err == -ENOENT) { /* Record exists, but no data available. Skip. */ (*seq)++; } else { /* Non-existent/non-finalized record. Must stop. */ return false; } } return true; } /** * prb_read_valid() - Non-blocking read of a requested record or (if gone) * the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @r: A record data buffer to store the read record to. * * This is the public function available to readers to read a record. * * The reader provides the @info and @text_buf buffers of @r to be * filled in. Any of the buffer pointers can be set to NULL if the reader * is not interested in that data. To ensure proper initialization of @r, * prb_rec_init_rd() should be used. * * Context: Any context. * Return: true if a record was read, otherwise false. * * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a not yet written record. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) { return _prb_read_valid(rb, &seq, r, NULL); } /** * prb_read_valid_info() - Non-blocking read of meta data for a requested * record or (if gone) the next available record. * * @rb: The ringbuffer to read from. * @seq: The sequence number of the record to read. * @info: A buffer to store the read record meta data to. * @line_count: A buffer to store the number of lines in the record text. * * This is the public function available to readers to read only the * meta data of a record. * * The reader provides the @info, @line_count buffers to be filled in. * Either of the buffer pointers can be set to NULL if the reader is not * interested in that data. * * Context: Any context. * Return: true if a record's meta data was read, otherwise false. * * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * * Failure means @seq refers to a not yet written record. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) { struct printk_record r; prb_rec_init_rd(&r, info, NULL, 0); return _prb_read_valid(rb, &seq, &r, line_count); } /** * prb_first_valid_seq() - Get the sequence number of the oldest available * record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the * first/oldest valid sequence number is. * * This provides readers a starting point to begin iterating the ringbuffer. * * Context: Any context. * Return: The sequence number of the first/oldest record or, if the * ringbuffer is empty, 0 is returned. */ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) { u64 seq = 0; if (!_prb_read_valid(rb, &seq, NULL, NULL)) return 0; return seq; } /** * prb_next_seq() - Get the sequence number after the last available record. * * @rb: The ringbuffer to get the sequence number from. * * This is the public function available to readers to see what the next * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently * available records should be skipped. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record * for readers. */ u64 prb_next_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; unsigned long id; u64 seq; /* Check if the cached @id still points to a valid @seq. */ id = atomic_long_read(&desc_ring->last_finalized_id); d_state = desc_read(desc_ring, id, NULL, &seq, NULL); if (d_state == desc_finalized || d_state == desc_reusable) { /* * Begin searching after the last finalized record. * * On 0, the search must begin at 0 because of hack#2 * of the bootstrapping phase it is not known if a * record at index 0 exists. */ if (seq != 0) seq++; } else { /* * The information about the last finalized sequence number * has gone. It should happen only when there is a flood of * new messages and the ringbuffer is rapidly recycled. * Give up and start from the beginning. */ seq = 0; } /* * The information about the last finalized @seq might be inaccurate. * Search forward to find the current one. */ while (_prb_read_valid(rb, &seq, NULL, NULL)) seq++; return seq; } /** * prb_init() - Initialize a ringbuffer to use provided external buffers. * * @rb: The ringbuffer to initialize. * @text_buf: The data buffer for text data. * @textbits: The size of @text_buf as a power-of-2 value. * @descs: The descriptor buffer for ringbuffer records. * @descbits: The count of @descs items as a power-of-2 value. * @infos: The printk_info buffer for ringbuffer records. * * This is the public function available to writers to setup a ringbuffer * during runtime using provided buffers. * * This must match the initialization of DEFINE_PRINTKRB(). * * Context: Any context. */ void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int textbits, struct prb_desc *descs, unsigned int descbits, struct printk_info *infos) { memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0])); memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0])); rb->desc_ring.count_bits = descbits; rb->desc_ring.descs = descs; rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.last_finalized_id, DESC0_ID(descbits)); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits)); atomic_long_set(&rb->fail, 0); atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits)); descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS; descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS; infos[0].seq = -(u64)_DESCS_COUNT(descbits); infos[_DESCS_COUNT(descbits) - 1].seq = 0; } /** * prb_record_text_space() - Query the full actual used ringbuffer space for * the text data of a reserved entry. * * @e: The successfully reserved entry to query. * * This is the public function available to writers to see how much actual * space is used in the ringbuffer to store the text data of the specified * entry. * * This function is only valid if @e has been successfully reserved using * prb_reserve(). * * Context: Any context. * Return: The size in bytes used by the text data of the associated record. */ unsigned int prb_record_text_space(struct prb_reserved_entry *e) { return e->text_space; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/freezer.c - Function to freeze a process * * Originally from kernel/power/process.c */ #include <linux/interrupt.h> #include <linux/suspend.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/mmu_context.h> #undef CREATE_TRACE_POINT #include <trace/hooks/cgroup.h> /* total number of freezing conditions in effect */ atomic_t system_freezing_cnt = ATOMIC_INIT(0); EXPORT_SYMBOL(system_freezing_cnt); /* indicate whether PM freezing is in effect, protected by * system_transition_mutex */ bool pm_freezing; bool pm_nosig_freezing; /* protects freezing and frozen transitions */ static DEFINE_SPINLOCK(freezer_lock); /** * freezing_slow_path - slow path for testing whether a task needs to be frozen * @p: task to be tested * * This function is called by freezing() if system_freezing_cnt isn't zero * and tests whether @p needs to enter and stay in frozen state. Can be * called under any context. The freezers are responsible for ensuring the * target tasks see the updated state. */ bool freezing_slow_path(struct task_struct *p) { if (p->flags & (PF_NOFREEZE | PF_SUSPEND_TASK)) return false; if (test_tsk_thread_flag(p, TIF_MEMDIE)) return false; if (pm_nosig_freezing || cgroup_freezing(p)) return true; if (pm_freezing && !(p->flags & PF_KTHREAD)) return true; return false; } EXPORT_SYMBOL(freezing_slow_path); /* Refrigerator is place where frozen processes are stored :-). */ bool __refrigerator(bool check_kthr_stop) { /* Hmm, should we be allowed to suspend when there are realtime processes around? */ bool was_frozen = false; long save = current->state; pr_debug("%s entered refrigerator\n", current->comm); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); spin_lock_irq(&freezer_lock); current->flags |= PF_FROZEN; if (!freezing(current) || (check_kthr_stop && kthread_should_stop())) current->flags &= ~PF_FROZEN; trace_android_rvh_refrigerator(pm_nosig_freezing); spin_unlock_irq(&freezer_lock); if (!(current->flags & PF_FROZEN)) break; was_frozen = true; schedule(); } pr_debug("%s left refrigerator\n", current->comm); /* * Restore saved task state before returning. The mb'd version * needs to be used; otherwise, it might silently break * synchronization which depends on ordered task state change. */ set_current_state(save); return was_frozen; } EXPORT_SYMBOL(__refrigerator); static void fake_signal_wake_up(struct task_struct *p) { unsigned long flags; if (lock_task_sighand(p, &flags)) { signal_wake_up(p, 0); unlock_task_sighand(p, &flags); } } /** * freeze_task - send a freeze request to given task * @p: task to send the request to * * If @p is freezing, the freeze request is sent either by sending a fake * signal (if it's not a kernel thread) or waking it up (if it's a kernel * thread). * * RETURNS: * %false, if @p is not freezing or already frozen; %true, otherwise */ bool freeze_task(struct task_struct *p) { unsigned long flags; /* * This check can race with freezer_do_not_count, but worst case that * will result in an extra wakeup being sent to the task. It does not * race with freezer_count(), the barriers in freezer_count() and * freezer_should_skip() ensure that either freezer_count() sees * freezing == true in try_to_freeze() and freezes, or * freezer_should_skip() sees !PF_FREEZE_SKIP and freezes the task * normally. */ if (freezer_should_skip(p)) return false; spin_lock_irqsave(&freezer_lock, flags); if (!freezing(p) || frozen(p)) { spin_unlock_irqrestore(&freezer_lock, flags); return false; } if (!(p->flags & PF_KTHREAD)) fake_signal_wake_up(p); else wake_up_state(p, TASK_INTERRUPTIBLE); spin_unlock_irqrestore(&freezer_lock, flags); return true; } void __thaw_task(struct task_struct *p) { unsigned long flags; const struct cpumask *mask = task_cpu_possible_mask(p); spin_lock_irqsave(&freezer_lock, flags); /* * Wake up frozen tasks. On asymmetric systems where tasks cannot * run on all CPUs, ttwu() may have deferred a wakeup generated * before thaw_secondary_cpus() had completed so we generate * additional wakeups here for tasks in the PF_FREEZER_SKIP state. */ if (frozen(p) || (frozen_or_skipped(p) && mask != cpu_possible_mask)) wake_up_process(p); spin_unlock_irqrestore(&freezer_lock, flags); } /** * set_freezable - make %current freezable * * Mark %current freezable and enter refrigerator if necessary. */ bool set_freezable(void) { might_sleep(); /* * Modify flags while holding freezer_lock. This ensures the * freezer notices that we aren't frozen yet or the freezing * condition is visible to try_to_freeze() below. */ spin_lock_irq(&freezer_lock); current->flags &= ~PF_NOFREEZE; spin_unlock_irq(&freezer_lock); return try_to_freeze(); } EXPORT_SYMBOL(set_freezable); |
| 605 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/types.h> struct page; /** * struct bio_vec - a contiguous range of physical memory addresses * @bv_page: First page associated with the address range. * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: * * nth_page(@bv_page, n) == @bv_page + n * * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { unsigned int idx = iter->bi_idx; if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } iter->bi_size -= bytes; bytes += iter->bi_bvec_done; while (bytes && bytes >= bv[idx].bv_len) { bytes -= bv[idx].bv_len; idx++; } iter->bi_idx = idx; iter->bi_bvec_done = bytes; return true; } static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) { iter->bi_bvec_done = 0; iter->bi_idx++; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } #endif /* __LINUX_BVEC_ITER_H */ |
| 16 623 566 260 22 22 26 248 260 315 22 314 52 627 627 625 627 281 12 281 282 42 327 70 16 326 70 72 72 72 72 72 72 72 72 72 72 72 1 72 80 79 80 72 2 4 72 72 72 505 540 540 43 44 44 8 8 445 776 845 777 445 845 915 918 127 127 975 286 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 | // SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/journal.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * Generic filesystem journal-writing code; part of the ext2fs * journaling system. * * This file manages journals: areas of disk reserved for logging * transactional updates. This includes the kernel journaling thread * which is responsible for scheduling updates to the log. * * We do not actually manage the physical storage of the journal in this * file: that is left to a per-journal policy function, which allows us * to store the journal within a filesystem-specified area for ext2 * journaling (ext2 can use a reserved inode for storing the log). */ #include <linux/module.h> #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/freezer.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/poison.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/math64.h> #include <linux/hash.h> #include <linux/log2.h> #include <linux/vmalloc.h> #include <linux/backing-dev.h> #include <linux/bitops.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #define CREATE_TRACE_POINTS #include <trace/events/jbd2.h> #include <linux/uaccess.h> #include <asm/page.h> #ifdef CONFIG_JBD2_DEBUG ushort jbd2_journal_enable_debug __read_mostly; EXPORT_SYMBOL(jbd2_journal_enable_debug); module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2"); #endif EXPORT_SYMBOL(jbd2_journal_extend); EXPORT_SYMBOL(jbd2_journal_stop); EXPORT_SYMBOL(jbd2_journal_lock_updates); EXPORT_SYMBOL(jbd2_journal_unlock_updates); EXPORT_SYMBOL(jbd2_journal_get_write_access); EXPORT_SYMBOL(jbd2_journal_get_create_access); EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); EXPORT_SYMBOL(jbd2_journal_forget); EXPORT_SYMBOL(jbd2_journal_flush); EXPORT_SYMBOL(jbd2_journal_revoke); EXPORT_SYMBOL(jbd2_journal_init_dev); EXPORT_SYMBOL(jbd2_journal_init_inode); EXPORT_SYMBOL(jbd2_journal_check_used_features); EXPORT_SYMBOL(jbd2_journal_check_available_features); EXPORT_SYMBOL(jbd2_journal_set_features); EXPORT_SYMBOL(jbd2_journal_load); EXPORT_SYMBOL(jbd2_journal_destroy); EXPORT_SYMBOL(jbd2_journal_abort); EXPORT_SYMBOL(jbd2_journal_errno); EXPORT_SYMBOL(jbd2_journal_ack_err); EXPORT_SYMBOL(jbd2_journal_clear_err); EXPORT_SYMBOL(jbd2_log_wait_commit); EXPORT_SYMBOL(jbd2_log_start_commit); EXPORT_SYMBOL(jbd2_journal_start_commit); EXPORT_SYMBOL(jbd2_journal_force_commit_nested); EXPORT_SYMBOL(jbd2_journal_wipe); EXPORT_SYMBOL(jbd2_journal_blocks_per_page); EXPORT_SYMBOL(jbd2_journal_invalidatepage); EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); EXPORT_SYMBOL(jbd2_journal_submit_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); EXPORT_SYMBOL(jbd2_inode_cache); static int jbd2_journal_create_slab(size_t slab_size); #ifdef CONFIG_JBD2_DEBUG void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...) { struct va_format vaf; va_list args; if (level > jbd2_journal_enable_debug) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_DEBUG "%s: (%s, %u): %pV", file, func, line, &vaf); va_end(args); } EXPORT_SYMBOL(__jbd2_debug); #endif /* Checksumming functions */ static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { if (!jbd2_journal_has_csum_v2or3_feature(j)) return 1; return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; } static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) { __u32 csum; __be32 old_csum; old_csum = sb->s_checksum; sb->s_checksum = 0; csum = jbd2_chksum(j, ~0, (char *)sb, sizeof(journal_superblock_t)); sb->s_checksum = old_csum; return cpu_to_be32(csum); } /* * Helper function used to manage commit timeouts */ static void commit_timeout(struct timer_list *t) { journal_t *journal = from_timer(journal, t, j_commit_timer); wake_up_process(journal->j_task); } /* * kjournald2: The main thread function used to manage a logging device * journal. * * This kernel thread is responsible for two things: * * 1) COMMIT: Every so often we need to commit the current state of the * filesystem to disk. The journal thread is responsible for writing * all of the metadata buffers to disk. If a fast commit is ongoing * journal thread waits until it's done and then continues from * there on. * * 2) CHECKPOINT: We cannot reuse a used section of the log file until all * of the data in that part of the log has been rewritten elsewhere on * the disk. Flushing these old buffers to reclaim space in the log is * known as checkpointing, and this thread is responsible for that job. */ static int kjournald2(void *arg) { journal_t *journal = arg; transaction_t *transaction; /* * Set up an interval timer which can be used to trigger a commit wakeup * after the commit interval expires */ timer_setup(&journal->j_commit_timer, commit_timeout, 0); set_freezable(); /* Record that the journal thread is running */ journal->j_task = current; wake_up(&journal->j_wait_done_commit); /* * Make sure that no allocations from this kernel thread will ever * recurse to the fs layer because we are responsible for the * transaction commit and any fs involvement might get stuck waiting for * the trasn. commit. */ memalloc_nofs_save(); /* * And now, wait forever for commit wakeup events. */ write_lock(&journal->j_state_lock); loop: if (journal->j_flags & JBD2_UNMOUNT) goto end_loop; jbd_debug(1, "commit_sequence=%u, commit_request=%u\n", journal->j_commit_sequence, journal->j_commit_request); if (journal->j_commit_sequence != journal->j_commit_request) { jbd_debug(1, "OK, requests differ\n"); write_unlock(&journal->j_state_lock); del_timer_sync(&journal->j_commit_timer); jbd2_journal_commit_transaction(journal); write_lock(&journal->j_state_lock); goto loop; } wake_up(&journal->j_wait_done_commit); if (freezing(current)) { /* * The simpler the better. Flushing journal isn't a * good idea, because that depends on threads that may * be already stopped. */ jbd_debug(1, "Now suspending kjournald2\n"); write_unlock(&journal->j_state_lock); try_to_freeze(); write_lock(&journal->j_state_lock); } else { /* * We assume on resume that commits are already there, * so we don't sleep */ DEFINE_WAIT(wait); int should_sleep = 1; prepare_to_wait(&journal->j_wait_commit, &wait, TASK_INTERRUPTIBLE); if (journal->j_commit_sequence != journal->j_commit_request) should_sleep = 0; transaction = journal->j_running_transaction; if (transaction && time_after_eq(jiffies, transaction->t_expires)) should_sleep = 0; if (journal->j_flags & JBD2_UNMOUNT) should_sleep = 0; if (should_sleep) { write_unlock(&journal->j_state_lock); schedule(); write_lock(&journal->j_state_lock); } finish_wait(&journal->j_wait_commit, &wait); } jbd_debug(1, "kjournald2 wakes\n"); /* * Were we woken up by a commit wakeup event? */ transaction = journal->j_running_transaction; if (transaction && time_after_eq(jiffies, transaction->t_expires)) { journal->j_commit_request = transaction->t_tid; jbd_debug(1, "woke because of timeout\n"); } goto loop; end_loop: del_timer_sync(&journal->j_commit_timer); journal->j_task = NULL; wake_up(&journal->j_wait_done_commit); jbd_debug(1, "Journal thread exiting.\n"); write_unlock(&journal->j_state_lock); return 0; } static int jbd2_journal_start_thread(journal_t *journal) { struct task_struct *t; t = kthread_run(kjournald2, journal, "jbd2/%s", journal->j_devname); if (IS_ERR(t)) return PTR_ERR(t); wait_event(journal->j_wait_done_commit, journal->j_task != NULL); return 0; } static void journal_kill_thread(journal_t *journal) { write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_UNMOUNT; while (journal->j_task) { write_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); wait_event(journal->j_wait_done_commit, journal->j_task == NULL); write_lock(&journal->j_state_lock); } write_unlock(&journal->j_state_lock); } /* * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal. * * Writes a metadata buffer to a given disk block. The actual IO is not * performed but a new buffer_head is constructed which labels the data * to be written with the correct destination disk block. * * Any magic-number escaping which needs to be done will cause a * copy-out here. If the buffer happens to start with the * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the * magic number is only written to the log for descripter blocks. In * this case, we copy the data and replace the first word with 0, and we * return a result code which indicates that this buffer needs to be * marked as an escaped buffer in the corresponding log descriptor * block. The missing word can then be restored when the block is read * during recovery. * * If the source buffer has already been modified by a new transaction * since we took the last commit snapshot, we use the frozen copy of * that data for IO. If we end up using the existing buffer_head's data * for the write, then we have to make sure nobody modifies it while the * IO is in progress. do_get_write_access() handles this. * * The function returns a pointer to the buffer_head to be used for IO. * * * Return value: * <0: Error * >=0: Finished OK * * On success: * Bit 0 set == escape performed on the data * Bit 1 set == buffer copy-out performed (kfree the data after IO) */ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr) { int need_copy_out = 0; int done_copy_out = 0; int do_escape = 0; char *mapped_data; struct buffer_head *new_bh; struct page *new_page; unsigned int new_offset; struct buffer_head *bh_in = jh2bh(jh_in); journal_t *journal = transaction->t_journal; /* * The buffer really shouldn't be locked: only the current committing * transaction is allowed to write it, so nobody else is allowed * to do any IO. * * akpm: except if we're journalling data, and write() output is * also part of a shared mapping, and another thread has * decided to launch a writepage() against this buffer. */ J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in)); new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL); /* keep subsequent assertions sane */ atomic_set(&new_bh->b_count, 1); spin_lock(&jh_in->b_state_lock); repeat: /* * If a new transaction has already done a buffer copy-out, then * we use that version of the data for the commit. */ if (jh_in->b_frozen_data) { done_copy_out = 1; new_page = virt_to_page(jh_in->b_frozen_data); new_offset = offset_in_page(jh_in->b_frozen_data); } else { new_page = jh2bh(jh_in)->b_page; new_offset = offset_in_page(jh2bh(jh_in)->b_data); } mapped_data = kmap_atomic(new_page); /* * Fire data frozen trigger if data already wasn't frozen. Do this * before checking for escaping, as the trigger may modify the magic * offset. If a copy-out happens afterwards, it will have the correct * data in the buffer. */ if (!done_copy_out) jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset, jh_in->b_triggers); /* * Check for escaping */ if (*((__be32 *)(mapped_data + new_offset)) == cpu_to_be32(JBD2_MAGIC_NUMBER)) { need_copy_out = 1; do_escape = 1; } kunmap_atomic(mapped_data); /* * Do we need to do a data copy? */ if (need_copy_out && !done_copy_out) { char *tmp; spin_unlock(&jh_in->b_state_lock); tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); if (!tmp) { brelse(new_bh); return -ENOMEM; } spin_lock(&jh_in->b_state_lock); if (jh_in->b_frozen_data) { jbd2_free(tmp, bh_in->b_size); goto repeat; } jh_in->b_frozen_data = tmp; mapped_data = kmap_atomic(new_page); memcpy(tmp, mapped_data + new_offset, bh_in->b_size); kunmap_atomic(mapped_data); new_page = virt_to_page(tmp); new_offset = offset_in_page(tmp); done_copy_out = 1; /* * This isn't strictly necessary, as we're using frozen * data for the escaping, but it keeps consistency with * b_frozen_data usage. */ jh_in->b_frozen_triggers = jh_in->b_triggers; } /* * Did we need to do an escaping? Now we've done all the * copying, we can finally do so. */ if (do_escape) { mapped_data = kmap_atomic(new_page); *((unsigned int *)(mapped_data + new_offset)) = 0; kunmap_atomic(mapped_data); } set_bh_page(new_bh, new_page, new_offset); new_bh->b_size = bh_in->b_size; new_bh->b_bdev = journal->j_dev; new_bh->b_blocknr = blocknr; new_bh->b_private = bh_in; set_buffer_mapped(new_bh); set_buffer_dirty(new_bh); *bh_out = new_bh; /* * The to-be-written buffer needs to get moved to the io queue, * and the original buffer whose contents we are shadowing or * copying is moved to the transaction's shadow queue. */ JBUFFER_TRACE(jh_in, "file as BJ_Shadow"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); spin_unlock(&journal->j_list_lock); set_buffer_shadow(bh_in); spin_unlock(&jh_in->b_state_lock); return do_escape | (done_copy_out << 1); } /* * Allocation code for the journal file. Manage the space left in the * journal, so that we can begin checkpointing when appropriate. */ /* * Called with j_state_lock locked for writing. * Returns true if a transaction commit was started. */ int __jbd2_log_start_commit(journal_t *journal, tid_t target) { /* Return if the txn has already requested to be committed */ if (journal->j_commit_request == target) return 0; /* * The only transaction we can possibly wait upon is the * currently running transaction (if it exists). Otherwise, * the target tid must be an old one. */ if (journal->j_running_transaction && journal->j_running_transaction->t_tid == target) { /* * We want a new commit: OK, mark the request and wakeup the * commit thread. We do _not_ do the commit ourselves. */ journal->j_commit_request = target; jbd_debug(1, "JBD2: requesting commit %u/%u\n", journal->j_commit_request, journal->j_commit_sequence); journal->j_running_transaction->t_requested = jiffies; wake_up(&journal->j_wait_commit); return 1; } else if (!tid_geq(journal->j_commit_request, target)) /* This should never happen, but if it does, preserve the evidence before kjournald goes into a loop and increments j_commit_sequence beyond all recognition. */ WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n", journal->j_commit_request, journal->j_commit_sequence, target, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); return 0; } int jbd2_log_start_commit(journal_t *journal, tid_t tid) { int ret; write_lock(&journal->j_state_lock); ret = __jbd2_log_start_commit(journal, tid); write_unlock(&journal->j_state_lock); return ret; } /* * Force and wait any uncommitted transactions. We can only force the running * transaction if we don't have an active handle, otherwise, we will deadlock. * Returns: <0 in case of error, * 0 if nothing to commit, * 1 if transaction was successfully committed. */ static int __jbd2_journal_force_commit(journal_t *journal) { transaction_t *transaction = NULL; tid_t tid; int need_to_start = 0, ret = 0; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && !current->journal_info) { transaction = journal->j_running_transaction; if (!tid_geq(journal->j_commit_request, transaction->t_tid)) need_to_start = 1; } else if (journal->j_committing_transaction) transaction = journal->j_committing_transaction; if (!transaction) { /* Nothing to commit */ read_unlock(&journal->j_state_lock); return 0; } tid = transaction->t_tid; read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); ret = jbd2_log_wait_commit(journal, tid); if (!ret) ret = 1; return ret; } /** * jbd2_journal_force_commit_nested - Force and wait upon a commit if the * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. * * This is used for forcing out undo-protected data which contains * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { int ret; ret = __jbd2_journal_force_commit(journal); return ret > 0; } /** * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction * if we don't have an active handle, otherwise, we will deadlock. */ int jbd2_journal_force_commit(journal_t *journal) { int ret; J_ASSERT(!current->journal_info); ret = __jbd2_journal_force_commit(journal); if (ret > 0) ret = 0; return ret; } /* * Start a commit of the current running transaction (if any). Returns true * if a transaction is going to be committed (or is currently already * committing), and fills its tid in at *ptid */ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) { int ret = 0; write_lock(&journal->j_state_lock); if (journal->j_running_transaction) { tid_t tid = journal->j_running_transaction->t_tid; __jbd2_log_start_commit(journal, tid); /* There's a running transaction and we've just made sure * it's commit has been scheduled. */ if (ptid) *ptid = tid; ret = 1; } else if (journal->j_committing_transaction) { /* * If commit has been started, then we have to wait for * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; ret = 1; } write_unlock(&journal->j_state_lock); return ret; } /* * Return 1 if a given transaction has not yet sent barrier request * connected with a transaction commit. If 0 is returned, transaction * may or may not have sent the barrier. Used to avoid sending barrier * twice in common cases. */ int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid) { int ret = 0; transaction_t *commit_trans; if (!(journal->j_flags & JBD2_BARRIER)) return 0; read_lock(&journal->j_state_lock); /* Transaction already committed? */ if (tid_geq(journal->j_commit_sequence, tid)) goto out; commit_trans = journal->j_committing_transaction; if (!commit_trans || commit_trans->t_tid != tid) { ret = 1; goto out; } /* * Transaction is being committed and we already proceeded to * submitting a flush to fs partition? */ if (journal->j_fs_dev != journal->j_dev) { if (!commit_trans->t_need_data_flush || commit_trans->t_state >= T_COMMIT_DFLUSH) goto out; } else { if (commit_trans->t_state >= T_COMMIT_JFLUSH) goto out; } ret = 1; out: read_unlock(&journal->j_state_lock); return ret; } EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier); /* * Wait for a specified commit to complete. * The caller may not hold the journal lock. */ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) { int err = 0; read_lock(&journal->j_state_lock); #ifdef CONFIG_PROVE_LOCKING /* * Some callers make sure transaction is already committing and in that * case we cannot block on open handles anymore. So don't warn in that * case. */ if (tid_gt(tid, journal->j_commit_sequence) && (!journal->j_committing_transaction || journal->j_committing_transaction->t_tid != tid)) { read_unlock(&journal->j_state_lock); jbd2_might_wait_for_commit(journal); read_lock(&journal->j_state_lock); } #endif #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { printk(KERN_ERR "%s: error: j_commit_request=%u, tid=%u\n", __func__, journal->j_commit_request, tid); } #endif while (tid_gt(tid, journal->j_commit_sequence)) { jbd_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", tid, journal->j_commit_sequence); read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); wait_event(journal->j_wait_done_commit, !tid_gt(tid, journal->j_commit_sequence)); read_lock(&journal->j_state_lock); } read_unlock(&journal->j_state_lock); if (unlikely(is_journal_aborted(journal))) err = -EIO; return err; } /* * Start a fast commit. If there's an ongoing fast or full commit wait for * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY * if a fast commit is not needed, either because there's an already a commit * going on or this tid has already been committed. Returns -EINVAL if no jbd2 * commit has yet been performed. */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) { if (unlikely(is_journal_aborted(journal))) return -EIO; /* * Fast commits only allowed if at least one full commit has * been processed. */ if (!journal->j_stats.ts_tid) return -EINVAL; write_lock(&journal->j_state_lock); if (tid <= journal->j_commit_sequence) { write_unlock(&journal->j_state_lock); return -EALREADY; } if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { DEFINE_WAIT(wait); prepare_to_wait(&journal->j_fc_wait, &wait, TASK_UNINTERRUPTIBLE); write_unlock(&journal->j_state_lock); schedule(); finish_wait(&journal->j_fc_wait, &wait); return -EALREADY; } journal->j_flags |= JBD2_FAST_COMMIT_ONGOING; write_unlock(&journal->j_state_lock); return 0; } EXPORT_SYMBOL(jbd2_fc_begin_commit); /* * Stop a fast commit. If fallback is set, this function starts commit of * TID tid before any other fast commit can start. */ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) { if (journal->j_fc_cleanup_callback) journal->j_fc_cleanup_callback(journal, 0); write_lock(&journal->j_state_lock); journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; if (fallback) journal->j_flags |= JBD2_FULL_COMMIT_ONGOING; write_unlock(&journal->j_state_lock); wake_up(&journal->j_fc_wait); if (fallback) return jbd2_complete_transaction(journal, tid); return 0; } int jbd2_fc_end_commit(journal_t *journal) { return __jbd2_fc_end_commit(journal, 0, false); } EXPORT_SYMBOL(jbd2_fc_end_commit); int jbd2_fc_end_commit_fallback(journal_t *journal) { tid_t tid; read_lock(&journal->j_state_lock); tid = journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0; read_unlock(&journal->j_state_lock); return __jbd2_fc_end_commit(journal, tid, true); } EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); /* Return 1 when transaction with given tid has already committed. */ int jbd2_transaction_committed(journal_t *journal, tid_t tid) { int ret = 1; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && journal->j_running_transaction->t_tid == tid) ret = 0; if (journal->j_committing_transaction && journal->j_committing_transaction->t_tid == tid) ret = 0; read_unlock(&journal->j_state_lock); return ret; } EXPORT_SYMBOL(jbd2_transaction_committed); /* * When this function returns the transaction corresponding to tid * will be completed. If the transaction has currently running, start * committing that transaction before waiting for it to complete. If * the transaction id is stale, it is by definition already completed, * so just return SUCCESS. */ int jbd2_complete_transaction(journal_t *journal, tid_t tid) { int need_to_wait = 1; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && journal->j_running_transaction->t_tid == tid) { if (journal->j_commit_request != tid) { /* transaction not yet started, so request it */ read_unlock(&journal->j_state_lock); jbd2_log_start_commit(journal, tid); goto wait_commit; } } else if (!(journal->j_committing_transaction && journal->j_committing_transaction->t_tid == tid)) need_to_wait = 0; read_unlock(&journal->j_state_lock); if (!need_to_wait) return 0; wait_commit: return jbd2_log_wait_commit(journal, tid); } EXPORT_SYMBOL(jbd2_complete_transaction); /* * Log buffer allocation routines: */ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) { unsigned long blocknr; write_lock(&journal->j_state_lock); J_ASSERT(journal->j_free > 1); blocknr = journal->j_head; journal->j_head++; journal->j_free--; if (journal->j_head == journal->j_last) journal->j_head = journal->j_first; write_unlock(&journal->j_state_lock); return jbd2_journal_bmap(journal, blocknr, retp); } /* Map one fast commit buffer for use by the file system */ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) { unsigned long long pblock; unsigned long blocknr; int ret = 0; struct buffer_head *bh; int fc_off; *bh_out = NULL; if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) { fc_off = journal->j_fc_off; blocknr = journal->j_fc_first + fc_off; journal->j_fc_off++; } else { ret = -EINVAL; } if (ret) return ret; ret = jbd2_journal_bmap(journal, blocknr, &pblock); if (ret) return ret; bh = __getblk(journal->j_dev, pblock, journal->j_blocksize); if (!bh) return -ENOMEM; journal->j_fc_wbuf[fc_off] = bh; *bh_out = bh; return 0; } EXPORT_SYMBOL(jbd2_fc_get_buf); /* * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf * for completion. */ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) { struct buffer_head *bh; int i, j_fc_off; j_fc_off = journal->j_fc_off; /* * Wait in reverse order to minimize chances of us being woken up before * all IOs have completed */ for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) { bh = journal->j_fc_wbuf[i]; wait_on_buffer(bh); put_bh(bh); journal->j_fc_wbuf[i] = NULL; if (unlikely(!buffer_uptodate(bh))) return -EIO; } return 0; } EXPORT_SYMBOL(jbd2_fc_wait_bufs); /* * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf * for completion. */ int jbd2_fc_release_bufs(journal_t *journal) { struct buffer_head *bh; int i, j_fc_off; j_fc_off = journal->j_fc_off; /* * Wait in reverse order to minimize chances of us being woken up before * all IOs have completed */ for (i = j_fc_off - 1; i >= 0; i--) { bh = journal->j_fc_wbuf[i]; if (!bh) break; put_bh(bh); journal->j_fc_wbuf[i] = NULL; } return 0; } EXPORT_SYMBOL(jbd2_fc_release_bufs); /* * Conversion of logical to physical block numbers for the journal * * On external journals the journal blocks are identity-mapped, so * this is a no-op. If needed, we can use j_blk_offset - everything is * ready. */ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, unsigned long long *retp) { int err = 0; unsigned long long ret; sector_t block = 0; if (journal->j_inode) { block = blocknr; ret = bmap(journal->j_inode, &block); if (ret || !block) { printk(KERN_ALERT "%s: journal block not found " "at offset %lu on %s\n", __func__, blocknr, journal->j_devname); err = -EIO; jbd2_journal_abort(journal, err); } else { *retp = block; } } else { *retp = blocknr; /* +journal->j_blk_offset */ } return err; } /* * We play buffer_head aliasing tricks to write data/metadata blocks to * the journal without copying their contents, but for journal * descriptor blocks we do need to generate bona fide buffers. * * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying * the buffer's contents they really should run flush_dcache_page(bh->b_page). * But we don't bother doing that, so there will be coherency problems with * mmaps of blockdevs which hold live JBD-controlled filesystems. */ struct buffer_head * jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type) { journal_t *journal = transaction->t_journal; struct buffer_head *bh; unsigned long long blocknr; journal_header_t *header; int err; err = jbd2_journal_next_log_block(journal, &blocknr); if (err) return NULL; bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); if (!bh) return NULL; atomic_dec(&transaction->t_outstanding_credits); lock_buffer(bh); memset(bh->b_data, 0, journal->j_blocksize); header = (journal_header_t *)bh->b_data; header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); header->h_blocktype = cpu_to_be32(type); header->h_sequence = cpu_to_be32(transaction->t_tid); set_buffer_uptodate(bh); unlock_buffer(bh); BUFFER_TRACE(bh, "return this buffer"); return bh; } void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh) { struct jbd2_journal_block_tail *tail; __u32 csum; if (!jbd2_journal_has_csum_v2or3(j)) return; tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - sizeof(struct jbd2_journal_block_tail)); tail->t_checksum = 0; csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); tail->t_checksum = cpu_to_be32(csum); } /* * Return tid of the oldest transaction in the journal and block in the journal * where the transaction starts. * * If the journal is now empty, return which will be the next transaction ID * we will write and where will that transaction start. * * The return value is 0 if journal tail cannot be pushed any further, 1 if * it can. */ int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block) { transaction_t *transaction; int ret; read_lock(&journal->j_state_lock); spin_lock(&journal->j_list_lock); transaction = journal->j_checkpoint_transactions; if (transaction) { *tid = transaction->t_tid; *block = transaction->t_log_start; } else if ((transaction = journal->j_committing_transaction) != NULL) { *tid = transaction->t_tid; *block = transaction->t_log_start; } else if ((transaction = journal->j_running_transaction) != NULL) { *tid = transaction->t_tid; *block = journal->j_head; } else { *tid = journal->j_transaction_sequence; *block = journal->j_head; } ret = tid_gt(*tid, journal->j_tail_sequence); spin_unlock(&journal->j_list_lock); read_unlock(&journal->j_state_lock); return ret; } /* * Update information in journal structure and in on disk journal superblock * about log tail. This function does not check whether information passed in * really pushes log tail further. It's responsibility of the caller to make * sure provided log tail information is valid (e.g. by holding * j_checkpoint_mutex all the time between computing log tail and calling this * function as is the case with jbd2_cleanup_journal_tail()). * * Requires j_checkpoint_mutex */ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { unsigned long freed; int ret; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); /* * We cannot afford for write to remain in drive's caches since as * soon as we update j_tail, next transaction can start reusing journal * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_SYNC | REQ_FUA); if (ret) goto out; write_lock(&journal->j_state_lock); freed = block - journal->j_tail; if (block < journal->j_tail) freed += journal->j_last - journal->j_first; trace_jbd2_update_log_tail(journal, tid, block, freed); jbd_debug(1, "Cleaning journal tail from %u to %u (offset %lu), " "freeing %lu\n", journal->j_tail_sequence, tid, block, freed); journal->j_free += freed; journal->j_tail_sequence = tid; journal->j_tail = block; write_unlock(&journal->j_state_lock); out: return ret; } /* * This is a variation of __jbd2_update_log_tail which checks for validity of * provided log tail and locks j_checkpoint_mutex. So it is safe against races * with other threads updating log tail. */ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { mutex_lock_io(&journal->j_checkpoint_mutex); if (tid_gt(tid, journal->j_tail_sequence)) __jbd2_update_log_tail(journal, tid, block); mutex_unlock(&journal->j_checkpoint_mutex); } struct jbd2_stats_proc_session { journal_t *journal; struct transaction_stats_s *stats; int start; int max; }; static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) { return *pos ? NULL : SEQ_START_TOKEN; } static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return NULL; } static int jbd2_seq_info_show(struct seq_file *seq, void *v) { struct jbd2_stats_proc_session *s = seq->private; if (v != SEQ_START_TOKEN) return 0; seq_printf(seq, "%lu transactions (%lu requested), " "each up to %u blocks\n", s->stats->ts_tid, s->stats->ts_requested, s->journal->j_max_transaction_buffers); if (s->stats->ts_tid == 0) return 0; seq_printf(seq, "average: \n %ums waiting for transaction\n", jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid)); seq_printf(seq, " %ums request delay\n", (s->stats->ts_requested == 0) ? 0 : jiffies_to_msecs(s->stats->run.rs_request_delay / s->stats->ts_requested)); seq_printf(seq, " %ums running transaction\n", jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid)); seq_printf(seq, " %ums transaction was being locked\n", jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid)); seq_printf(seq, " %ums flushing data (in ordered mode)\n", jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid)); seq_printf(seq, " %ums logging transaction\n", jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid)); seq_printf(seq, " %lluus average transaction commit time\n", div_u64(s->journal->j_average_commit_time, 1000)); seq_printf(seq, " %lu handles per transaction\n", s->stats->run.rs_handle_count / s->stats->ts_tid); seq_printf(seq, " %lu blocks per transaction\n", s->stats->run.rs_blocks / s->stats->ts_tid); seq_printf(seq, " %lu logged blocks per transaction\n", s->stats->run.rs_blocks_logged / s->stats->ts_tid); return 0; } static void jbd2_seq_info_stop(struct seq_file *seq, void *v) { } static const struct seq_operations jbd2_seq_info_ops = { .start = jbd2_seq_info_start, .next = jbd2_seq_info_next, .stop = jbd2_seq_info_stop, .show = jbd2_seq_info_show, }; static int jbd2_seq_info_open(struct inode *inode, struct file *file) { journal_t *journal = PDE_DATA(inode); struct jbd2_stats_proc_session *s; int rc, size; s = kmalloc(sizeof(*s), GFP_KERNEL); if (s == NULL) return -ENOMEM; size = sizeof(struct transaction_stats_s); s->stats = kmalloc(size, GFP_KERNEL); if (s->stats == NULL) { kfree(s); return -ENOMEM; } spin_lock(&journal->j_history_lock); memcpy(s->stats, &journal->j_stats, size); s->journal = journal; spin_unlock(&journal->j_history_lock); rc = seq_open(file, &jbd2_seq_info_ops); if (rc == 0) { struct seq_file *m = file->private_data; m->private = s; } else { kfree(s->stats); kfree(s); } return rc; } static int jbd2_seq_info_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; struct jbd2_stats_proc_session *s = seq->private; kfree(s->stats); kfree(s); return seq_release(inode, file); } static const struct proc_ops jbd2_info_proc_ops = { .proc_open = jbd2_seq_info_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = jbd2_seq_info_release, }; static struct proc_dir_entry *proc_jbd2_stats; static void jbd2_stats_proc_init(journal_t *journal) { journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { proc_create_data("info", S_IRUGO, journal->j_proc_entry, &jbd2_info_proc_ops, journal); } } static void jbd2_stats_proc_exit(journal_t *journal) { remove_proc_entry("info", journal->j_proc_entry); remove_proc_entry(journal->j_devname, proc_jbd2_stats); } /* Minimum size of descriptor tag */ static int jbd2_min_tag_size(void) { /* * Tag with 32-bit block numbers does not use last four bytes of the * structure */ return sizeof(journal_block_tag_t) - 4; } /* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing * journal blocks from disk. */ /* First: create and setup a journal_t object in memory. We initialise * very few fields yet: that has to wait until we have created the * journal structures from from scratch, or loaded them from disk. */ static journal_t *journal_init_common(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; int err; struct buffer_head *bh; int n; journal = kzalloc(sizeof(*journal), GFP_KERNEL); if (!journal) return NULL; init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_done_commit); init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); init_waitqueue_head(&journal->j_wait_reserved); init_waitqueue_head(&journal->j_fc_wait); mutex_init(&journal->j_abort_mutex); mutex_init(&journal->j_barrier); mutex_init(&journal->j_checkpoint_mutex); spin_lock_init(&journal->j_revoke_lock); spin_lock_init(&journal->j_list_lock); rwlock_init(&journal->j_state_lock); journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); journal->j_min_batch_time = 0; journal->j_max_batch_time = 15000; /* 15ms */ atomic_set(&journal->j_reserved_credits, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; /* Set up a default-sized revoke table for the new mount. */ err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH); if (err) goto err_cleanup; spin_lock_init(&journal->j_history_lock); lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", &jbd2_trans_commit_key, 0); /* journal descriptor can store up to n blocks -bzzz */ journal->j_blocksize = blocksize; journal->j_dev = bdev; journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; journal->j_total_len = len; /* We need enough buffers to write out full descriptor block. */ n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; journal->j_fc_wbuf = NULL; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_wbuf) goto err_cleanup; bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); if (!bh) { pr_err("%s: Cannot get buffer for journal superblock\n", __func__); goto err_cleanup; } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; return journal; err_cleanup: kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); kfree(journal); return NULL; } /* jbd2_journal_init_dev and jbd2_journal_init_inode: * * Create a journal structure assigned some fixed set of disk blocks to * the journal. We don't actually touch those disk blocks yet, but we * need to set up all of the mapping information to tell the journaling * system where the journal blocks are. * */ /** * journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure * @bdev: Block device on which to create the journal * @fs_dev: Device which hold journalled filesystem for this journal. * @start: Block nr Start of journal. * @len: Length of the journal in blocks. * @blocksize: blocksize of journalling device * * Returns: a newly created journal_t * * * jbd2_journal_init_dev creates a journal which maps a fixed contiguous * range of blocks on an arbitrary block device. * */ journal_t *jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { journal_t *journal; journal = journal_init_common(bdev, fs_dev, start, len, blocksize); if (!journal) return NULL; bdevname(journal->j_dev, journal->j_devname); strreplace(journal->j_devname, '/', '!'); jbd2_stats_proc_init(journal); return journal; } /** * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode. * @inode: An inode to create the journal in * * jbd2_journal_init_inode creates a journal which maps an on-disk inode as * the journal. The inode must exist already, must support bmap() and * must have all data blocks preallocated. */ journal_t *jbd2_journal_init_inode(struct inode *inode) { journal_t *journal; sector_t blocknr; char *p; int err = 0; blocknr = 0; err = bmap(inode, &blocknr); if (err || !blocknr) { pr_err("%s: Cannot locate journal superblock\n", __func__); return NULL; } jbd_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size, inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); journal = journal_init_common(inode->i_sb->s_bdev, inode->i_sb->s_bdev, blocknr, inode->i_size >> inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); if (!journal) return NULL; journal->j_inode = inode; bdevname(journal->j_dev, journal->j_devname); p = strreplace(journal->j_devname, '/', '!'); sprintf(p, "-%lu", journal->j_inode->i_ino); jbd2_stats_proc_init(journal); return journal; } /* * If the journal init or create aborts, we need to mark the journal * superblock as being NULL to prevent the journal destroy from writing * back a bogus superblock. */ static void journal_fail_superblock(journal_t *journal) { struct buffer_head *bh = journal->j_sb_buffer; brelse(bh); journal->j_sb_buffer = NULL; } /* * Given a journal_t structure, initialise the various fields for * startup of a new journaling session. We use this both when creating * a journal, and after recovering an old journal to reset it for * subsequent use. */ static int journal_reset(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; unsigned long long first, last; first = be32_to_cpu(sb->s_first); last = be32_to_cpu(sb->s_maxlen); if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) { printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n", first, last); journal_fail_superblock(journal); return -EINVAL; } journal->j_first = first; journal->j_last = last; journal->j_head = journal->j_first; journal->j_tail = journal->j_first; journal->j_free = journal->j_last - journal->j_first; journal->j_tail_sequence = journal->j_transaction_sequence; journal->j_commit_sequence = journal->j_transaction_sequence - 1; journal->j_commit_request = journal->j_commit_sequence; journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); /* * Now that journal recovery is done, turn fast commits off here. This * way, if fast commit was enabled before the crash but if now FS has * disabled it, we don't enable fast commits. */ jbd2_clear_feature_fast_commit(journal); /* * As a special case, if the on-disk copy is already marked as needing * no recovery (s_start == 0), then we can safely defer the superblock * update until the next commit by setting JBD2_FLUSHED. This avoids * attempting a write to a potential-readonly device. */ if (sb->s_start == 0) { jbd_debug(1, "JBD2: Skipping superblock update on recovered sb " "(start %ld, seq %u, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); journal->j_flags |= JBD2_FLUSHED; } else { /* Lock here to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); /* * Update log tail information. We use REQ_FUA since new * transaction will start reusing journal space and so we * must make sure information about current log tail is on * disk before that. */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, journal->j_tail, REQ_SYNC | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } return jbd2_journal_start_thread(journal); } /* * This function expects that the caller will have locked the journal * buffer head, and will return with it unlocked */ static int jbd2_write_superblock(journal_t *journal, int write_flags) { struct buffer_head *bh = journal->j_sb_buffer; journal_superblock_t *sb = journal->j_superblock; int ret; /* Buffer got discarded which means block device got invalidated */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal * superblock failed. This could happen because the * USB device was yanked out. Or it could happen to * be a transient write error and maybe the block will * be remapped. Nothing we can do but to retry the * write and hope for the best. */ printk(KERN_ERR "JBD2: previous I/O error detected " "for journal superblock update for %s.\n", journal->j_devname); clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); } if (jbd2_journal_has_csum_v2or3(journal)) sb->s_checksum = jbd2_superblock_csum(journal, sb); get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, write_flags, bh); wait_on_buffer(bh); if (buffer_write_io_error(bh)) { clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); ret = -EIO; } if (ret) { printk(KERN_ERR "JBD2: Error %d detected when updating " "journal superblock for %s.\n", ret, journal->j_devname); if (!is_journal_aborted(journal)) jbd2_journal_abort(journal, ret); } return ret; } /** * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk. * @journal: The journal to update. * @tail_tid: TID of the new transaction at the tail of the log * @tail_block: The first block of the transaction at the tail of the log * @write_op: With which operation should we write the journal sb * * Update a journal's superblock information about log tail and write it to * disk, waiting for the IO to complete. */ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, int write_op) { journal_superblock_t *sb = journal->j_superblock; int ret; if (is_journal_aborted(journal)) return -EIO; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", tail_block, tail_tid); lock_buffer(journal->j_sb_buffer); sb->s_sequence = cpu_to_be32(tail_tid); sb->s_start = cpu_to_be32(tail_block); ret = jbd2_write_superblock(journal, write_op); if (ret) goto out; /* Log is no longer empty */ write_lock(&journal->j_state_lock); WARN_ON(!sb->s_sequence); journal->j_flags &= ~JBD2_FLUSHED; write_unlock(&journal->j_state_lock); out: return ret; } /** * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. * @write_op: With which operation should we write the journal sb * * Update a journal's dynamic superblock fields to show that journal is empty. * Write updated superblock to disk waiting for IO to complete. */ static void jbd2_mark_journal_empty(journal_t *journal, int write_op) { journal_superblock_t *sb = journal->j_superblock; bool had_fast_commit = false; BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); lock_buffer(journal->j_sb_buffer); if (sb->s_start == 0) { /* Is it already empty? */ unlock_buffer(journal->j_sb_buffer); return; } jbd_debug(1, "JBD2: Marking journal as empty (seq %u)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); sb->s_start = cpu_to_be32(0); if (jbd2_has_feature_fast_commit(journal)) { /* * When journal is clean, no need to commit fast commit flag and * make file system incompatible with older kernels. */ jbd2_clear_feature_fast_commit(journal); had_fast_commit = true; } jbd2_write_superblock(journal, write_op); if (had_fast_commit) jbd2_set_feature_fast_commit(journal); /* Log is no longer empty */ write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_FLUSHED; write_unlock(&journal->j_state_lock); } /** * jbd2_journal_update_sb_errno() - Update error in the journal. * @journal: The journal to update. * * Update a journal's errno. Write updated superblock to disk waiting for IO * to complete. */ void jbd2_journal_update_sb_errno(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; int errcode; lock_buffer(journal->j_sb_buffer); errcode = journal->j_errno; if (errcode == -ESHUTDOWN) errcode = 0; jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); sb->s_errno = cpu_to_be32(errcode); jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); } EXPORT_SYMBOL(jbd2_journal_update_sb_errno); static int journal_revoke_records_per_block(journal_t *journal) { int record_size; int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); if (jbd2_has_feature_64bit(journal)) record_size = 8; else record_size = 4; if (jbd2_journal_has_csum_v2or3(journal)) space -= sizeof(struct jbd2_journal_block_tail); return space / record_size; } /* * Read the superblock for a given journal, performing initial * validation of the format. */ static int journal_get_superblock(journal_t *journal) { struct buffer_head *bh; journal_superblock_t *sb; int err = -EIO; bh = journal->j_sb_buffer; J_ASSERT(bh != NULL); if (!buffer_uptodate(bh)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { printk(KERN_ERR "JBD2: IO error reading journal superblock\n"); goto out; } } if (buffer_verified(bh)) return 0; sb = journal->j_superblock; err = -EINVAL; if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { printk(KERN_WARNING "JBD2: no valid journal superblock found\n"); goto out; } switch(be32_to_cpu(sb->s_header.h_blocktype)) { case JBD2_SUPERBLOCK_V1: journal->j_format_version = 1; break; case JBD2_SUPERBLOCK_V2: journal->j_format_version = 2; break; default: printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); goto out; } if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) journal->j_total_len = be32_to_cpu(sb->s_maxlen); else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { printk(KERN_WARNING "JBD2: journal file too short\n"); goto out; } if (be32_to_cpu(sb->s_first) == 0 || be32_to_cpu(sb->s_first) >= journal->j_total_len) { printk(KERN_WARNING "JBD2: Invalid start block of journal: %u\n", be32_to_cpu(sb->s_first)); goto out; } if (jbd2_has_feature_csum2(journal) && jbd2_has_feature_csum3(journal)) { /* Can't have checksum v2 and v3 at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " "at the same time!\n"); goto out; } if (jbd2_journal_has_csum_v2or3_feature(journal) && jbd2_has_feature_checksum(journal)) { /* Can't have checksum v1 and v2 on at the same time! */ printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " "at the same time!\n"); goto out; } if (!jbd2_verify_csum_type(journal, sb)) { printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } /* Load the checksum driver */ if (jbd2_journal_has_csum_v2or3_feature(journal)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); err = PTR_ERR(journal->j_chksum_driver); journal->j_chksum_driver = NULL; goto out; } } if (jbd2_journal_has_csum_v2or3(journal)) { /* Check superblock checksum */ if (sb->s_checksum != jbd2_superblock_csum(journal, sb)) { printk(KERN_ERR "JBD2: journal checksum error\n"); err = -EFSBADCRC; goto out; } /* Precompute checksum seed for all metadata */ journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); } journal->j_revoke_records_per_block = journal_revoke_records_per_block(journal); set_buffer_verified(bh); return 0; out: journal_fail_superblock(journal); return err; } /* * Load the on-disk journal superblock and read the key fields into the * journal_t. */ static int load_superblock(journal_t *journal) { int err; journal_superblock_t *sb; int num_fc_blocks; err = journal_get_superblock(journal); if (err) return err; sb = journal->j_superblock; journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); journal->j_tail = be32_to_cpu(sb->s_start); journal->j_first = be32_to_cpu(sb->s_first); journal->j_errno = be32_to_cpu(sb->s_errno); journal->j_last = be32_to_cpu(sb->s_maxlen); if (jbd2_has_feature_fast_commit(journal)) { journal->j_fc_last = be32_to_cpu(sb->s_maxlen); num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks); if (!num_fc_blocks) num_fc_blocks = JBD2_MIN_FC_BLOCKS; if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) journal->j_last = journal->j_fc_last - num_fc_blocks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; } return 0; } /** * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain * a journal, read the journal from disk to initialise the in-memory * structures. */ int jbd2_journal_load(journal_t *journal) { int err; journal_superblock_t *sb; err = load_superblock(journal); if (err) return err; sb = journal->j_superblock; /* If this is a V2 superblock, then we have to check the * features flags on it. */ if (journal->j_format_version >= 2) { if ((sb->s_feature_ro_compat & ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || (sb->s_feature_incompat & ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { printk(KERN_WARNING "JBD2: Unrecognised features on journal\n"); return -EINVAL; } } /* * Create a slab for this blocksize */ err = jbd2_journal_create_slab(be32_to_cpu(sb->s_blocksize)); if (err) return err; /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (jbd2_journal_recover(journal)) goto recovery_error; if (journal->j_failed_commit) { printk(KERN_ERR "JBD2: journal transaction %u on %s " "is corrupt.\n", journal->j_failed_commit, journal->j_devname); return -EFSCORRUPTED; } /* * clear JBD2_ABORT flag initialized in journal_init_common * here to update log tail information with the newest seq. */ journal->j_flags &= ~JBD2_ABORT; /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ if (journal_reset(journal)) goto recovery_error; journal->j_flags |= JBD2_LOADED; return 0; recovery_error: printk(KERN_WARNING "JBD2: recovery failed\n"); return -EIO; } /** * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the * journaled object. * Return <0 if we couldn't clean up the journal. */ int jbd2_journal_destroy(journal_t *journal) { int err = 0; /* Wait for the commit thread to wake up and die. */ journal_kill_thread(journal); /* Force a final log commit */ if (journal->j_running_transaction) jbd2_journal_commit_transaction(journal); /* Force any old transactions to disk */ /* Totally anal locking here... */ spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); /* * If checkpointing failed, just free the buffers to avoid * looping forever */ if (err) { jbd2_journal_destroy_checkpoint(journal); spin_lock(&journal->j_list_lock); break; } spin_lock(&journal->j_list_lock); } J_ASSERT(journal->j_running_transaction == NULL); J_ASSERT(journal->j_committing_transaction == NULL); J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock_io(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); journal->j_tail_sequence = ++journal->j_transaction_sequence; write_unlock(&journal->j_state_lock); jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_PREFLUSH | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; brelse(journal->j_sb_buffer); } if (journal->j_proc_entry) jbd2_stats_proc_exit(journal); iput(journal->j_inode); if (journal->j_revoke) jbd2_journal_destroy_revoke(journal); if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); return err; } /** * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Check whether the journal uses all of a given set of * features. Return true (non-zero) if it does. **/ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; if (!compat && !ro && !incompat) return 1; /* Load journal superblock if it is not loaded yet. */ if (journal->j_format_version == 0 && journal_get_superblock(journal) != 0) return 0; if (journal->j_format_version == 1) return 0; sb = journal->j_superblock; if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) && ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) && ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat)) return 1; return 0; } /** * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Check whether the journaling code supports the use of * all of a given set of features on this journal. Return true * (non-zero) if it can. */ int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { if (!compat && !ro && !incompat) return 1; /* We can support any known requested features iff the * superblock is in version 2. Otherwise we fail to support any * extended sb features. */ if (journal->j_format_version != 2) return 0; if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat && (ro & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro && (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat) return 1; return 0; } static int jbd2_journal_initialize_fast_commit(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; unsigned long long num_fc_blks; num_fc_blks = be32_to_cpu(sb->s_num_fc_blks); if (num_fc_blks == 0) num_fc_blks = JBD2_MIN_FC_BLOCKS; if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) return -ENOSPC; /* Are we called twice? */ WARN_ON(journal->j_fc_wbuf != NULL); journal->j_fc_wbuf = kmalloc_array(num_fc_blks, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_fc_wbuf) return -ENOMEM; journal->j_fc_wbufsize = num_fc_blks; journal->j_fc_last = journal->j_last; journal->j_last = journal->j_fc_last - num_fc_blks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; journal->j_free = journal->j_last - journal->j_first; journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); return 0; } /** * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Mark a given journal feature as present on the * superblock. Returns true if the requested features could be set. * */ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { #define INCOMPAT_FEATURE_ON(f) \ ((incompat & (f)) && !(sb->s_feature_incompat & cpu_to_be32(f))) #define COMPAT_FEATURE_ON(f) \ ((compat & (f)) && !(sb->s_feature_compat & cpu_to_be32(f))) journal_superblock_t *sb; if (jbd2_journal_check_used_features(journal, compat, ro, incompat)) return 1; if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; /* If enabling v2 checksums, turn on v3 instead */ if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) { incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2; incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3; } /* Asking for checksumming v3 and v1? Only give them v3. */ if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 && compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { if (jbd2_journal_initialize_fast_commit(journal)) { pr_err("JBD2: Cannot enable fast commits.\n"); return 0; } } /* Load the checksum driver if necessary */ if ((journal->j_chksum_driver == NULL) && INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); journal->j_chksum_driver = NULL; return 0; } /* Precompute checksum seed for all metadata */ journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, sizeof(sb->s_uuid)); } lock_buffer(journal->j_sb_buffer); /* If enabling v3 checksums, update superblock */ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { sb->s_checksum_type = JBD2_CRC32C_CHKSUM; sb->s_feature_compat &= ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); } /* If enabling v1 checksums, downgrade superblock */ if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) sb->s_feature_incompat &= ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 | JBD2_FEATURE_INCOMPAT_CSUM_V3); sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); unlock_buffer(journal->j_sb_buffer); journal->j_revoke_records_per_block = journal_revoke_records_per_block(journal); return 1; #undef COMPAT_FEATURE_ON #undef INCOMPAT_FEATURE_ON } /* * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Clear a given journal feature as present on the * superblock. */ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; sb->s_feature_compat &= ~cpu_to_be32(compat); sb->s_feature_ro_compat &= ~cpu_to_be32(ro); sb->s_feature_incompat &= ~cpu_to_be32(incompat); journal->j_revoke_records_per_block = journal_revoke_records_per_block(journal); } EXPORT_SYMBOL(jbd2_journal_clear_features); /** * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * * Flush all data for a given journal to disk and empty the journal. * Filesystems can use this when remounting readonly to ensure that * recovery does not need to happen on remount. */ int jbd2_journal_flush(journal_t *journal) { int err = 0; transaction_t *transaction = NULL; write_lock(&journal->j_state_lock); /* Force everything buffered to the log... */ if (journal->j_running_transaction) { transaction = journal->j_running_transaction; __jbd2_log_start_commit(journal, transaction->t_tid); } else if (journal->j_committing_transaction) transaction = journal->j_committing_transaction; /* Wait for the log commit to complete... */ if (transaction) { tid_t tid = transaction->t_tid; write_unlock(&journal->j_state_lock); jbd2_log_wait_commit(journal, tid); } else { write_unlock(&journal->j_state_lock); } /* ...and flush everything in the log out to disk. */ spin_lock(&journal->j_list_lock); while (!err && journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); mutex_lock_io(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); } spin_unlock(&journal->j_list_lock); if (is_journal_aborted(journal)) return -EIO; mutex_lock_io(&journal->j_checkpoint_mutex); if (!err) { err = jbd2_cleanup_journal_tail(journal); if (err < 0) { mutex_unlock(&journal->j_checkpoint_mutex); goto out; } err = 0; } /* Finally, mark the journal as really needing no recovery. * This sets s_start==0 in the underlying superblock, which is * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); J_ASSERT(!journal->j_committing_transaction); J_ASSERT(!journal->j_checkpoint_transactions); J_ASSERT(journal->j_head == journal->j_tail); J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); write_unlock(&journal->j_state_lock); out: return err; } /** * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * * Wipe out all of the contents of a journal, safely. This will produce * a warning if the journal contains any valid recovery information. * Must be called between journal_init_*() and jbd2_journal_load(). * * If 'write' is non-zero, then we wipe out the journal on disk; otherwise * we merely suppress recovery. */ int jbd2_journal_wipe(journal_t *journal, int write) { int err = 0; J_ASSERT (!(journal->j_flags & JBD2_LOADED)); err = load_superblock(journal); if (err) return err; if (!journal->j_tail) goto no_recovery; printk(KERN_WARNING "JBD2: %s recovery information on journal\n", write ? "Clearing" : "Ignoring"); err = jbd2_journal_skip_recovery(journal); if (write) { /* Lock to make assertions happy... */ mutex_lock_io(&journal->j_checkpoint_mutex); jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } no_recovery: return err; } /** * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. * * Perform a complete, immediate shutdown of the ENTIRE * journal (not of a single transaction). This operation cannot be * undone without closing and reopening the journal. * * The jbd2_journal_abort function is intended to support higher level error * recovery mechanisms such as the ext2/ext3 remount-readonly error * mode. * * Journal abort has very specific semantics. Any existing dirty, * unjournaled buffers in the main filesystem will still be written to * disk by bdflush, but the journaling mechanism will be suspended * immediately and no further transaction commits will be honoured. * * Any dirty, journaled buffers will be written back to disk without * hitting the journal. Atomicity cannot be guaranteed on an aborted * filesystem, but we _do_ attempt to leave as much data as possible * behind for fsck to use for cleanup. * * Any attempt to get a new transaction handle on a journal which is in * ABORT state will just result in an -EROFS error return. A * jbd2_journal_stop on an existing handle will return -EIO if we have * entered abort state during the update. * * Recursive transactions are not disturbed by journal abort until the * final jbd2_journal_stop, which will receive the -EIO error. * * Finally, the jbd2_journal_abort call allows the caller to supply an errno * which will be recorded (if possible) in the journal superblock. This * allows a client to record failure conditions in the middle of a * transaction without having to complete the transaction to record the * failure to disk. ext3_error, for example, now uses this * functionality. * */ void jbd2_journal_abort(journal_t *journal, int errno) { transaction_t *transaction; /* * Lock the aborting procedure until everything is done, this avoid * races between filesystem's error handling flow (e.g. ext4_abort()), * ensure panic after the error info is written into journal's * superblock. */ mutex_lock(&journal->j_abort_mutex); /* * ESHUTDOWN always takes precedence because a file system check * caused by any other journal abort error is not required after * a shutdown triggered. */ write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) { int old_errno = journal->j_errno; write_unlock(&journal->j_state_lock); if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) { journal->j_errno = errno; jbd2_journal_update_sb_errno(journal); } mutex_unlock(&journal->j_abort_mutex); return; } /* * Mark the abort as occurred and start current running transaction * to release all journaled buffer. */ pr_err("Aborting journal on device %s.\n", journal->j_devname); journal->j_flags |= JBD2_ABORT; journal->j_errno = errno; transaction = journal->j_running_transaction; if (transaction) __jbd2_log_start_commit(journal, transaction->t_tid); write_unlock(&journal->j_state_lock); /* * Record errno to the journal super block, so that fsck and jbd2 * layer could realise that a filesystem check is needed. */ jbd2_journal_update_sb_errno(journal); mutex_unlock(&journal->j_abort_mutex); } /** * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last * time the journal was mounted - if the journal was stopped * without calling abort this will be 0. * * If the journal has been aborted on this mount time -EROFS will * be returned. */ int jbd2_journal_errno(journal_t *journal) { int err; read_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) err = -EROFS; else err = journal->j_errno; read_unlock(&journal->j_state_lock); return err; } /** * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly * mode. */ int jbd2_journal_clear_err(journal_t *journal) { int err = 0; write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) err = -EROFS; else journal->j_errno = 0; write_unlock(&journal->j_state_lock); return err; } /** * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly * mode. */ void jbd2_journal_ack_err(journal_t *journal) { write_lock(&journal->j_state_lock); if (journal->j_errno) journal->j_flags |= JBD2_ACK_ERR; write_unlock(&journal->j_state_lock); } int jbd2_journal_blocks_per_page(struct inode *inode) { return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); } /* * helper functions to deal with 32 or 64bit block numbers. */ size_t journal_tag_bytes(journal_t *journal) { size_t sz; if (jbd2_has_feature_csum3(journal)) return sizeof(journal_block_tag3_t); sz = sizeof(journal_block_tag_t); if (jbd2_has_feature_csum2(journal)) sz += sizeof(__u16); if (jbd2_has_feature_64bit(journal)) return sz; else return sz - sizeof(__u32); } /* * JBD memory management * * These functions are used to allocate block-sized chunks of memory * used for making copies of buffer_head data. Very often it will be * page-sized chunks of data, but sometimes it will be in * sub-page-size chunks. (For example, 16k pages on Power systems * with a 4k block file system.) For blocks smaller than a page, we * use a SLAB allocator. There are slab caches for each block size, * which are allocated at mount time, if necessary, and we only free * (all of) the slab caches when/if the jbd2 module is unloaded. For * this reason we don't need to a mutex to protect access to * jbd2_slab[] allocating or releasing memory; only in * jbd2_journal_create_slab(). */ #define JBD2_MAX_SLABS 8 static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS]; static const char *jbd2_slab_names[JBD2_MAX_SLABS] = { "jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k", "jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k" }; static void jbd2_journal_destroy_slabs(void) { int i; for (i = 0; i < JBD2_MAX_SLABS; i++) { kmem_cache_destroy(jbd2_slab[i]); jbd2_slab[i] = NULL; } } static int jbd2_journal_create_slab(size_t size) { static DEFINE_MUTEX(jbd2_slab_create_mutex); int i = order_base_2(size) - 10; size_t slab_size; if (size == PAGE_SIZE) return 0; if (i >= JBD2_MAX_SLABS) return -EINVAL; if (unlikely(i < 0)) i = 0; mutex_lock(&jbd2_slab_create_mutex); if (jbd2_slab[i]) { mutex_unlock(&jbd2_slab_create_mutex); return 0; /* Already created */ } slab_size = 1 << (i+10); jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size, slab_size, 0, NULL); mutex_unlock(&jbd2_slab_create_mutex); if (!jbd2_slab[i]) { printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n"); return -ENOMEM; } return 0; } static struct kmem_cache *get_slab(size_t size) { int i = order_base_2(size) - 10; BUG_ON(i >= JBD2_MAX_SLABS); if (unlikely(i < 0)) i = 0; BUG_ON(jbd2_slab[i] == NULL); return jbd2_slab[i]; } void *jbd2_alloc(size_t size, gfp_t flags) { void *ptr; BUG_ON(size & (size-1)); /* Must be a power of 2 */ if (size < PAGE_SIZE) ptr = kmem_cache_alloc(get_slab(size), flags); else ptr = (void *)__get_free_pages(flags, get_order(size)); /* Check alignment; SLUB has gotten this wrong in the past, * and this can lead to user data corruption! */ BUG_ON(((unsigned long) ptr) & (size-1)); return ptr; } void jbd2_free(void *ptr, size_t size) { if (size < PAGE_SIZE) kmem_cache_free(get_slab(size), ptr); else free_pages((unsigned long)ptr, get_order(size)); }; /* * Journal_head storage management */ static struct kmem_cache *jbd2_journal_head_cache; #ifdef CONFIG_JBD2_DEBUG static atomic_t nr_journal_heads = ATOMIC_INIT(0); #endif static int __init jbd2_journal_init_journal_head_cache(void) { J_ASSERT(!jbd2_journal_head_cache); jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", sizeof(struct journal_head), 0, /* offset */ SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU, NULL); /* ctor */ if (!jbd2_journal_head_cache) { printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); return -ENOMEM; } return 0; } static void jbd2_journal_destroy_journal_head_cache(void) { kmem_cache_destroy(jbd2_journal_head_cache); jbd2_journal_head_cache = NULL; } /* * journal_head splicing and dicing */ static struct journal_head *journal_alloc_journal_head(void) { struct journal_head *ret; #ifdef CONFIG_JBD2_DEBUG atomic_inc(&nr_journal_heads); #endif ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); if (!ret) { jbd_debug(1, "out of memory for journal_head\n"); pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__); ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS | __GFP_NOFAIL); } if (ret) spin_lock_init(&ret->b_state_lock); return ret; } static void journal_free_journal_head(struct journal_head *jh) { #ifdef CONFIG_JBD2_DEBUG atomic_dec(&nr_journal_heads); memset(jh, JBD2_POISON_FREE, sizeof(*jh)); #endif kmem_cache_free(jbd2_journal_head_cache, jh); } /* * A journal_head is attached to a buffer_head whenever JBD has an * interest in the buffer. * * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit * is set. This bit is tested in core kernel code where we need to take * JBD-specific actions. Testing the zeroness of ->b_private is not reliable * there. * * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one. * * When a buffer has its BH_JBD bit set it is immune from being released by * core kernel code, mainly via ->b_count. * * A journal_head is detached from its buffer_head when the journal_head's * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint * transaction (b_cp_transaction) hold their references to b_jcount. * * Various places in the kernel want to attach a journal_head to a buffer_head * _before_ attaching the journal_head to a transaction. To protect the * journal_head in this situation, jbd2_journal_add_journal_head elevates the * journal_head's b_jcount refcount by one. The caller must call * jbd2_journal_put_journal_head() to undo this. * * So the typical usage would be: * * (Attach a journal_head if needed. Increments b_jcount) * struct journal_head *jh = jbd2_journal_add_journal_head(bh); * ... * (Get another reference for transaction) * jbd2_journal_grab_journal_head(bh); * jh->b_transaction = xxx; * (Put original reference) * jbd2_journal_put_journal_head(jh); */ /* * Give a buffer_head a journal_head. * * May sleep. */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) { struct journal_head *jh; struct journal_head *new_jh = NULL; repeat: if (!buffer_jbd(bh)) new_jh = journal_alloc_journal_head(); jbd_lock_bh_journal_head(bh); if (buffer_jbd(bh)) { jh = bh2jh(bh); } else { J_ASSERT_BH(bh, (atomic_read(&bh->b_count) > 0) || (bh->b_page && bh->b_page->mapping)); if (!new_jh) { jbd_unlock_bh_journal_head(bh); goto repeat; } jh = new_jh; new_jh = NULL; /* We consumed it */ set_buffer_jbd(bh); bh->b_private = jh; jh->b_bh = bh; get_bh(bh); BUFFER_TRACE(bh, "added journal_head"); } jh->b_jcount++; jbd_unlock_bh_journal_head(bh); if (new_jh) journal_free_journal_head(new_jh); return bh->b_private; } /* * Grab a ref against this buffer_head's journal_head. If it ended up not * having a journal_head, return NULL */ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) { struct journal_head *jh = NULL; jbd_lock_bh_journal_head(bh); if (buffer_jbd(bh)) { jh = bh2jh(bh); jh->b_jcount++; } jbd_unlock_bh_journal_head(bh); return jh; } EXPORT_SYMBOL(jbd2_journal_grab_journal_head); static void __journal_remove_journal_head(struct buffer_head *bh) { struct journal_head *jh = bh2jh(bh); J_ASSERT_JH(jh, jh->b_transaction == NULL); J_ASSERT_JH(jh, jh->b_next_transaction == NULL); J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); J_ASSERT_JH(jh, jh->b_jlist == BJ_None); J_ASSERT_BH(bh, buffer_jbd(bh)); J_ASSERT_BH(bh, jh2bh(jh) == bh); BUFFER_TRACE(bh, "remove journal_head"); /* Unlink before dropping the lock */ bh->b_private = NULL; jh->b_bh = NULL; /* debug, really */ clear_buffer_jbd(bh); } static void journal_release_journal_head(struct journal_head *jh, size_t b_size) { if (jh->b_frozen_data) { printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); jbd2_free(jh->b_frozen_data, b_size); } if (jh->b_committed_data) { printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__); jbd2_free(jh->b_committed_data, b_size); } journal_free_journal_head(jh); } /* * Drop a reference on the passed journal_head. If it fell to zero then * release the journal_head from the buffer_head. */ void jbd2_journal_put_journal_head(struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_journal_head(bh); J_ASSERT_JH(jh, jh->b_jcount > 0); --jh->b_jcount; if (!jh->b_jcount) { __journal_remove_journal_head(bh); jbd_unlock_bh_journal_head(bh); journal_release_journal_head(jh, bh->b_size); __brelse(bh); } else { jbd_unlock_bh_journal_head(bh); } } EXPORT_SYMBOL(jbd2_journal_put_journal_head); /* * Initialize jbd inode head */ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) { jinode->i_transaction = NULL; jinode->i_next_transaction = NULL; jinode->i_vfs_inode = inode; jinode->i_flags = 0; jinode->i_dirty_start = 0; jinode->i_dirty_end = 0; INIT_LIST_HEAD(&jinode->i_list); } /* * Function to be called before we start removing inode from memory (i.e., * clear_inode() is a fine place to be called from). It removes inode from * transaction's lists. */ void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode) { if (!journal) return; restart: spin_lock(&journal->j_list_lock); /* Is commit writing out inode - we have to wait */ if (jinode->i_flags & JI_COMMIT_RUNNING) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&journal->j_list_lock); schedule(); finish_wait(wq, &wait.wq_entry); goto restart; } if (jinode->i_transaction) { list_del(&jinode->i_list); jinode->i_transaction = NULL; } spin_unlock(&journal->j_list_lock); } #ifdef CONFIG_PROC_FS #define JBD2_STATS_PROC_NAME "fs/jbd2" static void __init jbd2_create_jbd_stats_proc_entry(void) { proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL); } static void __exit jbd2_remove_jbd_stats_proc_entry(void) { if (proc_jbd2_stats) remove_proc_entry(JBD2_STATS_PROC_NAME, NULL); } #else #define jbd2_create_jbd_stats_proc_entry() do {} while (0) #define jbd2_remove_jbd_stats_proc_entry() do {} while (0) #endif struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; static int __init jbd2_journal_init_inode_cache(void) { J_ASSERT(!jbd2_inode_cache); jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); if (!jbd2_inode_cache) { pr_emerg("JBD2: failed to create inode cache\n"); return -ENOMEM; } return 0; } static int __init jbd2_journal_init_handle_cache(void) { J_ASSERT(!jbd2_handle_cache); jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); if (!jbd2_handle_cache) { printk(KERN_EMERG "JBD2: failed to create handle cache\n"); return -ENOMEM; } return 0; } static void jbd2_journal_destroy_inode_cache(void) { kmem_cache_destroy(jbd2_inode_cache); jbd2_inode_cache = NULL; } static void jbd2_journal_destroy_handle_cache(void) { kmem_cache_destroy(jbd2_handle_cache); jbd2_handle_cache = NULL; } /* * Module startup and shutdown */ static int __init journal_init_caches(void) { int ret; ret = jbd2_journal_init_revoke_record_cache(); if (ret == 0) ret = jbd2_journal_init_revoke_table_cache(); if (ret == 0) ret = jbd2_journal_init_journal_head_cache(); if (ret == 0) ret = jbd2_journal_init_handle_cache(); if (ret == 0) ret = jbd2_journal_init_inode_cache(); if (ret == 0) ret = jbd2_journal_init_transaction_cache(); return ret; } static void jbd2_journal_destroy_caches(void) { jbd2_journal_destroy_revoke_record_cache(); jbd2_journal_destroy_revoke_table_cache(); jbd2_journal_destroy_journal_head_cache(); jbd2_journal_destroy_handle_cache(); jbd2_journal_destroy_inode_cache(); jbd2_journal_destroy_transaction_cache(); jbd2_journal_destroy_slabs(); } static int __init journal_init(void) { int ret; BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024); ret = journal_init_caches(); if (ret == 0) { jbd2_create_jbd_stats_proc_entry(); } else { jbd2_journal_destroy_caches(); } return ret; } static void __exit journal_exit(void) { #ifdef CONFIG_JBD2_DEBUG int n = atomic_read(&nr_journal_heads); if (n) printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n); #endif jbd2_remove_jbd_stats_proc_entry(); jbd2_journal_destroy_caches(); } MODULE_LICENSE("GPL"); MODULE_IMPORT_NS(ANDROID_GKI_VFS_EXPORT_ONLY); module_init(journal_init); module_exit(journal_exit); |
| 445 842 80 79 5 613 1026 1328 1105 605 1353 334 72 994 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com> * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ #ifndef _LINUX_JBD2_H #define _LINUX_JBD2_H /* Allow this file to be included directly into e2fsprogs */ #ifndef __KERNEL__ #include "jfs_compat.h" #define JBD2_DEBUG #else #include <linux/types.h> #include <linux/buffer_head.h> #include <linux/journal-head.h> #include <linux/stddef.h> #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> #include <linux/bit_spinlock.h> #include <linux/blkdev.h> #include <crypto/hash.h> #endif #define journal_oom_retry 1 /* * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds * certain classes of error which can occur due to failed IOs. Under * normal use we want ext4 to continue after such errors, because * hardware _can_ fail, but for debugging purposes when running tests on * known-good hardware we may want to trap these errors. */ #undef JBD2_PARANOID_IOFAIL /* * The default maximum commit age, in seconds. */ #define JBD2_DEFAULT_MAX_COMMIT_AGE 5 #ifdef CONFIG_JBD2_DEBUG /* * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal * consistency checks. By default we don't do this unless * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING extern ushort jbd2_journal_enable_debug; void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); #define jbd_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else #define jbd_debug(n, fmt, a...) /**/ #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 #define JBD2_MIN_FC_BLOCKS 256 #ifdef __KERNEL__ /** * typedef handle_t - The handle_t type represents a single atomic update being performed by some process. * * All filesystem modifications made by the process go * through this handle. Recursive operations (such as quota operations) * are gathered into a single update. * * The buffer credits field is used to account for journaled buffers * being modified by the running process. To ensure that there is * enough log space for all outstanding operations, we need to limit the * number of outstanding buffers possible at any time. When the * operation completes, any buffer credits not used are credited back to * the transaction, so that at all times we know how many buffers the * outstanding updates on a transaction might possibly touch. * * This is an opaque datatype. **/ typedef struct jbd2_journal_handle handle_t; /* Atomic operation type */ /** * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem. * * journal_t is linked to from the fs superblock structure. * * We use the journal_t to keep track of all outstanding transaction * activity on the filesystem, and to manage the state of the log * writing process. * * This is an opaque datatype. **/ typedef struct journal_s journal_t; /* Journal control structure */ #endif /* * Internal structures used by the logging mechanism: */ #define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */ /* * On-disk structures */ /* * Descriptor block types: */ #define JBD2_DESCRIPTOR_BLOCK 1 #define JBD2_COMMIT_BLOCK 2 #define JBD2_SUPERBLOCK_V1 3 #define JBD2_SUPERBLOCK_V2 4 #define JBD2_REVOKE_BLOCK 5 /* * Standard header for all descriptor blocks: */ typedef struct journal_header_s { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; } journal_header_t; /* * Checksum types. */ #define JBD2_CRC32_CHKSUM 1 #define JBD2_MD5_CHKSUM 2 #define JBD2_SHA1_CHKSUM 3 #define JBD2_CRC32C_CHKSUM 4 #define JBD2_CRC32_CHKSUM_SIZE 4 #define JBD2_CHECKSUM_BYTES (32 / sizeof(u32)) /* * Commit block header for storing transactional checksums: * * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum* * fields are used to store a checksum of the descriptor and data blocks. * * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum * field is used to store crc32c(uuid+commit_block). Each journal metadata * block gets its own checksum, and data block checksums are stored in * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses * journal_block_tag3_t to store a full 32-bit checksum. Everything else * is the same as v2. * * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; __be32 h_blocktype; __be32 h_sequence; unsigned char h_chksum_type; unsigned char h_chksum_size; unsigned char h_padding[2]; __be32 h_chksum[JBD2_CHECKSUM_BYTES]; __be64 h_commit_sec; __be32 h_commit_nsec; }; /* * The block tag: used to describe a single buffer in the journal. * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ typedef struct journal_block_tag3_s { __be32 t_blocknr; /* The on-disk block number */ __be32 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ __be32 t_checksum; /* crc32c(uuid+seq+block) */ } journal_block_tag3_t; typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ __be16 t_checksum; /* truncated crc32c(uuid+seq+block) */ __be16 t_flags; /* See below */ __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; /* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; /* * The revoke descriptor: used on disk to describe a series of blocks to * be revoked from the log */ typedef struct jbd2_journal_revoke_header_s { journal_header_t r_header; __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ #define JBD2_FLAG_DELETED 4 /* block deleted by this transaction */ #define JBD2_FLAG_LAST_TAG 8 /* last tag in this descriptor block */ /* * The journal superblock. All fields are in big-endian byte order. */ typedef struct journal_superblock_s { /* 0x0000 */ journal_header_t s_header; /* 0x000C */ /* Static information describing the journal */ __be32 s_blocksize; /* journal device blocksize */ __be32 s_maxlen; /* total blocks in journal file */ __be32 s_first; /* first block of log information */ /* 0x0018 */ /* Dynamic information describing the current state of the log */ __be32 s_sequence; /* first commit ID expected in log */ __be32 s_start; /* blocknr of start of log */ /* 0x0020 */ /* Error value, as set by jbd2_journal_abort(). */ __be32 s_errno; /* 0x0024 */ /* Remaining fields are only valid in a version-2 superblock */ __be32 s_feature_compat; /* compatible feature set */ __be32 s_feature_incompat; /* incompatible feature set */ __be32 s_feature_ro_compat; /* readonly-compatible feature set */ /* 0x0030 */ __u8 s_uuid[16]; /* 128-bit uuid for journal */ /* 0x0040 */ __be32 s_nr_users; /* Nr of filesystems sharing log */ __be32 s_dynsuper; /* Blocknr of dynamic superblock copy*/ /* 0x0048 */ __be32 s_max_transaction; /* Limit of journal blocks per trans.*/ __be32 s_max_trans_data; /* Limit of data blocks per trans. */ /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; /* 0x0054 */ __be32 s_num_fc_blks; /* Number of fast commit blocks */ /* 0x0058 */ __u32 s_padding[41]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ __u8 s_users[16*48]; /* ids of all fs'es sharing the log */ /* 0x0400 */ } journal_superblock_t; /* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */ #define JBD2_HAS_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) #define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) #define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ ((j)->j_format_version >= 2 && \ ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) #define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 #define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 #define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 /* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM #define JBD2_KNOWN_ROCOMPAT_FEATURES 0 #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ #include <linux/fs.h> #include <linux/sched.h> enum jbd_state_bits { BH_JBD /* Has an attached ext3 journal_head */ = BH_PrivateStart, BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ BH_Freed, /* Has been freed (truncated) */ BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ BH_JBDPrivateStart, /* First bit available for private use by FS */ }; BUFFER_FNS(JBD, jbd) BUFFER_FNS(JWrite, jwrite) BUFFER_FNS(JBDDirty, jbddirty) TAS_BUFFER_FNS(JBDDirty, jbddirty) BUFFER_FNS(Revoked, revoked) TAS_BUFFER_FNS(Revoked, revoked) BUFFER_FNS(RevokeValid, revokevalid) TAS_BUFFER_FNS(RevokeValid, revokevalid) BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; } static inline struct journal_head *bh2jh(struct buffer_head *bh) { return bh->b_private; } static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) { bit_spin_lock(BH_JournalHead, &bh->b_state); } static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) { bit_spin_unlock(BH_JournalHead, &bh->b_state); } #define J_ASSERT(assert) BUG_ON(!(assert)) #define J_ASSERT_BH(bh, expr) J_ASSERT(expr) #define J_ASSERT_JH(jh, expr) J_ASSERT(expr) #if defined(JBD2_PARANOID_IOFAIL) #define J_EXPECT(expr, why...) J_ASSERT(expr) #define J_EXPECT_BH(bh, expr, why...) J_ASSERT_BH(bh, expr) #define J_EXPECT_JH(jh, expr, why...) J_ASSERT_JH(jh, expr) #else #define __journal_expect(expr, why...) \ ({ \ int val = (expr); \ if (!val) { \ printk(KERN_ERR \ "JBD2 unexpected failure: %s: %s;\n", \ __func__, #expr); \ printk(KERN_ERR why "\n"); \ } \ val; \ }) #define J_EXPECT(expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_BH(bh, expr, why...) __journal_expect(expr, ## why) #define J_EXPECT_JH(jh, expr, why...) __journal_expect(expr, ## why) #endif /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 #define __JI_WRITE_DATA 1 #define __JI_WAIT_DATA 2 /* * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) /* Write allocated dirty buffers in this inode before commit */ #define JI_WRITE_DATA (1 << __JI_WRITE_DATA) /* Wait for outstanding data writes for this inode before commit */ #define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** * struct jbd2_inode - The jbd_inode type is the structure linking inodes in * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { /** * @i_transaction: * * Which transaction does this inode belong to? Either the running * transaction or the committing one. [j_list_lock] */ transaction_t *i_transaction; /** * @i_next_transaction: * * Pointer to the running transaction modifying inode's data in case * there is already a committing transaction touching it. [j_list_lock] */ transaction_t *i_next_transaction; /** * @i_list: List of inodes in the i_transaction [j_list_lock] */ struct list_head i_list; /** * @i_vfs_inode: * * VFS inode this inode belongs to [constant for lifetime of structure] */ struct inode *i_vfs_inode; /** * @i_flags: Flags of inode [j_list_lock] */ unsigned long i_flags; /** * @i_dirty_start: * * Offset in bytes where the dirty range for this inode starts. * [j_list_lock] */ loff_t i_dirty_start; /** * @i_dirty_end: * * Inclusive offset in bytes where the dirty range for this inode * ends. [j_list_lock] */ loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? * @h_journal: Which journal handle belongs to - used iff h_reserved set. * @h_rsv_handle: Handle reserved for finishing the logical operation. * @h_total_credits: Number of remaining buffers we are allowed to add to * journal. These are dirty buffers and revoke descriptor blocks. * @h_revoke_credits: Number of remaining revoke records available for handle * @h_ref: Reference count on this handle. * @h_err: Field for caller's use to track errors through large fs operations. * @h_sync: Flag for sync-on-close. * @h_jdata: Flag to force data journaling. * @h_reserved: Flag for handle for reserved credits. * @h_aborted: Flag indicating fatal error on handle. * @h_type: For handle statistics. * @h_line_no: For handle statistics. * @h_start_jiffies: Handle Start time. * @h_requested_credits: Holds @h_total_credits after handle is started. * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation * in so it can be fixed later. */ struct jbd2_journal_handle { union { transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; handle_t *h_rsv_handle; int h_total_credits; int h_revoke_credits; int h_revoke_credits_requested; int h_ref; int h_err; /* Flags [no locking] */ unsigned int h_sync: 1; unsigned int h_jdata: 1; unsigned int h_reserved: 1; unsigned int h_aborted: 1; unsigned int h_type: 8; unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; unsigned int saved_alloc_context; }; /* * Some stats for checkpoint phase */ struct transaction_chp_stats_s { unsigned long cs_chp_time; __u32 cs_forced_to_close; __u32 cs_written; __u32 cs_dropped; }; /* The transaction_t type is the guts of the journaling mechanism. It * tracks a compound transaction through its various states: * * RUNNING: accepting new updates * LOCKED: Updates still running but we don't accept new ones * RUNDOWN: Updates are tidying up but have finished requesting * new buffers to modify (state not used for now) * FLUSH: All updates complete, but we are still writing to disk * COMMIT: All data on disk, writing commit record * FINISHED: We still have to keep the transaction for checkpointing. * * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. */ /* * Lock ranking: * * j_list_lock * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock * ->b_state_lock * * b_state_lock * ->j_list_lock * * j_state_lock * ->t_handle_lock * * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ struct transaction_s { /* Pointer to the journal for this transaction. [no locking] */ journal_t *t_journal; /* Sequence number for this transaction [no locking] */ tid_t t_tid; /* * Transaction's current state * [no locking - only kjournald2 alters this] * [j_list_lock] guards transition of a transaction into T_FINISHED * state and subsequent call of __jbd2_journal_drop_transaction() * FIXME: needs barriers * KLUDGE: [use j_state_lock] */ enum { T_RUNNING, T_LOCKED, T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, T_COMMIT_JFLUSH, T_COMMIT_CALLBACK, T_FINISHED } t_state; /* * Where in the log does this transaction's commit start? [no locking] */ unsigned long t_log_start; /* Number of buffers on the t_buffers list [j_list_lock] */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet * modified by this transaction [j_list_lock] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this * transaction [j_list_lock] */ struct journal_head *t_buffers; /* * Doubly-linked circular list of all forget buffers (superseded * buffers which we can un-checkpoint once this transaction commits) * [j_list_lock] */ struct journal_head *t_forget; /* * Doubly-linked circular list of all buffers still to be flushed before * this transaction can be checkpointed. [j_list_lock] */ struct journal_head *t_checkpoint_list; /* * Doubly-linked circular list of all buffers submitted for IO while * checkpointing. [j_list_lock] */ struct journal_head *t_checkpoint_io_list; /* * Doubly-linked circular list of metadata buffers being shadowed by log * IO. The IO buffers on the iobuf list and the shadow buffers on this * list match each other one for one at all times. [j_list_lock] */ struct journal_head *t_shadow_list; /* * List of inodes associated with the transaction; e.g., ext4 uses * this to track inodes in data=ordered and data=journal mode that * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* * Protects info related to handles */ spinlock_t t_handle_lock; /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; /* * When transaction started */ unsigned long t_start; /* * When commit was requested */ unsigned long t_requested; /* * Checkpointing stats [j_checkpoint_sem] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction * [none] */ atomic_t t_updates; /* * Number of blocks reserved for this transaction in the journal. * This is including all credits reserved when starting transaction * handles as well as all journal descriptor blocks needed for this * transaction. [none] */ atomic_t t_outstanding_credits; /* * Number of revoke records for this transaction added by already * stopped handles. [none] */ atomic_t t_outstanding_revokes; /* * How many handles used this transaction? [none] */ atomic_t t_handle_count; /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ transaction_t *t_cpnext, *t_cpprev; /* * When will the transaction expire (become due for commit), in jiffies? * [no locking] */ unsigned long t_expires; /* * When this transaction started, in nanoseconds [no locking] */ ktime_t t_start_time; /* * This transaction is being forced and some process is * waiting for it to finish. */ unsigned int t_synchronous_commit:1; /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; /* * For use by the filesystem to store fs-specific data * structures associated with the transaction */ struct list_head t_private_list; }; struct transaction_run_stats_s { unsigned long rs_wait; unsigned long rs_request_delay; unsigned long rs_running; unsigned long rs_locked; unsigned long rs_flushing; unsigned long rs_logging; __u32 rs_handle_count; __u32 rs_blocks; __u32 rs_blocks_logged; }; struct transaction_stats_s { unsigned long ts_tid; unsigned long ts_requested; struct transaction_run_stats_s run; }; static inline unsigned long jbd2_time_diff(unsigned long start, unsigned long end) { if (end >= start) return end - start; return end + (MAX_JIFFY_OFFSET - start); } #define JBD2_NR_BATCH 64 enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; #define JBD2_FC_REPLAY_STOP 0 #define JBD2_FC_REPLAY_CONTINUE 1 /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. */ struct journal_s { /** * @j_flags: General journaling state flags [j_state_lock] */ unsigned long j_flags; /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; /** * @j_abort_mutex: Lock the whole aborting procedure. */ struct mutex j_abort_mutex; /** * @j_sb_buffer: The first part of the superblock buffer. */ struct buffer_head *j_sb_buffer; /** * @j_superblock: The second part of the superblock buffer. */ journal_superblock_t *j_superblock; /** * @j_format_version: Version of the superblock format. */ int j_format_version; /** * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; /** * @j_barrier_count: * * Number of processes waiting to create a barrier lock [j_state_lock] */ int j_barrier_count; /** * @j_barrier: The barrier lock itself. */ struct mutex j_barrier; /** * @j_running_transaction: * * Transactions: The current running transaction... * [j_state_lock] [caller holding open handle] */ transaction_t *j_running_transaction; /** * @j_committing_transaction: * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; /** * @j_checkpoint_transactions: * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; /** * @j_wait_transaction_locked: * * Wait queue for waiting for a locked transaction to start committing, * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; /** * @j_wait_done_commit: Wait queue for waiting for commit to complete. */ wait_queue_head_t j_wait_done_commit; /** * @j_wait_commit: Wait queue to trigger commit. */ wait_queue_head_t j_wait_commit; /** * @j_wait_updates: Wait queue to wait for updates to complete. */ wait_queue_head_t j_wait_updates; /** * @j_wait_reserved: * * Wait queue to wait for reserved buffer credits to drop. */ wait_queue_head_t j_wait_reserved; /** * @j_fc_wait: * * Wait queue to wait for completion of async fast commits. */ wait_queue_head_t j_fc_wait; /** * @j_checkpoint_mutex: * * Semaphore for locking against concurrent checkpoints. */ struct mutex j_checkpoint_mutex; /** * @j_chkpt_bhs: * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** * @j_head: * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; /** * @j_tail: * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; /** * @j_free: * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; /** * @j_first: * * The block number of the first usable block in the journal * [j_state_lock]. */ unsigned long j_first; /** * @j_last: * * The block number one beyond the last usable block in the journal * [j_state_lock]. */ unsigned long j_last; /** * @j_fc_first: * * The block number of the first fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_first; /** * @j_fc_off: * * Number of fast commit blocks currently allocated. Accessed only * during fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ unsigned long j_fc_off; /** * @j_fc_last: * * The block number one beyond the last fast commit block in the journal * [j_state_lock]. */ unsigned long j_fc_last; /** * @j_dev: Device where we store the journal. */ struct block_device *j_dev; /** * @j_blocksize: Block size for the location where we store the journal. */ int j_blocksize; /** * @j_blk_offset: * * Starting block offset into the device where we store the journal. */ unsigned long long j_blk_offset; /** * @j_devname: Journal device name. */ char j_devname[BDEVNAME_SIZE+24]; /** * @j_fs_dev: * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; /** * @j_total_len: Total maximum capacity of the journal region on disk. */ unsigned int j_total_len; /** * @j_reserved_credits: * * Number of buffers reserved from the running transaction. */ atomic_t j_reserved_credits; /** * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; /** * @j_inode: * * Optional inode where we store the journal. If present, all * journal block numbers are mapped into this inode via bmap(). */ struct inode *j_inode; /** * @j_tail_sequence: * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; /** * @j_transaction_sequence: * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; /** * @j_commit_sequence: * * Sequence number of the most recently committed transaction * [j_state_lock]. */ tid_t j_commit_sequence; /** * @j_commit_request: * * Sequence number of the most recent transaction wanting commit * [j_state_lock] */ tid_t j_commit_request; /** * @j_uuid: * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single * journal and to perform atomic updates across them. */ __u8 j_uuid[16]; /** * @j_task: Pointer to the current commit thread for this journal. */ struct task_struct *j_task; /** * @j_max_transaction_buffers: * * Maximum number of metadata buffers to allow in a single compound * commit transaction. */ int j_max_transaction_buffers; /** * @j_revoke_records_per_block: * * Number of revoke records that fit in one descriptor block. */ int j_revoke_records_per_block; /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; /** * @j_commit_timer: The timer used to wakeup the commit thread. */ struct timer_list j_commit_timer; /** * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; /** * @j_revoke: * * The revoke table - maintains the list of revoked blocks in the * current transaction. */ struct jbd2_revoke_table_s *j_revoke; /** * @j_revoke_table: Alternate revoke tables for j_revoke. */ struct jbd2_revoke_table_s *j_revoke_table[2]; /** * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; /** * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only * during a fast commit. Currently only process can do fast commit, so * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; /** * @j_wbufsize: * * Size of @j_wbuf array. */ int j_wbufsize; /** * @j_fc_wbufsize: * * Size of @j_fc_wbuf array. */ int j_fc_wbufsize; /** * @j_last_sync_writer: * * The pid of the last person to run a synchronous operation * through the journal. */ pid_t j_last_sync_writer; /** * @j_average_commit_time: * * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; /** * @j_min_batch_time: * * Minimum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; /** * @j_max_batch_time: * * Maximum time that we should wait for additional filesystem operations * to get batched into a synchronous handle in microseconds. */ u32 j_max_batch_time; /** * @j_commit_callback: * * This function is called when a transaction is closed. */ void (*j_commit_callback)(journal_t *, transaction_t *); /** * @j_submit_inode_data_buffers: * * This function is called for all inodes associated with the * committing transaction marked with JI_WRITE_DATA flag * before we start to write out the transaction to the journal. */ int (*j_submit_inode_data_buffers) (struct jbd2_inode *); /** * @j_finish_inode_data_buffers: * * This function is called for all inodes associated with the |