| 12 2 77 12 3 11 11 69 3 115 79 37 9 9 64 63 5 5 10 9 10 10 2 7 7 2 109 1 3 16 14 14 14 14 6 6 2 4 7 1 1 1 4 10 1 1 16 16 15 15 15 15 67 5 6 56 55 53 55 1 66 116 116 7 7 84 20 78 25 116 18 9 9 9 9 16 1 20 2 2 16 120 88 55 37 57 34 122 114 101 101 5 2 118 118 118 2 1 2 8 1 8 1 1 1 73 73 73 87 87 22 85 340 341 14 16 3 3 2 1 1 1 31 34 91 333 87 87 35 68 8 8 74 94 94 94 1 138 131 1 6 22 113 62 48 76 33 86 2 17 79 16 3 6 18 1 2 1 1 2 11 4 7 2 9 6 102 101 12 21 79 10 84 4 2 85 17 77 1 1 38 26 57 7 52 12 48 3 13 20 57 3 58 2 7 73 73 4 9 68 87 86 4 87 87 13 3 1 10 1 10 3 9 4 7 1 13 4 4 5 260 27 4 26 327 1 1 1 318 27 27 27 1 327 264 126 4264 4254 219 110 14 3 2 2 11 3 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2007 Patrick McHardy <kaber@trash.net> * * The code this is based on carried the following copyright notice: * --- * (C) Copyright 2001-2006 * Alex Zeffertt, Cambridge Broadband Ltd, ajz@cambridgebroadband.com * Re-worked by Ben Greear <greearb@candelatech.com> * --- */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/net_tstamp.h> #include <linux/ethtool.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/if_link.h> #include <linux/if_macvlan.h> #include <linux/hash.h> #include <linux/workqueue.h> #include <net/netdev_lock.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <linux/netpoll.h> #include <linux/phy.h> #define MACVLAN_HASH_BITS 8 #define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS) #define MACVLAN_DEFAULT_BC_QUEUE_LEN 1000 #define MACVLAN_F_PASSTHRU 1 #define MACVLAN_F_ADDRCHANGE 2 struct macvlan_port { struct net_device *dev; struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct sk_buff_head bc_queue; struct work_struct bc_work; u32 bc_queue_len_used; int bc_cutoff; u32 flags; int count; struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE]; DECLARE_BITMAP(bc_filter, MACVLAN_MC_FILTER_SZ); DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); unsigned char perm_addr[ETH_ALEN]; }; struct macvlan_source_entry { struct hlist_node hlist; struct macvlan_dev *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; struct macvlan_skb_cb { const struct macvlan_dev *src; }; #define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0])) static void macvlan_port_destroy(struct net_device *dev); static void update_port_bc_queue_len(struct macvlan_port *port); static inline bool macvlan_passthru(const struct macvlan_port *port) { return port->flags & MACVLAN_F_PASSTHRU; } static inline void macvlan_set_passthru(struct macvlan_port *port) { port->flags |= MACVLAN_F_PASSTHRU; } static inline bool macvlan_addr_change(const struct macvlan_port *port) { return port->flags & MACVLAN_F_ADDRCHANGE; } static inline void macvlan_set_addr_change(struct macvlan_port *port) { port->flags |= MACVLAN_F_ADDRCHANGE; } static inline void macvlan_clear_addr_change(struct macvlan_port *port) { port->flags &= ~MACVLAN_F_ADDRCHANGE; } /* Hash Ethernet address */ static u32 macvlan_eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, MACVLAN_HASH_BITS); } static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler_data); } static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, const unsigned char *addr) { struct macvlan_dev *vlan; u32 idx = macvlan_eth_hash(addr); hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } return NULL; } static struct macvlan_source_entry *macvlan_hash_lookup_source( const struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &vlan->port->vlan_source_hash[idx]; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && entry->vlan == vlan) return entry; } return NULL; } static int macvlan_hash_add_source(struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_port *port = vlan->port; struct macvlan_source_entry *entry; struct hlist_head *h; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) return 0; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; ether_addr_copy(entry->addr, addr); entry->vlan = vlan; h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; return 0; } static void macvlan_hash_add(struct macvlan_dev *vlan) { struct macvlan_port *port = vlan->port; const unsigned char *addr = vlan->dev->dev_addr; u32 idx = macvlan_eth_hash(addr); hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]); } static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync) { hlist_del_rcu(&vlan->hlist); if (sync) synchronize_rcu(); } static void macvlan_hash_change_addr(struct macvlan_dev *vlan, const unsigned char *addr) { macvlan_hash_del(vlan, true); /* Now that we are unhashed it is safe to change the device * address without confusing packet delivery. */ eth_hw_addr_set(vlan->dev, addr); macvlan_hash_add(vlan); } static bool macvlan_addr_busy(const struct macvlan_port *port, const unsigned char *addr) { /* Test to see if the specified address is * currently in use by the underlying device or * another macvlan. */ if (!macvlan_passthru(port) && !macvlan_addr_change(port) && ether_addr_equal_64bits(port->dev->dev_addr, addr)) return true; if (macvlan_hash_lookup(port, addr)) return true; return false; } static int macvlan_broadcast_one(struct sk_buff *skb, const struct macvlan_dev *vlan, const struct ethhdr *eth, bool local) { struct net_device *dev = vlan->dev; if (local) return __dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; return 0; } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) { return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT); } static unsigned int mc_hash(const struct macvlan_dev *vlan, const unsigned char *addr) { u32 val = get_unaligned((u32 *)(addr + 2)); val ^= macvlan_hash_mix(vlan); return hash_32(val, MACVLAN_MC_FILTER_BITS); } static void macvlan_broadcast(struct sk_buff *skb, const struct macvlan_port *port, struct net_device *src, enum macvlan_mode mode) { const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; struct sk_buff *nskb; unsigned int i; int err; unsigned int hash; if (skb->protocol == htons(ETH_P_PAUSE)) return; hash_for_each_rcu(port->vlan_hash, i, vlan, hlist) { if (vlan->dev == src || !(vlan->mode & mode)) continue; hash = mc_hash(vlan, eth->h_dest); if (!test_bit(hash, vlan->mc_filter)) continue; err = NET_RX_DROP; nskb = skb_clone(skb, GFP_ATOMIC); if (likely(nskb)) err = macvlan_broadcast_one(nskb, vlan, eth, mode == MACVLAN_MODE_BRIDGE) ?: netif_rx(nskb); macvlan_count_rx(vlan, skb->len + ETH_HLEN, err == NET_RX_SUCCESS, true); } } static void macvlan_multicast_rx(const struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { if (!src) /* frame comes from an external address */ macvlan_broadcast(skb, port, NULL, MACVLAN_MODE_PRIVATE | MACVLAN_MODE_VEPA | MACVLAN_MODE_PASSTHRU| MACVLAN_MODE_BRIDGE); else if (src->mode == MACVLAN_MODE_VEPA) /* flood to everyone except source */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA | MACVLAN_MODE_BRIDGE); else /* * flood only to VEPA ports, bridge ports * already saw the frame on the way out. */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA); } static void macvlan_process_broadcast(struct work_struct *w) { struct macvlan_port *port = container_of(w, struct macvlan_port, bc_work); struct sk_buff *skb; struct sk_buff_head list; __skb_queue_head_init(&list); spin_lock_bh(&port->bc_queue.lock); skb_queue_splice_tail_init(&port->bc_queue, &list); spin_unlock_bh(&port->bc_queue.lock); while ((skb = __skb_dequeue(&list))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; rcu_read_lock(); macvlan_multicast_rx(port, src, skb); rcu_read_unlock(); if (src) dev_put(src->dev); consume_skb(skb); cond_resched(); } } static void macvlan_broadcast_enqueue(struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { struct sk_buff *nskb; int err = -ENOMEM; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) goto err; MACVLAN_SKB_CB(nskb)->src = src; spin_lock(&port->bc_queue.lock); if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) { if (src) dev_hold(src->dev); __skb_queue_tail(&port->bc_queue, nskb); err = 0; } spin_unlock(&port->bc_queue.lock); queue_work(system_unbound_wq, &port->bc_work); if (err) goto free_nskb; return; free_nskb: kfree_skb(nskb); err: dev_core_stats_rx_dropped_inc(skb->dev); } static void macvlan_flush_sources(struct macvlan_port *port, struct macvlan_dev *vlan) { struct macvlan_source_entry *entry; struct hlist_node *next; int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) if (entry->vlan == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; } static void macvlan_forward_source_one(struct sk_buff *skb, struct macvlan_dev *vlan) { struct sk_buff *nskb; struct net_device *dev; int len; int ret; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; len = nskb->len + ETH_HLEN; nskb->dev = dev; if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) nskb->pkt_type = PACKET_HOST; ret = __netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); } static bool macvlan_forward_source(struct sk_buff *skb, struct macvlan_port *port, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &port->vlan_source_hash[idx]; bool consume = false; hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { if (entry->vlan->flags & MACVLAN_FLAG_NODST) consume = true; macvlan_forward_source_one(skb, entry->vlan); } } return consume; } /* called under rcu_read_lock() from netif_receive_skb */ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) { struct macvlan_port *port; struct sk_buff *skb = *pskb; const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; const struct macvlan_dev *src; struct net_device *dev; unsigned int len = 0; int ret; rx_handler_result_t handle_res; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; port = macvlan_port_get_rcu(skb->dev); if (is_multicast_ether_addr(eth->h_dest)) { unsigned int hash; skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { /* forward to original port. */ vlan = src; ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?: __netif_rx(skb); handle_res = RX_HANDLER_CONSUMED; goto out; } hash = mc_hash(NULL, eth->h_dest); if (test_bit(hash, port->bc_filter)) macvlan_broadcast_enqueue(port, src, skb); else if (test_bit(hash, port->mc_filter)) macvlan_multicast_rx(port, src, skb); return RX_HANDLER_PASS; } if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); else vlan = macvlan_hash_lookup(port, eth->h_dest); if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE) return RX_HANDLER_PASS; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } len = skb->len + ETH_HLEN; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) { ret = NET_RX_DROP; handle_res = RX_HANDLER_CONSUMED; goto out; } *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; ret = NET_RX_SUCCESS; handle_res = RX_HANDLER_ANOTHER; out: macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); return handle_res; } static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) { const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = skb_eth_hdr(skb); /* send to other bridge ports directly */ if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE); goto xmit_world; } dest = macvlan_hash_lookup(port, eth->h_dest); if (dest && dest->mode == MACVLAN_MODE_BRIDGE) { /* send to lowerdev first for its network taps */ dev_forward_skb(vlan->lowerdev, skb); return NET_XMIT_SUCCESS; } } xmit_world: skb->dev = vlan->lowerdev; return dev_queue_xmit_accel(skb, netdev_get_sb_channel(dev) ? dev : NULL); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER return netpoll_send_skb(vlan->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; if (unlikely(netpoll_tx_running(dev))) return macvlan_netpoll_send_skb(vlan, skb); ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(vlan->pcpu_stats->tx_dropped); } return ret; } static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return dev_hard_header(skb, lowerdev, type, daddr, saddr ? : dev->dev_addr, len); } static const struct header_ops macvlan_hard_header_ops = { .create = macvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; int err; if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto out; } goto hash_add; } err = -EADDRINUSE; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; /* Attempt to populate accel_priv which is used to offload the L2 * forwarding requests for unicast packets. */ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) vlan->accel_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); /* If earlier attempt to offload failed, or accel_priv is not * populated we must add the unicast address to the lower device. */ if (IS_ERR_OR_NULL(vlan->accel_priv)) { vlan->accel_priv = NULL; err = dev_uc_add(lowerdev, dev->dev_addr); if (err < 0) goto out; } if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(lowerdev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto clear_multi; } hash_add: macvlan_hash_add(vlan); return 0; clear_multi: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); del_unicast: if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } else { dev_uc_del(lowerdev, dev->dev_addr); } out: return err; } static int macvlan_stop(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } dev_uc_unsync(lowerdev, dev); dev_mc_unsync(lowerdev, dev); if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) dev_set_promiscuity(lowerdev, -1); goto hash_del; } if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(lowerdev, -1); dev_uc_del(lowerdev, dev->dev_addr); hash_del: macvlan_hash_del(vlan, !dev->dismantle); return 0; } static int macvlan_sync_address(struct net_device *dev, const unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; int err; if (!(dev->flags & IFF_UP)) { /* Just copy in the new address */ eth_hw_addr_set(dev, addr); } else { /* Rehash and update the device filters */ if (macvlan_addr_busy(vlan->port, addr)) return -EADDRINUSE; if (!macvlan_passthru(port)) { err = dev_uc_add(lowerdev, addr); if (err) return err; dev_uc_del(lowerdev, dev->dev_addr); } macvlan_hash_change_addr(vlan, addr); } if (macvlan_passthru(port) && !macvlan_addr_change(port)) { /* Since addr_change isn't set, we are here due to lower * device change. Save the lower-dev address so we can * restore it later. */ ether_addr_copy(vlan->port->perm_addr, lowerdev->dev_addr); } macvlan_clear_addr_change(port); return 0; } static int macvlan_set_mac_address(struct net_device *dev, void *p) { struct macvlan_dev *vlan = netdev_priv(dev); struct sockaddr_storage *addr = p; if (!is_valid_ether_addr(addr->__data)) return -EADDRNOTAVAIL; /* If the addresses are the same, this is a no-op */ if (ether_addr_equal(dev->dev_addr, addr->__data)) return 0; if (vlan->mode == MACVLAN_MODE_PASSTHRU) { macvlan_set_addr_change(vlan->port); return dev_set_mac_address(vlan->lowerdev, addr, NULL); } if (macvlan_addr_busy(vlan->port, addr->__data)) return -EADDRINUSE; return macvlan_sync_address(dev, addr->__data); } static void macvlan_change_rx_flags(struct net_device *dev, int change) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); } } static void macvlan_compute_filter(unsigned long *mc_filter, struct net_device *dev, struct macvlan_dev *vlan, int cutoff) { if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(mc_filter, MACVLAN_MC_FILTER_SZ); } else { DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ); struct netdev_hw_addr *ha; bitmap_zero(filter, MACVLAN_MC_FILTER_SZ); netdev_for_each_mc_addr(ha, dev) { if (!vlan && ha->synced <= cutoff) continue; __set_bit(mc_hash(vlan, ha->addr), filter); } __set_bit(mc_hash(vlan, dev->broadcast), filter); bitmap_copy(mc_filter, filter, MACVLAN_MC_FILTER_SZ); } } static void macvlan_recompute_bc_filter(struct macvlan_dev *vlan) { if (vlan->port->bc_cutoff < 0) { bitmap_zero(vlan->port->bc_filter, MACVLAN_MC_FILTER_SZ); return; } macvlan_compute_filter(vlan->port->bc_filter, vlan->lowerdev, NULL, vlan->port->bc_cutoff); } static void macvlan_set_mac_lists(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); macvlan_compute_filter(vlan->mc_filter, dev, vlan, 0); dev_uc_sync(vlan->lowerdev, dev); dev_mc_sync(vlan->lowerdev, dev); /* This is slightly inaccurate as we're including the subscription * list of vlan->lowerdev too. * * Bug alert: This only works if everyone has the same broadcast * address as lowerdev. As soon as someone changes theirs this * will break. * * However, this is already broken as when you change your broadcast * address we don't get called. * * The solution is to maintain a list of broadcast addresses like * we do for uc/mc, if you care. */ macvlan_compute_filter(vlan->port->mc_filter, vlan->lowerdev, NULL, 0); macvlan_recompute_bc_filter(vlan); } static void update_port_bc_cutoff(struct macvlan_dev *vlan, int cutoff) { if (vlan->port->bc_cutoff == cutoff) return; vlan->port->bc_cutoff = cutoff; macvlan_recompute_bc_filter(vlan); } static int macvlan_change_mtu(struct net_device *dev, int new_mtu) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->lowerdev->mtu < new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int macvlan_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return generic_hwtstamp_get_lower(real_dev, cfg); } static int macvlan_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct net_device *real_dev = macvlan_dev_real_dev(dev); if (!net_eq(dev_net(dev), &init_net)) return -EOPNOTSUPP; return generic_hwtstamp_set_lower(real_dev, cfg, extack); } /* * macvlan network devices have devices nesting below it and are a special * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ static struct lock_class_key macvlan_netdev_addr_lock_key; #define ALWAYS_ON_OFFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) #define ALWAYS_ON_FEATURES ALWAYS_ON_OFFLOADS #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_LRO | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static void macvlan_set_lockdep_class(struct net_device *dev) { netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macvlan_netdev_addr_lock_key); } static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, lowerdev); dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; port->count += 1; /* Get macvlan's reference to lowerdev */ netdev_hold(lowerdev, &vlan->dev_tracker, GFP_KERNEL); return 0; } static void macvlan_uninit(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; free_percpu(vlan->pcpu_stats); macvlan_flush_sources(port, vlan); port->count -= 1; if (!port->count) macvlan_port_destroy(port->dev); } static void macvlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->pcpu_stats) { struct vlan_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_errors = 0, tx_dropped = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(vlan->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* rx_errors & tx_dropped are u32, updated * without syncp protection. */ rx_errors += READ_ONCE(p->rx_errors); tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->rx_dropped = rx_errors; stats->tx_dropped = tx_dropped; } } static int macvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return vlan_vid_add(lowerdev, proto, vid); } static int macvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; vlan_vid_del(lowerdev, proto, vid); return 0; } static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_add_excl(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_add_excl(dev, addr); return err; } static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_del(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_del(dev, addr); return err; } static void macvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver)); strscpy(drvinfo->version, "0.1", sizeof(drvinfo->version)); } static int macvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct macvlan_dev *vlan = netdev_priv(dev); return __ethtool_get_link_ksettings(vlan->lowerdev, cmd); } static int macvlan_ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return ethtool_get_ts_info_by_layer(real_dev, info); } static netdev_features_t macvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct macvlan_dev *vlan = netdev_priv(dev); netdev_features_t lowerdev_features = vlan->lowerdev->features; netdev_features_t mask; features |= NETIF_F_ALL_FOR_ALL; features &= (vlan->set_features | ~MACVLAN_FEATURES); mask = features; lowerdev_features &= (features | ~NETIF_F_LRO); features = netdev_increment_features(lowerdev_features, features, mask); features |= ALWAYS_ON_FEATURES; features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES); return features; } #ifdef CONFIG_NET_POLL_CONTROLLER static void macvlan_dev_poll_controller(struct net_device *dev) { return; } static int macvlan_dev_netpoll_setup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *real_dev = vlan->lowerdev; struct netpoll *netpoll; int err; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; } vlan->netpoll = netpoll; out: return err; } static void macvlan_dev_netpoll_cleanup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; vlan->netpoll = NULL; __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int macvlan_dev_get_iflink(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return READ_ONCE(vlan->lowerdev->ifindex); } static const struct ethtool_ops macvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = macvlan_ethtool_get_link_ksettings, .get_drvinfo = macvlan_ethtool_get_drvinfo, .get_ts_info = macvlan_ethtool_get_ts_info, }; static const struct net_device_ops macvlan_netdev_ops = { .ndo_init = macvlan_init, .ndo_uninit = macvlan_uninit, .ndo_open = macvlan_open, .ndo_stop = macvlan_stop, .ndo_start_xmit = macvlan_start_xmit, .ndo_change_mtu = macvlan_change_mtu, .ndo_fix_features = macvlan_fix_features, .ndo_change_rx_flags = macvlan_change_rx_flags, .ndo_set_mac_address = macvlan_set_mac_address, .ndo_set_rx_mode = macvlan_set_mac_lists, .ndo_get_stats64 = macvlan_dev_get_stats64, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = macvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = macvlan_vlan_rx_kill_vid, .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, .ndo_netpoll_cleanup = macvlan_dev_netpoll_cleanup, #endif .ndo_get_iflink = macvlan_dev_get_iflink, .ndo_features_check = passthru_features_check, .ndo_hwtstamp_get = macvlan_hwtstamp_get, .ndo_hwtstamp_set = macvlan_hwtstamp_set, }; static void macvlan_dev_free(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); /* Get rid of the macvlan's reference to lowerdev */ netdev_put(vlan->lowerdev, &vlan->dev_tracker); } void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); /* ether_setup() has set dev->min_mtu to ETH_MIN_MTU. */ dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); dev->priv_flags |= IFF_UNICAST_FLT; dev->change_proto_down = true; dev->netdev_ops = &macvlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macvlan_dev_free; dev->header_ops = &macvlan_hard_header_ops; dev->ethtool_ops = &macvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(macvlan_common_setup); static void macvlan_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->priv_flags |= IFF_NO_QUEUE; } static int macvlan_port_create(struct net_device *dev) { struct macvlan_port *port; unsigned int i; int err; if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) return -EINVAL; if (netdev_is_rx_handler_busy(dev)) return -EBUSY; port = kzalloc(sizeof(*port), GFP_KERNEL); if (port == NULL) return -ENOMEM; port->dev = dev; ether_addr_copy(port->perm_addr, dev->dev_addr); INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_source_hash[i]); port->bc_queue_len_used = 0; port->bc_cutoff = 1; skb_queue_head_init(&port->bc_queue); INIT_WORK(&port->bc_work, macvlan_process_broadcast); err = netdev_rx_handler_register(dev, macvlan_handle_frame, port); if (err) kfree(port); else dev->priv_flags |= IFF_MACVLAN_PORT; return err; } static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); struct sk_buff *skb; dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); /* After this point, no packet can schedule bc_work anymore, * but we need to cancel it and purge left skbs if any. */ cancel_work_sync(&port->bc_work); while ((skb = __skb_dequeue(&port->bc_queue))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; if (src) dev_put(src->dev); kfree_skb(skb); } /* If the lower device address has been changed by passthru * macvlan, put it back. */ if (macvlan_passthru(port) && !ether_addr_equal(port->dev->dev_addr, port->perm_addr)) { struct sockaddr_storage ss; ss.ss_family = port->dev->type; memcpy(&ss.__data, port->perm_addr, port->dev->addr_len); dev_set_mac_address(port->dev, &ss, NULL); } kfree(port); } static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct nlattr *nla, *head; int rem, len; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; if (data[IFLA_MACVLAN_FLAGS] && nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~(MACVLAN_FLAG_NOPROMISC | MACVLAN_FLAG_NODST)) return -EINVAL; if (data[IFLA_MACVLAN_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) { case MACVLAN_MODE_PRIVATE: case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: case MACVLAN_MODE_PASSTHRU: case MACVLAN_MODE_SOURCE: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) { case MACVLAN_MACADDR_ADD: case MACVLAN_MACADDR_DEL: case MACVLAN_MACADDR_FLUSH: case MACVLAN_MACADDR_SET: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR]) { if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR]))) return -EADDRNOTAVAIL; } if (data[IFLA_MACVLAN_MACADDR_DATA]) { head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { if (nla_type(nla) != IFLA_MACVLAN_MACADDR || nla_len(nla) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(nla))) return -EADDRNOTAVAIL; } } if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; return 0; } /* * reconfigure list of remote source mac address * (only for macvlan devices in source mode) * Note regarding alignment: all netlink data is aligned to 4 Byte, which * suffices for both ether_addr_copy and ether_addr_equal_64bits usage. */ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, struct nlattr *data[]) { char *addr = NULL; int ret, rem, len; struct nlattr *nla, *head; struct macvlan_source_entry *entry; if (data[IFLA_MACVLAN_MACADDR]) addr = nla_data(data[IFLA_MACVLAN_MACADDR]); if (mode == MACVLAN_MACADDR_ADD) { if (!addr) return -EINVAL; return macvlan_hash_add_source(vlan, addr); } else if (mode == MACVLAN_MACADDR_DEL) { if (!addr) return -EINVAL; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) { macvlan_hash_del_source(entry); vlan->macaddr_count--; } } else if (mode == MACVLAN_MACADDR_FLUSH) { macvlan_flush_sources(vlan->port, vlan); } else if (mode == MACVLAN_MACADDR_SET) { macvlan_flush_sources(vlan->port, vlan); if (addr) { ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } if (!data[IFLA_MACVLAN_MACADDR_DATA]) return 0; head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } } else { return -EINVAL; } return 0; } int macvlan_common_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct macvlan_dev *vlan = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct net_device *lowerdev; struct macvlan_port *port; bool create = false; int macmode; int err; if (!tb[IFLA_LINK]) return -EINVAL; lowerdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (lowerdev == NULL) return -ENODEV; /* When creating macvlans or macvtaps on top of other macvlans - use * the real device as the lowerdev. */ if (netif_is_macvlan(lowerdev)) lowerdev = macvlan_dev_real_dev(lowerdev); if (!tb[IFLA_MTU]) dev->mtu = lowerdev->mtu; else if (dev->mtu > lowerdev->mtu) return -EINVAL; /* MTU range: 68 - lowerdev->max_mtu */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = lowerdev->max_mtu; if (!tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (!netif_is_macvlan_port(lowerdev)) { err = macvlan_port_create(lowerdev); if (err < 0) return err; create = true; } port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */ if (macvlan_passthru(port)) { /* The macvlan port must be not created this time, * still goto destroy_macvlan_port for readability. */ err = -EINVAL; goto destroy_macvlan_port; } vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); if (data && data[IFLA_MACVLAN_FLAGS]) vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); if (vlan->mode == MACVLAN_MODE_PASSTHRU) { if (port->count) { err = -EINVAL; goto destroy_macvlan_port; } macvlan_set_passthru(port); eth_hw_addr_inherit(dev, lowerdev); } if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) { err = -EINVAL; goto destroy_macvlan_port; } macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); err = macvlan_changelink_sources(vlan, macmode, data); if (err) goto destroy_macvlan_port; } vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN; if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); err = register_netdevice(dev); if (err < 0) goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev, extack); if (err) goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); update_port_bc_queue_len(vlan->port); netif_stacked_transfer_operstate(lowerdev, dev); linkwatch_fire_event(dev); return 0; unregister_netdev: /* macvlan_uninit would free the macvlan port */ unregister_netdevice(dev); return err; destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ if (create && macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); macvlan_port_destroy(port->dev); } return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { return macvlan_common_newlink(dev, params, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->mode == MACVLAN_MODE_SOURCE) macvlan_flush_sources(vlan->port, vlan); list_del_rcu(&vlan->list); update_port_bc_queue_len(vlan->port); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(vlan->lowerdev, dev); } EXPORT_SYMBOL_GPL(macvlan_dellink); static int macvlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); enum macvlan_mode mode; bool set_mode = false; enum macvlan_macaddr_mode macmode; int ret; /* Validate mode, but don't set yet: setting flags may fail. */ if (data && data[IFLA_MACVLAN_MODE]) { set_mode = true; mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); /* Passthrough mode can't be set or cleared dynamically */ if ((mode == MACVLAN_MODE_PASSTHRU) != (vlan->mode == MACVLAN_MODE_PASSTHRU)) return -EINVAL; if (vlan->mode == MACVLAN_MODE_SOURCE && vlan->mode != mode) macvlan_flush_sources(vlan->port, vlan); } if (data && data[IFLA_MACVLAN_FLAGS]) { __u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC; if (macvlan_passthru(vlan->port) && promisc) { int err; if (flags & MACVLAN_FLAG_NOPROMISC) err = dev_set_promiscuity(vlan->lowerdev, -1); else err = dev_set_promiscuity(vlan->lowerdev, 1); if (err < 0) return err; } vlan->flags = flags; } if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) { vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); update_port_bc_queue_len(vlan->port); } if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); if (set_mode) vlan->mode = mode; if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) return -EINVAL; macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); ret = macvlan_changelink_sources(vlan, macmode, data); if (ret) return ret; } return 0; } static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan) { if (vlan->macaddr_count == 0) return 0; return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */ + vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN); } static size_t macvlan_get_size(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return (0 + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */ + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */ ); } static int macvlan_fill_info_macaddr(struct sk_buff *skb, const struct macvlan_dev *vlan, const int i) { struct hlist_head *h = &vlan->port->vlan_source_hash[i]; struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (entry->vlan != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; } return 0; } static int macvlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; int i; struct nlattr *nest; if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count)) goto nla_put_failure; if (vlan->macaddr_count > 0) { nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA); if (nest == NULL) goto nla_put_failure; for (i = 0; i < MACVLAN_HASH_SIZE; i++) { if (macvlan_fill_info_macaddr(skb, vlan, i)) goto nla_put_failure; } nla_nest_end(skb, nest); } if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used)) goto nla_put_failure; if (port->bc_cutoff != 1 && nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, port->bc_cutoff)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { [IFLA_MACVLAN_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 }, [IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED }, [IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT }, [IFLA_MACVLAN_BC_CUTOFF] = { .type = NLA_S32 }, }; int macvlan_link_register(struct rtnl_link_ops *ops) { /* common fields */ ops->validate = macvlan_validate; ops->maxtype = IFLA_MACVLAN_MAX; ops->policy = macvlan_policy; ops->changelink = macvlan_changelink; ops->get_size = macvlan_get_size; ops->fill_info = macvlan_fill_info; return rtnl_link_register(ops); }; EXPORT_SYMBOL_GPL(macvlan_link_register); static struct net *macvlan_get_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvlan_link_ops = { .kind = "macvlan", .setup = macvlan_setup, .newlink = macvlan_newlink, .dellink = macvlan_dellink, .get_link_net = macvlan_get_link_net, .priv_size = sizeof(struct macvlan_dev), }; static void update_port_bc_queue_len(struct macvlan_port *port) { u32 max_bc_queue_len_req = 0; struct macvlan_dev *vlan; list_for_each_entry(vlan, &port->vlans, list) { if (vlan->bc_queue_len_req > max_bc_queue_len_req) max_bc_queue_len_req = vlan->bc_queue_len_req; } port->bc_queue_len_used = max_bc_queue_len_req; } static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan, *next; struct macvlan_port *port; LIST_HEAD(list_kill); if (!netif_is_macvlan_port(dev)) return NOTIFY_DONE; port = macvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) netif_stacked_transfer_operstate(vlan->lowerdev, vlan->dev); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { netif_inherit_tso_max(vlan->dev, dev); netdev_update_features(vlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(vlan, &port->vlans, list) { if (vlan->dev->mtu <= dev->mtu) continue; dev_set_mtu(vlan->dev, dev->mtu); } break; case NETDEV_CHANGEADDR: if (!macvlan_passthru(port)) return NOTIFY_DONE; vlan = list_first_entry_or_null(&port->vlans, struct macvlan_dev, list); if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr)) return NOTIFY_BAD; break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(vlan, next, &port->vlans, list) vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill); unregister_netdevice_many(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to all vlans */ list_for_each_entry(vlan, &port->vlans, list) call_netdevice_notifiers(event, vlan->dev); } return NOTIFY_DONE; } static struct notifier_block macvlan_notifier_block __read_mostly = { .notifier_call = macvlan_device_event, }; static int __init macvlan_init_module(void) { int err; register_netdevice_notifier(&macvlan_notifier_block); err = macvlan_link_register(&macvlan_link_ops); if (err < 0) goto err1; return 0; err1: unregister_netdevice_notifier(&macvlan_notifier_block); return err; } static void __exit macvlan_cleanup_module(void) { rtnl_link_unregister(&macvlan_link_ops); unregister_netdevice_notifier(&macvlan_notifier_block); } module_init(macvlan_init_module); module_exit(macvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Driver for MAC address based VLANs"); MODULE_ALIAS_RTNL_LINK("macvlan"); |
| 7893 7894 27 27 87 87 87 492 16688 16203 16214 16216 16201 16208 16701 16688 16200 16245 16202 11789 16731 18585 18590 1 219 151 724 542 17 756 18307 18310 18308 20359 20353 1287 1287 18 17 18 25 8 136 8934 13124 18636 18676 16469 18602 8 113 113 96 16418 16438 16469 6 6 16429 736 623 623 714 23 23 351 431 588 597 1 1 588 7 7 587 595 6 588 738 3 736 333 419 238 521 7 7 353 431 164 594 681 18 61 707 30 16019 1408 16015 185 15344 3836 15497 3030 3034 12305 12308 104 86 103 3 10 86 111 10 104 5 4 7 6 1 90 1 1 8 81 81 37 51 82 9 19 65 24 65 6 22 56 75 6 78 72 72 72 12 20 2 2 1 15 2 4 10 34 5 29 29 247 18601 18583 179 12 2 1 2 7 10 18589 18131 512 12606 42 33 32 33 9 8 1 9 8 8 8 12614 1582 16285 12574 12581 12583 4 4 22237 22244 22229 22066 5077 984 18624 18624 18467 18596 18618 18642 18627 13 41 12577 7773 7775 321 229 2194 2188 3 6296 2285 5537 1 2286 7 1644 772 771 2285 2283 1 2280 15 2286 229 2283 8397 5786 7261 8396 7248 180 8154 2169 141 4660 25 25 24 25 57 1 57 37 33 5 12 15 20 5 3 2 2 3 2 2 7 18 25 1 1 1 3 2 2 7 1 8 1 2 2 2 6 1 7 3 2 18611 1 225 18649 11 2 3 722 18227 15974 3461 2 18612 21 18499 104 18483 772 1 111 745 2 610 240 483 266 746 3 747 2 717 31 585 317 1 771 492 492 492 492 30 30 25575 13437 13435 1 5 3 3 5 5 5 2 3 3 3 3 1588 1588 1583 3 3 2161 1966 316 1 1 1838 385 1840 2159 2156 2169 1 2119 42 1 2145 7 792 1589 3 1582 594 996 2175 2168 2175 1 735 1231 1956 225 225 12005 1967 10599 1959 10624 10601 11988 2 15829 15709 501 78 31 1918 13989 10987 6093 5250 1368 5244 1367 5 2 5 3 5 5 5 5 5 3 2 5 5 5 5 5 2 3 5 492 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NETLINK Kernel-user communication protocol. * * Authors: Alan Cox <alan@lxorguk.ukuu.org.uk> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Patrick McHardy <kaber@trash.net> * * Tue Jun 26 14:36:48 MEST 2001 Herbert "herp" Rosmanith * added netlink_proto_exit * Tue Jan 22 18:32:44 BRST 2002 Arnaldo C. de Melo <acme@conectiva.com.br> * use nlk_sk, as sk->protinfo is on a diet 8) * Fri Jul 22 19:51:12 MEST 2005 Harald Welte <laforge@gnumonks.org> * - inc module use count of module that owns * the kernel socket in case userspace opens * socket of same protocol * - remove all module support, since netlink is * mandatory if CONFIG_NET=y these days */ #include <linux/module.h> #include <linux/bpf.h> #include <linux/capability.h> #include <linux/kernel.h> #include <linux/filter.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/un.h> #include <linux/fcntl.h> #include <linux/termios.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/security.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/bitops.h> #include <linux/mm.h> #include <linux/types.h> #include <linux/audit.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> #include <linux/rhashtable.h> #include <asm/cacheflush.h> #include <linux/hash.h> #include <linux/net_namespace.h> #include <linux/nospec.h> #include <linux/btf_ids.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> #include <net/scm.h> #include <net/netlink.h> #define CREATE_TRACE_POINTS #include <trace/events/netlink.h> #include "af_netlink.h" #include "genetlink.h" struct listeners { struct rcu_head rcu; unsigned long masks[]; }; /* state bits */ #define NETLINK_S_CONGESTED 0x0 static inline int netlink_is_kernel(struct sock *sk) { return nlk_test_bit(KERNEL_SOCKET, sk); } struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); static struct lock_class_key nlk_cb_mutex_keys[MAX_LINKS]; static const char *const nlk_cb_mutex_key_strings[MAX_LINKS + 1] = { "nlk_cb_mutex-ROUTE", "nlk_cb_mutex-1", "nlk_cb_mutex-USERSOCK", "nlk_cb_mutex-FIREWALL", "nlk_cb_mutex-SOCK_DIAG", "nlk_cb_mutex-NFLOG", "nlk_cb_mutex-XFRM", "nlk_cb_mutex-SELINUX", "nlk_cb_mutex-ISCSI", "nlk_cb_mutex-AUDIT", "nlk_cb_mutex-FIB_LOOKUP", "nlk_cb_mutex-CONNECTOR", "nlk_cb_mutex-NETFILTER", "nlk_cb_mutex-IP6_FW", "nlk_cb_mutex-DNRTMSG", "nlk_cb_mutex-KOBJECT_UEVENT", "nlk_cb_mutex-GENERIC", "nlk_cb_mutex-17", "nlk_cb_mutex-SCSITRANSPORT", "nlk_cb_mutex-ECRYPTFS", "nlk_cb_mutex-RDMA", "nlk_cb_mutex-CRYPTO", "nlk_cb_mutex-SMC", "nlk_cb_mutex-23", "nlk_cb_mutex-24", "nlk_cb_mutex-25", "nlk_cb_mutex-26", "nlk_cb_mutex-27", "nlk_cb_mutex-28", "nlk_cb_mutex-29", "nlk_cb_mutex-30", "nlk_cb_mutex-31", "nlk_cb_mutex-MAX_LINKS" }; static int netlink_dump(struct sock *sk, bool lock_taken); /* nl_table locking explained: * Lookup and traversal are protected with an RCU read-side lock. Insertion * and removal are protected with per bucket lock while using RCU list * modification primitives and may run in parallel to RCU protected lookups. * Destruction of the Netlink socket may only occur *after* nl_table_lock has * been acquired * either during or after the socket has been removed from * the list and after an RCU grace period. */ DEFINE_RWLOCK(nl_table_lock); EXPORT_SYMBOL_GPL(nl_table_lock); static atomic_t nl_table_users = ATOMIC_INIT(0); #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock)); static BLOCKING_NOTIFIER_HEAD(netlink_chain); static const struct rhashtable_params netlink_rhashtable_params; void do_trace_netlink_extack(const char *msg) { trace_netlink_extack(msg); } EXPORT_SYMBOL(do_trace_netlink_extack); static inline u32 netlink_group_mask(u32 group) { if (group > 32) return 0; return group ? 1 << (group - 1) : 0; } static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); if (new == NULL) return NULL; NETLINK_CB(new).portid = NETLINK_CB(skb).portid; NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group; NETLINK_CB(new).creds = NETLINK_CB(skb).creds; skb_put_data(new, skb->data, len); return new; } static unsigned int netlink_tap_net_id; struct netlink_tap_net { struct list_head netlink_tap_all; struct mutex netlink_tap_lock; }; int netlink_add_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); if (unlikely(nt->dev->type != ARPHRD_NETLINK)) return -EINVAL; mutex_lock(&nn->netlink_tap_lock); list_add_rcu(&nt->list, &nn->netlink_tap_all); mutex_unlock(&nn->netlink_tap_lock); __module_get(nt->module); return 0; } EXPORT_SYMBOL_GPL(netlink_add_tap); static int __netlink_remove_tap(struct netlink_tap *nt) { struct net *net = dev_net(nt->dev); struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); bool found = false; struct netlink_tap *tmp; mutex_lock(&nn->netlink_tap_lock); list_for_each_entry(tmp, &nn->netlink_tap_all, list) { if (nt == tmp) { list_del_rcu(&nt->list); found = true; goto out; } } pr_warn("__netlink_remove_tap: %p not found\n", nt); out: mutex_unlock(&nn->netlink_tap_lock); if (found) module_put(nt->module); return found ? 0 : -ENODEV; } int netlink_remove_tap(struct netlink_tap *nt) { int ret; ret = __netlink_remove_tap(nt); synchronize_net(); return ret; } EXPORT_SYMBOL_GPL(netlink_remove_tap); static __net_init int netlink_tap_init_net(struct net *net) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); INIT_LIST_HEAD(&nn->netlink_tap_all); mutex_init(&nn->netlink_tap_lock); return 0; } static struct pernet_operations netlink_tap_net_ops = { .init = netlink_tap_init_net, .id = &netlink_tap_net_id, .size = sizeof(struct netlink_tap_net), }; static bool netlink_filter_tap(const struct sk_buff *skb) { struct sock *sk = skb->sk; /* We take the more conservative approach and * whitelist socket protocols that may pass. */ switch (sk->sk_protocol) { case NETLINK_ROUTE: case NETLINK_USERSOCK: case NETLINK_SOCK_DIAG: case NETLINK_NFLOG: case NETLINK_XFRM: case NETLINK_FIB_LOOKUP: case NETLINK_NETFILTER: case NETLINK_GENERIC: return true; } return false; } static int __netlink_deliver_tap_skb(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; struct sock *sk = skb->sk; int ret = -ENOMEM; if (!net_eq(dev_net(dev), sock_net(sk))) return 0; dev_hold(dev); if (is_vmalloc_addr(skb->head)) nskb = netlink_to_full_skb(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); if (nskb) { nskb->dev = dev; nskb->protocol = htons((u16) sk->sk_protocol); nskb->pkt_type = netlink_is_kernel(sk) ? PACKET_KERNEL : PACKET_USER; skb_reset_network_header(nskb); ret = dev_queue_xmit(nskb); if (unlikely(ret > 0)) ret = net_xmit_errno(ret); } dev_put(dev); return ret; } static void __netlink_deliver_tap(struct sk_buff *skb, struct netlink_tap_net *nn) { int ret; struct netlink_tap *tmp; if (!netlink_filter_tap(skb)) return; list_for_each_entry_rcu(tmp, &nn->netlink_tap_all, list) { ret = __netlink_deliver_tap_skb(skb, tmp->dev); if (unlikely(ret)) break; } } static void netlink_deliver_tap(struct net *net, struct sk_buff *skb) { struct netlink_tap_net *nn = net_generic(net, netlink_tap_net_id); rcu_read_lock(); if (unlikely(!list_empty(&nn->netlink_tap_all))) __netlink_deliver_tap(skb, nn); rcu_read_unlock(); } static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src, struct sk_buff *skb) { if (!(netlink_is_kernel(dst) && netlink_is_kernel(src))) netlink_deliver_tap(sock_net(dst), skb); } static void netlink_overrun(struct sock *sk) { if (!nlk_test_bit(RECV_NO_ENOBUFS, sk)) { if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { WRITE_ONCE(sk->sk_err, ENOBUFS); sk_error_report(sk); } } atomic_inc(&sk->sk_drops); } static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); } static void netlink_skb_destructor(struct sk_buff *skb) { if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) vfree_atomic(skb->head); skb->head = NULL; } if (skb->sk != NULL) sock_rfree(skb); } static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) { WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } static void netlink_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); if (!sock_flag(sk, SOCK_DEAD)) { printk(KERN_ERR "Freeing alive netlink socket %p\n", sk); return; } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(nlk_sk(sk)->groups); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves * this, _but_ remember, it adds useless work on UP machines. */ void netlink_table_grab(void) __acquires(nl_table_lock) { might_sleep(); write_lock_irq(&nl_table_lock); if (atomic_read(&nl_table_users)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&nl_table_wait, &wait); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (atomic_read(&nl_table_users) == 0) break; write_unlock_irq(&nl_table_lock); schedule(); write_lock_irq(&nl_table_lock); } __set_current_state(TASK_RUNNING); remove_wait_queue(&nl_table_wait, &wait); } } void netlink_table_ungrab(void) __releases(nl_table_lock) { write_unlock_irq(&nl_table_lock); wake_up(&nl_table_wait); } static inline void netlink_lock_table(void) { unsigned long flags; /* read_lock() synchronizes us to netlink_table_grab */ read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); read_unlock_irqrestore(&nl_table_lock, flags); } static inline void netlink_unlock_table(void) { if (atomic_dec_and_test(&nl_table_users)) wake_up(&nl_table_wait); } struct netlink_compare_arg { possible_net_t pnet; u32 portid; }; /* Doing sizeof directly may yield 4 extra bytes on 64-bit. */ #define netlink_compare_arg_len \ (offsetof(struct netlink_compare_arg, portid) + sizeof(u32)) static inline int netlink_compare(struct rhashtable_compare_arg *arg, const void *ptr) { const struct netlink_compare_arg *x = arg->key; const struct netlink_sock *nlk = ptr; return nlk->portid != x->portid || !net_eq(sock_net(&nlk->sk), read_pnet(&x->pnet)); } static void netlink_compare_arg_init(struct netlink_compare_arg *arg, struct net *net, u32 portid) { memset(arg, 0, sizeof(*arg)); write_pnet(&arg->pnet, net); arg->portid = portid; } static struct sock *__netlink_lookup(struct netlink_table *table, u32 portid, struct net *net) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, net, portid); return rhashtable_lookup_fast(&table->hash, &arg, netlink_rhashtable_params); } static int __netlink_insert(struct netlink_table *table, struct sock *sk) { struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(sk), nlk_sk(sk)->portid); return rhashtable_lookup_insert_key(&table->hash, &arg, &nlk_sk(sk)->node, netlink_rhashtable_params); } static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { struct netlink_table *table = &nl_table[protocol]; struct sock *sk; rcu_read_lock(); sk = __netlink_lookup(table, portid, net); if (sk) sock_hold(sk); rcu_read_unlock(); return sk; } static const struct proto_ops netlink_ops; static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; unsigned long mask; unsigned int i; struct listeners *listeners; listeners = nl_deref_protected(tbl->listeners); if (!listeners) return; for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } listeners->masks[i] = mask; } /* this function is only called with the netlink table "grabbed", which * makes sure updates are visible before bind or setsockopt return. */ } static int netlink_insert(struct sock *sk, u32 portid) { struct netlink_table *table = &nl_table[sk->sk_protocol]; int err; lock_sock(sk); err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY; if (nlk_sk(sk)->bound) goto err; /* portid can be read locklessly from netlink_getname(). */ WRITE_ONCE(nlk_sk(sk)->portid, portid); sock_hold(sk); err = __netlink_insert(table, sk); if (err) { /* In case the hashtable backend returns with -EBUSY * from here, it must not escape to the caller. */ if (unlikely(err == -EBUSY)) err = -EOVERFLOW; if (err == -EEXIST) err = -EADDRINUSE; sock_put(sk); goto err; } /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); /* Paired with lockless reads from netlink_bind(), * netlink_connect() and netlink_sendmsg(). */ WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); return err; } static void netlink_remove(struct sock *sk) { struct netlink_table *table; table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, netlink_rhashtable_params)) { WARN_ON(refcount_read(&sk->sk_refcnt) == 1); __sock_put(sk); } netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { __sk_del_bind_node(sk); netlink_update_listeners(sk); } if (sk->sk_protocol == NETLINK_GENERIC) atomic_inc(&genl_sk_destructing_cnt); netlink_table_ungrab(); } static struct proto netlink_proto = { .name = "NETLINK", .owner = THIS_MODULE, .obj_size = sizeof(struct netlink_sock), }; static int __netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct netlink_sock *nlk; sock->ops = &netlink_ops; sk = sk_alloc(net, PF_NETLINK, GFP_KERNEL, &netlink_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); nlk = nlk_sk(sk); mutex_init(&nlk->nl_cb_mutex); lockdep_set_class_and_name(&nlk->nl_cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; sk->sk_protocol = protocol; return 0; } static int netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct module *module = NULL; struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release)(struct sock *sock, unsigned long *groups); int err = 0; sock->state = SS_UNCONNECTED; if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES if (!nl_table[protocol].registered) { netlink_unlock_table(); request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol); netlink_lock_table(); } #endif if (nl_table[protocol].registered && try_module_get(nl_table[protocol].module)) module = nl_table[protocol].module; else err = -EPROTONOSUPPORT; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; release = nl_table[protocol].release; netlink_unlock_table(); if (err < 0) goto out; err = __netlink_create(net, sock, protocol, kern); if (err < 0) goto out_module; sock_prot_inuse_add(net, &netlink_proto, 1); nlk = nlk_sk(sock->sk); nlk->module = module; nlk->netlink_bind = bind; nlk->netlink_unbind = unbind; nlk->netlink_release = release; out: return err; out_module: module_put(module); goto out; } static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); struct sock *sk = &nlk->sk; kfree(nlk->groups); nlk->groups = NULL; if (!refcount_dec_and_test(&sk->sk_refcnt)) return; sk_free(sk); } static int netlink_release(struct socket *sock) { struct sock *sk = sock->sk; struct netlink_sock *nlk; if (!sk) return 0; netlink_remove(sk); sock_orphan(sk); nlk = nlk_sk(sk); /* * OK. Socket is unlinked, any packets that arrive now * will be purged. */ if (nlk->netlink_release) nlk->netlink_release(sk, nlk->groups); /* must not acquire netlink_table_lock in any way again before unbind * and notifying genetlink is done as otherwise it might deadlock */ if (nlk->netlink_unbind) { int i; for (i = 0; i < nlk->ngroups; i++) if (test_bit(i, nlk->groups)) nlk->netlink_unbind(sock_net(sk), i + 1); } if (sk->sk_protocol == NETLINK_GENERIC && atomic_dec_return(&genl_sk_destructing_cnt) == 0) wake_up(&genl_sk_destructing_waitq); sock->sk = NULL; wake_up_interruptible_all(&nlk->wait); skb_queue_purge(&sk->sk_write_queue); if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, .portid = nlk->portid, }; blocking_notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); } /* Terminate any outstanding dump */ if (nlk->cb_running) { if (nlk->cb.done) nlk->cb.done(&nlk->cb); module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); WRITE_ONCE(nlk->cb_running, false); } module_put(nlk->module); if (netlink_is_kernel(sk)) { netlink_table_grab(); BUG_ON(nl_table[sk->sk_protocol].registered == 0); if (--nl_table[sk->sk_protocol].registered == 0) { struct listeners *old; old = nl_deref_protected(nl_table[sk->sk_protocol].listeners); RCU_INIT_POINTER(nl_table[sk->sk_protocol].listeners, NULL); kfree_rcu(old, rcu); nl_table[sk->sk_protocol].module = NULL; nl_table[sk->sk_protocol].bind = NULL; nl_table[sk->sk_protocol].unbind = NULL; nl_table[sk->sk_protocol].flags = 0; nl_table[sk->sk_protocol].registered = 0; } netlink_table_ungrab(); } sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_table *table = &nl_table[sk->sk_protocol]; s32 portid = task_tgid_vnr(current); int err; s32 rover = -4096; bool ok; retry: cond_resched(); rcu_read_lock(); ok = !__netlink_lookup(table, portid, net); rcu_read_unlock(); if (!ok) { /* Bind collision, search negative portid values. */ if (rover == -4096) /* rover will be in range [S32_MIN, -4097] */ rover = S32_MIN + get_random_u32_below(-4096 - S32_MIN); else if (rover >= -4096) rover = -4097; portid = rover--; goto retry; } err = netlink_insert(sk, portid); if (err == -EADDRINUSE) goto retry; /* If 2 threads race to autobind, that is fine. */ if (err == -EBUSY) err = 0; return err; } /** * __netlink_ns_capable - General netlink message capability test * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace. * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *user_ns, int cap) { return ((nsp->flags & NETLINK_SKB_DST) || file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) && ns_capable(user_ns, cap); } EXPORT_SYMBOL(__netlink_ns_capable); /** * netlink_ns_capable - General netlink message capability test * @skb: socket buffer holding a netlink command from userspace * @user_ns: The user namespace of the capability to use * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in the user namespace @user_ns. */ bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *user_ns, int cap) { return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap); } EXPORT_SYMBOL(netlink_ns_capable); /** * netlink_capable - Netlink global message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap in all user namespaces. */ bool netlink_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, &init_user_ns, cap); } EXPORT_SYMBOL(netlink_capable); /** * netlink_net_capable - Netlink network namespace message capability test * @skb: socket buffer holding a netlink command from userspace * @cap: The capability to use * * Test to see if the opener of the socket we received the message * from had when the netlink socket was created and the sender of the * message has the capability @cap over the network namespace of * the socket we received the message from. */ bool netlink_net_capable(const struct sk_buff *skb, int cap) { return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap); } EXPORT_SYMBOL(netlink_net_capable); static inline int netlink_allowed(const struct socket *sock, unsigned int flag) { return (nl_table[sock->sk->sk_protocol].flags & flag) || ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN); } static void netlink_update_subscriptions(struct sock *sk, unsigned int subscriptions) { struct netlink_sock *nlk = nlk_sk(sk); if (nlk->subscriptions && !subscriptions) __sk_del_bind_node(sk); else if (!nlk->subscriptions && subscriptions) sk_add_bind_node(sk, &nl_table[sk->sk_protocol].mc_list); nlk->subscriptions = subscriptions; } static int netlink_realloc_groups(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); unsigned int groups; unsigned long *new_groups; int err = 0; netlink_table_grab(); groups = nl_table[sk->sk_protocol].groups; if (!nl_table[sk->sk_protocol].registered) { err = -ENOENT; goto out_unlock; } if (nlk->ngroups >= groups) goto out_unlock; new_groups = krealloc(nlk->groups, NLGRPSZ(groups), GFP_ATOMIC); if (new_groups == NULL) { err = -ENOMEM; goto out_unlock; } memset((char *)new_groups + NLGRPSZ(nlk->ngroups), 0, NLGRPSZ(groups) - NLGRPSZ(nlk->ngroups)); nlk->groups = new_groups; nlk->ngroups = groups; out_unlock: netlink_table_ungrab(); return err; } static void netlink_undo_bind(int group, long unsigned int groups, struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); int undo; if (!nlk->netlink_unbind) return; for (undo = 0; undo < group; undo++) if (test_bit(undo, &groups)) nlk->netlink_unbind(sock_net(sk), undo + 1); } static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; unsigned long groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) return -EINVAL; if (nladdr->nl_family != AF_NETLINK) return -EINVAL; groups = nladdr->nl_groups; /* Only superuser is allowed to listen multicasts */ if (groups) { if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; } if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; /* Paired with WRITE_ONCE() in netlink_insert() */ bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); if (nladdr->nl_pid != nlk->portid) return -EINVAL; } if (nlk->netlink_bind && groups) { int group; /* nl_groups is a u32, so cap the maximum groups we can bind */ for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); if (!err) continue; netlink_undo_bind(group, groups, sk); return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0])) goto unlock; netlink_unlock_table(); netlink_table_grab(); netlink_update_subscriptions(sk, nlk->subscriptions + hweight32(groups) - hweight32(nlk->groups[0])); nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups; netlink_update_listeners(sk); netlink_table_ungrab(); return 0; unlock: netlink_unlock_table(); return err; } static int netlink_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { int err = 0; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; if (alen < sizeof(addr->sa_family)) return -EINVAL; if (addr->sa_family == AF_UNSPEC) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, 0); WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) return -EINVAL; if (alen < sizeof(struct sockaddr_nl)) return -EINVAL; if ((nladdr->nl_groups || nladdr->nl_pid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; /* No need for barriers here as we return to user-space without * using any of the bound attributes. * Paired with WRITE_ONCE() in netlink_insert(). */ if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { /* paired with READ_ONCE() in netlink_getsockbyportid() */ WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); /* dst_portid and dst_group can be read locklessly */ WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; } static int netlink_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, nladdr, addr); nladdr->nl_family = AF_NETLINK; nladdr->nl_pad = 0; if (peer) { /* Paired with WRITE_ONCE() in netlink_connect() */ nladdr->nl_pid = READ_ONCE(nlk->dst_portid); nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { /* Paired with WRITE_ONCE() in netlink_insert() */ nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); } return sizeof(*nladdr); } static int netlink_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* try to hand this ioctl down to the NIC drivers. */ return -ENOIOCTLCMD; } static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; struct netlink_sock *nlk; sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); if (!sock) return ERR_PTR(-ECONNREFUSED); /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); /* dst_portid and sk_state can be changed in netlink_connect() */ if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } return sock; } struct sock *netlink_getsockbyfd(int fd) { CLASS(fd, f)(fd); struct inode *inode; struct sock *sock; if (fd_empty(f)) return ERR_PTR(-EBADF); inode = file_inode(fd_file(f)); if (!S_ISSOCK(inode->i_mode)) return ERR_PTR(-ENOTSOCK); sock = SOCKET_I(inode)->sk; if (sock->sk_family != AF_NETLINK) return ERR_PTR(-EINVAL); sock_hold(sock); return sock; } struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast) { size_t head_size = SKB_HEAD_ALIGN(size); struct sk_buff *skb; void *data; if (head_size <= PAGE_SIZE || broadcast) return alloc_skb(size, GFP_KERNEL); data = kvmalloc(head_size, GFP_KERNEL); if (!data) return NULL; skb = __build_skb(data, head_size); if (!skb) kvfree(data); else if (is_vmalloc_addr(data)) skb->destructor = netlink_skb_destructor; return skb; } /* * Attach a skb to a netlink socket. * The caller must hold a reference to the destination socket. On error, the * reference is dropped. The skb is not send to the destination, just all * all error checks are performed and memory in the queue is reserved. * Return values: * < 0: error. skb freed, reference to sock dropped. * 0: continue * 1: repeat lookup - reference dropped while waiting for socket memory. */ int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { struct netlink_sock *nlk; nlk = nlk_sk(sk); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(NETLINK_S_CONGESTED, &nlk->state))) { DECLARE_WAITQUEUE(wait, current); if (!*timeo) { if (!ssk || netlink_is_kernel(ssk)) netlink_overrun(sk); sock_put(sk); kfree_skb(skb); return -EAGAIN; } __set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&nlk->wait, &wait); if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || test_bit(NETLINK_S_CONGESTED, &nlk->state)) && !sock_flag(sk, SOCK_DEAD)) *timeo = schedule_timeout(*timeo); __set_current_state(TASK_RUNNING); remove_wait_queue(&nlk->wait, &wait); sock_put(sk); if (signal_pending(current)) { kfree_skb(skb); return sock_intr_errno(*timeo); } return 1; } netlink_skb_set_owner_r(skb, sk); return 0; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = skb->len; netlink_deliver_tap(sock_net(sk), skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); return len; } int netlink_sendskb(struct sock *sk, struct sk_buff *skb) { int len = __netlink_sendskb(sk, skb); sock_put(sk); return len; } void netlink_detachskb(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); sock_put(sk); } static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation) { int delta; skb_assert_len(skb); WARN_ON(skb->sk != NULL); delta = skb->end - skb->tail; if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize) return skb; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, allocation); if (!nskb) return skb; consume_skb(skb); skb = nskb; } pskb_expand_head(skb, 0, -delta, (allocation & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); return skb; } static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, struct sock *ssk) { int ret; struct netlink_sock *nlk = nlk_sk(sk); ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); nlk->netlink_rcv(skb); consume_skb(skb); } else { kfree_skb(skb); } sock_put(sk); return ret; } int netlink_unicast(struct sock *ssk, struct sk_buff *skb, u32 portid, int nonblock) { struct sock *sk; int err; long timeo; skb = netlink_trim(skb, gfp_any()); timeo = sock_sndtimeo(ssk, nonblock); retry: sk = netlink_getsockbyportid(ssk, portid); if (IS_ERR(sk)) { kfree_skb(skb); return PTR_ERR(sk); } if (netlink_is_kernel(sk)) return netlink_unicast_kernel(sk, skb, ssk); if (sk_filter(sk, skb)) { err = skb->len; kfree_skb(skb); sock_put(sk); return err; } err = netlink_attachskb(sk, skb, &timeo, ssk); if (err == 1) goto retry; if (err) return err; return netlink_sendskb(sk, skb); } EXPORT_SYMBOL(netlink_unicast); int netlink_has_listeners(struct sock *sk, unsigned int group) { int res = 0; struct listeners *listeners; BUG_ON(!netlink_is_kernel(sk)); rcu_read_lock(); listeners = rcu_dereference(nl_table[sk->sk_protocol].listeners); if (listeners && group - 1 < nl_table[sk->sk_protocol].groups) res = test_bit(group - 1, listeners->masks); rcu_read_unlock(); return res; } EXPORT_SYMBOL_GPL(netlink_has_listeners); bool netlink_strict_get_check(struct sk_buff *skb) { return nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); } EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); } return -1; } struct netlink_broadcast_data { struct sock *exclude_sk; struct net *net; u32 portid; u32 group; int failure; int delivery_failure; int congested; int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); void *tx_data; }; static void do_one_broadcast(struct sock *sk, struct netlink_broadcast_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int val; if (p->exclude_sk == sk) return; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) return; if (!net_eq(sock_net(sk), p->net)) { if (!nlk_test_bit(LISTEN_ALL_NSID, sk)) return; if (!peernet_has_id(sock_net(sk), p->net)) return; if (!file_ns_capable(sk->sk_socket->file, p->net->user_ns, CAP_NET_BROADCAST)) return; } if (p->failure) { netlink_overrun(sk); return; } sock_hold(sk); if (p->skb2 == NULL) { if (skb_shared(p->skb)) { p->skb2 = skb_clone(p->skb, p->allocation); } else { p->skb2 = skb_get(p->skb); /* * skb ownership may have been set when * delivered to a previous socket. */ skb_orphan(p->skb2); } } if (p->skb2 == NULL) { netlink_overrun(sk); /* Clone failed. Notify ALL listeners. */ p->failure = 1; if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; goto out; } if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; goto out; } NETLINK_CB(p->skb2).nsid = peernet2id(sock_net(sk), p->net); if (NETLINK_CB(p->skb2).nsid != NETNSA_NSID_NOT_ASSIGNED) NETLINK_CB(p->skb2).nsid_is_set = true; val = netlink_broadcast_deliver(sk, p->skb2); if (val < 0) { netlink_overrun(sk); if (nlk_test_bit(BROADCAST_SEND_ERROR, sk)) p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; p->skb2 = NULL; } out: sock_put(sk); } int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation, netlink_filter_fn filter, void *filter_data) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct sock *sk; skb = netlink_trim(skb, allocation); info.exclude_sk = ssk; info.net = net; info.portid = portid; info.group = group; info.failure = 0; info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; info.skb = skb; info.skb2 = NULL; info.tx_filter = filter; info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ netlink_lock_table(); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); netlink_unlock_table(); if (info.delivery_failure) { kfree_skb(info.skb2); return -ENOBUFS; } consume_skb(info.skb2); if (info.delivered) { if (info.congested && gfpflags_allow_blocking(allocation)) yield(); return 0; } return -ESRCH; } EXPORT_SYMBOL(netlink_broadcast_filtered); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation) { return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, NULL, NULL); } EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; u32 portid; u32 group; int code; }; static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) { struct netlink_sock *nlk = nlk_sk(sk); int ret = 0; if (sk == p->exclude_sk) goto out; if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; if (p->code == ENOBUFS && nlk_test_bit(RECV_NO_ENOBUFS, sk)) { ret = 1; goto out; } WRITE_ONCE(sk->sk_err, p->code); sk_error_report(sk); out: return ret; } /** * netlink_set_err - report error to broadcast listeners * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() * @portid: the PORTID of a process that we want to skip (if any) * @group: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_NO_ENOBUFS socket option. */ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; unsigned long flags; struct sock *sk; int ret = 0; info.exclude_sk = ssk; info.portid = portid; info.group = group; /* sk->sk_err wants a positive error value */ info.code = -code; read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); /* must be called with netlink table grabbed */ static void netlink_update_socket_mc(struct netlink_sock *nlk, unsigned int group, int is_new) { int old, new = !!is_new, subscriptions; old = test_bit(group - 1, nlk->groups); subscriptions = nlk->subscriptions - old + new; __assign_bit(group - 1, nlk->groups, new); netlink_update_subscriptions(&nlk->sk, subscriptions); netlink_update_listeners(&nlk->sk); } static int netlink_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int val = 0; int nr = -1; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (optlen >= sizeof(int) && copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (optname) { case NETLINK_PKTINFO: nr = NETLINK_F_RECV_PKTINFO; break; case NETLINK_ADD_MEMBERSHIP: case NETLINK_DROP_MEMBERSHIP: { int err; if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV)) return -EPERM; err = netlink_realloc_groups(sk); if (err) return err; if (!val || val - 1 >= nlk->ngroups) return -EINVAL; if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) { err = nlk->netlink_bind(sock_net(sk), val); if (err) return err; } netlink_table_grab(); netlink_update_socket_mc(nlk, val, optname == NETLINK_ADD_MEMBERSHIP); netlink_table_ungrab(); if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind) nlk->netlink_unbind(sock_net(sk), val); break; } case NETLINK_BROADCAST_ERROR: nr = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: assign_bit(NETLINK_F_RECV_NO_ENOBUFS, &nlk->flags, val); if (val) { clear_bit(NETLINK_S_CONGESTED, &nlk->state); wake_up_interruptible(&nlk->wait); } break; case NETLINK_LISTEN_ALL_NSID: if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_BROADCAST)) return -EPERM; nr = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: nr = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: nr = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: nr = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (nr >= 0) assign_bit(nr, &nlk->flags, val); return 0; } static int netlink_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); unsigned int flag; int len, val; if (level != SOL_NETLINK) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case NETLINK_PKTINFO: flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { int pos, idx, shift, err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) break; idx = pos / sizeof(unsigned long); shift = (pos % sizeof(unsigned long)) * 8; if (put_user((u32)(nlk->groups[idx] >> shift), (u32 __user *)(optval + pos))) { err = -EFAULT; break; } } if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); return err; } case NETLINK_LISTEN_ALL_NSID: flag = NETLINK_F_LISTEN_ALL_NSID; break; case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: flag = NETLINK_F_EXT_ACK; break; case NETLINK_GET_STRICT_CHK: flag = NETLINK_F_STRICT_CHK; break; default: return -ENOPROTOOPT; } if (len < sizeof(int)) return -EINVAL; len = sizeof(int); val = test_bit(flag, &nlk->flags); if (put_user(len, optlen) || copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct nl_pktinfo info; info.group = NETLINK_CB(skb).dst_group; put_cmsg(msg, SOL_NETLINK, NETLINK_PKTINFO, sizeof(info), &info); } static void netlink_cmsg_listen_all_nsid(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { if (!NETLINK_CB(skb).nsid_is_set) return; put_cmsg(msg, SOL_NETLINK, NETLINK_LISTEN_ALL_NSID, sizeof(int), &NETLINK_CB(skb).nsid); } static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); u32 dst_portid; u32 dst_group; struct sk_buff *skb; int err; struct scm_cookie scm; u32 netlink_skb_flags = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (len == 0) { pr_warn_once("Zero length message leads to an empty skb\n"); return -ENODATA; } err = scm_send(sock, msg, &scm, true); if (err < 0) return err; if (msg->msg_namelen) { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_nl)) goto out; if (addr->nl_family != AF_NETLINK) goto out; dst_portid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; if ((dst_group || dst_portid) && !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND)) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { /* Paired with WRITE_ONCE() in netlink_connect() */ dst_portid = READ_ONCE(nlk->dst_portid); dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; } else { /* Ensure nlk is hashed and visible. */ smp_rmb(); } err = -EMSGSIZE; if (len > sk->sk_sndbuf - 32) goto out; err = -ENOBUFS; skb = netlink_alloc_large_skb(len, dst_group); if (skb == NULL) goto out; NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = scm.creds; NETLINK_CB(skb).flags = netlink_skb_flags; err = -EFAULT; if (memcpy_from_msg(skb_put(skb, len), msg, len)) { kfree_skb(skb); goto out; } err = security_netlink_send(sk, skb); if (err) { kfree_skb(skb); goto out; } if (dst_group) { refcount_inc(&skb->users); netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT); out: scm_destroy(&scm); return err; } static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct scm_cookie scm; struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); size_t copied, max_recvmsg_len; struct sk_buff *skb, *data_skb; int err, ret; if (flags & MSG_OOB) return -EOPNOTSUPP; copied = 0; skb = skb_recv_datagram(sk, flags, &err); if (skb == NULL) goto out; data_skb = skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES if (unlikely(skb_shinfo(skb)->frag_list)) { /* * If this skb has a frag_list, then here that means that we * will have to use the frag_list skb's data for compat tasks * and the regular skb's data for normal (non-compat) tasks. * * If we need to send the compat skb, assign it to the * 'data_skb' variable so that it will be used below for data * copying. We keep 'skb' for everything else, including * freeing both later. */ if (flags & MSG_CMSG_COMPAT) data_skb = skb_shinfo(skb)->frag_list; } #endif /* Record the max length of recvmsg() calls for future allocations */ max_recvmsg_len = max(READ_ONCE(nlk->max_recvmsg_len), len); max_recvmsg_len = min_t(size_t, max_recvmsg_len, SKB_WITH_OVERHEAD(32768)); WRITE_ONCE(nlk->max_recvmsg_len, max_recvmsg_len); copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name); addr->nl_family = AF_NETLINK; addr->nl_pad = 0; addr->nl_pid = NETLINK_CB(skb).portid; addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); msg->msg_namelen = sizeof(*addr); } if (nlk_test_bit(RECV_PKTINFO, sk)) netlink_cmsg_recv_pktinfo(msg, skb); if (nlk_test_bit(LISTEN_ALL_NSID, sk)) netlink_cmsg_listen_all_nsid(sk, msg, skb); memset(&scm, 0, sizeof(scm)); scm.creds = *NETLINK_CREDS(skb); if (flags & MSG_TRUNC) copied = data_skb->len; skb_free_datagram(sk, skb); if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk, false); if (ret) { WRITE_ONCE(sk->sk_err, -ret); sk_error_report(sk); } } scm_recv(sock, msg, &scm, flags); out: netlink_rcv_wake(sk); return err ? : copied; } static void netlink_data_ready(struct sock *sk) { BUG(); } /* * We export these functions to other modules. They provide a * complete set of kernel non-blocking support for message * queueing. */ struct sock * __netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; unsigned int groups; BUG_ON(!nl_table); if (unit < 0 || unit >= MAX_LINKS) return NULL; if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; if (__netlink_create(net, sock, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; if (!cfg || cfg->groups < 32) groups = 32; else groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; if (cfg && cfg->input) nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, 0)) goto out_sock_release; nlk = nlk_sk(sk); set_bit(NETLINK_F_KERNEL_SOCKET, &nlk->flags); netlink_table_grab(); if (!nl_table[unit].registered) { nl_table[unit].groups = groups; rcu_assign_pointer(nl_table[unit].listeners, listeners); nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; nl_table[unit].unbind = cfg->unbind; nl_table[unit].release = cfg->release; nl_table[unit].flags = cfg->flags; } nl_table[unit].registered = 1; } else { kfree(listeners); nl_table[unit].registered++; } netlink_table_ungrab(); return sk; out_sock_release: kfree(listeners); netlink_kernel_release(sk); return NULL; out_sock_release_nosk: sock_release(sock); return NULL; } EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) { if (sk == NULL || sk->sk_socket == NULL) return; sock_release(sk->sk_socket); } EXPORT_SYMBOL(netlink_kernel_release); int __netlink_change_ngroups(struct sock *sk, unsigned int groups) { struct listeners *new, *old; struct netlink_table *tbl = &nl_table[sk->sk_protocol]; if (groups < 32) groups = 32; if (NLGRPSZ(tbl->groups) < NLGRPSZ(groups)) { new = kzalloc(sizeof(*new) + NLGRPSZ(groups), GFP_ATOMIC); if (!new) return -ENOMEM; old = nl_deref_protected(tbl->listeners); memcpy(new->masks, old->masks, NLGRPSZ(tbl->groups)); rcu_assign_pointer(tbl->listeners, new); kfree_rcu(old, rcu); } tbl->groups = groups; return 0; } /** * netlink_change_ngroups - change number of multicast groups * * This changes the number of multicast groups that are available * on a certain netlink family. Note that it is not possible to * change the number of groups to below 32. Also note that it does * not implicitly call netlink_clear_multicast_users() when the * number of groups is reduced. * * @sk: The kernel netlink socket, as returned by netlink_kernel_create(). * @groups: The new number of groups. */ int netlink_change_ngroups(struct sock *sk, unsigned int groups) { int err; netlink_table_grab(); err = __netlink_change_ngroups(sk, groups); netlink_table_ungrab(); return err; } void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; struct hlist_node *tmp; sk_for_each_bound_safe(sk, tmp, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); nlh = skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; nlh->nlmsg_pid = portid; nlh->nlmsg_seq = seq; if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) memset(nlmsg_data(nlh) + len, 0, NLMSG_ALIGN(size) - size); return nlh; } EXPORT_SYMBOL(__nlmsg_put); static size_t netlink_ack_tlv_len(struct netlink_sock *nlk, int err, const struct netlink_ext_ack *extack) { size_t tlvlen; if (!extack || !test_bit(NETLINK_F_EXT_ACK, &nlk->flags)) return 0; tlvlen = 0; if (extack->_msg) tlvlen += nla_total_size(strlen(extack->_msg) + 1); if (extack->cookie_len) tlvlen += nla_total_size(extack->cookie_len); /* Following attributes are only reported as error (not warning) */ if (!err) return tlvlen; if (extack->bad_attr) tlvlen += nla_total_size(sizeof(u32)); if (extack->policy) tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy); if (extack->miss_type) tlvlen += nla_total_size(sizeof(u32)); if (extack->miss_nest) tlvlen += nla_total_size(sizeof(u32)); return tlvlen; } static bool nlmsg_check_in_payload(const struct nlmsghdr *nlh, const void *addr) { return !WARN_ON(addr < nlmsg_data(nlh) || addr - (const void *) nlh >= nlh->nlmsg_len); } static void netlink_ack_tlv_fill(struct sk_buff *skb, const struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { if (extack->_msg) WARN_ON(nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg)); if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, extack->cookie_len, extack->cookie)); if (!err) return; if (extack->bad_attr && nlmsg_check_in_payload(nlh, extack->bad_attr)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - (const u8 *)nlh)); if (extack->policy) netlink_policy_dump_write_attr(skb, extack->policy, NLMSGERR_ATTR_POLICY); if (extack->miss_type) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_TYPE, extack->miss_type)); if (extack->miss_nest && nlmsg_check_in_payload(nlh, extack->miss_nest)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_MISS_NEST, (u8 *)extack->miss_nest - (const u8 *)nlh)); } /* * It looks a bit ugly. * It would be better to create kernel thread. */ static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb, struct netlink_callback *cb, struct netlink_ext_ack *extack) { struct nlmsghdr *nlh; size_t extack_len; nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno), NLM_F_MULTI | cb->answer_flags); if (WARN_ON(!nlh)) return -ENOBUFS; nl_dump_check_consistent(cb, nlh); memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno)); extack_len = netlink_ack_tlv_len(nlk, nlk->dump_done_errno, extack); if (extack_len) { nlh->nlmsg_flags |= NLM_F_ACK_TLVS; if (skb_tailroom(skb) >= extack_len) { netlink_ack_tlv_fill(skb, cb->nlh, nlk->dump_done_errno, extack); nlmsg_end(skb, nlh); } } return 0; } static int netlink_dump(struct sock *sk, bool lock_taken) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; int alloc_min_size; int alloc_size; if (!lock_taken) mutex_lock(&nlk->nl_cb_mutex); if (!nlk->cb_running) { err = -EINVAL; goto errout_skb; } if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 32KiB allocation * to reduce number of system calls on dump operations, if user * ever provided a big enough buffer. */ cb = &nlk->cb; alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); max_recvmsg_len = READ_ONCE(nlk->max_recvmsg_len); if (alloc_min_size < max_recvmsg_len) { alloc_size = max_recvmsg_len; skb = alloc_skb(alloc_size, (GFP_KERNEL & ~__GFP_DIRECT_RECLAIM) | __GFP_NOWARN | __GFP_NORETRY); } if (!skb) { alloc_size = alloc_min_size; skb = alloc_skb(alloc_size, GFP_KERNEL); } if (!skb) goto errout_skb; /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as * could fit within the allocated skb. skb is typically allocated * with larger space than required (could be as much as near 2x the * requested size with align to next power of 2 approach). Allowing * dump to use the excess space makes it difficult for a user to have a * reasonable static buffer based on the expected largest dump of a * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); /* Make sure malicious BPF programs can not read unitialized memory * from skb->head -> skb->data */ skb_reset_network_header(skb); skb_reset_mac_header(skb); netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { cb->extack = &extack; nlk->dump_done_errno = cb->dump(skb, cb); /* EMSGSIZE plus something already in the skb means * that there's more to dump but current skb has filled up. * If the callback really wants to return EMSGSIZE to user space * it needs to do so again, on the next cb->dump() call, * without putting data in the skb. */ if (nlk->dump_done_errno == -EMSGSIZE && skb->len) nlk->dump_done_errno = skb->len; cb->extack = NULL; } if (nlk->dump_done_errno > 0 || skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) { mutex_unlock(&nlk->nl_cb_mutex); if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); return 0; } if (netlink_dump_done(nlk, skb, cb, &extack)) goto errout_skb; #ifdef CONFIG_COMPAT_NETLINK_MESSAGES /* frag_list skb's data is used for compat tasks * and the regular skb's data for normal (non-compat) tasks. * See netlink_recvmsg(). */ if (unlikely(skb_shinfo(skb)->frag_list)) { if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack)) goto errout_skb; } #endif if (sk_filter(sk, skb)) kfree_skb(skb); else __netlink_sendskb(sk, skb); if (cb->done) cb->done(cb); WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(&nlk->nl_cb_mutex); module_put(module); consume_skb(skb); return 0; errout_skb: mutex_unlock(&nlk->nl_cb_mutex); kfree_skb(skb); return err; } int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { struct netlink_callback *cb; struct netlink_sock *nlk; struct sock *sk; int ret; refcount_inc(&skb->users); sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { ret = -ECONNREFUSED; goto error_free; } nlk = nlk_sk(sk); mutex_lock(&nlk->nl_cb_mutex); /* A dump is in progress... */ if (nlk->cb_running) { ret = -EBUSY; goto error_unlock; } /* add reference of module which cb->dump belongs to */ if (!try_module_get(control->module)) { ret = -EPROTONOSUPPORT; goto error_unlock; } cb = &nlk->cb; memset(cb, 0, sizeof(*cb)); cb->dump = control->dump; cb->done = control->done; cb->nlh = nlh; cb->data = control->data; cb->module = control->module; cb->min_dump_alloc = control->min_dump_alloc; cb->flags = control->flags; cb->skb = skb; cb->strict_check = nlk_test_bit(STRICT_CHK, NETLINK_CB(skb).sk); if (control->start) { cb->extack = control->extack; ret = control->start(cb); cb->extack = NULL; if (ret) goto error_put; } WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; ret = netlink_dump(sk, true); sock_put(sk); if (ret) return ret; /* We successfully started a dump, by returning -EINTR we * signal not to send ACK even if it was requested. */ return -EINTR; error_put: module_put(control->module); error_unlock: sock_put(sk); mutex_unlock(&nlk->nl_cb_mutex); error_free: kfree_skb(skb); return ret; } EXPORT_SYMBOL(__netlink_dump_start); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct sk_buff *skb; struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); unsigned int flags = 0; size_t tlvlen; /* Error messages get the original request appened, unless the user * requests to cap the error message, and get extra error data if * requested. */ if (err && !test_bit(NETLINK_F_CAP_ACK, &nlk->flags)) payload += nlmsg_len(nlh); else flags |= NLM_F_CAPPED; tlvlen = netlink_ack_tlv_len(nlk, err, extack); if (tlvlen) flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(*errmsg), flags); if (!rep) goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; errmsg->msg = *nlh; if (!(flags & NLM_F_CAPPED)) { if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } if (tlvlen) netlink_ack_tlv_fill(skb, nlh, err, extack); nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); return; err_bad_put: nlmsg_free(skb); err_skb: WRITE_ONCE(NETLINK_CB(in_skb).sk->sk_err, ENOBUFS); sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; while (skb->len >= nlmsg_total_size(0)) { int msglen; memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return 0; /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) goto ack; /* Skip control messages */ if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) netlink_ack(skb, nlh, err, &extack); skip: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } return 0; } EXPORT_SYMBOL(netlink_rcv_skb); /** * nlmsg_notify - send a notification netlink message * @sk: netlink socket to use * @skb: notification message * @portid: destination netlink portid for reports or 0 * @group: destination multicast group or 0 * @report: 1 to report back, 0 to disable * @flags: allocation flags */ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags) { int err = 0; if (group) { int exclude_portid = 0; if (report) { refcount_inc(&skb->users); exclude_portid = portid; } /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); if (err == -ESRCH) err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); if (!err) err = err2; } return err; } EXPORT_SYMBOL(nlmsg_notify); #ifdef CONFIG_PROC_FS struct nl_seq_iter { struct seq_net_private p; struct rhashtable_iter hti; int link; }; static void netlink_walk_start(struct nl_seq_iter *iter) { rhashtable_walk_enter(&nl_table[iter->link].hash, &iter->hti); rhashtable_walk_start(&iter->hti); } static void netlink_walk_stop(struct nl_seq_iter *iter) { rhashtable_walk_stop(&iter->hti); rhashtable_walk_exit(&iter->hti); } static void *__netlink_seq_next(struct seq_file *seq) { struct nl_seq_iter *iter = seq->private; struct netlink_sock *nlk; do { for (;;) { nlk = rhashtable_walk_next(&iter->hti); if (IS_ERR(nlk)) { if (PTR_ERR(nlk) == -EAGAIN) continue; return nlk; } if (nlk) break; netlink_walk_stop(iter); if (++iter->link >= MAX_LINKS) return NULL; netlink_walk_start(iter); } } while (sock_net(&nlk->sk) != seq_file_net(seq)); return nlk; } static void *netlink_seq_start(struct seq_file *seq, loff_t *posp) __acquires(RCU) { struct nl_seq_iter *iter = seq->private; void *obj = SEQ_START_TOKEN; loff_t pos; iter->link = 0; netlink_walk_start(iter); for (pos = *posp; pos && obj && !IS_ERR(obj); pos--) obj = __netlink_seq_next(seq); return obj; } static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return __netlink_seq_next(seq); } static void netlink_native_seq_stop(struct seq_file *seq, void *v) { struct nl_seq_iter *iter = seq->private; if (iter->link >= MAX_LINKS) return; netlink_walk_stop(iter); } static int netlink_native_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk Eth Pid Groups " "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8u %-8lu\n", s, s->sk_protocol, nlk->portid, nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) ); } return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__netlink { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct netlink_sock *, sk); }; DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk) static int netlink_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__netlink ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.sk = nlk_sk((struct sock *)v); return bpf_iter_run_prog(prog, &ctx); } static int netlink_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return netlink_native_seq_show(seq, v); if (v != SEQ_START_TOKEN) return netlink_prog_seq_show(prog, &meta, v); return 0; } static void netlink_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)netlink_prog_seq_show(prog, &meta, v); } netlink_native_seq_stop(seq, v); } #else static int netlink_seq_show(struct seq_file *seq, void *v) { return netlink_native_seq_show(seq, v); } static void netlink_seq_stop(struct seq_file *seq, void *v) { netlink_native_seq_stop(seq, v); } #endif static const struct seq_operations netlink_seq_ops = { .start = netlink_seq_start, .next = netlink_seq_next, .stop = netlink_seq_stop, .show = netlink_seq_show, }; #endif int netlink_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_register_notifier); int netlink_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&netlink_chain, nb); } EXPORT_SYMBOL(netlink_unregister_notifier); static const struct proto_ops netlink_ops = { .family = PF_NETLINK, .owner = THIS_MODULE, .release = netlink_release, .bind = netlink_bind, .connect = netlink_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = netlink_getname, .poll = datagram_poll, .ioctl = netlink_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = netlink_setsockopt, .getsockopt = netlink_getsockopt, .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, .mmap = sock_no_mmap, }; static const struct net_proto_family netlink_family_ops = { .family = PF_NETLINK, .create = netlink_create, .owner = THIS_MODULE, /* for consistency 8) */ }; static int __net_init netlink_net_init(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("netlink", 0, net->proc_net, &netlink_seq_ops, sizeof(struct nl_seq_iter))) return -ENOMEM; #endif return 0; } static void __net_exit netlink_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("netlink", net->proc_net); #endif } static void __init netlink_add_usersock_entry(void) { struct listeners *listeners; int groups = 32; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) panic("netlink_add_usersock_entry: Cannot allocate listeners\n"); netlink_table_grab(); nl_table[NETLINK_USERSOCK].groups = groups; rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners); nl_table[NETLINK_USERSOCK].module = THIS_MODULE; nl_table[NETLINK_USERSOCK].registered = 1; nl_table[NETLINK_USERSOCK].flags = NL_CFG_F_NONROOT_SEND; netlink_table_ungrab(); } static struct pernet_operations __net_initdata netlink_net_ops = { .init = netlink_net_init, .exit = netlink_net_exit, }; static inline u32 netlink_hash(const void *data, u32 len, u32 seed) { const struct netlink_sock *nlk = data; struct netlink_compare_arg arg; netlink_compare_arg_init(&arg, sock_net(&nlk->sk), nlk->portid); return jhash2((u32 *)&arg, netlink_compare_arg_len / sizeof(u32), seed); } static const struct rhashtable_params netlink_rhashtable_params = { .head_offset = offsetof(struct netlink_sock, node), .key_len = netlink_compare_arg_len, .obj_hashfn = netlink_hash, .obj_cmpfn = netlink_compare, .automatic_shrinking = true, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) BTF_ID_LIST(btf_netlink_sock_id) BTF_ID(struct, netlink_sock) static const struct bpf_iter_seq_info netlink_seq_info = { .seq_ops = &netlink_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct nl_seq_iter), }; static struct bpf_iter_reg netlink_reg_info = { .target = "netlink", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__netlink, sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &netlink_seq_info, }; static int __init bpf_iter_register(void) { netlink_reg_info.ctx_arg_info[0].btf_id = *btf_netlink_sock_id; return bpf_iter_reg_target(&netlink_reg_info); } #endif static int __init netlink_proto_init(void) { int i; int err = proto_register(&netlink_proto, 0); if (err != 0) goto out; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) err = bpf_iter_register(); if (err) goto out; #endif BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) goto panic; for (i = 0; i < MAX_LINKS; i++) { if (rhashtable_init(&nl_table[i].hash, &netlink_rhashtable_params) < 0) goto panic; } netlink_add_usersock_entry(); sock_register(&netlink_family_ops); register_pernet_subsys(&netlink_net_ops); register_pernet_subsys(&netlink_tap_net_ops); /* The netlink device handler may be needed early. */ rtnetlink_init(); out: return err; panic: panic("netlink_init: Cannot allocate nl_table\n"); } core_initcall(netlink_proto_init); |
| 173 51 368 251 434 251 100 102 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * pm_runtime.h - Device run-time power management helper functions. * * Copyright (C) 2009 Rafael J. Wysocki <rjw@sisk.pl> */ #ifndef _LINUX_PM_RUNTIME_H #define _LINUX_PM_RUNTIME_H #include <linux/device.h> #include <linux/notifier.h> #include <linux/pm.h> #include <linux/jiffies.h> /* Runtime PM flag argument bits */ #define RPM_ASYNC 0x01 /* Request is asynchronous */ #define RPM_NOWAIT 0x02 /* Don't wait for concurrent state change */ #define RPM_GET_PUT 0x04 /* Increment/decrement the usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). * * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. * * If the underlying dev_pm_ops struct symbol has to be exported, use * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) #define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ EXPORT_GPL_DEV_PM_OPS(name) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #define EXPORT_NS_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn, ns) \ EXPORT_NS_GPL_DEV_PM_OPS(name, ns) = { \ RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; static inline bool queue_pm_work(struct work_struct *work) { return queue_work(pm_wq, work); } extern int pm_generic_runtime_suspend(struct device *dev); extern int pm_generic_runtime_resume(struct device *dev); extern bool pm_runtime_need_not_resume(struct device *dev); extern int pm_runtime_force_suspend(struct device *dev); extern int pm_runtime_force_resume(struct device *dev); extern int __pm_runtime_idle(struct device *dev, int rpmflags); extern int __pm_runtime_suspend(struct device *dev, int rpmflags); extern int __pm_runtime_resume(struct device *dev, int rpmflags); extern int pm_runtime_get_if_active(struct device *dev); extern int pm_runtime_get_if_in_use(struct device *dev); extern int pm_schedule_suspend(struct device *dev, unsigned int delay); extern int __pm_runtime_set_status(struct device *dev, unsigned int status); extern int pm_runtime_barrier(struct device *dev); extern bool pm_runtime_block_if_disabled(struct device *dev); extern void pm_runtime_unblock(struct device *dev); extern void pm_runtime_enable(struct device *dev); extern void __pm_runtime_disable(struct device *dev, bool check_resume); extern void pm_runtime_allow(struct device *dev); extern void pm_runtime_forbid(struct device *dev); extern void pm_runtime_no_callbacks(struct device *dev); extern void pm_runtime_irq_safe(struct device *dev); extern void __pm_runtime_use_autosuspend(struct device *dev, bool use); extern void pm_runtime_set_autosuspend_delay(struct device *dev, int delay); extern u64 pm_runtime_autosuspend_expiration(struct device *dev); extern void pm_runtime_set_memalloc_noio(struct device *dev, bool enable); extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); extern void pm_runtime_release_supplier(struct device_link *link); int devm_pm_runtime_set_active_enabled(struct device *dev); extern int devm_pm_runtime_enable(struct device *dev); int devm_pm_runtime_get_noresume(struct device *dev); /** * pm_suspend_ignore_children - Set runtime PM behavior regarding children. * @dev: Target device. * @enable: Whether or not to ignore possible dependencies on children. * * The dependencies of @dev on its children will not be taken into account by * the runtime PM framework going forward if @enable is %true, or they will * be taken into account otherwise. */ static inline void pm_suspend_ignore_children(struct device *dev, bool enable) { dev->power.ignore_children = enable; } /** * pm_runtime_get_noresume - Bump up runtime PM usage counter of a device. * @dev: Target device. */ static inline void pm_runtime_get_noresume(struct device *dev) { atomic_inc(&dev->power.usage_count); } /** * pm_runtime_put_noidle - Drop runtime PM usage counter of a device. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev unless it is 0 already. */ static inline void pm_runtime_put_noidle(struct device *dev) { atomic_add_unless(&dev->power.usage_count, -1, 0); } /** * pm_runtime_suspended - Check whether or not a device is runtime-suspended. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev and its runtime PM status is * %RPM_SUSPENDED, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED && !dev->power.disable_depth; } /** * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev and its runtime PM * status cannot change. */ static inline bool pm_runtime_active(struct device *dev) { return dev->power.runtime_status == RPM_ACTIVE || dev->power.disable_depth; } /** * pm_runtime_status_suspended - Check if runtime PM status is "suspended". * @dev: Target device. * * Return %true if the runtime PM status of @dev is %RPM_SUSPENDED, or %false * otherwise, regardless of whether or not runtime PM has been enabled for @dev. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which the * runtime PM status of @dev cannot change. */ static inline bool pm_runtime_status_suspended(struct device *dev) { return dev->power.runtime_status == RPM_SUSPENDED; } /** * pm_runtime_enabled - Check if runtime PM is enabled. * @dev: Target device. * * Return %true if runtime PM is enabled for @dev or %false otherwise. * * Note that the return value of this function can only be trusted if it is * called under the runtime PM lock of @dev or under conditions in which * runtime PM cannot be either disabled or enabled for @dev. */ static inline bool pm_runtime_enabled(struct device *dev) { return !dev->power.disable_depth; } /** * pm_runtime_blocked - Check if runtime PM enabling is blocked. * @dev: Target device. * * Do not call this function outside system suspend/resume code paths. */ static inline bool pm_runtime_blocked(struct device *dev) { return dev->power.last_status == RPM_BLOCKED; } /** * pm_runtime_has_no_callbacks - Check if runtime PM callbacks may be present. * @dev: Target device. * * Return %true if @dev is a special device without runtime PM callbacks or * %false otherwise. */ static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return dev->power.no_callbacks; } /** * pm_runtime_mark_last_busy - Update the last access time of a device. * @dev: Target device. * * Update the last access time of @dev used by the runtime PM autosuspend * mechanism to the current time as returned by ktime_get_mono_fast_ns(). */ static inline void pm_runtime_mark_last_busy(struct device *dev) { WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } /** * pm_runtime_is_irq_safe - Check if runtime PM can work in interrupt context. * @dev: Target device. * * Return %true if @dev has been marked as an "IRQ-safe" device (with respect * to runtime PM), in which case its runtime PM callabcks can be expected to * work correctly when invoked from interrupt handlers. */ static inline bool pm_runtime_is_irq_safe(struct device *dev) { return dev->power.irq_safe; } extern u64 pm_runtime_suspended_time(struct device *dev); #else /* !CONFIG_PM */ static inline bool queue_pm_work(struct work_struct *work) { return false; } static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; } static inline int pm_generic_runtime_resume(struct device *dev) { return 0; } static inline bool pm_runtime_need_not_resume(struct device *dev) {return true; } static inline int pm_runtime_force_suspend(struct device *dev) { return 0; } static inline int pm_runtime_force_resume(struct device *dev) { return 0; } static inline int __pm_runtime_idle(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_suspend(struct device *dev, int rpmflags) { return -ENOSYS; } static inline int __pm_runtime_resume(struct device *dev, int rpmflags) { return 1; } static inline int pm_schedule_suspend(struct device *dev, unsigned int delay) { return -ENOSYS; } static inline int pm_runtime_get_if_in_use(struct device *dev) { return -EINVAL; } static inline int pm_runtime_get_if_active(struct device *dev) { return -EINVAL; } static inline int __pm_runtime_set_status(struct device *dev, unsigned int status) { return 0; } static inline int pm_runtime_barrier(struct device *dev) { return 0; } static inline bool pm_runtime_block_if_disabled(struct device *dev) { return true; } static inline void pm_runtime_unblock(struct device *dev) {} static inline void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline bool pm_runtime_blocked(struct device *dev) { return true; } static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_set_active_enabled(struct device *dev) { return 0; } static inline int devm_pm_runtime_enable(struct device *dev) { return 0; } static inline int devm_pm_runtime_get_noresume(struct device *dev) { return 0; } static inline void pm_suspend_ignore_children(struct device *dev, bool enable) {} static inline void pm_runtime_get_noresume(struct device *dev) {} static inline void pm_runtime_put_noidle(struct device *dev) {} static inline bool pm_runtime_suspended(struct device *dev) { return false; } static inline bool pm_runtime_active(struct device *dev) { return true; } static inline bool pm_runtime_status_suspended(struct device *dev) { return false; } static inline bool pm_runtime_enabled(struct device *dev) { return false; } static inline void pm_runtime_no_callbacks(struct device *dev) {} static inline void pm_runtime_irq_safe(struct device *dev) {} static inline bool pm_runtime_is_irq_safe(struct device *dev) { return false; } static inline bool pm_runtime_has_no_callbacks(struct device *dev) { return false; } static inline void pm_runtime_mark_last_busy(struct device *dev) {} static inline void __pm_runtime_use_autosuspend(struct device *dev, bool use) {} static inline void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) {} static inline u64 pm_runtime_autosuspend_expiration( struct device *dev) { return 0; } static inline void pm_runtime_set_memalloc_noio(struct device *dev, bool enable){} static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} static inline void pm_runtime_release_supplier(struct device_link *link) {} #endif /* !CONFIG_PM */ /** * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it. * @dev: Target device. * * Invoke the "idle check" callback of @dev and, depending on its return value, * set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend has been enabled for it). */ static inline int pm_runtime_idle(struct device *dev) { return __pm_runtime_idle(dev, 0); } /** * pm_runtime_suspend - Suspend a device synchronously. * @dev: Target device. */ static inline int pm_runtime_suspend(struct device *dev) { return __pm_runtime_suspend(dev, 0); } /** * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it. * @dev: Target device. * * Set up autosuspend of @dev or suspend it (depending on whether or not * autosuspend is enabled for it) without engaging its "idle check" callback. */ static inline int pm_runtime_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_AUTO); } /** * pm_runtime_resume - Resume a device synchronously. * @dev: Target device. */ static inline int pm_runtime_resume(struct device *dev) { return __pm_runtime_resume(dev, 0); } /** * pm_request_idle - Queue up "idle check" execution for a device. * @dev: Target device. * * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev * asynchronously. */ static inline int pm_request_idle(struct device *dev) { return __pm_runtime_idle(dev, RPM_ASYNC); } /** * pm_request_resume - Queue up runtime-resume of a device. * @dev: Target device. */ static inline int pm_request_resume(struct device *dev) { return __pm_runtime_resume(dev, RPM_ASYNC); } /** * pm_request_autosuspend - Queue up autosuspend of a device. * @dev: Target device. * * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev * asynchronously. */ static inline int pm_request_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_get - Bump up usage counter and queue up resume of a device. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and queue up a work item to * carry out runtime-resume of it. */ static inline int pm_runtime_get(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT | RPM_ASYNC); } /** * pm_runtime_get_sync - Bump up usage counter of a device and resume it. * @dev: Target device. * * Bump up the runtime PM usage counter of @dev and carry out runtime-resume of * it synchronously. * * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. * Consider using pm_runtime_resume_and_get() instead of it, especially * if its return value is checked by the caller, as this is likely to result * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { return __pm_runtime_resume(dev, RPM_GET_PUT); } /** * pm_runtime_resume_and_get - Bump up usage counter of a device and resume it. * @dev: Target device. * * Resume @dev synchronously and if that is successful, increment its runtime * PM usage counter. Return 0 if the runtime PM usage counter of @dev has been * incremented or a negative error code otherwise. */ static inline int pm_runtime_resume_and_get(struct device *dev) { int ret; ret = __pm_runtime_resume(dev, RPM_GET_PUT); if (ret < 0) { pm_runtime_put_noidle(dev); return ret; } return 0; } /** * pm_runtime_put - Drop device usage counter and queue up "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). */ static inline int pm_runtime_put(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } DEFINE_FREE(pm_runtime_put, struct device *, if (_T) pm_runtime_put(_T)) /** * __pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int __pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_autosuspend(). */ static inline int pm_runtime_put_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_ASYNC | RPM_AUTO); } /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, invoke the "idle check" callback of @dev and, depending on its * return value, set up autosuspend of @dev or suspend it (depending on whether * or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_idle() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync(struct device *dev) { return __pm_runtime_idle(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_suspend - Drop device usage counter and suspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, carry out runtime-suspend of @dev synchronously. * * The possible return values of this function are the same as for * pm_runtime_suspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_suspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT); } /** * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0. * @dev: Target device. * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending * on whether or not autosuspend has been enabled for it). * * The possible return values of this function are the same as for * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains * decremented in all cases, even if it returns an error code. */ static inline int pm_runtime_put_sync_autosuspend(struct device *dev) { return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO); } /** * pm_runtime_set_active - Set runtime PM status to "active". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_ACTIVE and ensure that dependencies * of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_active(struct device *dev) { return __pm_runtime_set_status(dev, RPM_ACTIVE); } /** * pm_runtime_set_suspended - Set runtime PM status to "suspended". * @dev: Target device. * * Set the runtime PM status of @dev to %RPM_SUSPENDED and ensure that * dependencies of it will be taken into account. * * It is not valid to call this function for devices with runtime PM enabled. */ static inline int pm_runtime_set_suspended(struct device *dev) { return __pm_runtime_set_status(dev, RPM_SUSPENDED); } /** * pm_runtime_disable - Disable runtime PM for a device. * @dev: Target device. * * Prevent the runtime PM framework from working with @dev by incrementing its * "disable" counter. * * If the counter is zero when this function runs and there is a pending runtime * resume request for @dev, it will be resumed. If the counter is still zero at * that point, all of the pending runtime PM requests for @dev will be canceled * and all runtime PM operations in progress involving it will be waited for to * complete. * * For each invocation of this function for @dev, there must be a matching * pm_runtime_enable() call, so that runtime PM is eventually enabled for it * again. */ static inline void pm_runtime_disable(struct device *dev) { __pm_runtime_disable(dev, true); } /** * pm_runtime_use_autosuspend - Allow autosuspend to be used for a device. * @dev: Target device. * * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). * * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() * at driver exit time unless your driver initially enabled pm_runtime * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, true); } /** * pm_runtime_dont_use_autosuspend - Prevent autosuspend from being used. * @dev: Target device. * * Prevent the runtime PM autosuspend mechanism from being used for @dev which * means that "autosuspend" will be handled as direct runtime-suspend for it * going forward. */ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) { __pm_runtime_use_autosuspend(dev, false); } #endif |
| 1 1303 23 27 628 603 1 606 1380 103 320 1702 37 604 259 14 603 13 604 65 94 22 108 8 98 98 1 2 1827 67 1192 600 620 23 1 119 119 25 16 8 15 212 25 209 97 218 3 296 184 211 184 955 127 191 56 33 24 27 1 27 1 31 23 457 453 30 330 442 16 1 15 16 122 200 148 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_SCHED_GENERIC_H #define __NET_SCHED_GENERIC_H #include <linux/netdevice.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/pkt_sched.h> #include <linux/pkt_cls.h> #include <linux/percpu.h> #include <linux/dynamic_queue_limits.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/atomic.h> #include <linux/hashtable.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> #include <net/flow_offload.h> #include <linux/xarray.h> struct Qdisc_ops; struct qdisc_walker; struct tcf_walker; struct module; struct bpf_flow_keys; struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; struct qdisc_rate_table *next; int refcnt; }; enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, __QDISC_STATE_DRAINING, }; enum qdisc_state2_t { /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. * Use qdisc_run_begin/end() or qdisc_is_running() instead. */ __QDISC_STATE2_RUNNING, }; #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) #define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) #define QDISC_STATE_NON_EMPTY (QDISC_STATE_MISSED | \ QDISC_STATE_DRAINING) struct qdisc_size_table { struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; u16 data[]; }; /* similar to sk_buff_head, but skb->prev pointer is undefined. */ struct qdisc_skb_head { struct sk_buff *head; struct sk_buff *tail; __u32 qlen; spinlock_t lock; }; struct Qdisc { int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *sch); unsigned int flags; #define TCQ_F_BUILTIN 1 #define TCQ_F_INGRESS 2 #define TCQ_F_CAN_BYPASS 4 #define TCQ_F_MQROOT 8 #define TCQ_F_ONETXQUEUE 0x10 /* dequeue_skb() can assume all skbs are for * q->dev_queue : It can test * netif_xmit_frozen_or_stopped() before * dequeueing next packet. * Its true for MQ/MQPRIO slaves, or non * multiqueue device. */ #define TCQ_F_WARN_NONWC (1 << 16) #define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */ #define TCQ_F_NOPARENT 0x40 /* root of its hierarchy : * qdisc_tree_decrease_qlen() should stop. */ #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ #define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */ #define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */ u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; struct hlist_node hash; u32 handle; u32 parent; struct netdev_queue *dev_queue; struct net_rate_estimator __rcu *rate_est; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; int pad; refcount_t refcnt; /* * For performance sake on SMP, we put highly modified fields at the end */ struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; int owner; unsigned long state; unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; struct sk_buff_head skb_bad_txq; spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; struct rcu_head rcu; netdevice_tracker dev_tracker; struct lock_class_key root_lock_key; /* private data */ long privdata[] ____cacheline_aligned; }; static inline void qdisc_refcount_inc(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; refcount_inc(&qdisc->refcnt); } static inline bool qdisc_refcount_dec_if_one(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return true; return refcount_dec_if_one(&qdisc->refcnt); } /* Intended to be used by unlocked users, when concurrent qdisc release is * possible. */ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return qdisc; if (refcount_inc_not_zero(&qdisc->refcnt)) return qdisc; return NULL; } /* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc * root_lock section, or provide their own memory barriers -- ordering * against qdisc_run_begin/end() atomic bit operations. */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); return test_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) { return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY); } static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) { return q->flags & TCQ_F_CPUSTATS; } static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) return nolock_qdisc_is_empty(qdisc); return !READ_ONCE(qdisc->q.qlen); } /* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with * the qdisc root lock acquired. */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { if (spin_trylock(&qdisc->seqlock)) return true; /* No need to insist if the MISSED flag was already set. * Note that test_and_set_bit() also gives us memory ordering * guarantees wrt potential earlier enqueue() and below * spin_trylock(), both of which are necessary to prevent races */ if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state)) return false; /* Try to take the lock again to make sure that we will either * grab it or the CPU that still has it will see MISSED set * when testing it in qdisc_run_end() */ return spin_trylock(&qdisc->seqlock); } return !__test_and_set_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } static inline void qdisc_run_end(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); /* spin_unlock() only has store-release semantic. The unlock * and test_bit() ordering is a store-load ordering, so a full * memory barrier is needed here. */ smp_mb(); if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc); } else { __clear_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); } } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) { return qdisc->flags & TCQ_F_ONETXQUEUE; } static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { unsigned int flags; /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); int (*graft)(struct Qdisc *, unsigned long cl, struct Qdisc *, struct Qdisc **, struct netlink_ext_ack *extack); struct Qdisc * (*leaf)(struct Qdisc *, unsigned long cl); void (*qlen_notify)(struct Qdisc *, unsigned long); /* Class manipulation routines */ unsigned long (*find)(struct Qdisc *, u32 classid); int (*change)(struct Qdisc *, u32, u32, struct nlattr **, unsigned long *, struct netlink_ext_ack *); int (*delete)(struct Qdisc *, unsigned long, struct netlink_ext_ack *); void (*walk)(struct Qdisc *, struct qdisc_walker * arg); /* Filter manipulation */ struct tcf_block * (*tcf_block)(struct Qdisc *sch, unsigned long arg, struct netlink_ext_ack *extack); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); /* rtnetlink specific */ int (*dump)(struct Qdisc *, unsigned long, struct sk_buff *skb, struct tcmsg*); int (*dump_stats)(struct Qdisc *, unsigned long, struct gnet_dump *); }; /* Qdisc_class_ops flag values */ /* Implements API that doesn't require rtnl lock */ enum qdisc_class_ops_flags { QDISC_CLASS_OPS_DOIT_UNLOCKED = 1, }; struct Qdisc_ops { struct Qdisc_ops *next; const struct Qdisc_class_ops *cl_ops; char id[IFNAMSIZ]; int priv_size; unsigned int static_flags; int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free); struct sk_buff * (*dequeue)(struct Qdisc *); struct sk_buff * (*peek)(struct Qdisc *); int (*init)(struct Qdisc *sch, struct nlattr *arg, struct netlink_ext_ack *extack); void (*reset)(struct Qdisc *); void (*destroy)(struct Qdisc *); int (*change)(struct Qdisc *sch, struct nlattr *arg, struct netlink_ext_ack *extack); void (*attach)(struct Qdisc *sch); int (*change_tx_queue_len)(struct Qdisc *, unsigned int); void (*change_real_num_tx)(struct Qdisc *sch, unsigned int new_real_tx); int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); void (*ingress_block_set)(struct Qdisc *sch, u32 block_index); void (*egress_block_set)(struct Qdisc *sch, u32 block_index); u32 (*ingress_block_get)(struct Qdisc *sch); u32 (*egress_block_get)(struct Qdisc *sch); struct module *owner; }; struct tcf_result { union { struct { unsigned long class; u32 classid; }; const struct tcf_proto *goto_tp; }; }; struct tcf_chain; struct tcf_proto_ops { struct list_head head; char kind[IFNAMSIZ]; int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); void (*destroy)(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack); void* (*get)(struct tcf_proto*, u32 handle); void (*put)(struct tcf_proto *tp, void *f); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, void **, u32, struct netlink_ext_ack *); int (*delete)(struct tcf_proto *tp, void *arg, bool *last, bool rtnl_held, struct netlink_ext_ack *); bool (*delete_empty)(struct tcf_proto *tp); void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); void (*hw_add)(struct tcf_proto *tp, void *type_data); void (*hw_del)(struct tcf_proto *tp, void *type_data); void (*bind_class)(void *, u32, unsigned long, void *, unsigned long); void * (*tmplt_create)(struct net *net, struct tcf_chain *chain, struct nlattr **tca, struct netlink_ext_ack *extack); void (*tmplt_destroy)(void *tmplt_priv); void (*tmplt_reoffload)(struct tcf_chain *chain, bool add, flow_setup_cb_t *cb, void *cb_priv); struct tcf_exts * (*get_exts)(const struct tcf_proto *tp, u32 handle); /* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*, bool); int (*terse_dump)(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t, bool rtnl_held); int (*tmplt_dump)(struct sk_buff *skb, struct net *net, void *tmplt_priv); struct module *owner; int flags; }; /* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags * are expected to implement tcf_proto_ops->delete_empty(), otherwise race * conditions can occur when filters are inserted/deleted simultaneously. */ enum tcf_proto_ops_flags { TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; struct tcf_proto { /* Fast access part */ struct tcf_proto __rcu *next; void __rcu *root; /* called under RCU BH lock*/ int (*classify)(struct sk_buff *, const struct tcf_proto *, struct tcf_result *); __be16 protocol; /* All the rest */ u32 prio; void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; /* Lock protects tcf_proto shared state and can be used by unlocked * classifiers to protect their private data. */ spinlock_t lock; bool deleting; bool counted; bool usesw; refcount_t refcnt; struct rcu_head rcu; struct hlist_node destroy_ht_node; }; struct qdisc_skb_cb { struct { unsigned int pkt_len; u16 slave_dev_queue_mapping; u16 tc_classid; }; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { /* Protects filter_chain. */ struct mutex filter_chain_lock; struct tcf_proto __rcu *filter_chain; struct list_head list; struct tcf_block *block; u32 index; /* chain index */ unsigned int refcnt; unsigned int action_refcnt; bool explicitly_created; bool flushing; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; struct rcu_head rcu; }; struct tcf_block { struct xarray ports; /* datapath accessible */ /* Lock protects tcf_block and lifetime-management data of chains * attached to the block (refcnt, action_refcnt, explicitly_created). */ struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ u32 classid; /* which class this block belongs to */ refcount_t refcnt; struct net *net; struct Qdisc *q; struct rw_semaphore cb_lock; /* protects cb_list and offload counters */ struct flow_block flow_block; struct list_head owner_list; bool keep_dst; atomic_t useswcnt; atomic_t offloadcnt; /* Number of oddloaded filters */ unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */ unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */ struct { struct tcf_chain *chain; struct list_head filter_chain_list; } chain0; struct rcu_head rcu; DECLARE_HASHTABLE(proto_destroy_ht, 7); struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */ }; struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index); static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain) { return lockdep_is_held(&chain->filter_chain_lock); } static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp) { return lockdep_is_held(&tp->lock); } #define tcf_chain_dereference(p, chain) \ rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain)) #define tcf_proto_dereference(p, tp) \ rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp)) static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb)); BUILD_BUG_ON(sizeof(qcb->data) < sz); } static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; } static inline int qdisc_qlen_sum(const struct Qdisc *q) { __u32 qlen = q->qstats.qlen; int i; if (qdisc_is_percpu_stats(q)) { for_each_possible_cpu(i) qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen; } else { qlen += q->q.qlen; } return qlen; } static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb) { return (struct qdisc_skb_cb *)skb->cb; } static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc) { return &qdisc->q.lock; } static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) { struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc); return q; } static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) { return rcu_dereference_bh(qdisc->dev_queue->qdisc); } static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { return rcu_dereference_rtnl(qdisc->dev_queue->qdisc_sleeping); } static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) { struct Qdisc *root = qdisc_root_sleeping(qdisc); ASSERT_RTNL(); return qdisc_lock(root); } static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; } static inline void sch_tree_lock(struct Qdisc *q) { if (q->flags & TCQ_F_MQROOT) spin_lock_bh(qdisc_lock(q)); else spin_lock_bh(qdisc_root_sleeping_lock(q)); } static inline void sch_tree_unlock(struct Qdisc *q) { if (q->flags & TCQ_F_MQROOT) spin_unlock_bh(qdisc_lock(q)); else spin_unlock_bh(qdisc_root_sleeping_lock(q)); } extern struct Qdisc noop_qdisc; extern struct Qdisc_ops noop_qdisc_ops; extern struct Qdisc_ops pfifo_fast_ops; extern const u8 sch_default_prio2band[TC_PRIO_MAX + 1]; extern struct Qdisc_ops mq_qdisc_ops; extern struct Qdisc_ops noqueue_qdisc_ops; extern const struct Qdisc_ops *default_qdisc_ops; static inline const struct Qdisc_ops * get_default_qdisc_ops(const struct net_device *dev, int ntx) { return ntx < dev->real_num_tx_queues ? default_qdisc_ops : &pfifo_fast_ops; } struct Qdisc_class_common { u32 classid; unsigned int filter_cnt; struct hlist_node hnode; }; struct Qdisc_class_hash { struct hlist_head *hash; unsigned int hashsize; unsigned int hashmask; unsigned int hashelems; }; static inline unsigned int qdisc_class_hash(u32 id, u32 mask) { id ^= id >> 8; id ^= id >> 4; return id & mask; } static inline struct Qdisc_class_common * qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id) { struct Qdisc_class_common *cl; unsigned int h; if (!id) return NULL; h = qdisc_class_hash(id, hash->hashmask); hlist_for_each_entry(cl, &hash->hash[h], hnode) { if (cl->classid == id) return cl; } return NULL; } static inline bool qdisc_class_in_use(const struct Qdisc_class_common *cl) { return cl->filter_cnt > 0; } static inline void qdisc_class_get(struct Qdisc_class_common *cl) { unsigned int res; if (check_add_overflow(cl->filter_cnt, 1, &res)) WARN(1, "Qdisc class overflow"); cl->filter_cnt = res; } static inline void qdisc_class_put(struct Qdisc_class_common *cl) { unsigned int res; if (check_sub_overflow(cl->filter_cnt, 1, &res)) WARN(1, "Qdisc class underflow"); cl->filter_cnt = res; } static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid) { u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY; return (hwtc < netdev_get_num_tc(dev)) ? hwtc : -EINVAL; } int qdisc_class_hash_init(struct Qdisc_class_hash *); void qdisc_class_hash_insert(struct Qdisc_class_hash *, struct Qdisc_class_common *); void qdisc_class_hash_remove(struct Qdisc_class_hash *, struct Qdisc_class_common *); void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); void qdisc_class_hash_destroy(struct Qdisc_class_hash *); int dev_qdisc_change_tx_queue_len(struct net_device *dev); void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx); void dev_init_scheduler(struct net_device *dev); void dev_shutdown(struct net_device *dev); void dev_activate(struct net_device *dev); void dev_deactivate(struct net_device *dev); void dev_deactivate_many(struct list_head *head); struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); void qdisc_destroy(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); #ifdef CONFIG_NET_SCHED int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data); 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); #else static inline int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data) { q->flags &= ~TCQ_F_OFFLOADED; return 0; } static inline 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) { } #endif void qdisc_offload_query_caps(struct net_device *dev, enum tc_setup_type type, void *caps, size_t caps_len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); int skb_do_redirect(struct sk_buff *); static inline bool skb_at_tc_ingress(const struct sk_buff *skb) { #ifdef CONFIG_NET_XGRESS return skb->tc_at_ingress; #else return false; #endif } static inline bool skb_skip_tc_classify(struct sk_buff *skb) { #ifdef CONFIG_NET_CLS_ACT if (skb->tc_skip_classify) { skb->tc_skip_classify = 0; return true; } #endif return false; } /* Reset all TX qdiscs greater than index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); } } } /* Are all TX queues of the device empty? */ static inline bool qdisc_all_tx_empty(const struct net_device *dev) { unsigned int i; rcu_read_lock(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); const struct Qdisc *q = rcu_dereference(txq->qdisc); if (!qdisc_is_empty(q)) { rcu_read_unlock(); return false; } } rcu_read_unlock(); return true; } /* Are any of the TX qdiscs changing? */ static inline bool qdisc_tx_changing(const struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (rcu_access_pointer(txq->qdisc) != rcu_access_pointer(txq->qdisc_sleeping)) return true; } return false; } /* "noqueue" qdisc identified by not having any enqueue, see noqueue_init() */ static inline bool qdisc_txq_has_no_queue(const struct netdev_queue *txq) { struct Qdisc *qdisc = rcu_access_pointer(txq->qdisc); return qdisc->enqueue == NULL; } /* Is the device using the noop qdisc on all queues? */ static inline bool qdisc_tx_is_noop(const struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (rcu_access_pointer(txq->qdisc) != &noop_qdisc) return false; } return true; } static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb) { return qdisc_skb_cb(skb)->pkt_len; } /* additional qdisc xmit flags (NET_XMIT_MASK in linux/netdevice.h) */ enum net_xmit_qdisc_t { __NET_XMIT_STOLEN = 0x00010000, __NET_XMIT_BYPASS = 0x00020000, }; #ifdef CONFIG_NET_CLS_ACT #define net_xmit_drop_count(e) ((e) & __NET_XMIT_STOLEN ? 0 : 1) #else #define net_xmit_drop_count(e) (1) #endif static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); if (stab) __qdisc_calculate_pkt_len(skb, stab); #endif } static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { return sch->enqueue(skb, sch, to_free); } static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, __u64 bytes, __u64 packets) { u64_stats_update_begin(&bstats->syncp); u64_stats_add(&bstats->bytes, bytes); u64_stats_add(&bstats->packets, packets); u64_stats_update_end(&bstats->syncp); } static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { _bstats_update(bstats, qdisc_pkt_len(skb), skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1); } static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(this_cpu_ptr(sch->cpu_bstats), skb); } static inline void qdisc_bstats_update(struct Qdisc *sch, const struct sk_buff *skb) { bstats_update(&sch->bstats, skb); } static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog -= qdisc_pkt_len(skb); } static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch, const struct sk_buff *skb) { this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { sch->qstats.backlog += qdisc_pkt_len(skb); } static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch, const struct sk_buff *skb) { this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb)); } static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch) { this_cpu_dec(sch->cpu_qstats->qlen); } static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->requeues); } static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count) { sch->qstats.drops += count; } static inline void qstats_drop_inc(struct gnet_stats_queue *qstats) { qstats->drops++; } static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats) { qstats->overlimits++; } static inline void qdisc_qstats_drop(struct Qdisc *sch) { qstats_drop_inc(&sch->qstats); } static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch) { this_cpu_inc(sch->cpu_qstats->drops); } static inline void qdisc_qstats_overlimit(struct Qdisc *sch) { sch->qstats.overlimits++; } static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch) { __u32 qlen = qdisc_qlen_sum(sch); return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen); } static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen, __u32 *backlog) { struct gnet_stats_queue qstats = { 0 }; gnet_stats_add_queue(&qstats, sch->cpu_qstats, &sch->qstats); *qlen = qstats.qlen + qdisc_qlen(sch); *backlog = qstats.backlog; } static inline void qdisc_purge_queue(struct Qdisc *sch) { __u32 qlen, backlog; qdisc_qstats_qlen_backlog(sch, &qlen, &backlog); qdisc_reset(sch); qdisc_tree_reduce_backlog(sch, qlen, backlog); } static inline void __qdisc_enqueue_tail(struct sk_buff *skb, struct qdisc_skb_head *qh) { struct sk_buff *last = qh->tail; if (last) { skb->next = NULL; last->next = skb; qh->tail = skb; } else { qh->tail = skb; qh->head = skb; } qh->qlen++; } static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) { __qdisc_enqueue_tail(skb, &sch->q); qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } static inline void __qdisc_enqueue_head(struct sk_buff *skb, struct qdisc_skb_head *qh) { skb->next = qh->head; if (!qh->head) qh->tail = skb; qh->head = skb; qh->qlen++; } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) { struct sk_buff *skb = qh->head; if (likely(skb != NULL)) { qh->head = skb->next; qh->qlen--; if (qh->head == NULL) qh->tail = NULL; skb->next = NULL; } return skb; } static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool direct) { struct sk_buff *skb; skb = __skb_dequeue(&sch->gso_skb); if (skb) { sch->q.qlen--; return skb; } if (direct) return __qdisc_dequeue_head(&sch->q); else return sch->dequeue(sch); } static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) { struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); if (likely(skb != NULL)) { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); } return skb; } struct tc_skb_cb { struct qdisc_skb_cb qdisc_cb; u32 drop_reason; u16 zone; /* Only valid if post_ct = true */ u16 mru; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; }; static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) { struct tc_skb_cb *cb = (struct tc_skb_cb *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); return cb; } static inline enum skb_drop_reason tcf_get_drop_reason(const struct sk_buff *skb) { return tc_skb_cb(skb)->drop_reason; } static inline void tcf_set_drop_reason(const struct sk_buff *skb, enum skb_drop_reason reason) { tc_skb_cb(skb)->drop_reason = reason; } /* Instead of calling kfree_skb() while root qdisc lock is held, * queue the skb for future freeing at end of __dev_xmit_skb() */ static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free) { skb->next = *to_free; *to_free = skb; } static inline void __qdisc_drop_all(struct sk_buff *skb, struct sk_buff **to_free) { if (skb->prev) skb->prev->next = *to_free; else skb->next = *to_free; *to_free = skb; } static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch, struct qdisc_skb_head *qh, struct sk_buff **to_free) { struct sk_buff *skb = __qdisc_dequeue_head(qh); if (likely(skb != NULL)) { unsigned int len = qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); __qdisc_drop(skb, to_free); return len; } return 0; } static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch) { const struct qdisc_skb_head *qh = &sch->q; return qh->head; } /* generic pseudo peek method for non-work-conserving qdisc */ static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch) { struct sk_buff *skb = skb_peek(&sch->gso_skb); /* we can reuse ->gso_skb because peek isn't called for root qdiscs */ if (!skb) { skb = sch->dequeue(sch); if (skb) { __skb_queue_head(&sch->gso_skb, skb); /* it's still part of the queue */ qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; } } return skb; } static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch, struct sk_buff *skb) { if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_backlog_dec(sch, skb); qdisc_bstats_cpu_update(sch, skb); qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); sch->q.qlen--; } } static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch, unsigned int pkt_len) { if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_qlen_inc(sch); this_cpu_add(sch->cpu_qstats->backlog, pkt_len); } else { sch->qstats.backlog += pkt_len; sch->q.qlen++; } } /* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */ static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch) { struct sk_buff *skb = skb_peek(&sch->gso_skb); if (skb) { skb = __skb_dequeue(&sch->gso_skb); if (qdisc_is_percpu_stats(sch)) { qdisc_qstats_cpu_backlog_dec(sch, skb); qdisc_qstats_cpu_qlen_dec(sch); } else { qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; } } else { skb = sch->dequeue(sch); } return skb; } static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh) { /* * We do not know the backlog in bytes of this list, it * is up to the caller to correct it */ ASSERT_RTNL(); if (qh->qlen) { rtnl_kfree_skbs(qh->head, qh->tail); qh->head = NULL; qh->tail = NULL; qh->qlen = 0; } } static inline void qdisc_reset_queue(struct Qdisc *sch) { __qdisc_reset_queue(&sch->q); } static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, struct Qdisc **pold) { struct Qdisc *old; sch_tree_lock(sch); old = *pold; *pold = new; if (old != NULL) qdisc_purge_queue(old); sch_tree_unlock(sch); return old; } static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch) { rtnl_kfree_skbs(skb, skb); qdisc_qstats_drop(sch); } static inline int qdisc_drop_cpu(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); qdisc_qstats_cpu_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; } static inline int qdisc_drop_reason(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free, enum skb_drop_reason reason) { tcf_set_drop_reason(skb, reason); return qdisc_drop(skb, sch, to_free); } static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { __qdisc_drop_all(skb, to_free); qdisc_qstats_drop(sch); return NET_XMIT_DROP; } struct psched_ratecfg { u64 rate_bytes_ps; /* bytes per second */ u32 mult; u16 overhead; u16 mpu; u8 linklayer; u8 shift; }; static inline u64 psched_l2t_ns(const struct psched_ratecfg *r, unsigned int len) { len += r->overhead; if (len < r->mpu) len = r->mpu; if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift; return ((u64)len * r->mult) >> r->shift; } void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64); static inline void psched_ratecfg_getrate(struct tc_ratespec *res, const struct psched_ratecfg *r) { memset(res, 0, sizeof(*res)); /* legacy struct tc_ratespec has a 32bit @rate field * Qdisc using 64bit rate should add new attributes * in order to maintain compatibility. */ res->rate = min_t(u64, r->rate_bytes_ps, ~0U); res->overhead = r->overhead; res->mpu = r->mpu; res->linklayer = (r->linklayer & TC_LINKLAYER_MASK); } struct psched_pktrate { u64 rate_pkts_ps; /* packets per second */ u32 mult; u8 shift; }; static inline u64 psched_pkt2t_ns(const struct psched_pktrate *r, unsigned int pkt_num) { return ((u64)pkt_num * r->mult) >> r->shift; } void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64); /* Mini Qdisc serves for specific needs of ingress/clsact Qdisc. * The fast path only needs to access filter list and to update stats */ struct mini_Qdisc { struct tcf_proto *filter_list; struct tcf_block *block; struct gnet_stats_basic_sync __percpu *cpu_bstats; struct gnet_stats_queue __percpu *cpu_qstats; unsigned long rcu_state; }; static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq, const struct sk_buff *skb) { bstats_update(this_cpu_ptr(miniq->cpu_bstats), skb); } static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq) { this_cpu_inc(miniq->cpu_qstats->drops); } struct mini_Qdisc_pair { struct mini_Qdisc miniq1; struct mini_Qdisc miniq2; struct mini_Qdisc __rcu **p_miniq; }; void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head); void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq); void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); /* Make sure qdisc is no longer in SCHED state. */ static inline void qdisc_synchronize(const struct Qdisc *q) { while (test_bit(__QDISC_STATE_SCHED, &q->state)) msleep(1); } #endif |
| 195 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SHARED_IO_H #define _ASM_X86_SHARED_IO_H #include <linux/types.h> #define BUILDIO(bwl, bw, type) \ static __always_inline void __out##bwl(type value, u16 port) \ { \ asm volatile("out" #bwl " %" #bw "0, %w1" \ : : "a"(value), "Nd"(port)); \ } \ \ static __always_inline type __in##bwl(u16 port) \ { \ type value; \ asm volatile("in" #bwl " %w1, %" #bw "0" \ : "=a"(value) : "Nd"(port)); \ return value; \ } BUILDIO(b, b, u8) BUILDIO(w, w, u16) BUILDIO(l, , u32) #undef BUILDIO #define inb __inb #define inw __inw #define inl __inl #define outb __outb #define outw __outw #define outl __outl #endif |
| 40 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include "rxe.h" static struct workqueue_struct *rxe_wq; int rxe_alloc_wq(void) { rxe_wq = alloc_workqueue("rxe_wq", WQ_UNBOUND, WQ_MAX_ACTIVE); if (!rxe_wq) return -ENOMEM; return 0; } void rxe_destroy_wq(void) { destroy_workqueue(rxe_wq); } /* Check if task is idle i.e. not running, not scheduled in * work queue and not draining. If so move to busy to * reserve a slot in do_task() by setting to busy and taking * a qp reference to cover the gap from now until the task finishes. * state will move out of busy if task returns a non zero value * in do_task(). If state is already busy it is raised to armed * to indicate to do_task that additional pass should be made * over the task. * Context: caller should hold task->lock. * Returns: true if state transitioned from idle to busy else false. */ static bool __reserve_if_idle(struct rxe_task *task) { WARN_ON(rxe_read(task->qp) <= 0); if (task->state == TASK_STATE_IDLE) { rxe_get(task->qp); task->state = TASK_STATE_BUSY; task->num_sched++; return true; } if (task->state == TASK_STATE_BUSY) task->state = TASK_STATE_ARMED; return false; } /* check if task is idle or drained and not currently * scheduled in the work queue. This routine is * called by rxe_cleanup_task or rxe_disable_task to * see if the queue is empty. * Context: caller should hold task->lock. * Returns true if done else false. */ static bool __is_done(struct rxe_task *task) { if (work_pending(&task->work)) return false; if (task->state == TASK_STATE_IDLE || task->state == TASK_STATE_DRAINED) { return true; } return false; } /* a locked version of __is_done */ static bool is_done(struct rxe_task *task) { unsigned long flags; int done; spin_lock_irqsave(&task->lock, flags); done = __is_done(task); spin_unlock_irqrestore(&task->lock, flags); return done; } /* do_task is a wrapper for the three tasks (requester, * completer, responder) and calls them in a loop until * they return a non-zero value. It is called indirectly * when rxe_sched_task schedules the task. They must * call __reserve_if_idle to move the task to busy before * calling or scheduling. The task can also be moved to * drained or invalid by calls to rxe_cleanup_task or * rxe_disable_task. In that case tasks which get here * are not executed but just flushed. The tasks are * designed to look to see if there is work to do and * then do part of it before returning here with a return * value of zero until all the work has been consumed then * it returns a non-zero value. * The number of times the task can be run is limited by * max iterations so one task cannot hold the cpu forever. * If the limit is hit and work remains the task is rescheduled. */ static void do_task(struct rxe_task *task) { unsigned int iterations; unsigned long flags; int resched = 0; int cont; int ret; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (task->state >= TASK_STATE_DRAINED) { rxe_put(task->qp); task->num_done++; spin_unlock_irqrestore(&task->lock, flags); return; } spin_unlock_irqrestore(&task->lock, flags); do { iterations = RXE_MAX_ITERATIONS; cont = 0; do { ret = task->func(task->qp); } while (ret == 0 && iterations-- > 0); spin_lock_irqsave(&task->lock, flags); /* we're not done yet but we ran out of iterations. * yield the cpu and reschedule the task */ if (!ret) { task->state = TASK_STATE_IDLE; resched = 1; goto exit; } switch (task->state) { case TASK_STATE_BUSY: task->state = TASK_STATE_IDLE; break; /* someone tried to schedule the task while we * were running, keep going */ case TASK_STATE_ARMED: task->state = TASK_STATE_BUSY; cont = 1; break; case TASK_STATE_DRAINING: task->state = TASK_STATE_DRAINED; break; default: WARN_ON(1); rxe_dbg_qp(task->qp, "unexpected task state = %d\n", task->state); task->state = TASK_STATE_IDLE; } exit: if (!cont) { task->num_done++; if (WARN_ON(task->num_done != task->num_sched)) rxe_dbg_qp( task->qp, "%ld tasks scheduled, %ld tasks done\n", task->num_sched, task->num_done); } spin_unlock_irqrestore(&task->lock, flags); } while (cont); task->ret = ret; if (resched) rxe_sched_task(task); rxe_put(task->qp); } /* wrapper around do_task to fix argument for work queue */ static void do_work(struct work_struct *work) { do_task(container_of(work, struct rxe_task, work)); } int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp, int (*func)(struct rxe_qp *)) { WARN_ON(rxe_read(qp) <= 0); task->qp = qp; task->func = func; task->state = TASK_STATE_IDLE; spin_lock_init(&task->lock); INIT_WORK(&task->work, do_work); return 0; } /* rxe_cleanup_task is only called from rxe_do_qp_cleanup in * process context. The qp is already completed with no * remaining references. Once the queue is drained the * task is moved to invalid and returns. The qp cleanup * code then calls the task functions directly without * using the task struct to drain any late arriving packets * or work requests. */ void rxe_cleanup_task(struct rxe_task *task) { unsigned long flags; spin_lock_irqsave(&task->lock, flags); if (!__is_done(task) && task->state < TASK_STATE_DRAINED) { task->state = TASK_STATE_DRAINING; } else { task->state = TASK_STATE_INVALID; spin_unlock_irqrestore(&task->lock, flags); return; } spin_unlock_irqrestore(&task->lock, flags); /* now the task cannot be scheduled or run just wait * for the previously scheduled tasks to finish. */ while (!is_done(task)) cond_resched(); spin_lock_irqsave(&task->lock, flags); task->state = TASK_STATE_INVALID; spin_unlock_irqrestore(&task->lock, flags); } /* schedule the task to run later as a work queue entry. * the queue_work call can be called holding * the lock. */ void rxe_sched_task(struct rxe_task *task) { unsigned long flags; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (__reserve_if_idle(task)) queue_work(rxe_wq, &task->work); spin_unlock_irqrestore(&task->lock, flags); } /* rxe_disable/enable_task are only called from * rxe_modify_qp in process context. Task is moved * to the drained state by do_task. */ void rxe_disable_task(struct rxe_task *task) { unsigned long flags; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (!__is_done(task) && task->state < TASK_STATE_DRAINED) { task->state = TASK_STATE_DRAINING; } else { task->state = TASK_STATE_DRAINED; spin_unlock_irqrestore(&task->lock, flags); return; } spin_unlock_irqrestore(&task->lock, flags); while (!is_done(task)) cond_resched(); spin_lock_irqsave(&task->lock, flags); task->state = TASK_STATE_DRAINED; spin_unlock_irqrestore(&task->lock, flags); } void rxe_enable_task(struct rxe_task *task) { unsigned long flags; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (task->state == TASK_STATE_INVALID) { spin_unlock_irqrestore(&task->lock, flags); return; } task->state = TASK_STATE_IDLE; spin_unlock_irqrestore(&task->lock, flags); } |
| 116 116 116 116 66 50 50 50 50 103 103 103 86 50 50 105 105 105 105 66 66 66 66 66 66 66 2582 2586 66 66 66 66 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/devres.c - device resource management * * Copyright (c) 2006 SUSE Linux Products GmbH * Copyright (c) 2006 Tejun Heo <teheo@suse.de> */ #include <linux/device.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/percpu.h> #include <asm/sections.h> #include "base.h" #include "trace.h" struct devres_node { struct list_head entry; dr_release_t release; const char *name; size_t size; }; struct devres { struct devres_node node; /* * Some archs want to perform DMA into kmalloc caches * and need a guaranteed alignment larger than * the alignment of a 64-bit integer. * Thus we use ARCH_DMA_MINALIGN for data[] which will force the same * alignment for struct devres when allocated by kmalloc(). */ u8 __aligned(ARCH_DMA_MINALIGN) data[]; }; struct devres_group { struct devres_node node[2]; void *id; int color; /* -- 8 pointers */ }; static void set_node_dbginfo(struct devres_node *node, const char *name, size_t size) { node->name = name; node->size = size; } #ifdef CONFIG_DEBUG_DEVRES static int log_devres = 0; module_param_named(log, log_devres, int, S_IRUGO | S_IWUSR); static void devres_dbg(struct device *dev, struct devres_node *node, const char *op) { if (unlikely(log_devres)) dev_err(dev, "DEVRES %3s %p %s (%zu bytes)\n", op, node, node->name, node->size); } #else /* CONFIG_DEBUG_DEVRES */ #define devres_dbg(dev, node, op) do {} while (0) #endif /* CONFIG_DEBUG_DEVRES */ static void devres_log(struct device *dev, struct devres_node *node, const char *op) { trace_devres_log(dev, op, node, node->name, node->size); devres_dbg(dev, node, op); } /* * Release functions for devres group. These callbacks are used only * for identification. */ static void group_open_release(struct device *dev, void *res) { /* noop */ } static void group_close_release(struct device *dev, void *res) { /* noop */ } static struct devres_group *node_to_group(struct devres_node *node) { if (node->release == &group_open_release) return container_of(node, struct devres_group, node[0]); if (node->release == &group_close_release) return container_of(node, struct devres_group, node[1]); return NULL; } static bool check_dr_size(size_t size, size_t *tot_size) { /* We must catch any near-SIZE_MAX cases that could overflow. */ if (unlikely(check_add_overflow(sizeof(struct devres), size, tot_size))) return false; /* Actually allocate the full kmalloc bucket size. */ *tot_size = kmalloc_size_roundup(*tot_size); return true; } static __always_inline struct devres *alloc_dr(dr_release_t release, size_t size, gfp_t gfp, int nid) { size_t tot_size; struct devres *dr; if (!check_dr_size(size, &tot_size)) return NULL; dr = kmalloc_node_track_caller(tot_size, gfp, nid); if (unlikely(!dr)) return NULL; /* No need to clear memory twice */ if (!(gfp & __GFP_ZERO)) memset(dr, 0, offsetof(struct devres, data)); INIT_LIST_HEAD(&dr->node.entry); dr->node.release = release; return dr; } static void add_dr(struct device *dev, struct devres_node *node) { devres_log(dev, node, "ADD"); BUG_ON(!list_empty(&node->entry)); list_add_tail(&node->entry, &dev->devres_head); } static void replace_dr(struct device *dev, struct devres_node *old, struct devres_node *new) { devres_log(dev, old, "REPLACE"); BUG_ON(!list_empty(&new->entry)); list_replace(&old->entry, &new->entry); } /** * __devres_alloc_node - Allocate device resource data * @release: Release function devres will be associated with * @size: Allocation size * @gfp: Allocation flags * @nid: NUMA node * @name: Name of the resource * * Allocate devres of @size bytes. The allocated area is zeroed, then * associated with @release. The returned pointer can be passed to * other devres_*() functions. * * RETURNS: * Pointer to allocated devres on success, NULL on failure. */ void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name) { struct devres *dr; dr = alloc_dr(release, size, gfp | __GFP_ZERO, nid); if (unlikely(!dr)) return NULL; set_node_dbginfo(&dr->node, name, size); return dr->data; } EXPORT_SYMBOL_GPL(__devres_alloc_node); /** * devres_for_each_res - Resource iterator * @dev: Device to iterate resource from * @release: Look for resources associated with this release function * @match: Match function (optional) * @match_data: Data for the match function * @fn: Function to be called for each matched resource. * @data: Data for @fn, the 3rd parameter of @fn * * Call @fn for each devres of @dev which is associated with @release * and for which @match returns 1. * * RETURNS: * void */ void devres_for_each_res(struct device *dev, dr_release_t release, dr_match_t match, void *match_data, void (*fn)(struct device *, void *, void *), void *data) { struct devres_node *node; struct devres_node *tmp; unsigned long flags; if (!fn) return; spin_lock_irqsave(&dev->devres_lock, flags); list_for_each_entry_safe_reverse(node, tmp, &dev->devres_head, entry) { struct devres *dr = container_of(node, struct devres, node); if (node->release != release) continue; if (match && !match(dev, dr->data, match_data)) continue; fn(dev, dr->data, data); } spin_unlock_irqrestore(&dev->devres_lock, flags); } EXPORT_SYMBOL_GPL(devres_for_each_res); /** * devres_free - Free device resource data * @res: Pointer to devres data to free * * Free devres created with devres_alloc(). */ void devres_free(void *res) { if (res) { struct devres *dr = container_of(res, struct devres, data); BUG_ON(!list_empty(&dr->node.entry)); kfree(dr); } } EXPORT_SYMBOL_GPL(devres_free); /** * devres_add - Register device resource * @dev: Device to add resource to * @res: Resource to register * * Register devres @res to @dev. @res should have been allocated * using devres_alloc(). On driver detach, the associated release * function will be invoked and devres will be freed automatically. */ void devres_add(struct device *dev, void *res) { struct devres *dr = container_of(res, struct devres, data); unsigned long flags; spin_lock_irqsave(&dev->devres_lock, flags); add_dr(dev, &dr->node); spin_unlock_irqrestore(&dev->devres_lock, flags); } EXPORT_SYMBOL_GPL(devres_add); static struct devres *find_dr(struct device *dev, dr_release_t release, dr_match_t match, void *match_data) { struct devres_node *node; list_for_each_entry_reverse(node, &dev->devres_head, entry) { struct devres *dr = container_of(node, struct devres, node); if (node->release != release) continue; if (match && !match(dev, dr->data, match_data)) continue; return dr; } return NULL; } /** * devres_find - Find device resource * @dev: Device to lookup resource from * @release: Look for resources associated with this release function * @match: Match function (optional) * @match_data: Data for the match function * * Find the latest devres of @dev which is associated with @release * and for which @match returns 1. If @match is NULL, it's considered * to match all. * * RETURNS: * Pointer to found devres, NULL if not found. */ void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data) { struct devres *dr; unsigned long flags; spin_lock_irqsave(&dev->devres_lock, flags); dr = find_dr(dev, release, match, match_data); spin_unlock_irqrestore(&dev->devres_lock, flags); if (dr) return dr->data; return NULL; } EXPORT_SYMBOL_GPL(devres_find); /** * devres_get - Find devres, if non-existent, add one atomically * @dev: Device to lookup or add devres for * @new_res: Pointer to new initialized devres to add if not found * @match: Match function (optional) * @match_data: Data for the match function * * Find the latest devres of @dev which has the same release function * as @new_res and for which @match return 1. If found, @new_res is * freed; otherwise, @new_res is added atomically. * * RETURNS: * Pointer to found or added devres. */ void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data) { struct devres *new_dr = container_of(new_res, struct devres, data); struct devres *dr; unsigned long flags; spin_lock_irqsave(&dev->devres_lock, flags); dr = find_dr(dev, new_dr->node.release, match, match_data); if (!dr) { add_dr(dev, &new_dr->node); dr = new_dr; new_res = NULL; } spin_unlock_irqrestore(&dev->devres_lock, flags); devres_free(new_res); return dr->data; } EXPORT_SYMBOL_GPL(devres_get); /** * devres_remove - Find a device resource and remove it * @dev: Device to find resource from * @release: Look for resources associated with this release function * @match: Match function (optional) * @match_data: Data for the match function * * Find the latest devres of @dev associated with @release and for * which @match returns 1. If @match is NULL, it's considered to * match all. If found, the resource is removed atomically and * returned. * * RETURNS: * Pointer to removed devres on success, NULL if not found. */ void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data) { struct devres *dr; unsigned long flags; spin_lock_irqsave(&dev->devres_lock, flags); dr = find_dr(dev, release, match, match_data); if (dr) { list_del_init(&dr->node.entry); devres_log(dev, &dr->node, "REM"); } spin_unlock_irqrestore(&dev->devres_lock, flags); if (dr) return dr->data; return NULL; } EXPORT_SYMBOL_GPL(devres_remove); /** * devres_destroy - Find a device resource and destroy it * @dev: Device to find resource from * @release: Look for resources associated with this release function * @match: Match function (optional) * @match_data: Data for the match function * * Find the latest devres of @dev associated with @release and for * which @match returns 1. If @match is NULL, it's considered to * match all. If found, the resource is removed atomically and freed. * * Note that the release function for the resource will not be called, * only the devres-allocated data will be freed. The caller becomes * responsible for freeing any other data. * * RETURNS: * 0 if devres is found and freed, -ENOENT if not found. */ int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data) { void *res; res = devres_remove(dev, release, match, match_data); if (unlikely(!res)) return -ENOENT; devres_free(res); return 0; } EXPORT_SYMBOL_GPL(devres_destroy); /** * devres_release - Find a device resource and destroy it, calling release * @dev: Device to find resource from * @release: Look for resources associated with this release function * @match: Match function (optional) * @match_data: Data for the match function * * Find the latest devres of @dev associated with @release and for * which @match returns 1. If @match is NULL, it's considered to * match all. If found, the resource is removed atomically, the * release function called and the resource freed. * * RETURNS: * 0 if devres is found and freed, -ENOENT if not found. */ int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data) { void *res; res = devres_remove(dev, release, match, match_data); if (unlikely(!res)) return -ENOENT; (*release)(dev, res); devres_free(res); return 0; } EXPORT_SYMBOL_GPL(devres_release); static int remove_nodes(struct device *dev, struct list_head *first, struct list_head *end, struct list_head *todo) { struct devres_node *node, *n; int cnt = 0, nr_groups = 0; /* First pass - move normal devres entries to @todo and clear * devres_group colors. */ node = list_entry(first, struct devres_node, entry); list_for_each_entry_safe_from(node, n, end, entry) { struct devres_group *grp; grp = node_to_group(node); if (grp) { /* clear color of group markers in the first pass */ grp->color = 0; nr_groups++; } else { /* regular devres entry */ if (&node->entry == first) first = first->next; list_move_tail(&node->entry, todo); cnt++; } } if (!nr_groups) return cnt; /* Second pass - Scan groups and color them. A group gets * color value of two iff the group is wholly contained in * [current node, end). That is, for a closed group, both opening * and closing markers should be in the range, while just the * opening marker is enough for an open group. */ node = list_entry(first, struct devres_node, entry); list_for_each_entry_safe_from(node, n, end, entry) { struct devres_group *grp; grp = node_to_group(node); BUG_ON(!grp || list_empty(&grp->node[0].entry)); grp->color++; if (list_empty(&grp->node[1].entry)) grp->color++; BUG_ON(grp->color <= 0 || grp->color > 2); if (grp->color == 2) { /* No need to update current node or end. The removed * nodes are always before both. */ list_move_tail(&grp->node[0].entry, todo); list_del_init(&grp->node[1].entry); } } return cnt; } static void release_nodes(struct device *dev, struct list_head *todo) { struct devres *dr, *tmp; /* Release. Note that both devres and devres_group are * handled as devres in the following loop. This is safe. */ list_for_each_entry_safe_reverse(dr, tmp, todo, node.entry) { devres_log(dev, &dr->node, "REL"); dr->node.release(dev, dr->data); kfree(dr); } } /** * devres_release_all - Release all managed resources * @dev: Device to release resources for * * Release all resources associated with @dev. This function is * called on driver detach. */ int devres_release_all(struct device *dev) { unsigned long flags; LIST_HEAD(todo); int cnt; /* Looks like an uninitialized device structure */ if (WARN_ON(dev->devres_head.next == NULL)) return -ENODEV; /* Nothing to release if list is empty */ if (list_empty(&dev->devres_head)) return 0; spin_lock_irqsave(&dev->devres_lock, flags); cnt = remove_nodes(dev, dev->devres_head.next, &dev->devres_head, &todo); spin_unlock_irqrestore(&dev->devres_lock, flags); release_nodes(dev, &todo); return cnt; } /** * devres_open_group - Open a new devres group * @dev: Device to open devres group for * @id: Separator ID * @gfp: Allocation flags * * Open a new devres group for @dev with @id. For @id, using a * pointer to an object which won't be used for another group is * recommended. If @id is NULL, address-wise unique ID is created. * * RETURNS: * ID of the new group, NULL on failure. */ void *devres_open_group(struct device *dev, void *id, gfp_t gfp) { struct devres_group *grp; unsigned long flags; grp = kmalloc(sizeof(*grp), gfp); if (unlikely(!grp)) return NULL; grp->node[0].release = &group_open_release; grp->node[1].release = &group_close_release; INIT_LIST_HEAD(&grp->node[0].entry); INIT_LIST_HEAD(&grp->node[1].entry); set_node_dbginfo(&grp->node[0], "grp<", 0); set_node_dbginfo(&grp->node[1], "grp>", 0); grp->id = grp; if (id) grp->id = id; grp->color = 0; spin_lock_irqsave(&dev->devres_lock, flags); add_dr(dev, &grp->node[0]); spin_unlock_irqrestore(&dev->devres_lock, flags); return grp->id; } EXPORT_SYMBOL_GPL(devres_open_group); /* * Find devres group with ID @id. If @id is NULL, look for the latest open * group. */ static struct devres_group *find_group(struct device *dev, void *id) { struct devres_node *node; list_for_each_entry_reverse(node, &dev->devres_head, entry) { struct devres_group *grp; if (node->release != &group_open_release) continue; grp = container_of(node, struct devres_group, node[0]); if (id) { if (grp->id == id) return grp; } else if (list_empty(&grp->node[1].entry)) return grp; } return NULL; } /** * devres_close_group - Close a devres group * @dev: Device to close devres group for * @id: ID of target group, can be NULL * * Close the group identified by @id. If @id is NULL, the latest open * group is selected. */ void devres_close_group(struct device *dev, void *id) { struct devres_group *grp; unsigned long flags; spin_lock_irqsave(&dev->devres_lock, flags); grp = find_group(dev, id); if (grp) add_dr(dev, &grp->node[1]); else WARN_ON(1); spin_unlock_irqrestore(&dev->devres_lock, flags); } EXPORT_SYMBOL_GPL(devres_close_group); /** * devres_remove_group - Remove a devres group * @dev: Device to remove group for * @id: ID of target group, can be NULL * * Remove the group identified by @id. If @id is NULL, the latest * open group is selected. Note that removing a group doesn't affect * any other resources. */ void devres_remove_group(struct device *dev, void *id) { struct devres_group *grp; unsigned long flags; spin_lock_irqsave(&dev->devres_lock, flags); grp = find_group(dev, id); if (grp) { list_del_init(&grp->node[0].entry); list_del_init(&grp->node[1].entry); devres_log(dev, &grp->node[0], "REM"); } else WARN_ON(1); spin_unlock_irqrestore(&dev->devres_lock, flags); kfree(grp); } EXPORT_SYMBOL_GPL(devres_remove_group); /** * devres_release_group - Release resources in a devres group * @dev: Device to release group for * @id: ID of target group, can be NULL * * Release all resources in the group identified by @id. If @id is * NULL, the latest open group is selected. The selected group and * groups properly nested inside the selected group are removed. * * RETURNS: * The number of released non-group resources. */ int devres_release_group(struct device *dev, void *id) { struct devres_group *grp; unsigned long flags; LIST_HEAD(todo); int cnt = 0; spin_lock_irqsave(&dev->devres_lock, flags); grp = find_group(dev, id); if (grp) { struct list_head *first = &grp->node[0].entry; struct list_head *end = &dev->devres_head; if (!list_empty(&grp->node[1].entry)) end = grp->node[1].entry.next; cnt = remove_nodes(dev, first, end, &todo); spin_unlock_irqrestore(&dev->devres_lock, flags); release_nodes(dev, &todo); } else if (list_empty(&dev->devres_head)) { /* * dev is probably dying via devres_release_all(): groups * have already been removed and are on the process of * being released - don't touch and don't warn. */ spin_unlock_irqrestore(&dev->devres_lock, flags); } else { WARN_ON(1); spin_unlock_irqrestore(&dev->devres_lock, flags); } return cnt; } EXPORT_SYMBOL_GPL(devres_release_group); /* * Custom devres actions allow inserting a simple function call * into the teardown sequence. */ struct action_devres { void *data; void (*action)(void *); }; static int devm_action_match(struct device *dev, void *res, void *p) { struct action_devres *devres = res; struct action_devres *target = p; return devres->action == target->action && devres->data == target->data; } static void devm_action_release(struct device *dev, void *res) { struct action_devres *devres = res; devres->action(devres->data); } /** * __devm_add_action() - add a custom action to list of managed resources * @dev: Device that owns the action * @action: Function that should be called * @data: Pointer to data passed to @action implementation * @name: Name of the resource (for debugging purposes) * * This adds a custom action to the list of managed resources so that * it gets executed as part of standard resource unwinding. */ int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name) { struct action_devres *devres; devres = __devres_alloc_node(devm_action_release, sizeof(struct action_devres), GFP_KERNEL, NUMA_NO_NODE, name); if (!devres) return -ENOMEM; devres->data = data; devres->action = action; devres_add(dev, devres); return 0; } EXPORT_SYMBOL_GPL(__devm_add_action); bool devm_is_action_added(struct device *dev, void (*action)(void *), void *data) { struct action_devres devres = { .data = data, .action = action, }; return devres_find(dev, devm_action_release, devm_action_match, &devres); } EXPORT_SYMBOL_GPL(devm_is_action_added); /** * devm_remove_action_nowarn() - removes previously added custom action * @dev: Device that owns the action * @action: Function implementing the action * @data: Pointer to data passed to @action implementation * * Removes instance of @action previously added by devm_add_action(). * Both action and data should match one of the existing entries. * * In contrast to devm_remove_action(), this function does not WARN() if no * entry could have been found. * * This should only be used if the action is contained in an object with * independent lifetime management, e.g. the Devres rust abstraction. * * Causing the warning from regular driver code most likely indicates an abuse * of the devres API. * * Returns: 0 on success, -ENOENT if no entry could have been found. */ int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data) { struct action_devres devres = { .data = data, .action = action, }; return devres_destroy(dev, devm_action_release, devm_action_match, &devres); } EXPORT_SYMBOL_GPL(devm_remove_action_nowarn); /** * devm_release_action() - release previously added custom action * @dev: Device that owns the action * @action: Function implementing the action * @data: Pointer to data passed to @action implementation * * Releases and removes instance of @action previously added by * devm_add_action(). Both action and data should match one of the * existing entries. */ void devm_release_action(struct device *dev, void (*action)(void *), void *data) { struct action_devres devres = { .data = data, .action = action, }; WARN_ON(devres_release(dev, devm_action_release, devm_action_match, &devres)); } EXPORT_SYMBOL_GPL(devm_release_action); /* * Managed kmalloc/kfree */ static void devm_kmalloc_release(struct device *dev, void *res) { /* noop */ } static int devm_kmalloc_match(struct device *dev, void *res, void *data) { return res == data; } /** * devm_kmalloc - Resource-managed kmalloc * @dev: Device to allocate memory for * @size: Allocation size * @gfp: Allocation gfp flags * * Managed kmalloc. Memory allocated with this function is * automatically freed on driver detach. Like all other devres * resources, guaranteed alignment is unsigned long long. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) { struct devres *dr; if (unlikely(!size)) return ZERO_SIZE_PTR; /* use raw alloc_dr for kmalloc caller tracing */ dr = alloc_dr(devm_kmalloc_release, size, gfp, dev_to_node(dev)); if (unlikely(!dr)) return NULL; /* * This is named devm_kzalloc_release for historical reasons * The initial implementation did not support kmalloc, only kzalloc */ set_node_dbginfo(&dr->node, "devm_kzalloc_release", size); devres_add(dev, dr->data); return dr->data; } EXPORT_SYMBOL_GPL(devm_kmalloc); /** * devm_krealloc - Resource-managed krealloc() * @dev: Device to re-allocate memory for * @ptr: Pointer to the memory chunk to re-allocate * @new_size: New allocation size * @gfp: Allocation gfp flags * * Managed krealloc(). Resizes the memory chunk allocated with devm_kmalloc(). * Behaves similarly to regular krealloc(): if @ptr is NULL or ZERO_SIZE_PTR, * it's the equivalent of devm_kmalloc(). If new_size is zero, it frees the * previously allocated memory and returns ZERO_SIZE_PTR. This function doesn't * change the order in which the release callback for the re-alloc'ed devres * will be called (except when falling back to devm_kmalloc() or when freeing * resources when new_size is zero). The contents of the memory are preserved * up to the lesser of new and old sizes. */ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp) { size_t total_new_size, total_old_size; struct devres *old_dr, *new_dr; unsigned long flags; if (unlikely(!new_size)) { devm_kfree(dev, ptr); return ZERO_SIZE_PTR; } if (unlikely(ZERO_OR_NULL_PTR(ptr))) return devm_kmalloc(dev, new_size, gfp); if (WARN_ON(is_kernel_rodata((unsigned long)ptr))) /* * We cannot reliably realloc a const string returned by * devm_kstrdup_const(). */ return NULL; if (!check_dr_size(new_size, &total_new_size)) return NULL; total_old_size = ksize(container_of(ptr, struct devres, data)); if (total_old_size == 0) { WARN(1, "Pointer doesn't point to dynamically allocated memory."); return NULL; } /* * If new size is smaller or equal to the actual number of bytes * allocated previously - just return the same pointer. */ if (total_new_size <= total_old_size) return ptr; /* * Otherwise: allocate new, larger chunk. We need to allocate before * taking the lock as most probably the caller uses GFP_KERNEL. * alloc_dr() will call check_dr_size() to reserve extra memory * for struct devres automatically, so size @new_size user request * is delivered to it directly as devm_kmalloc() does. */ new_dr = alloc_dr(devm_kmalloc_release, new_size, gfp, dev_to_node(dev)); if (!new_dr) return NULL; /* * The spinlock protects the linked list against concurrent * modifications but not the resource itself. */ spin_lock_irqsave(&dev->devres_lock, flags); old_dr = find_dr(dev, devm_kmalloc_release, devm_kmalloc_match, ptr); if (!old_dr) { spin_unlock_irqrestore(&dev->devres_lock, flags); kfree(new_dr); WARN(1, "Memory chunk not managed or managed by a different device."); return NULL; } replace_dr(dev, &old_dr->node, &new_dr->node); spin_unlock_irqrestore(&dev->devres_lock, flags); /* * We can copy the memory contents after releasing the lock as we're * no longer modifying the list links. */ memcpy(new_dr->data, old_dr->data, total_old_size - offsetof(struct devres, data)); /* * Same for releasing the old devres - it's now been removed from the * list. This is also the reason why we must not use devm_kfree() - the * links are no longer valid. */ kfree(old_dr); return new_dr->data; } EXPORT_SYMBOL_GPL(devm_krealloc); /** * devm_kstrdup - Allocate resource managed space and * copy an existing string into that. * @dev: Device to allocate memory for * @s: the string to duplicate * @gfp: the GFP mask used in the devm_kmalloc() call when * allocating memory * RETURNS: * Pointer to allocated string on success, NULL on failure. */ char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) { if (!s) return NULL; return devm_kmemdup(dev, s, strlen(s) + 1, gfp); } EXPORT_SYMBOL_GPL(devm_kstrdup); /** * devm_kstrdup_const - resource managed conditional string duplication * @dev: device for which to duplicate the string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Strings allocated by devm_kstrdup_const will be automatically freed when * the associated device is detached. * * RETURNS: * Source string if it is in .rodata section otherwise it falls back to * devm_kstrdup. */ const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return devm_kstrdup(dev, s, gfp); } EXPORT_SYMBOL_GPL(devm_kstrdup_const); /** * devm_kvasprintf - Allocate resource managed space and format a string * into that. * @dev: Device to allocate memory for * @gfp: the GFP mask used in the devm_kmalloc() call when * allocating memory * @fmt: The printf()-style format string * @ap: Arguments for the format string * RETURNS: * Pointer to allocated string on success, NULL on failure. */ char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap) { unsigned int len; char *p; va_list aq; va_copy(aq, ap); len = vsnprintf(NULL, 0, fmt, aq); va_end(aq); p = devm_kmalloc(dev, len+1, gfp); if (!p) return NULL; vsnprintf(p, len+1, fmt, ap); return p; } EXPORT_SYMBOL(devm_kvasprintf); /** * devm_kasprintf - Allocate resource managed space and format a string * into that. * @dev: Device to allocate memory for * @gfp: the GFP mask used in the devm_kmalloc() call when * allocating memory * @fmt: The printf()-style format string * @...: Arguments for the format string * RETURNS: * Pointer to allocated string on success, NULL on failure. */ char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...) { va_list ap; char *p; va_start(ap, fmt); p = devm_kvasprintf(dev, gfp, fmt, ap); va_end(ap); return p; } EXPORT_SYMBOL_GPL(devm_kasprintf); /** * devm_kfree - Resource-managed kfree * @dev: Device this memory belongs to * @p: Memory to free * * Free memory allocated with devm_kmalloc(). */ void devm_kfree(struct device *dev, const void *p) { int rc; /* * Special cases: pointer to a string in .rodata returned by * devm_kstrdup_const() or NULL/ZERO ptr. */ if (unlikely(is_kernel_rodata((unsigned long)p) || ZERO_OR_NULL_PTR(p))) return; rc = devres_destroy(dev, devm_kmalloc_release, devm_kmalloc_match, (void *)p); WARN_ON(rc); } EXPORT_SYMBOL_GPL(devm_kfree); /** * devm_kmemdup - Resource-managed kmemdup * @dev: Device this memory belongs to * @src: Memory region to duplicate * @len: Memory region length * @gfp: GFP mask to use * * Duplicate region of a memory using resource managed kmalloc */ void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp) { void *p; p = devm_kmalloc(dev, len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL_GPL(devm_kmemdup); struct pages_devres { unsigned long addr; unsigned int order; }; static int devm_pages_match(struct device *dev, void *res, void *p) { struct pages_devres *devres = res; struct pages_devres *target = p; return devres->addr == target->addr; } static void devm_pages_release(struct device *dev, void *res) { struct pages_devres *devres = res; free_pages(devres->addr, devres->order); } /** * devm_get_free_pages - Resource-managed __get_free_pages * @dev: Device to allocate memory for * @gfp_mask: Allocation gfp flags * @order: Allocation size is (1 << order) pages * * Managed get_free_pages. Memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Address of allocated memory on success, 0 on failure. */ unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order) { struct pages_devres *devres; unsigned long addr; addr = __get_free_pages(gfp_mask, order); if (unlikely(!addr)) return 0; devres = devres_alloc(devm_pages_release, sizeof(struct pages_devres), GFP_KERNEL); if (unlikely(!devres)) { free_pages(addr, order); return 0; } devres->addr = addr; devres->order = order; devres_add(dev, devres); return addr; } EXPORT_SYMBOL_GPL(devm_get_free_pages); /** * devm_free_pages - Resource-managed free_pages * @dev: Device this memory belongs to * @addr: Memory to free * * Free memory allocated with devm_get_free_pages(). Unlike free_pages, * there is no need to supply the @order. */ void devm_free_pages(struct device *dev, unsigned long addr) { struct pages_devres devres = { .addr = addr }; WARN_ON(devres_release(dev, devm_pages_release, devm_pages_match, &devres)); } EXPORT_SYMBOL_GPL(devm_free_pages); static void devm_percpu_release(struct device *dev, void *pdata) { void __percpu *p; p = *(void __percpu **)pdata; free_percpu(p); } static int devm_percpu_match(struct device *dev, void *data, void *p) { struct devres *devr = container_of(data, struct devres, data); return *(void **)devr->data == p; } /** * __devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @size: Size of per-cpu memory to allocate * @align: Alignment of per-cpu memory to allocate * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align) { void *p; void __percpu *pcpu; pcpu = __alloc_percpu(size, align); if (!pcpu) return NULL; p = devres_alloc(devm_percpu_release, sizeof(void *), GFP_KERNEL); if (!p) { free_percpu(pcpu); return NULL; } *(void __percpu **)p = pcpu; devres_add(dev, p); return pcpu; } EXPORT_SYMBOL_GPL(__devm_alloc_percpu); /** * devm_free_percpu - Resource-managed free_percpu * @dev: Device this memory belongs to * @pdata: Per-cpu memory to free * * Free memory allocated with devm_alloc_percpu(). */ void devm_free_percpu(struct device *dev, void __percpu *pdata) { /* * Use devres_release() to prevent memory leakage as * devm_free_pages() does. */ WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match, (void *)(__force unsigned long)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); |
| 289 290 264 289 12 241 289 290 289 138 100 183 12 26 265 8 8 8 8 262 289 1 8 4 4 9 9 7 7 7 1 9 2 2 2 3 2 3 3 2 3 5 5 5 3 2 5 3 3 3 3 3 2 2 2 2 3 3 2 2 24 77 30 71 73 73 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 | /* * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ipv6.h> #include <net/inet6_hashtables.h> #include <net/addrconf.h> #include "rds.h" #include "loop.h" #define RDS_CONNECTION_HASH_BITS 12 #define RDS_CONNECTION_HASH_ENTRIES (1 << RDS_CONNECTION_HASH_BITS) #define RDS_CONNECTION_HASH_MASK (RDS_CONNECTION_HASH_ENTRIES - 1) /* converting this to RCU is a chore for another day.. */ static DEFINE_SPINLOCK(rds_conn_lock); static unsigned long rds_conn_count; static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES]; static struct kmem_cache *rds_conn_slab; static struct hlist_head *rds_conn_bucket(const struct in6_addr *laddr, const struct in6_addr *faddr) { static u32 rds6_hash_secret __read_mostly; static u32 rds_hash_secret __read_mostly; u32 lhash, fhash, hash; net_get_random_once(&rds_hash_secret, sizeof(rds_hash_secret)); net_get_random_once(&rds6_hash_secret, sizeof(rds6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; #if IS_ENABLED(CONFIG_IPV6) fhash = __ipv6_addr_jhash(faddr, rds6_hash_secret); #else fhash = (__force u32)faddr->s6_addr32[3]; #endif hash = __inet_ehashfn(lhash, 0, fhash, 0, rds_hash_secret); return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK]; } #define rds_conn_info_set(var, test, suffix) do { \ if (test) \ var |= RDS_INFO_CONNECTION_FLAG_##suffix; \ } while (0) /* rcu read lock must be held or the connection spinlock */ static struct rds_connection *rds_conn_lookup(struct net *net, struct hlist_head *head, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, u8 tos, int dev_if) { struct rds_connection *conn, *ret = NULL; hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (ipv6_addr_equal(&conn->c_faddr, faddr) && ipv6_addr_equal(&conn->c_laddr, laddr) && conn->c_trans == trans && conn->c_tos == tos && net == rds_conn_net(conn) && conn->c_dev_if == dev_if) { ret = conn; break; } } rdsdebug("returning conn %p for %pI6c -> %pI6c\n", ret, laddr, faddr); return ret; } /* * This is called by transports as they're bringing down a connection. * It clears partial message state so that the transport can start sending * and receiving over this connection again in the future. It is up to * the transport to have serialized this call with its send and recv. */ static void rds_conn_path_reset(struct rds_conn_path *cp) { struct rds_connection *conn = cp->cp_conn; rdsdebug("connection %pI6c to %pI6c reset\n", &conn->c_laddr, &conn->c_faddr); rds_stats_inc(s_conn_reset); rds_send_path_reset(cp); cp->cp_flags = 0; /* Do not clear next_rx_seq here, else we cannot distinguish * retransmitted packets from new packets, and will hand all * of them to the application. That is not consistent with the * reliability guarantees of RDS. */ } static void __rds_conn_path_init(struct rds_connection *conn, struct rds_conn_path *cp, bool is_outgoing) { spin_lock_init(&cp->cp_lock); cp->cp_next_tx_seq = 1; init_waitqueue_head(&cp->cp_waitq); INIT_LIST_HEAD(&cp->cp_send_queue); INIT_LIST_HEAD(&cp->cp_retrans); cp->cp_conn = conn; atomic_set(&cp->cp_state, RDS_CONN_DOWN); cp->cp_send_gen = 0; cp->cp_reconnect_jiffies = 0; cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION; INIT_DELAYED_WORK(&cp->cp_send_w, rds_send_worker); INIT_DELAYED_WORK(&cp->cp_recv_w, rds_recv_worker); INIT_DELAYED_WORK(&cp->cp_conn_w, rds_connect_worker); INIT_WORK(&cp->cp_down_w, rds_shutdown_worker); mutex_init(&cp->cp_cm_lock); cp->cp_flags = 0; } /* * There is only every one 'conn' for a given pair of addresses in the * system at a time. They contain messages to be retransmitted and so * span the lifetime of the actual underlying transport connections. * * For now they are not garbage collected once they're created. They * are torn down as the module is removed, if ever. */ static struct rds_connection *__rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, gfp_t gfp, u8 tos, int is_outgoing, int dev_if) { struct rds_connection *conn, *parent = NULL; struct hlist_head *head = rds_conn_bucket(laddr, faddr); struct rds_transport *loop_trans; unsigned long flags; int ret, i; int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rcu_read_lock(); conn = rds_conn_lookup(net, head, laddr, faddr, trans, tos, dev_if); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && ipv6_addr_equal(laddr, faddr) && !is_outgoing) { /* This is a looped back IB connection, and we're * called by the code handling the incoming connect. * We need a second connection object into which we * can stick the other QP. */ parent = conn; conn = parent->c_passive; } rcu_read_unlock(); if (conn) goto out; conn = kmem_cache_zalloc(rds_conn_slab, gfp); if (!conn) { conn = ERR_PTR(-ENOMEM); goto out; } conn->c_path = kcalloc(npaths, sizeof(struct rds_conn_path), gfp); if (!conn->c_path) { kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(-ENOMEM); goto out; } INIT_HLIST_NODE(&conn->c_hash_node); conn->c_laddr = *laddr; conn->c_isv6 = !ipv6_addr_v4mapped(laddr); conn->c_faddr = *faddr; conn->c_dev_if = dev_if; conn->c_tos = tos; #if IS_ENABLED(CONFIG_IPV6) /* If the local address is link local, set c_bound_if to be the * index used for this connection. Otherwise, set it to 0 as * the socket is not bound to an interface. c_bound_if is used * to look up a socket when a packet is received */ if (ipv6_addr_type(laddr) & IPV6_ADDR_LINKLOCAL) conn->c_bound_if = dev_if; else #endif conn->c_bound_if = 0; rds_conn_net_set(conn, net); ret = rds_cong_get_maps(conn); if (ret) { kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(ret); goto out; } /* * This is where a connection becomes loopback. If *any* RDS sockets * can bind to the destination address then we'd rather the messages * flow through loopback rather than either transport. */ loop_trans = rds_trans_get_preferred(net, faddr, conn->c_dev_if); if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; if (trans->t_prefer_loopback) { if (likely(is_outgoing)) { /* "outgoing" connection to local address. * Protocol says it wants the connection * handled by the loopback transport. * This is what TCP does. */ trans = &rds_loop_transport; } else { /* No transport currently in use * should end up here, but if it * does, reset/destroy the connection. */ kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(-EOPNOTSUPP); goto out; } } } conn->c_trans = trans; init_waitqueue_head(&conn->c_hs_waitq); for (i = 0; i < npaths; i++) { __rds_conn_path_init(conn, &conn->c_path[i], is_outgoing); conn->c_path[i].cp_index = i; } rcu_read_lock(); if (rds_destroy_pending(conn)) ret = -ENETDOWN; else ret = trans->conn_alloc(conn, GFP_ATOMIC); if (ret) { rcu_read_unlock(); kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(ret); goto out; } rdsdebug("allocated conn %p for %pI6c -> %pI6c over %s %s\n", conn, laddr, faddr, strnlen(trans->t_name, sizeof(trans->t_name)) ? trans->t_name : "[unknown]", is_outgoing ? "(outgoing)" : ""); /* * Since we ran without holding the conn lock, someone could * have created the same conn (either normal or passive) in the * interim. We check while holding the lock. If we won, we complete * init and return our conn. If we lost, we rollback and return the * other one. */ spin_lock_irqsave(&rds_conn_lock, flags); if (parent) { /* Creating passive conn */ if (parent->c_passive) { trans->conn_free(conn->c_path[0].cp_transport_data); kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = parent->c_passive; } else { parent->c_passive = conn; rds_cong_add_conn(conn); rds_conn_count++; } } else { /* Creating normal conn */ struct rds_connection *found; found = rds_conn_lookup(net, head, laddr, faddr, trans, tos, dev_if); if (found) { struct rds_conn_path *cp; int i; for (i = 0; i < npaths; i++) { cp = &conn->c_path[i]; /* The ->conn_alloc invocation may have * allocated resource for all paths, so all * of them may have to be freed here. */ if (cp->cp_transport_data) trans->conn_free(cp->cp_transport_data); } kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = found; } else { conn->c_my_gen_num = rds_gen_num; conn->c_peer_gen_num = 0; hlist_add_head_rcu(&conn->c_hash_node, head); rds_cong_add_conn(conn); rds_conn_count++; } } spin_unlock_irqrestore(&rds_conn_lock, flags); rcu_read_unlock(); out: return conn; } struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, u8 tos, gfp_t gfp, int dev_if) { return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 0, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create); struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, u8 tos, gfp_t gfp, int dev_if) { return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 1, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); void rds_conn_shutdown(struct rds_conn_path *cp) { struct rds_connection *conn = cp->cp_conn; /* shut it down unless it's down already */ if (!rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_DOWN)) { /* * Quiesce the connection mgmt handlers before we start tearing * things down. We don't hold the mutex for the entire * duration of the shutdown operation, else we may be * deadlocking with the CM handler. Instead, the CM event * handler is supposed to check for state DISCONNECTING */ mutex_lock(&cp->cp_cm_lock); if (!rds_conn_path_transition(cp, RDS_CONN_UP, RDS_CONN_DISCONNECTING) && !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DISCONNECTING)) { rds_conn_path_error(cp, "shutdown called in state %d\n", atomic_read(&cp->cp_state)); mutex_unlock(&cp->cp_cm_lock); return; } mutex_unlock(&cp->cp_cm_lock); wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); wait_event(cp->cp_waitq, !test_bit(RDS_RECV_REFILL, &cp->cp_flags)); conn->c_trans->conn_path_shutdown(cp); rds_conn_path_reset(cp); if (!rds_conn_path_transition(cp, RDS_CONN_DISCONNECTING, RDS_CONN_DOWN) && !rds_conn_path_transition(cp, RDS_CONN_ERROR, RDS_CONN_DOWN)) { /* This can happen - eg when we're in the middle of tearing * down the connection, and someone unloads the rds module. * Quite reproducible with loopback connections. * Mostly harmless. * * Note that this also happens with rds-tcp because * we could have triggered rds_conn_path_drop in irq * mode from rds_tcp_state change on the receipt of * a FIN, thus we need to recheck for RDS_CONN_ERROR * here. */ rds_conn_path_error(cp, "%s: failed to transition " "to state DOWN, current state " "is %d\n", __func__, atomic_read(&cp->cp_state)); return; } } /* Then reconnect if it's still live. * The passive side of an IB loopback connection is never added * to the conn hash, so we never trigger a reconnect on this * conn - the reconnect is always triggered by the active peer. */ cancel_delayed_work_sync(&cp->cp_conn_w); rcu_read_lock(); if (!hlist_unhashed(&conn->c_hash_node)) { rcu_read_unlock(); rds_queue_reconnect(cp); } else { rcu_read_unlock(); } } /* destroy a single rds_conn_path. rds_conn_destroy() iterates over * all paths using rds_conn_path_destroy() */ static void rds_conn_path_destroy(struct rds_conn_path *cp) { struct rds_message *rm, *rtmp; if (!cp->cp_transport_data) return; /* make sure lingering queued work won't try to ref the conn */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); rds_conn_path_drop(cp, true); flush_work(&cp->cp_down_w); /* tear down queued messages */ list_for_each_entry_safe(rm, rtmp, &cp->cp_send_queue, m_conn_item) { list_del_init(&rm->m_conn_item); BUG_ON(!list_empty(&rm->m_sock_item)); rds_message_put(rm); } if (cp->cp_xmit_rm) rds_message_put(cp->cp_xmit_rm); WARN_ON(delayed_work_pending(&cp->cp_send_w)); WARN_ON(delayed_work_pending(&cp->cp_recv_w)); WARN_ON(delayed_work_pending(&cp->cp_conn_w)); WARN_ON(work_pending(&cp->cp_down_w)); cp->cp_conn->c_trans->conn_free(cp->cp_transport_data); } /* * Stop and free a connection. * * This can only be used in very limited circumstances. It assumes that once * the conn has been shutdown that no one else is referencing the connection. * We can only ensure this in the rmmod path in the current code. */ void rds_conn_destroy(struct rds_connection *conn) { unsigned long flags; int i; struct rds_conn_path *cp; int npaths = (conn->c_trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rdsdebug("freeing conn %p for %pI4 -> " "%pI4\n", conn, &conn->c_laddr, &conn->c_faddr); /* Ensure conn will not be scheduled for reconnect */ spin_lock_irq(&rds_conn_lock); hlist_del_init_rcu(&conn->c_hash_node); spin_unlock_irq(&rds_conn_lock); synchronize_rcu(); /* shut the connection down */ for (i = 0; i < npaths; i++) { cp = &conn->c_path[i]; rds_conn_path_destroy(cp); BUG_ON(!list_empty(&cp->cp_retrans)); } /* * The congestion maps aren't freed up here. They're * freed by rds_cong_exit() after all the connections * have been freed. */ rds_cong_remove_conn(conn); kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); spin_lock_irqsave(&rds_conn_lock, flags); rds_conn_count--; spin_unlock_irqrestore(&rds_conn_lock, flags); } EXPORT_SYMBOL_GPL(rds_conn_destroy); static void __rds_inc_msg_cp(struct rds_incoming *inc, struct rds_info_iterator *iter, void *saddr, void *daddr, int flip, bool isv6) { #if IS_ENABLED(CONFIG_IPV6) if (isv6) rds6_inc_info_copy(inc, iter, saddr, daddr, flip); else #endif rds_inc_info_copy(inc, iter, *(__be32 *)saddr, *(__be32 *)daddr, flip); } static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, int want_send, bool isv6) { struct hlist_head *head; struct list_head *list; struct rds_connection *conn; struct rds_message *rm; unsigned int total = 0; unsigned long flags; size_t i; int j; if (isv6) len /= sizeof(struct rds6_info_message); else len /= sizeof(struct rds_info_message); rcu_read_lock(); for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { hlist_for_each_entry_rcu(conn, head, c_hash_node) { struct rds_conn_path *cp; int npaths; if (!isv6 && conn->c_isv6) continue; npaths = (conn->c_trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); for (j = 0; j < npaths; j++) { cp = &conn->c_path[j]; if (want_send) list = &cp->cp_send_queue; else list = &cp->cp_retrans; spin_lock_irqsave(&cp->cp_lock, flags); /* XXX too lazy to maintain counts.. */ list_for_each_entry(rm, list, m_conn_item) { total++; if (total <= len) __rds_inc_msg_cp(&rm->m_inc, iter, &conn->c_laddr, &conn->c_faddr, 0, isv6); } spin_unlock_irqrestore(&cp->cp_lock, flags); } } } rcu_read_unlock(); lens->nr = total; if (isv6) lens->each = sizeof(struct rds6_info_message); else lens->each = sizeof(struct rds_info_message); } static void rds_conn_message_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, int want_send) { rds_conn_message_info_cmn(sock, len, iter, lens, want_send, false); } #if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_message_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, int want_send) { rds_conn_message_info_cmn(sock, len, iter, lens, want_send, true); } #endif static void rds_conn_message_info_send(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { rds_conn_message_info(sock, len, iter, lens, 1); } #if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_message_info_send(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { rds6_conn_message_info(sock, len, iter, lens, 1); } #endif static void rds_conn_message_info_retrans(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { rds_conn_message_info(sock, len, iter, lens, 0); } #if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_message_info_retrans(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { rds6_conn_message_info(sock, len, iter, lens, 0); } #endif void rds_for_each_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, int (*visitor)(struct rds_connection *, void *), u64 *buffer, size_t item_len) { struct hlist_head *head; struct rds_connection *conn; size_t i; rcu_read_lock(); lens->nr = 0; lens->each = item_len; for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { hlist_for_each_entry_rcu(conn, head, c_hash_node) { /* XXX no c_lock usage.. */ if (!visitor(conn, buffer)) continue; /* We copy as much as we can fit in the buffer, * but we count all items so that the caller * can resize the buffer. */ if (len >= item_len) { rds_info_copy(iter, buffer, item_len); len -= item_len; } lens->nr++; } } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rds_for_each_conn_info); static void rds_walk_conn_path_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens, int (*visitor)(struct rds_conn_path *, void *), u64 *buffer, size_t item_len) { struct hlist_head *head; struct rds_connection *conn; size_t i; rcu_read_lock(); lens->nr = 0; lens->each = item_len; for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { hlist_for_each_entry_rcu(conn, head, c_hash_node) { struct rds_conn_path *cp; /* XXX We only copy the information from the first * path for now. The problem is that if there are * more than one underlying paths, we cannot report * information of all of them using the existing * API. For example, there is only one next_tx_seq, * which path's next_tx_seq should we report? It is * a bug in the design of MPRDS. */ cp = conn->c_path; /* XXX no cp_lock usage.. */ if (!visitor(cp, buffer)) continue; /* We copy as much as we can fit in the buffer, * but we count all items so that the caller * can resize the buffer. */ if (len >= item_len) { rds_info_copy(iter, buffer, item_len); len -= item_len; } lens->nr++; } } rcu_read_unlock(); } static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer) { struct rds_info_connection *cinfo = buffer; struct rds_connection *conn = cp->cp_conn; if (conn->c_isv6) return 0; cinfo->next_tx_seq = cp->cp_next_tx_seq; cinfo->next_rx_seq = cp->cp_next_rx_seq; cinfo->laddr = conn->c_laddr.s6_addr32[3]; cinfo->faddr = conn->c_faddr.s6_addr32[3]; cinfo->tos = conn->c_tos; strscpy_pad(cinfo->transport, conn->c_trans->t_name); cinfo->flags = 0; rds_conn_info_set(cinfo->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags), SENDING); /* XXX Future: return the state rather than these funky bits */ rds_conn_info_set(cinfo->flags, atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING, CONNECTING); rds_conn_info_set(cinfo->flags, atomic_read(&cp->cp_state) == RDS_CONN_UP, CONNECTED); return 1; } #if IS_ENABLED(CONFIG_IPV6) static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer) { struct rds6_info_connection *cinfo6 = buffer; struct rds_connection *conn = cp->cp_conn; cinfo6->next_tx_seq = cp->cp_next_tx_seq; cinfo6->next_rx_seq = cp->cp_next_rx_seq; cinfo6->laddr = conn->c_laddr; cinfo6->faddr = conn->c_faddr; strscpy_pad(cinfo6->transport, conn->c_trans->t_name); cinfo6->flags = 0; rds_conn_info_set(cinfo6->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags), SENDING); /* XXX Future: return the state rather than these funky bits */ rds_conn_info_set(cinfo6->flags, atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING, CONNECTING); rds_conn_info_set(cinfo6->flags, atomic_read(&cp->cp_state) == RDS_CONN_UP, CONNECTED); /* Just return 1 as there is no error case. This is a helper function * for rds_walk_conn_path_info() and it wants a return value. */ return 1; } #endif static void rds_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { u64 buffer[(sizeof(struct rds_info_connection) + 7) / 8]; rds_walk_conn_path_info(sock, len, iter, lens, rds_conn_info_visitor, buffer, sizeof(struct rds_info_connection)); } #if IS_ENABLED(CONFIG_IPV6) static void rds6_conn_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { u64 buffer[(sizeof(struct rds6_info_connection) + 7) / 8]; rds_walk_conn_path_info(sock, len, iter, lens, rds6_conn_info_visitor, buffer, sizeof(struct rds6_info_connection)); } #endif int rds_conn_init(void) { int ret; ret = rds_loop_net_init(); /* register pernet callback */ if (ret) return ret; rds_conn_slab = KMEM_CACHE(rds_connection, 0); if (!rds_conn_slab) { rds_loop_net_exit(); return -ENOMEM; } rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info); rds_info_register_func(RDS_INFO_SEND_MESSAGES, rds_conn_message_info_send); rds_info_register_func(RDS_INFO_RETRANS_MESSAGES, rds_conn_message_info_retrans); #if IS_ENABLED(CONFIG_IPV6) rds_info_register_func(RDS6_INFO_CONNECTIONS, rds6_conn_info); rds_info_register_func(RDS6_INFO_SEND_MESSAGES, rds6_conn_message_info_send); rds_info_register_func(RDS6_INFO_RETRANS_MESSAGES, rds6_conn_message_info_retrans); #endif return 0; } void rds_conn_exit(void) { rds_loop_net_exit(); /* unregister pernet callback */ rds_loop_exit(); WARN_ON(!hlist_empty(rds_conn_hash)); kmem_cache_destroy(rds_conn_slab); rds_info_deregister_func(RDS_INFO_CONNECTIONS, rds_conn_info); rds_info_deregister_func(RDS_INFO_SEND_MESSAGES, rds_conn_message_info_send); rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES, rds_conn_message_info_retrans); #if IS_ENABLED(CONFIG_IPV6) rds_info_deregister_func(RDS6_INFO_CONNECTIONS, rds6_conn_info); rds_info_deregister_func(RDS6_INFO_SEND_MESSAGES, rds6_conn_message_info_send); rds_info_deregister_func(RDS6_INFO_RETRANS_MESSAGES, rds6_conn_message_info_retrans); #endif } /* * Force a disconnect */ void rds_conn_path_drop(struct rds_conn_path *cp, bool destroy) { atomic_set(&cp->cp_state, RDS_CONN_ERROR); rcu_read_lock(); if (!destroy && rds_destroy_pending(cp->cp_conn)) { rcu_read_unlock(); return; } queue_work(rds_wq, &cp->cp_down_w); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rds_conn_path_drop); void rds_conn_drop(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); rds_conn_path_drop(&conn->c_path[0], false); } EXPORT_SYMBOL_GPL(rds_conn_drop); /* * If the connection is down, trigger a connect. We may have scheduled a * delayed reconnect however - in this case we should not interfere. */ void rds_conn_path_connect_if_down(struct rds_conn_path *cp) { rcu_read_lock(); if (rds_destroy_pending(cp->cp_conn)) { rcu_read_unlock(); return; } if (rds_conn_path_state(cp) == RDS_CONN_DOWN && !test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags)) queue_delayed_work(rds_wq, &cp->cp_conn_w, 0); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down); /* Check connectivity of all paths */ void rds_check_all_paths(struct rds_connection *conn) { int i = 0; do { rds_conn_path_connect_if_down(&conn->c_path[i]); } while (++i < conn->c_npaths); } void rds_conn_connect_if_down(struct rds_connection *conn) { WARN_ON(conn->c_trans->t_mp_capable); rds_conn_path_connect_if_down(&conn->c_path[0]); } EXPORT_SYMBOL_GPL(rds_conn_connect_if_down); void __rds_conn_path_error(struct rds_conn_path *cp, const char *fmt, ...) { va_list ap; va_start(ap, fmt); vprintk(fmt, ap); va_end(ap); rds_conn_path_drop(cp, false); } |
| 73 1 1 1 6 64 63 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 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-only /* String matching match for iptables * * (C) 2005 Pablo Neira Ayuso <pablo@eurodev.net> */ #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_string.h> #include <linux/textsearch.h> MODULE_AUTHOR("Pablo Neira Ayuso <pablo@eurodev.net>"); MODULE_DESCRIPTION("Xtables: string-based matching"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_string"); MODULE_ALIAS("ip6t_string"); MODULE_ALIAS("ebt_string"); static bool string_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_string_info *conf = par->matchinfo; bool invert; invert = conf->u.v1.flags & XT_STRING_FLAG_INVERT; return (skb_find_text((struct sk_buff *)skb, conf->from_offset, conf->to_offset, conf->config) != UINT_MAX) ^ invert; } #define STRING_TEXT_PRIV(m) ((struct xt_string_info *)(m)) static int string_mt_check(const struct xt_mtchk_param *par) { struct xt_string_info *conf = par->matchinfo; struct ts_config *ts_conf; int flags = TS_AUTOLOAD; /* Damn, can't handle this case properly with iptables... */ if (conf->from_offset > conf->to_offset) return -EINVAL; if (conf->algo[XT_STRING_MAX_ALGO_NAME_SIZE - 1] != '\0') return -EINVAL; if (conf->patlen > XT_STRING_MAX_PATTERN_SIZE) return -EINVAL; if (conf->u.v1.flags & ~(XT_STRING_FLAG_IGNORECASE | XT_STRING_FLAG_INVERT)) return -EINVAL; if (conf->u.v1.flags & XT_STRING_FLAG_IGNORECASE) flags |= TS_IGNORECASE; ts_conf = textsearch_prepare(conf->algo, conf->pattern, conf->patlen, GFP_KERNEL, flags); if (IS_ERR(ts_conf)) return PTR_ERR(ts_conf); conf->config = ts_conf; return 0; } static void string_mt_destroy(const struct xt_mtdtor_param *par) { textsearch_destroy(STRING_TEXT_PRIV(par->matchinfo)->config); } static struct xt_match xt_string_mt_reg __read_mostly = { .name = "string", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = string_mt_check, .match = string_mt, .destroy = string_mt_destroy, .matchsize = sizeof(struct xt_string_info), .usersize = offsetof(struct xt_string_info, config), .me = THIS_MODULE, }; static int __init string_mt_init(void) { return xt_register_match(&xt_string_mt_reg); } static void __exit string_mt_exit(void) { xt_unregister_match(&xt_string_mt_reg); } module_init(string_mt_init); module_exit(string_mt_exit); |
| 3 3 1 2 2 2 2 2 1 4 1 5 5 1 4 2 2 2 2 2 2 4 4 4 4 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_skbprio.c SKB Priority Queue. * * Authors: Nishanth Devarajan, <ndev2021@gmail.com> * Cody Doucette, <doucette@bu.edu> * original idea by Michel Machado, Cody Doucette, and Qiaobin Fu */ #include <linux/string.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/pkt_sched.h> #include <net/sch_generic.h> #include <net/inet_ecn.h> /* SKB Priority Queue * ================================= * * Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes * packets according to their skb->priority field. Under congestion, * Skbprio drops already-enqueued lower priority packets to make space * available for higher priority packets; it was conceived as a solution * for denial-of-service defenses that need to route packets with different * priorities as a mean to overcome DoS attacks. */ struct skbprio_sched_data { /* Queue state. */ struct sk_buff_head qdiscs[SKBPRIO_MAX_PRIORITY]; struct gnet_stats_queue qstats[SKBPRIO_MAX_PRIORITY]; u16 highest_prio; u16 lowest_prio; }; static u16 calc_new_high_prio(const struct skbprio_sched_data *q) { int prio; for (prio = q->highest_prio - 1; prio >= q->lowest_prio; prio--) { if (!skb_queue_empty(&q->qdiscs[prio])) return prio; } /* SKB queue is empty, return 0 (default highest priority setting). */ return 0; } static u16 calc_new_low_prio(const struct skbprio_sched_data *q) { int prio; for (prio = q->lowest_prio + 1; prio <= q->highest_prio; prio++) { if (!skb_queue_empty(&q->qdiscs[prio])) return prio; } /* SKB queue is empty, return SKBPRIO_MAX_PRIORITY - 1 * (default lowest priority setting). */ return SKBPRIO_MAX_PRIORITY - 1; } static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1; struct skbprio_sched_data *q = qdisc_priv(sch); struct sk_buff_head *qdisc; struct sk_buff_head *lp_qdisc; struct sk_buff *to_drop; u16 prio, lp; /* Obtain the priority of @skb. */ prio = min(skb->priority, max_priority); qdisc = &q->qdiscs[prio]; /* sch->limit can change under us from skbprio_change() */ if (sch->q.qlen < READ_ONCE(sch->limit)) { __skb_queue_tail(qdisc, skb); qdisc_qstats_backlog_inc(sch, skb); q->qstats[prio].backlog += qdisc_pkt_len(skb); /* Check to update highest and lowest priorities. */ if (prio > q->highest_prio) q->highest_prio = prio; if (prio < q->lowest_prio) q->lowest_prio = prio; sch->q.qlen++; return NET_XMIT_SUCCESS; } /* If this packet has the lowest priority, drop it. */ lp = q->lowest_prio; if (prio <= lp) { q->qstats[prio].drops++; q->qstats[prio].overlimits++; return qdisc_drop(skb, sch, to_free); } __skb_queue_tail(qdisc, skb); qdisc_qstats_backlog_inc(sch, skb); q->qstats[prio].backlog += qdisc_pkt_len(skb); /* Drop the packet at the tail of the lowest priority qdisc. */ lp_qdisc = &q->qdiscs[lp]; to_drop = __skb_dequeue_tail(lp_qdisc); BUG_ON(!to_drop); qdisc_qstats_backlog_dec(sch, to_drop); qdisc_drop(to_drop, sch, to_free); q->qstats[lp].backlog -= qdisc_pkt_len(to_drop); q->qstats[lp].drops++; q->qstats[lp].overlimits++; /* Check to update highest and lowest priorities. */ if (skb_queue_empty(lp_qdisc)) { if (q->lowest_prio == q->highest_prio) { q->lowest_prio = prio; q->highest_prio = prio; } else { q->lowest_prio = calc_new_low_prio(q); } } if (prio > q->highest_prio) q->highest_prio = prio; return NET_XMIT_CN; } static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) { struct skbprio_sched_data *q = qdisc_priv(sch); struct sk_buff_head *hpq = &q->qdiscs[q->highest_prio]; struct sk_buff *skb = __skb_dequeue(hpq); if (unlikely(!skb)) return NULL; sch->q.qlen--; qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); q->qstats[q->highest_prio].backlog -= qdisc_pkt_len(skb); /* Update highest priority field. */ if (skb_queue_empty(hpq)) { if (q->lowest_prio == q->highest_prio) { q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } else { q->highest_prio = calc_new_high_prio(q); } } return skb; } static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct tc_skbprio_qopt *ctl = nla_data(opt); if (opt->nla_len != nla_attr_size(sizeof(*ctl))) return -EINVAL; WRITE_ONCE(sch->limit, ctl->limit); return 0; } static int skbprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct skbprio_sched_data *q = qdisc_priv(sch); int prio; /* Initialise all queues, one for each possible priority. */ for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_head_init(&q->qdiscs[prio]); memset(&q->qstats, 0, sizeof(q->qstats)); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; sch->limit = 64; if (!opt) return 0; return skbprio_change(sch, opt, extack); } static int skbprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_skbprio_qopt opt; opt.limit = READ_ONCE(sch->limit); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) return -1; return skb->len; } static void skbprio_reset(struct Qdisc *sch) { struct skbprio_sched_data *q = qdisc_priv(sch); int prio; for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_purge(&q->qdiscs[prio]); memset(&q->qstats, 0, sizeof(q->qstats)); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } static void skbprio_destroy(struct Qdisc *sch) { struct skbprio_sched_data *q = qdisc_priv(sch); int prio; for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++) __skb_queue_purge(&q->qdiscs[prio]); } static struct Qdisc *skbprio_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; } static unsigned long skbprio_find(struct Qdisc *sch, u32 classid) { return 0; } static int skbprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { tcm->tcm_handle |= TC_H_MIN(cl); return 0; } static int skbprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct skbprio_sched_data *q = qdisc_priv(sch); if (gnet_stats_copy_queue(d, NULL, &q->qstats[cl - 1], q->qstats[cl - 1].qlen) < 0) return -1; return 0; } static void skbprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) { unsigned int i; if (arg->stop) return; for (i = 0; i < SKBPRIO_MAX_PRIORITY; i++) { if (!tc_qdisc_stats_dump(sch, i + 1, arg)) break; } } static const struct Qdisc_class_ops skbprio_class_ops = { .leaf = skbprio_leaf, .find = skbprio_find, .dump = skbprio_dump_class, .dump_stats = skbprio_dump_class_stats, .walk = skbprio_walk, }; static struct Qdisc_ops skbprio_qdisc_ops __read_mostly = { .cl_ops = &skbprio_class_ops, .id = "skbprio", .priv_size = sizeof(struct skbprio_sched_data), .enqueue = skbprio_enqueue, .dequeue = skbprio_dequeue, .peek = qdisc_peek_dequeued, .init = skbprio_init, .reset = skbprio_reset, .change = skbprio_change, .dump = skbprio_dump, .destroy = skbprio_destroy, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("skbprio"); static int __init skbprio_module_init(void) { return register_qdisc(&skbprio_qdisc_ops); } static void __exit skbprio_module_exit(void) { unregister_qdisc(&skbprio_qdisc_ops); } module_init(skbprio_module_init) module_exit(skbprio_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SKB priority based scheduling qdisc"); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include "netlink.h" #include "common.h" #include "bitset.h" #include "../core/dev.h" #include "ts.h" struct tsconfig_req_info { struct ethnl_req_info base; }; struct tsconfig_reply_data { struct ethnl_reply_data base; struct hwtstamp_provider_desc hwprov_desc; struct { u32 tx_type; u32 rx_filter; u32 flags; } hwtst_config; }; #define TSCONFIG_REPDATA(__reply_base) \ container_of(__reply_base, struct tsconfig_reply_data, base) const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1] = { [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int tsconfig_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); struct hwtstamp_provider *hwprov = NULL; struct net_device *dev = reply_base->dev; struct kernel_hwtstamp_config cfg = {}; int ret; if (!dev->netdev_ops->ndo_hwtstamp_get) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev_get_hwtstamp_phylib(dev, &cfg); if (ret) goto out; data->hwtst_config.tx_type = BIT(cfg.tx_type); data->hwtst_config.rx_filter = BIT(cfg.rx_filter); data->hwtst_config.flags = cfg.flags; data->hwprov_desc.index = -1; hwprov = rtnl_dereference(dev->hwprov); if (hwprov) { data->hwprov_desc.index = hwprov->desc.index; data->hwprov_desc.qualifier = hwprov->desc.qualifier; } else { struct kernel_ethtool_ts_info ts_info = {}; ts_info.phc_index = -1; ret = __ethtool_get_ts_info(dev, &ts_info); if (ret) goto out; if (ts_info.phc_index == -1) return -ENODEV; data->hwprov_desc.index = ts_info.phc_index; data->hwprov_desc.qualifier = ts_info.phc_qualifier; } out: ethnl_ops_complete(dev); return ret; } static int tsconfig_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int len = 0; int ret; BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_FLAG_CNT > 32); if (data->hwtst_config.flags) { ret = ethnl_bitset32_size(&data->hwtst_config.flags, NULL, __HWTSTAMP_FLAG_CNT, ts_flags_names, compact); if (ret < 0) return ret; len += ret; /* _TSCONFIG_HWTSTAMP_FLAGS */ } if (data->hwtst_config.tx_type) { ret = ethnl_bitset32_size(&data->hwtst_config.tx_type, NULL, __HWTSTAMP_TX_CNT, ts_tx_type_names, compact); if (ret < 0) return ret; len += ret; /* _TSCONFIG_TX_TYPES */ } if (data->hwtst_config.rx_filter) { ret = ethnl_bitset32_size(&data->hwtst_config.rx_filter, NULL, __HWTSTAMP_FILTER_CNT, ts_rx_filter_names, compact); if (ret < 0) return ret; len += ret; /* _TSCONFIG_RX_FILTERS */ } if (data->hwprov_desc.index >= 0) /* _TSCONFIG_HWTSTAMP_PROVIDER */ len += nla_total_size(0) + 2 * nla_total_size(sizeof(u32)); return len; } static int tsconfig_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct tsconfig_reply_data *data = TSCONFIG_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int ret; if (data->hwtst_config.flags) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, &data->hwtst_config.flags, NULL, __HWTSTAMP_FLAG_CNT, ts_flags_names, compact); if (ret < 0) return ret; } if (data->hwtst_config.tx_type) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_TX_TYPES, &data->hwtst_config.tx_type, NULL, __HWTSTAMP_TX_CNT, ts_tx_type_names, compact); if (ret < 0) return ret; } if (data->hwtst_config.rx_filter) { ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_RX_FILTERS, &data->hwtst_config.rx_filter, NULL, __HWTSTAMP_FILTER_CNT, ts_rx_filter_names, compact); if (ret < 0) return ret; } if (data->hwprov_desc.index >= 0) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_INDEX, data->hwprov_desc.index) || nla_put_u32(skb, ETHTOOL_A_TS_HWTSTAMP_PROVIDER_QUALIFIER, data->hwprov_desc.qualifier)) { nla_nest_cancel(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest); } return 0; } /* TSCONFIG_SET */ const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1] = { [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER] = NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), [ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS] = { .type = NLA_NESTED }, [ETHTOOL_A_TSCONFIG_RX_FILTERS] = { .type = NLA_NESTED }, [ETHTOOL_A_TSCONFIG_TX_TYPES] = { .type = NLA_NESTED }, }; static int tsconfig_send_reply(struct net_device *dev, struct genl_info *info) { struct tsconfig_reply_data *reply_data; struct tsconfig_req_info *req_info; struct sk_buff *rskb; void *reply_payload; int reply_len = 0; int ret; req_info = kzalloc(sizeof(*req_info), GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(sizeof(*reply_data), GFP_KERNEL); if (!reply_data) { kfree(req_info); return -ENOMEM; } ASSERT_RTNL(); reply_data->base.dev = dev; ret = tsconfig_prepare_data(&req_info->base, &reply_data->base, info); if (ret < 0) goto err_cleanup; ret = tsconfig_reply_size(&req_info->base, &reply_data->base); if (ret < 0) goto err_cleanup; reply_len = ret + ethnl_reply_header_size(); rskb = ethnl_reply_init(reply_len, dev, ETHTOOL_MSG_TSCONFIG_SET_REPLY, ETHTOOL_A_TSCONFIG_HEADER, info, &reply_payload); if (!rskb) goto err_cleanup; ret = tsconfig_fill_reply(rskb, &req_info->base, &reply_data->base); if (ret < 0) goto err_cleanup; genlmsg_end(rskb, reply_payload); ret = genlmsg_reply(rskb, info); err_cleanup: kfree(reply_data); kfree(req_info); return ret; } static int ethnl_set_tsconfig_validate(struct ethnl_req_info *req_base, struct genl_info *info) { const struct net_device_ops *ops = req_base->dev->netdev_ops; if (!ops->ndo_hwtstamp_set || !ops->ndo_hwtstamp_get) return -EOPNOTSUPP; return 1; } static struct hwtstamp_provider * tsconfig_set_hwprov_from_desc(struct net_device *dev, struct genl_info *info, struct hwtstamp_provider_desc *hwprov_desc) { struct kernel_ethtool_ts_info ts_info; struct hwtstamp_provider *hwprov; struct nlattr **tb = info->attrs; struct phy_device *phy = NULL; enum hwtstamp_source source; int ret; ret = ethtool_net_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); if (!ret) { /* Found */ source = HWTSTAMP_SOURCE_NETDEV; } else { phy = ethtool_phy_get_ts_info_by_phc(dev, &ts_info, hwprov_desc); if (IS_ERR(phy)) { if (PTR_ERR(phy) == -ENODEV) NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], "phc not in this net device topology"); return ERR_CAST(phy); } source = HWTSTAMP_SOURCE_PHYLIB; } hwprov = kzalloc(sizeof(*hwprov), GFP_KERNEL); if (!hwprov) return ERR_PTR(-ENOMEM); hwprov->desc.index = hwprov_desc->index; hwprov->desc.qualifier = hwprov_desc->qualifier; hwprov->source = source; hwprov->phydev = phy; return hwprov; } static int ethnl_set_tsconfig(struct ethnl_req_info *req_base, struct genl_info *info) { struct kernel_hwtstamp_config hwtst_config = {0}; bool hwprov_mod = false, config_mod = false; struct hwtstamp_provider *hwprov = NULL; struct net_device *dev = req_base->dev; struct nlattr **tb = info->attrs; int ret; BUILD_BUG_ON(__HWTSTAMP_TX_CNT >= 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT >= 32); BUILD_BUG_ON(__HWTSTAMP_FLAG_CNT > 32); if (!netif_device_present(dev)) return -ENODEV; if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER]) { struct hwtstamp_provider_desc __hwprov_desc = {.index = -1}; struct hwtstamp_provider *__hwprov; __hwprov = rtnl_dereference(dev->hwprov); if (__hwprov) { __hwprov_desc.index = __hwprov->desc.index; __hwprov_desc.qualifier = __hwprov->desc.qualifier; } ret = ts_parse_hwtst_provider(tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER], &__hwprov_desc, info->extack, &hwprov_mod); if (ret < 0) return ret; if (hwprov_mod) { hwprov = tsconfig_set_hwprov_from_desc(dev, info, &__hwprov_desc); if (IS_ERR(hwprov)) return PTR_ERR(hwprov); } } /* Get current hwtstamp config if we are not changing the * hwtstamp source. It will be zeroed in the other case. */ if (!hwprov_mod) { ret = dev_get_hwtstamp_phylib(dev, &hwtst_config); if (ret < 0 && ret != -EOPNOTSUPP) goto err_free_hwprov; } /* Get the hwtstamp config from netlink */ if (tb[ETHTOOL_A_TSCONFIG_TX_TYPES]) { u32 req_tx_type; req_tx_type = BIT(hwtst_config.tx_type); ret = ethnl_update_bitset32(&req_tx_type, __HWTSTAMP_TX_CNT, tb[ETHTOOL_A_TSCONFIG_TX_TYPES], ts_tx_type_names, info->extack, &config_mod); if (ret < 0) goto err_free_hwprov; /* Select only one tx type at a time */ if (ffs(req_tx_type) != fls(req_tx_type)) { ret = -EINVAL; goto err_free_hwprov; } hwtst_config.tx_type = ffs(req_tx_type) - 1; } if (tb[ETHTOOL_A_TSCONFIG_RX_FILTERS]) { u32 req_rx_filter; req_rx_filter = BIT(hwtst_config.rx_filter); ret = ethnl_update_bitset32(&req_rx_filter, __HWTSTAMP_FILTER_CNT, tb[ETHTOOL_A_TSCONFIG_RX_FILTERS], ts_rx_filter_names, info->extack, &config_mod); if (ret < 0) goto err_free_hwprov; /* Select only one rx filter at a time */ if (ffs(req_rx_filter) != fls(req_rx_filter)) { ret = -EINVAL; goto err_free_hwprov; } hwtst_config.rx_filter = ffs(req_rx_filter) - 1; } if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS]) { ret = ethnl_update_bitset32(&hwtst_config.flags, __HWTSTAMP_FLAG_CNT, tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS], ts_flags_names, info->extack, &config_mod); if (ret < 0) goto err_free_hwprov; } ret = net_hwtstamp_validate(&hwtst_config); if (ret) goto err_free_hwprov; if (hwprov_mod) { struct kernel_hwtstamp_config zero_config = {0}; struct hwtstamp_provider *__hwprov; /* Disable current time stamping if we try to enable * another one */ ret = dev_set_hwtstamp_phylib(dev, &zero_config, info->extack); if (ret < 0) goto err_free_hwprov; /* Change the selected hwtstamp source */ __hwprov = rcu_replace_pointer_rtnl(dev->hwprov, hwprov); if (__hwprov) kfree_rcu(__hwprov, rcu_head); } if (config_mod) { ret = dev_set_hwtstamp_phylib(dev, &hwtst_config, info->extack); if (ret < 0) return ret; } if (hwprov_mod || config_mod) { ret = tsconfig_send_reply(dev, info); if (ret && ret != -EOPNOTSUPP) { NL_SET_ERR_MSG(info->extack, "error while reading the new configuration set"); return ret; } } /* tsconfig has no notification */ return 0; err_free_hwprov: kfree(hwprov); return ret; } const struct ethnl_request_ops ethnl_tsconfig_request_ops = { .request_cmd = ETHTOOL_MSG_TSCONFIG_GET, .reply_cmd = ETHTOOL_MSG_TSCONFIG_GET_REPLY, .hdr_attr = ETHTOOL_A_TSCONFIG_HEADER, .req_info_size = sizeof(struct tsconfig_req_info), .reply_data_size = sizeof(struct tsconfig_reply_data), .prepare_data = tsconfig_prepare_data, .reply_size = tsconfig_reply_size, .fill_reply = tsconfig_fill_reply, .set_validate = ethnl_set_tsconfig_validate, .set = ethnl_set_tsconfig, }; |
| 851 851 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_PGTABLE_INVERT_H #define _ASM_PGTABLE_INVERT_H 1 #ifndef __ASSEMBLER__ /* * A clear pte value is special, and doesn't get inverted. * * Note that even users that only pass a pgprot_t (rather * than a full pte) won't trigger the special zero case, * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED * set. So the all zero case really is limited to just the * cleared page table entry case. */ static inline bool __pte_needs_invert(u64 val) { return val && !(val & _PAGE_PRESENT); } /* Get a mask to xor with the page table entry to get the correct pfn. */ static inline u64 protnone_mask(u64 val) { return __pte_needs_invert(val) ? ~0ull : 0; } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) { /* * When a PTE transitions from NONE to !NONE or vice-versa * invert the PFN part to stop speculation. * pte_pfn undoes this when needed. */ if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) val = (val & ~mask) | (~val & mask); return val; } #endif /* __ASSEMBLER__ */ #endif |
| 10 6 3 4 4 2 3 11 11 52 41 11 37 10 29 12 23 10 10 17 9 9 16 3 3 6 11 11 3 6 5 4 382 330 5 4 1 2 1 2 16 16 3 215 3 152 92 3 2 10 2 16 10 2 3 2 61 3 24 38 5 27 2 5 18 14 5 5 10 10 5 5 10 10 5 3 2 2 2 2 1 2 13 31 51 36 15 35 4 46 46 46 5 26 19 18 3 4 4 180 180 5 180 33 2 29 3 1 25 26 26 1 8 6 7 2 40 1 39 2 1 33 40 1 39 1 38 1 1642 133 73 28 29 1 41 15 7 120 1390 4 4 5 4 4 4 2 1 2 4 2 2 1 4 1 5 1 3 1 3 1 1 1 9 1 7 1 2 6 1 1 1 1 1 1 1 1 1 2 5 4 8 2 1 5 1172 227 178 14 27 35 19 35 1 35 79 2 1 1 1 1 1 2 1 4 2 2 2 1 1 2 1 1 1 2 34 4 19 23 2 1 1 30 3 1 25 1 1 5 17 7 4 40 40 1 39 1021 92 2 90 21 3 3 90 1640 5 615 1 1018 11 1 10 6 3 219 1 8 6 206 147 2 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 5 2 1 3 2 1 18 8 10 10 8 12 6 1 1 1 1 1 1 9 11 3 120 1 18 17 217 101 1 79 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The IP to API glue. * * Authors: see ip.c * * Fixes: * Many : Split from ip.c , see ip.c for history. * Martin Mares : TOS setting fixed. * Alan Cox : Fixed a couple of oopses in Martin's * TOS tweaks. * Mike McLagan : Routing by source */ #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/tcp_states.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/netfilter.h> #include <linux/route.h> #include <linux/mroute.h> #include <net/inet_ecn.h> #include <net/route.h> #include <net/xfrm.h> #include <net/compat.h> #include <net/checksum.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/transp_v6.h> #endif #include <net/ip_fib.h> #include <linux/errqueue.h> #include <linux/uaccess.h> /* * SOL_IP control messages. */ static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct in_pktinfo info = *PKTINFO_SKB_CB(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } static void ip_cmsg_recv_ttl(struct msghdr *msg, struct sk_buff *skb) { int ttl = ip_hdr(skb)->ttl; put_cmsg(msg, SOL_IP, IP_TTL, sizeof(int), &ttl); } static void ip_cmsg_recv_tos(struct msghdr *msg, struct sk_buff *skb) { put_cmsg(msg, SOL_IP, IP_TOS, 1, &ip_hdr(skb)->tos); } static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) { if (IPCB(skb)->opt.optlen == 0) return; put_cmsg(msg, SOL_IP, IP_RECVOPTS, IPCB(skb)->opt.optlen, ip_hdr(skb) + 1); } static void ip_cmsg_recv_retopts(struct net *net, struct msghdr *msg, struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; if (IPCB(skb)->opt.optlen == 0) return; if (ip_options_echo(net, opt, skb)) { msg->msg_flags |= MSG_CTRUNC; return; } ip_options_undo(opt); put_cmsg(msg, SOL_IP, IP_RETOPTS, opt->optlen, opt->__data); } static void ip_cmsg_recv_fragsize(struct msghdr *msg, struct sk_buff *skb) { int val; if (IPCB(skb)->frag_max_size == 0) return; val = IPCB(skb)->frag_max_size; put_cmsg(msg, SOL_IP, IP_RECVFRAGSIZE, sizeof(val), &val); } static void ip_cmsg_recv_checksum(struct msghdr *msg, struct sk_buff *skb, int tlen, int offset) { __wsum csum = skb->csum; if (skb->ip_summed != CHECKSUM_COMPLETE) return; if (offset != 0) { int tend_off = skb_transport_offset(skb) + tlen; csum = csum_sub(csum, skb_checksum(skb, tend_off, offset, 0)); } put_cmsg(msg, SOL_IP, IP_CHECKSUM, sizeof(__wsum), &csum); } static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) { struct lsm_context ctx; u32 secid; int err; err = security_socket_getpeersec_dgram(NULL, skb, &secid); if (err) return; err = security_secid_to_secctx(secid, &ctx); if (err < 0) return; put_cmsg(msg, SOL_IP, SCM_SECURITY, ctx.len, ctx.context); security_release_secctx(&ctx); } static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { __be16 _ports[2], *ports; struct sockaddr_in sin; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ ports = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_ports), &_ports); if (!ports) return; sin.sin_family = AF_INET; sin.sin_addr.s_addr = ip_hdr(skb)->daddr; sin.sin_port = ports[1]; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin); } void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, int tlen, int offset) { unsigned long flags = inet_cmsg_flags(inet_sk(sk)); if (!flags) return; /* Ordered by supposed usage frequency */ if (flags & IP_CMSG_PKTINFO) { ip_cmsg_recv_pktinfo(msg, skb); flags &= ~IP_CMSG_PKTINFO; if (!flags) return; } if (flags & IP_CMSG_TTL) { ip_cmsg_recv_ttl(msg, skb); flags &= ~IP_CMSG_TTL; if (!flags) return; } if (flags & IP_CMSG_TOS) { ip_cmsg_recv_tos(msg, skb); flags &= ~IP_CMSG_TOS; if (!flags) return; } if (flags & IP_CMSG_RECVOPTS) { ip_cmsg_recv_opts(msg, skb); flags &= ~IP_CMSG_RECVOPTS; if (!flags) return; } if (flags & IP_CMSG_RETOPTS) { ip_cmsg_recv_retopts(sock_net(sk), msg, skb); flags &= ~IP_CMSG_RETOPTS; if (!flags) return; } if (flags & IP_CMSG_PASSSEC) { ip_cmsg_recv_security(msg, skb); flags &= ~IP_CMSG_PASSSEC; if (!flags) return; } if (flags & IP_CMSG_ORIGDSTADDR) { ip_cmsg_recv_dstaddr(msg, skb); flags &= ~IP_CMSG_ORIGDSTADDR; if (!flags) return; } if (flags & IP_CMSG_CHECKSUM) ip_cmsg_recv_checksum(msg, skb, tlen, offset); if (flags & IP_CMSG_RECVFRAGSIZE) ip_cmsg_recv_fragsize(msg, skb); } EXPORT_SYMBOL(ip_cmsg_recv_offset); int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; struct net *net = sock_net(sk); for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; #if IS_ENABLED(CONFIG_IPV6) if (allow_ipv6 && cmsg->cmsg_level == SOL_IPV6 && cmsg->cmsg_type == IPV6_PKTINFO) { struct in6_pktinfo *src_info; if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) return -EINVAL; src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) return -EINVAL; if (src_info->ipi6_ifindex) ipc->oif = src_info->ipi6_ifindex; ipc->addr = src_info->ipi6_addr.s6_addr32[3]; continue; } #endif if (cmsg->cmsg_level == SOL_SOCKET) { err = __sock_cmsg_send(sk, cmsg, &ipc->sockc); if (err) return err; continue; } if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - sizeof(struct cmsghdr); /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, KERNEL_SOCKPTR(CMSG_DATA(cmsg)), err < 40 ? err : 40); if (err) return err; break; case IP_PKTINFO: { struct in_pktinfo *info; if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct in_pktinfo))) return -EINVAL; info = (struct in_pktinfo *)CMSG_DATA(cmsg); if (info->ipi_ifindex) ipc->oif = info->ipi_ifindex; ipc->addr = info->ipi_spec_dst.s_addr; break; } case IP_TTL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) return -EINVAL; val = *(int *)CMSG_DATA(cmsg); if (val < 1 || val > 255) return -EINVAL; ipc->ttl = val; break; case IP_TOS: if (cmsg->cmsg_len == CMSG_LEN(sizeof(int))) val = *(int *)CMSG_DATA(cmsg); else if (cmsg->cmsg_len == CMSG_LEN(sizeof(u8))) val = *(u8 *)CMSG_DATA(cmsg); else return -EINVAL; if (val < 0 || val > 255) return -EINVAL; ipc->tos = val; ipc->sockc.priority = rt_tos2priority(ipc->tos); break; case IP_PROTOCOL: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) return -EINVAL; val = *(int *)CMSG_DATA(cmsg); if (val < 1 || val > 255) return -EINVAL; ipc->protocol = val; break; default: return -EINVAL; } } return 0; } static void ip_ra_destroy_rcu(struct rcu_head *head) { struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu); sock_put(ra->saved_sk); kfree(ra); } int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)) { struct ip_ra_chain *ra, *new_ra; struct ip_ra_chain __rcu **rap; struct net *net = sock_net(sk); if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW) return -EINVAL; new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; if (on && !new_ra) return -ENOMEM; mutex_lock(&net->ipv4.ra_mutex); for (rap = &net->ipv4.ra_chain; (ra = rcu_dereference_protected(*rap, lockdep_is_held(&net->ipv4.ra_mutex))) != NULL; rap = &ra->next) { if (ra->sk == sk) { if (on) { mutex_unlock(&net->ipv4.ra_mutex); kfree(new_ra); return -EADDRINUSE; } /* dont let ip_call_ra_chain() use sk again */ ra->sk = NULL; RCU_INIT_POINTER(*rap, ra->next); mutex_unlock(&net->ipv4.ra_mutex); if (ra->destructor) ra->destructor(sk); /* * Delay sock_put(sk) and kfree(ra) after one rcu grace * period. This guarantee ip_call_ra_chain() dont need * to mess with socket refcounts. */ ra->saved_sk = sk; call_rcu(&ra->rcu, ip_ra_destroy_rcu); return 0; } } if (!new_ra) { mutex_unlock(&net->ipv4.ra_mutex); return -ENOBUFS; } new_ra->sk = sk; new_ra->destructor = destructor; RCU_INIT_POINTER(new_ra->next, ra); rcu_assign_pointer(*rap, new_ra); sock_hold(sk); mutex_unlock(&net->ipv4.ra_mutex); return 0; } static void ipv4_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out) { switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: case ICMP_TIME_EXCEEDED: case ICMP_PARAMETERPROB: ip_icmp_error_rfc4884(skb, out, sizeof(struct icmphdr), icmp_hdr(skb)->un.reserved[1] * 4); } } void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { struct sock_exterr_skb *serr; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP; serr->ee.ee_type = icmp_hdr(skb)->type; serr->ee.ee_code = icmp_hdr(skb)->code; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&(((struct iphdr *)(icmp_hdr(skb) + 1))->daddr) - skb_network_header(skb); serr->port = port; if (skb_pull(skb, payload - skb->data)) { if (inet_test_bit(RECVERR_RFC4884, sk)) ipv4_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb) == 0) return; } kfree_skb(skb); } EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { struct sock_exterr_skb *serr; struct iphdr *iph; struct sk_buff *skb; if (!inet_test_bit(RECVERR, sk)) return; skb = alloc_skb(sizeof(struct iphdr), GFP_ATOMIC); if (!skb) return; skb_put(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->daddr = daddr; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_type = 0; serr->ee.ee_code = 0; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); serr->port = port; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } /* For some errors we have valid addr_offset even with zero payload and * zero port. Also, addr_offset should be supported if port is set. */ static inline bool ipv4_datagram_support_addr(struct sock_exterr_skb *serr) { return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port; } /* IPv4 supports cmsg on all imcp errors and some timestamps * * Timestamp code paths do not initialize the fields expected by cmsg: * the PKTINFO fields in skb->cb[]. Fill those in here. */ static bool ipv4_datagram_support_cmsg(const struct sock *sk, struct sk_buff *skb, int ee_origin) { struct in_pktinfo *info; if (ee_origin == SO_EE_ORIGIN_ICMP) return true; if (ee_origin == SO_EE_ORIGIN_LOCAL) return false; /* Support IP_PKTINFO on tstamp packets if requested, to correlate * timestamp with egress dev. Not possible for packets without iif * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ info = PKTINFO_SKB_CB(skb); if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) || !info->ipi_ifindex) return false; info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr; return true; } /* * Handle MSG_ERRQUEUE */ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct sock_exterr_skb *serr; struct sk_buff *skb; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in offender; } errhdr; int err; int copied; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) 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 (unlikely(err)) { kfree_skb(skb); return err; } sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); if (sin && ipv4_datagram_support_addr(serr)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset); sin->sin_port = serr->port; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); if (ipv4_datagram_support_cmsg(sk, skb, serr->ee.ee_origin)) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } put_cmsg(msg, SOL_IP, IP_RECVERR, sizeof(errhdr), &errhdr); /* Now we could try to dump offended packet options */ msg->msg_flags |= MSG_ERRQUEUE; err = copied; consume_skb(skb); out: return err; } void __ip_sock_set_tos(struct sock *sk, int val) { u8 old_tos = inet_sk(sk)->tos; if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; val |= old_tos & INET_ECN_MASK; } if (old_tos != val) { WRITE_ONCE(inet_sk(sk)->tos, val); WRITE_ONCE(sk->sk_priority, rt_tos2priority(val)); sk_dst_reset(sk); } } void ip_sock_set_tos(struct sock *sk, int val) { sockopt_lock_sock(sk); __ip_sock_set_tos(sk, val); sockopt_release_sock(sk); } EXPORT_SYMBOL(ip_sock_set_tos); void ip_sock_set_freebind(struct sock *sk) { inet_set_bit(FREEBIND, sk); } EXPORT_SYMBOL(ip_sock_set_freebind); void ip_sock_set_recverr(struct sock *sk) { inet_set_bit(RECVERR, sk); } EXPORT_SYMBOL(ip_sock_set_recverr); int ip_sock_set_mtu_discover(struct sock *sk, int val) { if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) return -EINVAL; WRITE_ONCE(inet_sk(sk)->pmtudisc, val); return 0; } EXPORT_SYMBOL(ip_sock_set_mtu_discover); void ip_sock_set_pktinfo(struct sock *sk) { inet_set_bit(PKTINFO, sk); } EXPORT_SYMBOL(ip_sock_set_pktinfo); /* * Socket option code for IP. This is the end of the line after any * TCP,UDP etc options on an IP socket. */ static bool setsockopt_needs_rtnl(int optname) { switch (optname) { case IP_ADD_MEMBERSHIP: case IP_ADD_SOURCE_MEMBERSHIP: case IP_BLOCK_SOURCE: case IP_DROP_MEMBERSHIP: case IP_DROP_SOURCE_MEMBERSHIP: case IP_MSFILTER: case IP_UNBLOCK_SOURCE: case MCAST_BLOCK_SOURCE: case MCAST_MSFILTER: case MCAST_JOIN_GROUP: case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_UNBLOCK_SOURCE: return true; } return false; } static int set_mcast_msfilter(struct sock *sk, int ifindex, int numsrc, int fmode, struct sockaddr_storage *group, struct sockaddr_storage *list) { struct ip_msfilter *msf; struct sockaddr_in *psin; int err, i; msf = kmalloc(IP_MSFILTER_SIZE(numsrc), GFP_KERNEL); if (!msf) return -ENOBUFS; psin = (struct sockaddr_in *)group; if (psin->sin_family != AF_INET) goto Eaddrnotavail; msf->imsf_multiaddr = psin->sin_addr.s_addr; msf->imsf_interface = 0; msf->imsf_fmode = fmode; msf->imsf_numsrc = numsrc; for (i = 0; i < numsrc; ++i) { psin = (struct sockaddr_in *)&list[i]; if (psin->sin_family != AF_INET) goto Eaddrnotavail; msf->imsf_slist_flex[i] = psin->sin_addr.s_addr; } err = ip_mc_msfilter(sk, msf, ifindex); kfree(msf); return err; Eaddrnotavail: kfree(msf); return -EADDRNOTAVAIL; } static int copy_group_source_from_sockptr(struct group_source_req *greqs, sockptr_t optval, int optlen) { if (in_compat_syscall()) { struct compat_group_source_req gr32; if (optlen != sizeof(gr32)) return -EINVAL; if (copy_from_sockptr(&gr32, optval, sizeof(gr32))) return -EFAULT; greqs->gsr_interface = gr32.gsr_interface; greqs->gsr_group = gr32.gsr_group; greqs->gsr_source = gr32.gsr_source; } else { if (optlen != sizeof(*greqs)) return -EINVAL; if (copy_from_sockptr(greqs, optval, sizeof(*greqs))) return -EFAULT; } return 0; } static int do_mcast_group_source(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct group_source_req greqs; struct ip_mreq_source mreqs; struct sockaddr_in *psin; int omode, add, err; err = copy_group_source_from_sockptr(&greqs, optval, optlen); if (err) return err; if (greqs.gsr_group.ss_family != AF_INET || greqs.gsr_source.ss_family != AF_INET) return -EADDRNOTAVAIL; psin = (struct sockaddr_in *)&greqs.gsr_group; mreqs.imr_multiaddr = psin->sin_addr.s_addr; psin = (struct sockaddr_in *)&greqs.gsr_source; mreqs.imr_sourceaddr = psin->sin_addr.s_addr; mreqs.imr_interface = 0; /* use index for mc_source */ if (optname == MCAST_BLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 1; } else if (optname == MCAST_UNBLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 0; } else if (optname == MCAST_JOIN_SOURCE_GROUP) { struct ip_mreqn mreq; psin = (struct sockaddr_in *)&greqs.gsr_group; mreq.imr_multiaddr = psin->sin_addr; mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) return err; greqs.gsr_interface = mreq.imr_ifindex; omode = MCAST_INCLUDE; add = 1; } else /* MCAST_LEAVE_SOURCE_GROUP */ { omode = MCAST_INCLUDE; add = 0; } return ip_mc_source(add, omode, sk, &mreqs, greqs.gsr_interface); } static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { struct group_filter *gsf = NULL; int err; if (optlen < GROUP_FILTER_SIZE(0)) return -EINVAL; if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max)) return -ENOBUFS; gsf = memdup_sockptr(optval, optlen); if (IS_ERR(gsf)) return PTR_ERR(gsf); /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (gsf->gf_numsrc >= 0x1ffffff || gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = -EINVAL; if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) goto out_free_gsf; err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc, gsf->gf_fmode, &gsf->gf_group, gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return err; } static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; unsigned int n; void *p; int err; if (optlen < size0) return -EINVAL; if (optlen > READ_ONCE(sock_net(sk)->core.sysctl_optmem_max) - 4) return -ENOBUFS; p = kmalloc(optlen + 4, GFP_KERNEL); if (!p) return -ENOMEM; gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ err = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ n = gf32->gf_numsrc; err = -ENOBUFS; if (n >= 0x1ffffff) goto out_free_gsf; err = -EINVAL; if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, &gf32->gf_group, gf32->gf_slist_flex); out_free_gsf: kfree(p); return err; } static int ip_mcast_join_leave(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct ip_mreqn mreq = { }; struct sockaddr_in *psin; struct group_req greq; if (optlen < sizeof(struct group_req)) return -EINVAL; if (copy_from_sockptr(&greq, optval, sizeof(greq))) return -EFAULT; psin = (struct sockaddr_in *)&greq.gr_group; if (psin->sin_family != AF_INET) return -EINVAL; mreq.imr_multiaddr = psin->sin_addr; mreq.imr_ifindex = greq.gr_interface; if (optname == MCAST_JOIN_GROUP) return ip_mc_join_group(sk, &mreq); return ip_mc_leave_group(sk, &mreq); } static int compat_ip_mcast_join_leave(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct compat_group_req greq; struct ip_mreqn mreq = { }; struct sockaddr_in *psin; if (optlen < sizeof(struct compat_group_req)) return -EINVAL; if (copy_from_sockptr(&greq, optval, sizeof(greq))) return -EFAULT; psin = (struct sockaddr_in *)&greq.gr_group; if (psin->sin_family != AF_INET) return -EINVAL; mreq.imr_multiaddr = psin->sin_addr; mreq.imr_ifindex = greq.gr_interface; if (optname == MCAST_JOIN_GROUP) return ip_mc_join_group(sk, &mreq); return ip_mc_leave_group(sk, &mreq); } DEFINE_STATIC_KEY_FALSE(ip4_min_ttl); int do_ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int val = 0, err, retv; bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { case IP_PKTINFO: case IP_RECVTTL: case IP_RECVOPTS: case IP_RECVTOS: case IP_RETOPTS: case IP_TOS: case IP_TTL: case IP_HDRINCL: case IP_MTU_DISCOVER: case IP_RECVERR: case IP_ROUTER_ALERT: case IP_FREEBIND: case IP_PASSSEC: case IP_TRANSPARENT: case IP_MINTTL: case IP_NODEFRAG: case IP_BIND_ADDRESS_NO_PORT: case IP_UNICAST_IF: case IP_MULTICAST_TTL: case IP_MULTICAST_ALL: case IP_MULTICAST_LOOP: case IP_RECVORIGDSTADDR: case IP_CHECKSUM: case IP_RECVFRAGSIZE: case IP_RECVERR_RFC4884: case IP_LOCAL_PORT_RANGE: if (optlen >= sizeof(int)) { if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; } else if (optlen >= sizeof(char)) { unsigned char ucval; if (copy_from_sockptr(&ucval, optval, sizeof(ucval))) return -EFAULT; val = (int) ucval; } } /* If optlen==0, it is equivalent to val == 0 */ if (optname == IP_ROUTER_ALERT) { retv = ip_ra_control(sk, val ? 1 : 0, NULL); if (retv == 0) inet_assign_bit(RTALERT, sk, val); return retv; } if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); /* Handle options that can be set without locking the socket. */ switch (optname) { case IP_PKTINFO: inet_assign_bit(PKTINFO, sk, val); return 0; case IP_RECVTTL: inet_assign_bit(TTL, sk, val); return 0; case IP_RECVTOS: inet_assign_bit(TOS, sk, val); return 0; case IP_RECVOPTS: inet_assign_bit(RECVOPTS, sk, val); return 0; case IP_RETOPTS: inet_assign_bit(RETOPTS, sk, val); return 0; case IP_PASSSEC: inet_assign_bit(PASSSEC, sk, val); return 0; case IP_RECVORIGDSTADDR: inet_assign_bit(ORIGDSTADDR, sk, val); return 0; case IP_RECVFRAGSIZE: if (sk->sk_type != SOCK_RAW && sk->sk_type != SOCK_DGRAM) return -EINVAL; inet_assign_bit(RECVFRAGSIZE, sk, val); return 0; case IP_RECVERR: inet_assign_bit(RECVERR, sk, val); if (!val) skb_errqueue_purge(&sk->sk_error_queue); return 0; case IP_RECVERR_RFC4884: if (val < 0 || val > 1) return -EINVAL; inet_assign_bit(RECVERR_RFC4884, sk, val); return 0; case IP_FREEBIND: if (optlen < 1) return -EINVAL; inet_assign_bit(FREEBIND, sk, val); return 0; case IP_HDRINCL: if (sk->sk_type != SOCK_RAW) return -ENOPROTOOPT; inet_assign_bit(HDRINCL, sk, val); return 0; case IP_MULTICAST_LOOP: if (optlen < 1) return -EINVAL; inet_assign_bit(MC_LOOP, sk, val); return 0; case IP_MULTICAST_ALL: if (optlen < 1) return -EINVAL; if (val != 0 && val != 1) return -EINVAL; inet_assign_bit(MC_ALL, sk, val); return 0; case IP_TRANSPARENT: if (!!val && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (optlen < 1) return -EINVAL; inet_assign_bit(TRANSPARENT, sk, val); return 0; case IP_NODEFRAG: if (sk->sk_type != SOCK_RAW) return -ENOPROTOOPT; inet_assign_bit(NODEFRAG, sk, val); return 0; case IP_BIND_ADDRESS_NO_PORT: inet_assign_bit(BIND_ADDRESS_NO_PORT, sk, val); return 0; case IP_TTL: if (optlen < 1) return -EINVAL; if (val != -1 && (val < 1 || val > 255)) return -EINVAL; WRITE_ONCE(inet->uc_ttl, val); return 0; case IP_MINTTL: if (optlen < 1) return -EINVAL; if (val < 0 || val > 255) return -EINVAL; if (val) static_branch_enable(&ip4_min_ttl); WRITE_ONCE(inet->min_ttl, val); return 0; case IP_MULTICAST_TTL: if (sk->sk_type == SOCK_STREAM) return -EINVAL; if (optlen < 1) return -EINVAL; if (val == -1) val = 1; if (val < 0 || val > 255) return -EINVAL; WRITE_ONCE(inet->mc_ttl, val); return 0; case IP_MTU_DISCOVER: return ip_sock_set_mtu_discover(sk, val); case IP_TOS: /* This sets both TOS and Precedence */ ip_sock_set_tos(sk, val); return 0; case IP_LOCAL_PORT_RANGE: { u16 lo = val; u16 hi = val >> 16; if (optlen != sizeof(u32)) return -EINVAL; if (lo != 0 && hi != 0 && lo > hi) return -EINVAL; WRITE_ONCE(inet->local_port_range, val); return 0; } } err = 0; if (needs_rtnl) rtnl_lock(); sockopt_lock_sock(sk); switch (optname) { case IP_OPTIONS: { struct ip_options_rcu *old, *opt = NULL; if (optlen > 40) goto e_inval; err = ip_options_get(sock_net(sk), &opt, optval, optlen); if (err) break; old = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_test_bit(IS_ICSK, sk)) { struct inet_connection_sock *icsk = inet_csk(sk); #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET || (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && inet->inet_daddr != LOOPBACK4_IPV6)) { #endif if (old) icsk->icsk_ext_hdr_len -= old->opt.optlen; if (opt) icsk->icsk_ext_hdr_len += opt->opt.optlen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); #if IS_ENABLED(CONFIG_IPV6) } #endif } rcu_assign_pointer(inet->inet_opt, opt); if (old) kfree_rcu(old, rcu); break; } case IP_CHECKSUM: if (val) { if (!(inet_test_bit(CHECKSUM, sk))) { inet_inc_convert_csum(sk); inet_set_bit(CHECKSUM, sk); } } else { if (inet_test_bit(CHECKSUM, sk)) { inet_dec_convert_csum(sk); inet_clear_bit(CHECKSUM, sk); } } break; case IP_UNICAST_IF: { struct net_device *dev = NULL; int ifindex; int midx; if (optlen != sizeof(int)) goto e_inval; ifindex = (__force int)ntohl((__force __be32)val); if (ifindex == 0) { WRITE_ONCE(inet->uc_index, 0); err = 0; break; } dev = dev_get_by_index(sock_net(sk), ifindex); err = -EADDRNOTAVAIL; if (!dev) break; midx = l3mdev_master_ifindex(dev); dev_put(dev); err = -EINVAL; if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; WRITE_ONCE(inet->uc_index, ifindex); err = 0; break; } case IP_MULTICAST_IF: { struct ip_mreqn mreq; struct net_device *dev = NULL; int midx; if (sk->sk_type == SOCK_STREAM) goto e_inval; /* * Check the arguments are allowable */ if (optlen < sizeof(struct in_addr)) goto e_inval; err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { if (copy_from_sockptr(&mreq, optval, sizeof(mreq))) break; } else { memset(&mreq, 0, sizeof(mreq)); if (optlen >= sizeof(struct ip_mreq)) { if (copy_from_sockptr(&mreq, optval, sizeof(struct ip_mreq))) break; } else if (optlen >= sizeof(struct in_addr)) { if (copy_from_sockptr(&mreq.imr_address, optval, sizeof(struct in_addr))) break; } } if (!mreq.imr_ifindex) { if (mreq.imr_address.s_addr == htonl(INADDR_ANY)) { WRITE_ONCE(inet->mc_index, 0); WRITE_ONCE(inet->mc_addr, 0); err = 0; break; } dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr); if (dev) mreq.imr_ifindex = dev->ifindex; } else dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex); err = -EADDRNOTAVAIL; if (!dev) break; midx = l3mdev_master_ifindex(dev); dev_put(dev); err = -EINVAL; if (sk->sk_bound_dev_if && mreq.imr_ifindex != sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if) break; WRITE_ONCE(inet->mc_index, mreq.imr_ifindex); WRITE_ONCE(inet->mc_addr, mreq.imr_address.s_addr); err = 0; break; } case IP_ADD_MEMBERSHIP: case IP_DROP_MEMBERSHIP: { struct ip_mreqn mreq; err = -EPROTO; if (inet_test_bit(IS_ICSK, sk)) break; if (optlen < sizeof(struct ip_mreq)) goto e_inval; err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { if (copy_from_sockptr(&mreq, optval, sizeof(mreq))) break; } else { memset(&mreq, 0, sizeof(mreq)); if (copy_from_sockptr(&mreq, optval, sizeof(struct ip_mreq))) break; } if (optname == IP_ADD_MEMBERSHIP) err = ip_mc_join_group(sk, &mreq); else err = ip_mc_leave_group(sk, &mreq); break; } case IP_MSFILTER: { struct ip_msfilter *msf; if (optlen < IP_MSFILTER_SIZE(0)) goto e_inval; if (optlen > READ_ONCE(net->core.sysctl_optmem_max)) { err = -ENOBUFS; break; } msf = memdup_sockptr(optval, optlen); if (IS_ERR(msf)) { err = PTR_ERR(msf); break; } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { kfree(msf); err = -ENOBUFS; break; } if (IP_MSFILTER_SIZE(msf->imsf_numsrc) > optlen) { kfree(msf); err = -EINVAL; break; } err = ip_mc_msfilter(sk, msf, 0); kfree(msf); break; } case IP_BLOCK_SOURCE: case IP_UNBLOCK_SOURCE: case IP_ADD_SOURCE_MEMBERSHIP: case IP_DROP_SOURCE_MEMBERSHIP: { struct ip_mreq_source mreqs; int omode, add; if (optlen != sizeof(struct ip_mreq_source)) goto e_inval; if (copy_from_sockptr(&mreqs, optval, sizeof(mreqs))) { err = -EFAULT; break; } if (optname == IP_BLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 1; } else if (optname == IP_UNBLOCK_SOURCE) { omode = MCAST_EXCLUDE; add = 0; } else if (optname == IP_ADD_SOURCE_MEMBERSHIP) { struct ip_mreqn mreq; mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr; mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; add = 1; } else /* IP_DROP_SOURCE_MEMBERSHIP */ { omode = MCAST_INCLUDE; add = 0; } err = ip_mc_source(add, omode, sk, &mreqs, 0); break; } case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: if (in_compat_syscall()) err = compat_ip_mcast_join_leave(sk, optname, optval, optlen); else err = ip_mcast_join_leave(sk, optname, optval, optlen); break; case MCAST_JOIN_SOURCE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_BLOCK_SOURCE: case MCAST_UNBLOCK_SOURCE: err = do_mcast_group_source(sk, optname, optval, optlen); break; case MCAST_MSFILTER: if (in_compat_syscall()) err = compat_ip_set_mcast_msfilter(sk, optval, optlen); else err = ip_set_mcast_msfilter(sk, optval, optlen); break; case IP_IPSEC_POLICY: case IP_XFRM_POLICY: err = -EPERM; if (!sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) break; err = xfrm_user_policy(sk, optname, optval, optlen); break; default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return err; e_inval: sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return -EINVAL; } /** * ipv4_pktinfo_prepare - transfer some info from rtable to skb * @sk: socket * @skb: buffer * @drop_dst: if true, drops skb dst * * To support IP_CMSG_PKTINFO option, we store rt_iif and specific * destination in skb->cb[] before dst drop. * This way, receiver doesn't make cache line misses to read rtable. */ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst) { struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); bool prepare = inet_test_bit(PKTINFO, sk) || ipv6_sk_rxinfo(sk); if (prepare && skb_rtable(skb)) { /* skb->cb is overloaded: prior to this point it is IP{6}CB * which has interface index (iif) as the first member of the * underlying inet{6}_skb_parm struct. This code then overlays * PKTINFO_SKB_CB and in_pktinfo also has iif as the first * element so the iif is picked up from the prior IPCB. If iif * is the loopback interface, then return the sending interface * (e.g., process binds socket to eth0 for Tx which is * redirected to loopback in the rtable/dst). */ struct rtable *rt = skb_rtable(skb); bool l3slave = ipv4_l3mdev_skb(IPCB(skb)->flags); if (pktinfo->ipi_ifindex == LOOPBACK_IFINDEX) pktinfo->ipi_ifindex = inet_iif(skb); else if (l3slave && rt && rt->rt_iif) pktinfo->ipi_ifindex = rt->rt_iif; pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb); } else { pktinfo->ipi_ifindex = 0; pktinfo->ipi_spec_dst.s_addr = 0; } if (drop_dst) skb_dst_drop(skb); } int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { int err; if (level != SOL_IP) return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_HDRINCL && optname != IP_IPSEC_POLICY && optname != IP_XFRM_POLICY && !ip_mroute_opt(optname)) err = nf_setsockopt(sk, PF_INET, optname, optval, optlen); #endif return err; } EXPORT_SYMBOL(ip_setsockopt); /* * Get the options. Note for future reference. The GET of IP options gets * the _received_ ones. The set sets the _sent_ ones. */ static bool getsockopt_needs_rtnl(int optname) { switch (optname) { case IP_MSFILTER: case MCAST_MSFILTER: return true; } return false; } static int ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter gsf; int num, gsf_size; int err; if (len < size0) return -EINVAL; if (copy_from_sockptr(&gsf, optval, size0)) return -EFAULT; num = gsf.gf_numsrc; err = ip_mc_gsfget(sk, &gsf, optval, offsetof(struct group_filter, gf_slist_flex)); if (err) return err; if (gsf.gf_numsrc < num) num = gsf.gf_numsrc; gsf_size = GROUP_FILTER_SIZE(num); if (copy_to_sockptr(optlen, &gsf_size, sizeof(int)) || copy_to_sockptr(optval, &gsf, size0)) return -EFAULT; return 0; } static int compat_ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, sockptr_t optlen, int len) { const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter gf32; struct group_filter gf; int num; int err; if (len < size0) return -EINVAL; if (copy_from_sockptr(&gf32, optval, size0)) return -EFAULT; gf.gf_interface = gf32.gf_interface; gf.gf_fmode = gf32.gf_fmode; num = gf.gf_numsrc = gf32.gf_numsrc; gf.gf_group = gf32.gf_group; err = ip_mc_gsfget(sk, &gf, optval, offsetof(struct compat_group_filter, gf_slist_flex)); if (err) return err; if (gf.gf_numsrc < num) num = gf.gf_numsrc; len = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32)); if (copy_to_sockptr(optlen, &len, sizeof(int)) || copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode), &gf.gf_fmode, sizeof(gf.gf_fmode)) || copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc), &gf.gf_numsrc, sizeof(gf.gf_numsrc))) return -EFAULT; return 0; } int do_ip_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_sock *inet = inet_sk(sk); bool needs_rtnl = getsockopt_needs_rtnl(optname); int val, err = 0; int len; if (level != SOL_IP) return -EOPNOTSUPP; if (ip_mroute_opt(optname)) return ip_mroute_getsockopt(sk, optname, optval, optlen); if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; /* Handle options that can be read without locking the socket. */ switch (optname) { case IP_PKTINFO: val = inet_test_bit(PKTINFO, sk); goto copyval; case IP_RECVTTL: val = inet_test_bit(TTL, sk); goto copyval; case IP_RECVTOS: val = inet_test_bit(TOS, sk); goto copyval; case IP_RECVOPTS: val = inet_test_bit(RECVOPTS, sk); goto copyval; case IP_RETOPTS: val = inet_test_bit(RETOPTS, sk); goto copyval; case IP_PASSSEC: val = inet_test_bit(PASSSEC, sk); goto copyval; case IP_RECVORIGDSTADDR: val = inet_test_bit(ORIGDSTADDR, sk); goto copyval; case IP_CHECKSUM: val = inet_test_bit(CHECKSUM, sk); goto copyval; case IP_RECVFRAGSIZE: val = inet_test_bit(RECVFRAGSIZE, sk); goto copyval; case IP_RECVERR: val = inet_test_bit(RECVERR, sk); goto copyval; case IP_RECVERR_RFC4884: val = inet_test_bit(RECVERR_RFC4884, sk); goto copyval; case IP_FREEBIND: val = inet_test_bit(FREEBIND, sk); goto copyval; case IP_HDRINCL: val = inet_test_bit(HDRINCL, sk); goto copyval; case IP_MULTICAST_LOOP: val = inet_test_bit(MC_LOOP, sk); goto copyval; case IP_MULTICAST_ALL: val = inet_test_bit(MC_ALL, sk); goto copyval; case IP_TRANSPARENT: val = inet_test_bit(TRANSPARENT, sk); goto copyval; case IP_NODEFRAG: val = inet_test_bit(NODEFRAG, sk); goto copyval; case IP_BIND_ADDRESS_NO_PORT: val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); goto copyval; case IP_ROUTER_ALERT: val = inet_test_bit(RTALERT, sk); goto copyval; case IP_TTL: val = READ_ONCE(inet->uc_ttl); if (val < 0) val = READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_default_ttl); goto copyval; case IP_MINTTL: val = READ_ONCE(inet->min_ttl); goto copyval; case IP_MULTICAST_TTL: val = READ_ONCE(inet->mc_ttl); goto copyval; case IP_MTU_DISCOVER: val = READ_ONCE(inet->pmtudisc); goto copyval; case IP_TOS: val = READ_ONCE(inet->tos); goto copyval; case IP_OPTIONS: { unsigned char optbuf[sizeof(struct ip_options)+40]; struct ip_options *opt = (struct ip_options *)optbuf; struct ip_options_rcu *inet_opt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); opt->optlen = 0; if (inet_opt) memcpy(optbuf, &inet_opt->opt, sizeof(struct ip_options) + inet_opt->opt.optlen); rcu_read_unlock(); if (opt->optlen == 0) { len = 0; return copy_to_sockptr(optlen, &len, sizeof(int)); } ip_options_undo(opt); len = min_t(unsigned int, len, opt->optlen); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, opt->__data, len)) return -EFAULT; return 0; } case IP_MTU: { struct dst_entry *dst; val = 0; dst = sk_dst_get(sk); if (dst) { val = dst_mtu(dst); dst_release(dst); } if (!val) return -ENOTCONN; goto copyval; } case IP_PKTOPTIONS: { struct msghdr msg; if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; if (optval.is_kernel) { msg.msg_control_is_user = false; msg.msg_control = optval.kernel; } else { msg.msg_control_is_user = true; msg.msg_control_user = optval.user; } msg.msg_controllen = len; msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; if (inet_test_bit(PKTINFO, sk)) { struct in_pktinfo info; info.ipi_addr.s_addr = READ_ONCE(inet->inet_rcv_saddr); info.ipi_spec_dst.s_addr = READ_ONCE(inet->inet_rcv_saddr); info.ipi_ifindex = READ_ONCE(inet->mc_index); put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } if (inet_test_bit(TTL, sk)) { int hlim = READ_ONCE(inet->mc_ttl); put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); } if (inet_test_bit(TOS, sk)) { int tos = READ_ONCE(inet->rcv_tos); put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); } len -= msg.msg_controllen; return copy_to_sockptr(optlen, &len, sizeof(int)); } case IP_UNICAST_IF: val = (__force int)htonl((__u32) READ_ONCE(inet->uc_index)); goto copyval; case IP_MULTICAST_IF: { struct in_addr addr; len = min_t(unsigned int, len, sizeof(struct in_addr)); addr.s_addr = READ_ONCE(inet->mc_addr); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &addr, len)) return -EFAULT; return 0; } case IP_LOCAL_PORT_RANGE: val = READ_ONCE(inet->local_port_range); goto copyval; } if (needs_rtnl) rtnl_lock(); sockopt_lock_sock(sk); switch (optname) { case IP_MSFILTER: { struct ip_msfilter msf; if (len < IP_MSFILTER_SIZE(0)) { err = -EINVAL; goto out; } if (copy_from_sockptr(&msf, optval, IP_MSFILTER_SIZE(0))) { err = -EFAULT; goto out; } err = ip_mc_msfget(sk, &msf, optval, optlen); goto out; } case MCAST_MSFILTER: if (in_compat_syscall()) err = compat_ip_get_mcast_msfilter(sk, optval, optlen, len); else err = ip_get_mcast_msfilter(sk, optval, optlen, len); goto out; case IP_PROTOCOL: val = inet_sk(sk)->inet_num; break; default: sockopt_release_sock(sk); return -ENOPROTOOPT; } sockopt_release_sock(sk); copyval: if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &ucval, 1)) return -EFAULT; } else { len = min_t(unsigned int, sizeof(int), len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; } return 0; out: sockopt_release_sock(sk); if (needs_rtnl) rtnl_unlock(); return err; } int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int err; err = do_ip_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && !ip_mroute_opt(optname)) { int len; if (get_user(len, optlen)) return -EFAULT; err = nf_getsockopt(sk, PF_INET, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); return err; } #endif return err; } EXPORT_SYMBOL(ip_getsockopt); |
| 63 632 649 649 224 431 431 431 809 71 740 35 11 35 787 787 787 810 810 485 333 132 681 862 38 861 734 133 133 734 3 3 3 916 916 395 916 8 4 856 850 2 2 1 2 808 1 2 2 649 642 7 567 84 649 649 649 648 2 35 24 7 2 2 1 1 2 1 6 2 1 2 1 881 86 814 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Fd transport layer. Includes deprecated socket layer. * * Copyright (C) 2006 by Russ Cox <rsc@swtch.com> * Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net> * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/in6.h> #include <linux/module.h> #include <linux/net.h> #include <linux/ipv6.h> #include <linux/kthread.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/un.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/file.h> #include <linux/parser.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include <linux/syscalls.h> /* killme */ #define P9_PORT 564 #define MAX_SOCK_BUF (1024*1024) #define MAXPOLLWADDR 2 static struct p9_trans_module p9_tcp_trans; static struct p9_trans_module p9_fd_trans; /** * struct p9_fd_opts - per-transport options * @rfd: file descriptor for reading (trans=fd) * @wfd: file descriptor for writing (trans=fd) * @port: port to connect to (trans=tcp) * @privport: port is privileged */ struct p9_fd_opts { int rfd; int wfd; u16 port; bool privport; }; /* * Option Parsing (code inspired by NFS code) * - a little lazy - parse all fd-transport options */ enum { /* Options that take integer arguments */ Opt_port, Opt_rfdno, Opt_wfdno, Opt_err, /* Options that take no arguments */ Opt_privport, }; static const match_table_t tokens = { {Opt_port, "port=%u"}, {Opt_rfdno, "rfdno=%u"}, {Opt_wfdno, "wfdno=%u"}, {Opt_privport, "privport"}, {Opt_err, NULL}, }; enum { Rworksched = 1, /* read work scheduled or running */ Rpending = 2, /* can read */ Wworksched = 4, /* write work scheduled or running */ Wpending = 8, /* can write */ }; struct p9_poll_wait { struct p9_conn *conn; wait_queue_entry_t wait; wait_queue_head_t *wait_addr; }; /** * struct p9_conn - fd mux connection state information * @mux_list: list link for mux to manage multiple connections (?) * @client: reference to client instance for this connection * @err: error state * @req_lock: lock protecting req_list and requests statuses * @req_list: accounting for requests which have been sent * @unsent_req_list: accounting for requests that haven't been sent * @rreq: read request * @wreq: write request * @tmp_buf: temporary buffer to read in header * @rc: temporary fcall for reading current frame * @wpos: write position for current frame * @wsize: amount of data to write for current frame * @wbuf: current write buffer * @poll_pending_link: pending links to be polled per conn * @poll_wait: array of wait_q's for various worker threads * @pt: poll state * @rq: current read work * @wq: current write work * @wsched: ???? * */ struct p9_conn { struct list_head mux_list; struct p9_client *client; int err; spinlock_t req_lock; struct list_head req_list; struct list_head unsent_req_list; struct p9_req_t *rreq; struct p9_req_t *wreq; char tmp_buf[P9_HDRSZ]; struct p9_fcall rc; int wpos; int wsize; char *wbuf; struct list_head poll_pending_link; struct p9_poll_wait poll_wait[MAXPOLLWADDR]; poll_table pt; struct work_struct rq; struct work_struct wq; unsigned long wsched; }; /** * struct p9_trans_fd - transport state * @rd: reference to file to read from * @wr: reference of file to write to * @conn: connection state reference * */ struct p9_trans_fd { struct file *rd; struct file *wr; struct p9_conn conn; }; static void p9_poll_workfn(struct work_struct *work); static DEFINE_SPINLOCK(p9_poll_lock); static LIST_HEAD(p9_poll_pending_list); static DECLARE_WORK(p9_poll_work, p9_poll_workfn); static unsigned int p9_ipport_resv_min = P9_DEF_MIN_RESVPORT; static unsigned int p9_ipport_resv_max = P9_DEF_MAX_RESVPORT; static void p9_mux_poll_stop(struct p9_conn *m) { unsigned long flags; int i; for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) { struct p9_poll_wait *pwait = &m->poll_wait[i]; if (pwait->wait_addr) { remove_wait_queue(pwait->wait_addr, &pwait->wait); pwait->wait_addr = NULL; } } spin_lock_irqsave(&p9_poll_lock, flags); list_del_init(&m->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); flush_work(&p9_poll_work); } /** * p9_conn_cancel - cancel all pending requests with error * @m: mux data * @err: error code * */ static void p9_conn_cancel(struct p9_conn *m, int err) { struct p9_req_t *req, *rtmp; LIST_HEAD(cancel_list); p9_debug(P9_DEBUG_ERROR, "mux %p err %d\n", m, err); spin_lock(&m->req_lock); if (READ_ONCE(m->err)) { spin_unlock(&m->req_lock); return; } WRITE_ONCE(m->err, err); ASSERT_EXCLUSIVE_WRITER(m->err); list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); WRITE_ONCE(req->status, REQ_STATUS_ERROR); } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); WRITE_ONCE(req->status, REQ_STATUS_ERROR); } spin_unlock(&m->req_lock); list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); if (!req->t_err) req->t_err = err; p9_client_cb(m->client, req, REQ_STATUS_ERROR); } } static __poll_t p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt, int *err) { __poll_t ret; struct p9_trans_fd *ts = NULL; if (client && client->status == Connected) ts = client->trans; if (!ts) { if (err) *err = -EREMOTEIO; return EPOLLERR; } ret = vfs_poll(ts->rd, pt); if (ts->rd != ts->wr) ret = (ret & ~EPOLLOUT) | (vfs_poll(ts->wr, pt) & ~EPOLLIN); return ret; } /** * p9_fd_read- read from a fd * @client: client instance * @v: buffer to receive data into * @len: size of receive buffer * */ static int p9_fd_read(struct p9_client *client, void *v, int len) { int ret; struct p9_trans_fd *ts = NULL; loff_t pos; if (client && client->status != Disconnected) ts = client->trans; if (!ts) return -EREMOTEIO; if (!(ts->rd->f_flags & O_NONBLOCK)) p9_debug(P9_DEBUG_ERROR, "blocking read ...\n"); pos = ts->rd->f_pos; ret = kernel_read(ts->rd, v, len, &pos); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) client->status = Disconnected; return ret; } /** * p9_read_work - called when there is some data to be read from a transport * @work: container of work to be done * */ static void p9_read_work(struct work_struct *work) { __poll_t n; int err; struct p9_conn *m; m = container_of(work, struct p9_conn, rq); if (READ_ONCE(m->err) < 0) return; p9_debug(P9_DEBUG_TRANS, "start mux %p pos %zd\n", m, m->rc.offset); if (!m->rc.sdata) { m->rc.sdata = m->tmp_buf; m->rc.offset = 0; m->rc.capacity = P9_HDRSZ; /* start by reading header */ } clear_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "read mux %p pos %zd size: %zd = %zd\n", m, m->rc.offset, m->rc.capacity, m->rc.capacity - m->rc.offset); err = p9_fd_read(m->client, m->rc.sdata + m->rc.offset, m->rc.capacity - m->rc.offset); p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err); if (err == -EAGAIN) goto end_clear; if (err <= 0) goto error; m->rc.offset += err; /* header read in */ if ((!m->rreq) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new header\n"); /* Header size */ m->rc.size = P9_HDRSZ; err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, "error parsing header: %d\n", err); goto error; } p9_debug(P9_DEBUG_TRANS, "mux %p pkt: size: %d bytes tag: %d\n", m, m->rc.size, m->rc.tag); m->rreq = p9_tag_lookup(m->client, m->rc.tag); if (!m->rreq || (m->rreq->status != REQ_STATUS_SENT)) { p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", m->rc.tag); err = -EIO; goto error; } if (m->rc.size > m->rreq->rc.capacity) { p9_debug(P9_DEBUG_ERROR, "requested packet size too big: %d for tag %d with capacity %zd\n", m->rc.size, m->rc.tag, m->rreq->rc.capacity); err = -EIO; goto error; } if (!m->rreq->rc.sdata) { p9_debug(P9_DEBUG_ERROR, "No recv fcall for tag %d (req %p), disconnecting!\n", m->rc.tag, m->rreq); p9_req_put(m->client, m->rreq); m->rreq = NULL; err = -EIO; goto error; } m->rc.sdata = m->rreq->rc.sdata; memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity); m->rc.capacity = m->rc.size; } /* packet is read in * not an else because some packets (like clunk) have no payload */ if ((m->rreq) && (m->rc.offset == m->rc.capacity)) { p9_debug(P9_DEBUG_TRANS, "got new packet\n"); m->rreq->rc.size = m->rc.offset; spin_lock(&m->req_lock); if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); } else if (m->rreq->status == REQ_STATUS_FLSHD) { /* Ignore replies associated with a cancelled request. */ p9_debug(P9_DEBUG_TRANS, "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->req_lock); p9_debug(P9_DEBUG_ERROR, "Request tag %d errored out while we were reading the reply\n", m->rc.tag); err = -EIO; goto error; } spin_unlock(&m->req_lock); m->rc.sdata = NULL; m->rc.offset = 0; m->rc.capacity = 0; p9_req_put(m->client, m->rreq); m->rreq = NULL; } end_clear: clear_bit(Rworksched, &m->wsched); if (!list_empty(&m->req_list)) { if (test_and_clear_bit(Rpending, &m->wsched)) n = EPOLLIN; else n = p9_fd_poll(m->client, NULL, NULL); if ((n & EPOLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } return; error: p9_conn_cancel(m, err); clear_bit(Rworksched, &m->wsched); } /** * p9_fd_write - write to a socket * @client: client instance * @v: buffer to send data from * @len: size of send buffer * */ static int p9_fd_write(struct p9_client *client, void *v, int len) { ssize_t ret; struct p9_trans_fd *ts = NULL; if (client && client->status != Disconnected) ts = client->trans; if (!ts) return -EREMOTEIO; if (!(ts->wr->f_flags & O_NONBLOCK)) p9_debug(P9_DEBUG_ERROR, "blocking write ...\n"); ret = kernel_write(ts->wr, v, len, &ts->wr->f_pos); if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN) client->status = Disconnected; return ret; } /** * p9_write_work - called when a transport can send some data * @work: container for work to be done * */ static void p9_write_work(struct work_struct *work) { __poll_t n; int err; struct p9_conn *m; struct p9_req_t *req; m = container_of(work, struct p9_conn, wq); if (READ_ONCE(m->err) < 0) { clear_bit(Wworksched, &m->wsched); return; } if (!m->wsize) { spin_lock(&m->req_lock); if (list_empty(&m->unsent_req_list)) { clear_bit(Wworksched, &m->wsched); spin_unlock(&m->req_lock); return; } req = list_entry(m->unsent_req_list.next, struct p9_req_t, req_list); WRITE_ONCE(req->status, REQ_STATUS_SENT); p9_debug(P9_DEBUG_TRANS, "move req %p\n", req); list_move_tail(&req->req_list, &m->req_list); m->wbuf = req->tc.sdata; m->wsize = req->tc.size; m->wpos = 0; p9_req_get(req); m->wreq = req; spin_unlock(&m->req_lock); } p9_debug(P9_DEBUG_TRANS, "mux %p pos %d size %d\n", m, m->wpos, m->wsize); clear_bit(Wpending, &m->wsched); err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos); p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err); if (err == -EAGAIN) goto end_clear; if (err < 0) goto error; else if (err == 0) { err = -EREMOTEIO; goto error; } m->wpos += err; if (m->wpos == m->wsize) { m->wpos = m->wsize = 0; p9_req_put(m->client, m->wreq); m->wreq = NULL; } end_clear: clear_bit(Wworksched, &m->wsched); if (m->wsize || !list_empty(&m->unsent_req_list)) { if (test_and_clear_bit(Wpending, &m->wsched)) n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); if ((n & EPOLLOUT) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } return; error: p9_conn_cancel(m, err); clear_bit(Wworksched, &m->wsched); } static int p9_pollwake(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { struct p9_poll_wait *pwait = container_of(wait, struct p9_poll_wait, wait); struct p9_conn *m = pwait->conn; unsigned long flags; spin_lock_irqsave(&p9_poll_lock, flags); if (list_empty(&m->poll_pending_link)) list_add_tail(&m->poll_pending_link, &p9_poll_pending_list); spin_unlock_irqrestore(&p9_poll_lock, flags); schedule_work(&p9_poll_work); return 1; } /** * p9_pollwait - add poll task to the wait queue * @filp: file pointer being polled * @wait_address: wait_q to block on * @p: poll state * * called by files poll operation to add v9fs-poll task to files wait queue */ static void p9_pollwait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) { struct p9_conn *m = container_of(p, struct p9_conn, pt); struct p9_poll_wait *pwait = NULL; int i; for (i = 0; i < ARRAY_SIZE(m->poll_wait); i++) { if (m->poll_wait[i].wait_addr == NULL) { pwait = &m->poll_wait[i]; break; } } if (!pwait) { p9_debug(P9_DEBUG_ERROR, "not enough wait_address slots\n"); return; } pwait->conn = m; pwait->wait_addr = wait_address; init_waitqueue_func_entry(&pwait->wait, p9_pollwake); add_wait_queue(wait_address, &pwait->wait); } /** * p9_conn_create - initialize the per-session mux data * @client: client instance * * Note: Creates the polling task if this is the first session. */ static void p9_conn_create(struct p9_client *client) { __poll_t n; struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p msize %d\n", client, client->msize); INIT_LIST_HEAD(&m->mux_list); m->client = client; spin_lock_init(&m->req_lock); INIT_LIST_HEAD(&m->req_list); INIT_LIST_HEAD(&m->unsent_req_list); INIT_WORK(&m->rq, p9_read_work); INIT_WORK(&m->wq, p9_write_work); INIT_LIST_HEAD(&m->poll_pending_link); init_poll_funcptr(&m->pt, p9_pollwait); n = p9_fd_poll(client, &m->pt, NULL); if (n & EPOLLIN) { p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); set_bit(Rpending, &m->wsched); } if (n & EPOLLOUT) { p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); set_bit(Wpending, &m->wsched); } } /** * p9_poll_mux - polls a mux and schedules read or write works if necessary * @m: connection to poll * */ static void p9_poll_mux(struct p9_conn *m) { __poll_t n; int err = -ECONNRESET; if (READ_ONCE(m->err) < 0) return; n = p9_fd_poll(m->client, NULL, &err); if (n & (EPOLLERR | EPOLLHUP | EPOLLNVAL)) { p9_debug(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n); p9_conn_cancel(m, err); } if (n & EPOLLIN) { set_bit(Rpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can read\n", m); if (!test_and_set_bit(Rworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m); schedule_work(&m->rq); } } if (n & EPOLLOUT) { set_bit(Wpending, &m->wsched); p9_debug(P9_DEBUG_TRANS, "mux %p can write\n", m); if ((m->wsize || !list_empty(&m->unsent_req_list)) && !test_and_set_bit(Wworksched, &m->wsched)) { p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m); schedule_work(&m->wq); } } } /** * p9_fd_request - send 9P request * The function can sleep until the request is scheduled for sending. * The function can be interrupted. Return from the function is not * a guarantee that the request is sent successfully. * * @client: client instance * @req: request to be sent * */ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req) { __poll_t n; int err; struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", m, current, &req->tc, req->tc.id); spin_lock(&m->req_lock); err = READ_ONCE(m->err); if (err < 0) { spin_unlock(&m->req_lock); return err; } WRITE_ONCE(req->status, REQ_STATUS_UNSENT); list_add_tail(&req->req_list, &m->unsent_req_list); spin_unlock(&m->req_lock); if (test_and_clear_bit(Wpending, &m->wsched)) n = EPOLLOUT; else n = p9_fd_poll(m->client, NULL, NULL); if (n & EPOLLOUT && !test_and_set_bit(Wworksched, &m->wsched)) schedule_work(&m->wq); return 0; } static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; int ret = 1; p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&m->req_lock); if (req->status == REQ_STATUS_UNSENT) { list_del(&req->req_list); WRITE_ONCE(req->status, REQ_STATUS_FLSHD); p9_req_put(client, req); ret = 0; } spin_unlock(&m->req_lock); return ret; } static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_fd *ts = client->trans; struct p9_conn *m = &ts->conn; p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); spin_lock(&m->req_lock); /* Ignore cancelled request if message has been received * before lock. */ if (req->status == REQ_STATUS_RCVD) { spin_unlock(&m->req_lock); return 0; } /* we haven't received a response for oldreq, * remove it from the list. */ list_del(&req->req_list); WRITE_ONCE(req->status, REQ_STATUS_FLSHD); spin_unlock(&m->req_lock); p9_req_put(client, req); return 0; } static int p9_fd_show_options(struct seq_file *m, struct p9_client *clnt) { if (clnt->trans_mod == &p9_tcp_trans) { if (clnt->trans_opts.tcp.port != P9_PORT) seq_printf(m, ",port=%u", clnt->trans_opts.tcp.port); } else if (clnt->trans_mod == &p9_fd_trans) { if (clnt->trans_opts.fd.rfd != ~0) seq_printf(m, ",rfd=%u", clnt->trans_opts.fd.rfd); if (clnt->trans_opts.fd.wfd != ~0) seq_printf(m, ",wfd=%u", clnt->trans_opts.fd.wfd); } return 0; } /** * parse_opts - parse mount options into p9_fd_opts structure * @params: options string passed from mount * @opts: fd transport-specific structure to parse options into * * Returns 0 upon success, -ERRNO upon failure */ static int parse_opts(char *params, struct p9_fd_opts *opts) { char *p; substring_t args[MAX_OPT_ARGS]; int option; char *options, *tmp_options; opts->port = P9_PORT; opts->rfd = ~0; opts->wfd = ~0; opts->privport = false; if (!params) return 0; tmp_options = kstrdup(params, GFP_KERNEL); if (!tmp_options) { p9_debug(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; int r; if (!*p) continue; token = match_token(p, tokens, args); if ((token != Opt_err) && (token != Opt_privport)) { r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); continue; } } switch (token) { case Opt_port: opts->port = option; break; case Opt_rfdno: opts->rfd = option; break; case Opt_wfdno: opts->wfd = option; break; case Opt_privport: opts->privport = true; break; default: continue; } } kfree(tmp_options); return 0; } static int p9_fd_open(struct p9_client *client, int rfd, int wfd) { struct p9_trans_fd *ts = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!ts) return -ENOMEM; ts->rd = fget(rfd); if (!ts->rd) goto out_free_ts; if (!(ts->rd->f_mode & FMODE_READ)) goto out_put_rd; /* Prevent workers from hanging on IO when fd is a pipe. * It's technically possible for userspace or concurrent mounts to * modify this flag concurrently, which will likely result in a * broken filesystem. However, just having bad flags here should * not crash the kernel or cause any other sort of bug, so mark this * particular data race as intentional so that tooling (like KCSAN) * can allow it and detect further problems. */ data_race(ts->rd->f_flags |= O_NONBLOCK); ts->wr = fget(wfd); if (!ts->wr) goto out_put_rd; if (!(ts->wr->f_mode & FMODE_WRITE)) goto out_put_wr; data_race(ts->wr->f_flags |= O_NONBLOCK); client->trans = ts; client->status = Connected; return 0; out_put_wr: fput(ts->wr); out_put_rd: fput(ts->rd); out_free_ts: kfree(ts); return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) { struct p9_trans_fd *p; struct file *file; p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); if (!p) { sock_release(csocket); return -ENOMEM; } csocket->sk->sk_allocation = GFP_NOIO; csocket->sk->sk_use_task_frag = false; file = sock_alloc_file(csocket, 0, NULL); if (IS_ERR(file)) { pr_err("%s (%d): failed to map fd\n", __func__, task_pid_nr(current)); kfree(p); return PTR_ERR(file); } get_file(file); p->wr = p->rd = file; client->trans = p; client->status = Connected; p->rd->f_flags |= O_NONBLOCK; p9_conn_create(client); return 0; } /** * p9_conn_destroy - cancels all pending requests of mux * @m: mux to destroy * */ static void p9_conn_destroy(struct p9_conn *m) { p9_debug(P9_DEBUG_TRANS, "mux %p prev %p next %p\n", m, m->mux_list.prev, m->mux_list.next); p9_mux_poll_stop(m); cancel_work_sync(&m->rq); if (m->rreq) { p9_req_put(m->client, m->rreq); m->rreq = NULL; } cancel_work_sync(&m->wq); if (m->wreq) { p9_req_put(m->client, m->wreq); m->wreq = NULL; } p9_conn_cancel(m, -ECONNRESET); m->client = NULL; } /** * p9_fd_close - shutdown file descriptor transport * @client: client instance * */ static void p9_fd_close(struct p9_client *client) { struct p9_trans_fd *ts; if (!client) return; ts = client->trans; if (!ts) return; client->status = Disconnected; p9_conn_destroy(&ts->conn); if (ts->rd) fput(ts->rd); if (ts->wr) fput(ts->wr); kfree(ts); } static int p9_bind_privport(struct socket *sock) { struct sockaddr_storage stor = { 0 }; int port, err = -EINVAL; stor.ss_family = sock->ops->family; if (stor.ss_family == AF_INET) ((struct sockaddr_in *)&stor)->sin_addr.s_addr = htonl(INADDR_ANY); else ((struct sockaddr_in6 *)&stor)->sin6_addr = in6addr_any; for (port = p9_ipport_resv_max; port >= p9_ipport_resv_min; port--) { if (stor.ss_family == AF_INET) ((struct sockaddr_in *)&stor)->sin_port = htons((ushort)port); else ((struct sockaddr_in6 *)&stor)->sin6_port = htons((ushort)port); err = kernel_bind(sock, (struct sockaddr *)&stor, sizeof(stor)); if (err != -EADDRINUSE) break; } return err; } static int p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) { int err; char port_str[6]; struct socket *csocket; struct sockaddr_storage stor = { 0 }; struct p9_fd_opts opts; err = parse_opts(args, &opts); if (err < 0) return err; if (!addr) return -EINVAL; sprintf(port_str, "%u", opts.port); err = inet_pton_with_scope(current->nsproxy->net_ns, AF_UNSPEC, addr, port_str, &stor); if (err < 0) return err; csocket = NULL; client->trans_opts.tcp.port = opts.port; client->trans_opts.tcp.privport = opts.privport; err = __sock_create(current->nsproxy->net_ns, stor.ss_family, SOCK_STREAM, IPPROTO_TCP, &csocket, 1); if (err) { pr_err("%s (%d): problem creating socket\n", __func__, task_pid_nr(current)); return err; } if (opts.privport) { err = p9_bind_privport(csocket); if (err < 0) { pr_err("%s (%d): problem binding to privport\n", __func__, task_pid_nr(current)); sock_release(csocket); return err; } } err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&stor, sizeof(stor), 0); if (err < 0) { pr_err("%s (%d): problem connecting socket to %s\n", __func__, task_pid_nr(current), addr); sock_release(csocket); return err; } return p9_socket_open(client, csocket); } static int p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) { int err; struct socket *csocket; struct sockaddr_un sun_server; csocket = NULL; if (!addr || !strlen(addr)) return -EINVAL; if (strlen(addr) >= UNIX_PATH_MAX) { pr_err("%s (%d): address too long: %s\n", __func__, task_pid_nr(current), addr); return -ENAMETOOLONG; } sun_server.sun_family = PF_UNIX; strcpy(sun_server.sun_path, addr); err = __sock_create(current->nsproxy->net_ns, PF_UNIX, SOCK_STREAM, 0, &csocket, 1); if (err < 0) { pr_err("%s (%d): problem creating socket\n", __func__, task_pid_nr(current)); return err; } err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sun_server, sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { pr_err("%s (%d): problem connecting socket: %s: %d\n", __func__, task_pid_nr(current), addr, err); sock_release(csocket); return err; } return p9_socket_open(client, csocket); } static int p9_fd_create(struct p9_client *client, const char *addr, char *args) { int err; struct p9_fd_opts opts; err = parse_opts(args, &opts); if (err < 0) return err; client->trans_opts.fd.rfd = opts.rfd; client->trans_opts.fd.wfd = opts.wfd; if (opts.rfd == ~0 || opts.wfd == ~0) { pr_err("Insufficient options for proto=fd\n"); return -ENOPROTOOPT; } err = p9_fd_open(client, opts.rfd, opts.wfd); if (err < 0) return err; p9_conn_create(client); return 0; } static struct p9_trans_module p9_tcp_trans = { .name = "tcp", .maxsize = MAX_SOCK_BUF, .pooled_rbuffers = false, .def = 0, .create = p9_fd_create_tcp, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("tcp"); static struct p9_trans_module p9_unix_trans = { .name = "unix", .maxsize = MAX_SOCK_BUF, .def = 0, .create = p9_fd_create_unix, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("unix"); static struct p9_trans_module p9_fd_trans = { .name = "fd", .maxsize = MAX_SOCK_BUF, .def = 0, .create = p9_fd_create, .close = p9_fd_close, .request = p9_fd_request, .cancel = p9_fd_cancel, .cancelled = p9_fd_cancelled, .show_options = p9_fd_show_options, .owner = THIS_MODULE, }; MODULE_ALIAS_9P("fd"); /** * p9_poll_workfn - poll worker thread * @work: work queue * * polls all v9fs transports for new events and queues the appropriate * work to the work queue * */ static void p9_poll_workfn(struct work_struct *work) { unsigned long flags; p9_debug(P9_DEBUG_TRANS, "start %p\n", current); spin_lock_irqsave(&p9_poll_lock, flags); while (!list_empty(&p9_poll_pending_list)) { struct p9_conn *conn = list_first_entry(&p9_poll_pending_list, struct p9_conn, poll_pending_link); list_del_init(&conn->poll_pending_link); spin_unlock_irqrestore(&p9_poll_lock, flags); p9_poll_mux(conn); spin_lock_irqsave(&p9_poll_lock, flags); } spin_unlock_irqrestore(&p9_poll_lock, flags); p9_debug(P9_DEBUG_TRANS, "finish\n"); } static int __init p9_trans_fd_init(void) { v9fs_register_trans(&p9_tcp_trans); v9fs_register_trans(&p9_unix_trans); v9fs_register_trans(&p9_fd_trans); return 0; } static void __exit p9_trans_fd_exit(void) { flush_work(&p9_poll_work); v9fs_unregister_trans(&p9_tcp_trans); v9fs_unregister_trans(&p9_unix_trans); v9fs_unregister_trans(&p9_fd_trans); } module_init(p9_trans_fd_init); module_exit(p9_trans_fd_exit); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_DESCRIPTION("Filedescriptor Transport for 9P"); MODULE_LICENSE("GPL"); |
| 483 1528 1527 1074 483 483 284 284 174 174 174 174 41 2 39 39 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004 IBM Corporation * * Author: Serge Hallyn <serue@us.ibm.com> */ #include <linux/export.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/sched/task.h> static struct kmem_cache *uts_ns_cache __ro_after_init; static struct ucounts *inc_uts_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_UTS_NAMESPACES); } static void dec_uts_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_UTS_NAMESPACES); } static struct uts_namespace *create_uts_ns(void) { struct uts_namespace *uts_ns; uts_ns = kmem_cache_alloc(uts_ns_cache, GFP_KERNEL); if (uts_ns) refcount_set(&uts_ns->ns.count, 1); return uts_ns; } /* * Clone a new ns copying an original utsname, setting refcount to 1 * @old_ns: namespace to clone * Return ERR_PTR(-ENOMEM) on error (failure to allocate), new ns otherwise */ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; ucounts = inc_uts_namespaces(user_ns); if (!ucounts) goto fail; err = -ENOMEM; ns = create_uts_ns(); if (!ns) goto fail_dec; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free; ns->ucounts = ucounts; ns->ns.ops = &utsns_operations; down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); ns->user_ns = get_user_ns(user_ns); up_read(&uts_sem); return ns; fail_free: kmem_cache_free(uts_ns_cache, ns); fail_dec: dec_uts_namespaces(ucounts); fail: return ERR_PTR(err); } /* * Copy task tsk's utsname namespace, or clone it if flags * specifies CLONE_NEWUTS. In latter case, changes to the * utsname of this process won't be seen by parent, and vice * versa. */ struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *new_ns; BUG_ON(!old_ns); get_uts_ns(old_ns); if (!(flags & CLONE_NEWUTS)) return old_ns; new_ns = clone_uts_ns(user_ns, old_ns); put_uts_ns(old_ns); return new_ns; } void free_uts_ns(struct uts_namespace *ns) { dec_uts_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kmem_cache_free(uts_ns_cache, ns); } static inline struct uts_namespace *to_uts_ns(struct ns_common *ns) { return container_of(ns, struct uts_namespace, ns); } static struct ns_common *utsns_get(struct task_struct *task) { struct uts_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->uts_ns; get_uts_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void utsns_put(struct ns_common *ns) { put_uts_ns(to_uts_ns(ns)); } static int utsns_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct uts_namespace *ns = to_uts_ns(new); if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; get_uts_ns(ns); put_uts_ns(nsproxy->uts_ns); nsproxy->uts_ns = ns; return 0; } static struct user_namespace *utsns_owner(struct ns_common *ns) { return to_uts_ns(ns)->user_ns; } const struct proc_ns_operations utsns_operations = { .name = "uts", .type = CLONE_NEWUTS, .get = utsns_get, .put = utsns_put, .install = utsns_install, .owner = utsns_owner, }; void __init uts_ns_init(void) { uts_ns_cache = kmem_cache_create_usercopy( "uts_namespace", sizeof(struct uts_namespace), 0, SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct uts_namespace, name), sizeof_field(struct uts_namespace, name), NULL); } |
| 1613 36 36 2745 36 36 589 7 366 368 36 599 569 29 599 36 598 598 599 599 598 599 599 45 36 598 36 599 599 1008 1006 1000 938 127 951 58 949 58 76 76 951 951 58 953 953 15 335 942 949 950 348 148 347 1 1 950 946 91 90 1145 2653 1954 2706 2002 1676 2701 349 2703 526 2704 2001 662 1204 2709 1908 114 1616 1491 613 611 612 114 114 1613 1614 449 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Resizable, Scalable, Concurrent Hash Table * * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * * Code partially derived from nft_hash * Rewritten with rehash code from br_multicast plus single list * pointer as suggested by Josh Triplett */ #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/log2.h> #include <linux/sched.h> #include <linux/rculist.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/rhashtable.h> #include <linux/err.h> #include <linux/export.h> #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U union nested_table { union nested_table __rcu *table; struct rhash_lock_head __rcu *bucket; }; static u32 head_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, const struct rhash_head *he) { return rht_head_hashfn(ht, tbl, he, ht->p); } #ifdef CONFIG_PROVE_LOCKING #define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT)) int lockdep_rht_mutex_is_held(struct rhashtable *ht) { return (debug_locks) ? lockdep_is_held(&ht->mutex) : 1; } EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash) { if (!debug_locks) return 1; if (unlikely(tbl->nest)) return 1; return bit_spin_is_locked(0, (unsigned long *)&tbl->buckets[hash]); } EXPORT_SYMBOL_GPL(lockdep_rht_bucket_is_held); #else #define ASSERT_RHT_MUTEX(HT) #endif static inline union nested_table *nested_table_top( const struct bucket_table *tbl) { /* The top-level bucket entry does not need RCU protection * because it's set at the same time as tbl->nest. */ return (void *)rcu_dereference_protected(tbl->buckets[0], 1); } static void nested_table_free(union nested_table *ntbl, unsigned int size) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); const unsigned int len = 1 << shift; unsigned int i; ntbl = rcu_dereference_protected(ntbl->table, 1); if (!ntbl) return; if (size > len) { size >>= shift; for (i = 0; i < len; i++) nested_table_free(ntbl + i, size); } kfree(ntbl); } static void nested_bucket_table_free(const struct bucket_table *tbl) { unsigned int size = tbl->size >> tbl->nest; unsigned int len = 1 << tbl->nest; union nested_table *ntbl; unsigned int i; ntbl = nested_table_top(tbl); for (i = 0; i < len; i++) nested_table_free(ntbl + i, size); kfree(ntbl); } static void bucket_table_free(const struct bucket_table *tbl) { if (tbl->nest) nested_bucket_table_free(tbl); kvfree(tbl); } static void bucket_table_free_rcu(struct rcu_head *head) { bucket_table_free(container_of(head, struct bucket_table, rcu)); } static union nested_table *nested_table_alloc(struct rhashtable *ht, union nested_table __rcu **prev, bool leaf) { union nested_table *ntbl; int i; ntbl = rcu_dereference(*prev); if (ntbl) return ntbl; ntbl = alloc_hooks_tag(ht->alloc_tag, kmalloc_noprof(PAGE_SIZE, GFP_ATOMIC|__GFP_ZERO)); if (ntbl && leaf) { for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) INIT_RHT_NULLS_HEAD(ntbl[i].bucket); } if (cmpxchg((union nested_table **)prev, NULL, ntbl) == NULL) return ntbl; /* Raced with another thread. */ kfree(ntbl); return rcu_dereference(*prev); } static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, size_t nbuckets, gfp_t gfp) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); struct bucket_table *tbl; size_t size; if (nbuckets < (1 << (shift + 1))) return NULL; size = sizeof(*tbl) + sizeof(tbl->buckets[0]); tbl = alloc_hooks_tag(ht->alloc_tag, kmalloc_noprof(size, gfp|__GFP_ZERO)); if (!tbl) return NULL; if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets, false)) { kfree(tbl); return NULL; } tbl->nest = (ilog2(nbuckets) - 1) % shift + 1; return tbl; } static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, size_t nbuckets, gfp_t gfp) { struct bucket_table *tbl = NULL; size_t size; int i; static struct lock_class_key __key; tbl = alloc_hooks_tag(ht->alloc_tag, kvmalloc_node_noprof(struct_size(tbl, buckets, nbuckets), gfp|__GFP_ZERO, NUMA_NO_NODE)); size = nbuckets; if (tbl == NULL && !gfpflags_allow_blocking(gfp)) { tbl = nested_bucket_table_alloc(ht, nbuckets, gfp); nbuckets = 0; } if (tbl == NULL) return NULL; lockdep_init_map(&tbl->dep_map, "rhashtable_bucket", &__key, 0); tbl->size = size; rcu_head_init(&tbl->rcu); INIT_LIST_HEAD(&tbl->walkers); tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) INIT_RHT_NULLS_HEAD(tbl->buckets[i]); return tbl; } static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, struct bucket_table *tbl) { struct bucket_table *new_tbl; do { new_tbl = tbl; tbl = rht_dereference_rcu(tbl->future_tbl, ht); } while (tbl); return new_tbl; } static int rhashtable_rehash_one(struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); int err = -EAGAIN; struct rhash_head *head, *next, *entry; struct rhash_head __rcu **pprev = NULL; unsigned int new_hash; unsigned long flags; if (new_tbl->nest) goto out; err = -ENOENT; rht_for_each_from(entry, rht_ptr(bkt, old_tbl, old_hash), old_tbl, old_hash) { err = 0; next = rht_dereference_bucket(entry->next, old_tbl, old_hash); if (rht_is_a_nulls(next)) break; pprev = &entry->next; } if (err) goto out; new_hash = head_hashfn(ht, new_tbl, entry); flags = rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING); head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash); RCU_INIT_POINTER(entry->next, head); rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry, flags); if (pprev) rcu_assign_pointer(*pprev, next); else /* Need to preserved the bit lock. */ rht_assign_locked(bkt, next); out: return err; } static int rhashtable_rehash_chain(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); unsigned long flags; int err; if (!bkt) return 0; flags = rht_lock(old_tbl, bkt); while (!(err = rhashtable_rehash_one(ht, bkt, old_hash))) ; if (err == -ENOENT) err = 0; rht_unlock(old_tbl, bkt, flags); return err; } static int rhashtable_rehash_attach(struct rhashtable *ht, struct bucket_table *old_tbl, struct bucket_table *new_tbl) { /* Make insertions go into the new, empty table right away. Deletions * and lookups will be attempted in both tables until we synchronize. * As cmpxchg() provides strong barriers, we do not need * rcu_assign_pointer(). */ if (cmpxchg((struct bucket_table **)&old_tbl->future_tbl, NULL, new_tbl) != NULL) return -EEXIST; return 0; } static int rhashtable_rehash_table(struct rhashtable *ht) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct bucket_table *new_tbl; struct rhashtable_walker *walker; unsigned int old_hash; int err; new_tbl = rht_dereference(old_tbl->future_tbl, ht); if (!new_tbl) return 0; for (old_hash = 0; old_hash < old_tbl->size; old_hash++) { err = rhashtable_rehash_chain(ht, old_hash); if (err) return err; cond_resched(); } /* Publish the new table pointer. */ rcu_assign_pointer(ht->tbl, new_tbl); spin_lock(&ht->lock); list_for_each_entry(walker, &old_tbl->walkers, list) walker->tbl = NULL; /* Wait for readers. All new readers will see the new * table, and thus no references to the old table will * remain. * We do this inside the locked region so that * rhashtable_walk_stop() can use rcu_head_after_call_rcu() * to check if it should not re-link the table. */ call_rcu(&old_tbl->rcu, bucket_table_free_rcu); spin_unlock(&ht->lock); return rht_dereference(new_tbl->future_tbl, ht) ? -EAGAIN : 0; } static int rhashtable_rehash_alloc(struct rhashtable *ht, struct bucket_table *old_tbl, unsigned int size) { struct bucket_table *new_tbl; int err; ASSERT_RHT_MUTEX(ht); new_tbl = bucket_table_alloc(ht, size, GFP_KERNEL); if (new_tbl == NULL) return -ENOMEM; err = rhashtable_rehash_attach(ht, old_tbl, new_tbl); if (err) bucket_table_free(new_tbl); return err; } /** * rhashtable_shrink - Shrink hash table while allowing concurrent lookups * @ht: the hash table to shrink * * This function shrinks the hash table to fit, i.e., the smallest * size would not cause it to expand right away automatically. * * The caller must ensure that no concurrent resizing occurs by holding * ht->mutex. * * The caller must ensure that no concurrent table mutations take place. * It is however valid to have concurrent lookups if they are RCU protected. * * It is valid to have concurrent insertions and deletions protected by per * bucket locks or concurrent RCU protected lookups and traversals. */ static int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); unsigned int nelems = atomic_read(&ht->nelems); unsigned int size = 0; if (nelems) size = roundup_pow_of_two(nelems * 3 / 2); if (size < ht->p.min_size) size = ht->p.min_size; if (old_tbl->size <= size) return 0; if (rht_dereference(old_tbl->future_tbl, ht)) return -EEXIST; return rhashtable_rehash_alloc(ht, old_tbl, size); } static void rht_deferred_worker(struct work_struct *work) { struct rhashtable *ht; struct bucket_table *tbl; int err = 0; ht = container_of(work, struct rhashtable, run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); tbl = rhashtable_last_table(ht, tbl); if (rht_grow_above_75(ht, tbl)) err = rhashtable_rehash_alloc(ht, tbl, tbl->size * 2); else if (ht->p.automatic_shrinking && rht_shrink_below_30(ht, tbl)) err = rhashtable_shrink(ht); else if (tbl->nest) err = rhashtable_rehash_alloc(ht, tbl, tbl->size); if (!err || err == -EEXIST) { int nerr; nerr = rhashtable_rehash_table(ht); err = err ?: nerr; } mutex_unlock(&ht->mutex); if (err) schedule_work(&ht->run_work); } static int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl) { struct bucket_table *old_tbl; struct bucket_table *new_tbl; unsigned int size; int err; old_tbl = rht_dereference_rcu(ht->tbl, ht); size = tbl->size; err = -EBUSY; if (rht_grow_above_75(ht, tbl)) size *= 2; /* Do not schedule more than one rehash */ else if (old_tbl != tbl) goto fail; err = -ENOMEM; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC | __GFP_NOWARN); if (new_tbl == NULL) goto fail; err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { bucket_table_free(new_tbl); if (err == -EEXIST) err = 0; } else schedule_work(&ht->run_work); return err; fail: /* Do not fail the insert if someone else did a rehash. */ if (likely(rcu_access_pointer(tbl->future_tbl))) return 0; /* Schedule async rehash to retry allocation in process context. */ if (err == -ENOMEM) schedule_work(&ht->run_work); return err; } static void *rhashtable_lookup_one(struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, const void *key, struct rhash_head *obj) { struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; struct rhash_head __rcu **pprev = NULL; struct rhash_head *head; int elasticity; elasticity = RHT_ELASTICITY; rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; struct rhlist_head *plist; elasticity--; if (!key || (ht->p.obj_cmpfn ? ht->p.obj_cmpfn(&arg, rht_obj(ht, head)) : rhashtable_compare(&arg, rht_obj(ht, head)))) { pprev = &head->next; continue; } if (!ht->rhlist) return rht_obj(ht, head); list = container_of(obj, struct rhlist_head, rhead); plist = container_of(head, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, plist); head = rht_dereference_bucket(head->next, tbl, hash); RCU_INIT_POINTER(list->rhead.next, head); if (pprev) rcu_assign_pointer(*pprev, obj); else /* Need to preserve the bit lock */ rht_assign_locked(bkt, obj); return NULL; } if (elasticity <= 0) return ERR_PTR(-EAGAIN); return ERR_PTR(-ENOENT); } static struct bucket_table *rhashtable_insert_one( struct rhashtable *ht, struct rhash_lock_head __rcu **bkt, struct bucket_table *tbl, unsigned int hash, struct rhash_head *obj, void *data) { struct bucket_table *new_tbl; struct rhash_head *head; if (!IS_ERR_OR_NULL(data)) return ERR_PTR(-EEXIST); if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT) return ERR_CAST(data); new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (new_tbl) return new_tbl; if (PTR_ERR(data) != -ENOENT) return ERR_CAST(data); if (unlikely(rht_grow_above_max(ht, tbl))) return ERR_PTR(-E2BIG); if (unlikely(rht_grow_above_100(ht, tbl))) return ERR_PTR(-EAGAIN); head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); if (ht->rhlist) { struct rhlist_head *list; list = container_of(obj, struct rhlist_head, rhead); RCU_INIT_POINTER(list->next, NULL); } /* bkt is always the head of the list, so it holds * the lock, which we need to preserve */ rht_assign_locked(bkt, obj); return NULL; } static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, struct rhash_head *obj) { struct bucket_table *new_tbl; struct bucket_table *tbl; struct rhash_lock_head __rcu **bkt; unsigned long flags; unsigned int hash; void *data; new_tbl = rcu_dereference(ht->tbl); do { tbl = new_tbl; hash = rht_head_hashfn(ht, tbl, obj, ht->p); if (rcu_access_pointer(tbl->future_tbl)) /* Failure is OK */ bkt = rht_bucket_var(tbl, hash); else bkt = rht_bucket_insert(ht, tbl, hash); if (bkt == NULL) { new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { bool inserted; flags = rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, hash, obj, data); inserted = data && !new_tbl; if (inserted) atomic_inc(&ht->nelems); if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); rht_unlock(tbl, bkt, flags); if (inserted && rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); } } while (!IS_ERR_OR_NULL(new_tbl)); if (PTR_ERR(data) == -EAGAIN) data = ERR_PTR(rhashtable_insert_rehash(ht, tbl) ?: -EAGAIN); return data; } void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, struct rhash_head *obj) { void *data; do { rcu_read_lock(); data = rhashtable_try_insert(ht, key, obj); rcu_read_unlock(); } while (PTR_ERR(data) == -EAGAIN); return data; } EXPORT_SYMBOL_GPL(rhashtable_insert_slow); /** * rhashtable_walk_enter - Initialise an iterator * @ht: Table to walk over * @iter: Hash table Iterator * * This function prepares a hash table walk. * * Note that if you restart a walk after rhashtable_walk_stop you * may see the same object twice. Also, you may miss objects if * there are removals in between rhashtable_walk_stop and the next * call to rhashtable_walk_start. * * For a completely stable walk you should construct your own data * structure outside the hash table. * * This function may be called from any process context, including * non-preemptible context, but cannot be called from softirq or * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ void rhashtable_walk_enter(struct rhashtable *ht, struct rhashtable_iter *iter) { iter->ht = ht; iter->p = NULL; iter->slot = 0; iter->skip = 0; iter->end_of_table = 0; spin_lock(&ht->lock); iter->walker.tbl = rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock)); list_add(&iter->walker.list, &iter->walker.tbl->walkers); spin_unlock(&ht->lock); } EXPORT_SYMBOL_GPL(rhashtable_walk_enter); /** * rhashtable_walk_exit - Free an iterator * @iter: Hash table Iterator * * This function frees resources allocated by rhashtable_walk_enter. */ void rhashtable_walk_exit(struct rhashtable_iter *iter) { spin_lock(&iter->ht->lock); if (iter->walker.tbl) list_del(&iter->walker.list); spin_unlock(&iter->ht->lock); } EXPORT_SYMBOL_GPL(rhashtable_walk_exit); /** * rhashtable_walk_start_check - Start a hash table walk * @iter: Hash table iterator * * Start a hash table walk at the current iterator position. Note that we take * the RCU lock in all cases including when we return an error. So you must * always call rhashtable_walk_stop to clean up. * * Returns zero if successful. * * Returns -EAGAIN if resize event occurred. Note that the iterator * will rewind back to the beginning and you may use it immediately * by calling rhashtable_walk_next. * * rhashtable_walk_start is defined as an inline variant that returns * void. This is preferred in cases where the caller would ignore * resize events and always continue. */ int rhashtable_walk_start_check(struct rhashtable_iter *iter) __acquires(RCU) { struct rhashtable *ht = iter->ht; bool rhlist = ht->rhlist; rcu_read_lock(); spin_lock(&ht->lock); if (iter->walker.tbl) list_del(&iter->walker.list); spin_unlock(&ht->lock); if (iter->end_of_table) return 0; if (!iter->walker.tbl) { iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht); iter->slot = 0; iter->skip = 0; return -EAGAIN; } if (iter->p && !rhlist) { /* * We need to validate that 'p' is still in the table, and * if so, update 'skip' */ struct rhash_head *p; int skip = 0; rht_for_each_rcu(p, iter->walker.tbl, iter->slot) { skip++; if (p == iter->p) { iter->skip = skip; goto found; } } iter->p = NULL; } else if (iter->p && rhlist) { /* Need to validate that 'list' is still in the table, and * if so, update 'skip' and 'p'. */ struct rhash_head *p; struct rhlist_head *list; int skip = 0; rht_for_each_rcu(p, iter->walker.tbl, iter->slot) { for (list = container_of(p, struct rhlist_head, rhead); list; list = rcu_dereference(list->next)) { skip++; if (list == iter->list) { iter->p = p; iter->skip = skip; goto found; } } } iter->p = NULL; } found: return 0; } EXPORT_SYMBOL_GPL(rhashtable_walk_start_check); /** * __rhashtable_walk_find_next - Find the next element in a table (or the first * one in case of a new walk). * * @iter: Hash table iterator * * Returns the found object or NULL when the end of the table is reached. * * Returns -EAGAIN if resize event occurred. */ static void *__rhashtable_walk_find_next(struct rhashtable_iter *iter) { struct bucket_table *tbl = iter->walker.tbl; struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; bool rhlist = ht->rhlist; if (!tbl) return NULL; for (; iter->slot < tbl->size; iter->slot++) { int skip = iter->skip; rht_for_each_rcu(p, tbl, iter->slot) { if (rhlist) { list = container_of(p, struct rhlist_head, rhead); do { if (!skip) goto next; skip--; list = rcu_dereference(list->next); } while (list); continue; } if (!skip) break; skip--; } next: if (!rht_is_a_nulls(p)) { iter->skip++; iter->p = p; iter->list = list; return rht_obj(ht, rhlist ? &list->rhead : p); } iter->skip = 0; } iter->p = NULL; /* Ensure we see any new tables. */ smp_rmb(); iter->walker.tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (iter->walker.tbl) { iter->slot = 0; iter->skip = 0; return ERR_PTR(-EAGAIN); } else { iter->end_of_table = true; } return NULL; } /** * rhashtable_walk_next - Return the next object and advance the iterator * @iter: Hash table iterator * * Note that you must call rhashtable_walk_stop when you are finished * with the walk. * * Returns the next object or NULL when the end of the table is reached. * * Returns -EAGAIN if resize event occurred. Note that the iterator * will rewind back to the beginning and you may continue to use it. */ void *rhashtable_walk_next(struct rhashtable_iter *iter) { struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; bool rhlist = ht->rhlist; if (p) { if (!rhlist || !(list = rcu_dereference(list->next))) { p = rcu_dereference(p->next); list = container_of(p, struct rhlist_head, rhead); } if (!rht_is_a_nulls(p)) { iter->skip++; iter->p = p; iter->list = list; return rht_obj(ht, rhlist ? &list->rhead : p); } /* At the end of this slot, switch to next one and then find * next entry from that point. */ iter->skip = 0; iter->slot++; } return __rhashtable_walk_find_next(iter); } EXPORT_SYMBOL_GPL(rhashtable_walk_next); /** * rhashtable_walk_peek - Return the next object but don't advance the iterator * @iter: Hash table iterator * * Returns the next object or NULL when the end of the table is reached. * * Returns -EAGAIN if resize event occurred. Note that the iterator * will rewind back to the beginning and you may continue to use it. */ void *rhashtable_walk_peek(struct rhashtable_iter *iter) { struct rhlist_head *list = iter->list; struct rhashtable *ht = iter->ht; struct rhash_head *p = iter->p; if (p) return rht_obj(ht, ht->rhlist ? &list->rhead : p); /* No object found in current iter, find next one in the table. */ if (iter->skip) { /* A nonzero skip value points to the next entry in the table * beyond that last one that was found. Decrement skip so * we find the current value. __rhashtable_walk_find_next * will restore the original value of skip assuming that * the table hasn't changed. */ iter->skip--; } return __rhashtable_walk_find_next(iter); } EXPORT_SYMBOL_GPL(rhashtable_walk_peek); /** * rhashtable_walk_stop - Finish a hash table walk * @iter: Hash table iterator * * Finish a hash table walk. Does not reset the iterator to the start of the * hash table. */ void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { struct rhashtable *ht; struct bucket_table *tbl = iter->walker.tbl; if (!tbl) goto out; ht = iter->ht; spin_lock(&ht->lock); if (rcu_head_after_call_rcu(&tbl->rcu, bucket_table_free_rcu)) /* This bucket table is being freed, don't re-link it. */ iter->walker.tbl = NULL; else list_add(&iter->walker.list, &tbl->walkers); spin_unlock(&ht->lock); out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(rhashtable_walk_stop); static size_t rounded_hashtable_size(const struct rhashtable_params *params) { size_t retsize; if (params->nelem_hint) retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3), (unsigned long)params->min_size); else retsize = max(HASH_DEFAULT_SIZE, (unsigned long)params->min_size); return retsize; } static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) { return jhash2(key, length, seed); } /** * rhashtable_init - initialize a new hash table * @ht: hash table to be initialized * @params: configuration parameters * * Initializes a new hash table based on the provided configuration * parameters. A table can be configured either with a variable or * fixed length key: * * Configuration Example 1: Fixed length keys * struct test_obj { * int key; * void * my_member; * struct rhash_head node; * }; * * struct rhashtable_params params = { * .head_offset = offsetof(struct test_obj, node), * .key_offset = offsetof(struct test_obj, key), * .key_len = sizeof(int), * .hashfn = jhash, * }; * * Configuration Example 2: Variable length keys * struct test_obj { * [...] * struct rhash_head node; * }; * * u32 my_hash_fn(const void *data, u32 len, u32 seed) * { * struct test_obj *obj = data; * * return [... hash ...]; * } * * struct rhashtable_params params = { * .head_offset = offsetof(struct test_obj, node), * .hashfn = jhash, * .obj_hashfn = my_hash_fn, * }; */ int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params) { struct bucket_table *tbl; size_t size; if ((!params->key_len && !params->obj_hashfn) || (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); memcpy(&ht->p, params, sizeof(*params)); alloc_tag_record(ht->alloc_tag); if (params->min_size) ht->p.min_size = roundup_pow_of_two(params->min_size); /* Cap total entries at 2^31 to avoid nelems overflow. */ ht->max_elems = 1u << 31; if (params->max_size) { ht->p.max_size = rounddown_pow_of_two(params->max_size); if (ht->p.max_size < ht->max_elems / 2) ht->max_elems = ht->p.max_size * 2; } ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); size = rounded_hashtable_size(&ht->p); ht->key_len = ht->p.key_len; if (!params->hashfn) { ht->p.hashfn = jhash; if (!(ht->key_len & (sizeof(u32) - 1))) { ht->key_len /= sizeof(u32); ht->p.hashfn = rhashtable_jhash2; } } /* * This is api initialization and thus we need to guarantee the * initial rhashtable allocation. Upon failure, retry with the * smallest possible size with __GFP_NOFAIL semantics. */ tbl = bucket_table_alloc(ht, size, GFP_KERNEL); if (unlikely(tbl == NULL)) { size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE); tbl = bucket_table_alloc(ht, size, GFP_KERNEL | __GFP_NOFAIL); } atomic_set(&ht->nelems, 0); RCU_INIT_POINTER(ht->tbl, tbl); INIT_WORK(&ht->run_work, rht_deferred_worker); return 0; } EXPORT_SYMBOL_GPL(rhashtable_init_noprof); /** * rhltable_init - initialize a new hash list table * @hlt: hash list table to be initialized * @params: configuration parameters * * Initializes a new hash list table. * * See documentation for rhashtable_init. */ int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params) { int err; err = rhashtable_init_noprof(&hlt->ht, params); hlt->ht.rhlist = true; return err; } EXPORT_SYMBOL_GPL(rhltable_init_noprof); static void rhashtable_free_one(struct rhashtable *ht, struct rhash_head *obj, void (*free_fn)(void *ptr, void *arg), void *arg) { struct rhlist_head *list; if (!ht->rhlist) { free_fn(rht_obj(ht, obj), arg); return; } list = container_of(obj, struct rhlist_head, rhead); do { obj = &list->rhead; list = rht_dereference(list->next, ht); free_fn(rht_obj(ht, obj), arg); } while (list); } /** * rhashtable_free_and_destroy - free elements and destroy hash table * @ht: the hash table to destroy * @free_fn: callback to release resources of element * @arg: pointer passed to free_fn * * Stops an eventual async resize. If defined, invokes free_fn for each * element to releasal resources. Please note that RCU protected * readers may still be accessing the elements. Releasing of resources * must occur in a compatible manner. Then frees the bucket array. * * This function will eventually sleep to wait for an async resize * to complete. The caller is responsible that no further write operations * occurs in parallel. */ void rhashtable_free_and_destroy(struct rhashtable *ht, void (*free_fn)(void *ptr, void *arg), void *arg) { struct bucket_table *tbl, *next_tbl; unsigned int i; cancel_work_sync(&ht->run_work); mutex_lock(&ht->mutex); tbl = rht_dereference(ht->tbl, ht); restart: if (free_fn) { for (i = 0; i < tbl->size; i++) { struct rhash_head *pos, *next; cond_resched(); for (pos = rht_ptr_exclusive(rht_bucket(tbl, i)), next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL; !rht_is_a_nulls(pos); pos = next, next = !rht_is_a_nulls(pos) ? rht_dereference(pos->next, ht) : NULL) rhashtable_free_one(ht, pos, free_fn, arg); } } next_tbl = rht_dereference(tbl->future_tbl, ht); bucket_table_free(tbl); if (next_tbl) { tbl = next_tbl; goto restart; } mutex_unlock(&ht->mutex); } EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy); void rhashtable_destroy(struct rhashtable *ht) { return rhashtable_free_and_destroy(ht, NULL, NULL); } EXPORT_SYMBOL_GPL(rhashtable_destroy); struct rhash_lock_head __rcu **__rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; unsigned int subhash = hash; union nested_table *ntbl; ntbl = nested_table_top(tbl); ntbl = rht_dereference_bucket_rcu(ntbl[index].table, tbl, hash); subhash >>= tbl->nest; while (ntbl && size > (1 << shift)) { index = subhash & ((1 << shift) - 1); ntbl = rht_dereference_bucket_rcu(ntbl[index].table, tbl, hash); size >>= shift; subhash >>= shift; } if (!ntbl) return NULL; return &ntbl[subhash].bucket; } EXPORT_SYMBOL_GPL(__rht_bucket_nested); struct rhash_lock_head __rcu **rht_bucket_nested( const struct bucket_table *tbl, unsigned int hash) { static struct rhash_lock_head __rcu *rhnull; if (!rhnull) INIT_RHT_NULLS_HEAD(rhnull); return __rht_bucket_nested(tbl, hash) ?: &rhnull; } EXPORT_SYMBOL_GPL(rht_bucket_nested); struct rhash_lock_head __rcu **rht_bucket_nested_insert( struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) { const unsigned int shift = PAGE_SHIFT - ilog2(sizeof(void *)); unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; union nested_table *ntbl; ntbl = nested_table_top(tbl); hash >>= tbl->nest; ntbl = nested_table_alloc(ht, &ntbl[index].table, size <= (1 << shift)); while (ntbl && size > (1 << shift)) { index = hash & ((1 << shift) - 1); size >>= shift; hash >>= shift; ntbl = nested_table_alloc(ht, &ntbl[index].table, size <= (1 << shift)); } if (!ntbl) return NULL; return &ntbl[hash].bucket; } EXPORT_SYMBOL_GPL(rht_bucket_nested_insert); |
| 9 2 1 1 1 1 2 1 13 18 3 1 15 2 14 15 5 13 4 12 2 7 13 10 2 1 2 109 14 2 25 84 1 73 10 24 15 11 2 1 8 2 15 59 78 3 75 3 3 2 1 2 126 126 258 111 1 2 2 3 1 10 89 3 1 6 9 12 2 1 1 9 2 2 3 3 1 1 1 57 4 1 1 2 6 42 36 1 3 17 2 78 1 2 1 13 10 391 12 1 68 2 80 80 2 83 83 83 10 1 1 8 7 8 2 1 5 2 94 94 94 95 80 80 17 17 17 86 73 73 73 73 73 72 73 14 44 17 9 5 45 7 21 8 16 1 13 59 4 55 72 72 55 10 10 10 2 2 10 10 2 1 4 3 3 7 3 4 2 2 48 63 63 63 8 2 6 4 4 127 1 125 126 1 1 9 8 2 7 1 4 2 13 13 3 1 1 4 2 1 1 16 16 16 1 6 1 6 77 1 14 13 1 12 2 12 2 4 7 11 8 2 1 1 126 126 126 126 126 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic PPP layer for Linux. * * Copyright 1999-2002 Paul Mackerras. * * The generic PPP layer handles the PPP network interfaces, the * /dev/ppp device, packet and VJ compression, and multilink. * It talks to PPP `channels' via the interface defined in * include/linux/ppp_channel.h. Channels provide the basic means for * sending and receiving PPP frames on some kind of communications * channel. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. * * ==FILEVERSION 20041108== */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/ppp_defs.h> #include <linux/filter.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/rwsem.h> #include <linux/stddef.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/unaligned.h> #include <net/netdev_lock.h> #include <net/slhc_vj.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #define PPP_VERSION "2.4.2" /* * Network protocols we support. */ #define NP_IP 0 /* Internet Protocol V4 */ #define NP_IPV6 1 /* Internet Protocol V6 */ #define NP_IPX 2 /* IPX protocol */ #define NP_AT 3 /* Appletalk protocol */ #define NP_MPLS_UC 4 /* MPLS unicast */ #define NP_MPLS_MC 5 /* MPLS multicast */ #define NUM_NP 6 /* Number of NPs. */ #define MPHDRLEN 6 /* multilink protocol header length */ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ #define PPP_PROTO_LEN 2 #define PPP_LCP_HDRLEN 4 /* The filter instructions generated by libpcap are constructed * assuming a four-byte PPP header on each packet, where the last * 2 bytes are the protocol field defined in the RFC and the first * byte of the first 2 bytes indicates the direction. * The second byte is currently unused, but we still need to initialize * it to prevent crafted BPF programs from reading them which would * cause reading of uninitialized data. */ #define PPP_FILTER_OUTBOUND_TAG 0x0100 #define PPP_FILTER_INBOUND_TAG 0x0000 /* * An instance of /dev/ppp can be associated with either a ppp * interface unit or a ppp channel. In both cases, file->private_data * points to one of these. */ struct ppp_file { enum { INTERFACE=1, CHANNEL } kind; struct sk_buff_head xq; /* pppd transmit queue */ struct sk_buff_head rq; /* receive queue for pppd */ wait_queue_head_t rwait; /* for poll on reading /dev/ppp */ refcount_t refcnt; /* # refs (incl /dev/ppp attached) */ int hdrlen; /* space to leave for headers */ int index; /* interface unit / channel number */ int dead; /* unit/channel has been shut down */ }; #define PF_TO_X(pf, X) container_of(pf, X, file) #define PF_TO_PPP(pf) PF_TO_X(pf, struct ppp) #define PF_TO_CHANNEL(pf) PF_TO_X(pf, struct channel) /* * Data structure to hold primary network stats for which * we want to use 64 bit storage. Other network stats * are stored in dev->stats of the ppp strucute. */ struct ppp_link_stats { u64 rx_packets; u64 tx_packets; u64 rx_bytes; u64 tx_bytes; }; /* * Data structure describing one ppp unit. * A ppp unit corresponds to a ppp network interface device * and represents a multilink bundle. * It can have 0 or more ppp channels connected to it. */ struct ppp { struct ppp_file file; /* stuff for read/write/poll 0 */ struct file *owner; /* file that owns this unit 48 */ struct list_head channels; /* list of attached channels 4c */ int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ unsigned int rstate; /* receive state bits 6c */ int debug; /* debug flags 70 */ struct slcompress *vj; /* state for VJ header compression */ enum NPmode npmode[NUM_NP]; /* what to do with each net proto 78 */ struct sk_buff *xmit_pending; /* a packet ready to go out 88 */ struct compressor *xcomp; /* transmit packet compressor 8c */ void *xc_state; /* its internal state 90 */ struct compressor *rcomp; /* receive decompressor 94 */ void *rc_state; /* its internal state 98 */ unsigned long last_xmit; /* jiffies when last pkt sent 9c */ unsigned long last_recv; /* jiffies when last pkt rcvd a0 */ struct net_device *dev; /* network interface device a4 */ int closing; /* is device closing down? a8 */ #ifdef CONFIG_PPP_MULTILINK int nxchan; /* next channel to send something on */ u32 nxseq; /* next sequence number to send */ int mrru; /* MP: max reconst. receive unit */ u32 nextseq; /* MP: seq no of next packet */ u32 minseq; /* MP: min of most recent seqnos */ struct sk_buff_head mrq; /* MP: receive reconstruction queue */ #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER struct bpf_prog *pass_filter; /* filter for packets to pass */ struct bpf_prog *active_filter; /* filter for pkts to reset idle */ #endif /* CONFIG_PPP_FILTER */ struct net *ppp_net; /* the net we belong to */ struct ppp_link_stats stats64; /* 64 bit network stats */ }; /* * Bits in flags: SC_NO_TCP_CCID, SC_CCP_OPEN, SC_CCP_UP, SC_LOOP_TRAFFIC, * SC_MULTILINK, SC_MP_SHORTSEQ, SC_MP_XSHORTSEQ, SC_COMP_TCP, SC_REJ_COMP_TCP, * SC_MUST_COMP * Bits in rstate: SC_DECOMP_RUN, SC_DC_ERROR, SC_DC_FERROR. * Bits in xstate: SC_COMP_RUN */ #define SC_FLAG_BITS (SC_NO_TCP_CCID|SC_CCP_OPEN|SC_CCP_UP|SC_LOOP_TRAFFIC \ |SC_MULTILINK|SC_MP_SHORTSEQ|SC_MP_XSHORTSEQ \ |SC_COMP_TCP|SC_REJ_COMP_TCP|SC_MUST_COMP) /* * Private data structure for each channel. * This includes the data structure used for multilink. */ struct channel { struct ppp_file file; /* stuff for read/write/poll */ struct list_head list; /* link in all/new_channels list */ struct ppp_channel *chan; /* public channel data structure */ struct rw_semaphore chan_sem; /* protects `chan' during chan ioctl */ spinlock_t downl; /* protects `chan', file.xq dequeue */ struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ netns_tracker ns_tracker; struct list_head clist; /* link in list of channels per unit */ rwlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ u32 lastseq; /* MP: last sequence # received */ int speed; /* speed of the corresponding ppp channel*/ #endif /* CONFIG_PPP_MULTILINK */ }; struct ppp_config { struct file *file; s32 unit; bool ifname_is_set; }; /* * SMP locking issues: * Both the ppp.rlock and ppp.wlock locks protect the ppp.channels * list and the ppp.n_channels field, you need to take both locks * before you modify them. * The lock ordering is: channel.upl -> ppp.wlock -> ppp.rlock -> * channel.downl. */ static DEFINE_MUTEX(ppp_mutex); static atomic_t ppp_unit_count = ATOMIC_INIT(0); static atomic_t channel_count = ATOMIC_INIT(0); /* per-net private data for this module */ static unsigned int ppp_net_id __read_mostly; struct ppp_net { /* units to ppp mapping */ struct idr units_idr; /* * all_ppp_mutex protects the units_idr mapping. * It also ensures that finding a ppp unit in the units_idr * map and updating its file.refcnt field is atomic. */ struct mutex all_ppp_mutex; /* channels */ struct list_head all_channels; struct list_head new_channels; int last_channel_index; /* * all_channels_lock protects all_channels and * last_channel_index, and the atomicity of find * a channel and updating its file.refcnt field. */ spinlock_t all_channels_lock; }; /* Get the PPP protocol number from a skb */ #define PPP_PROTO(skb) get_unaligned_be16((skb)->data) /* We limit the length of ppp->file.rq to this (arbitrary) value */ #define PPP_MAX_RQLEN 32 /* * Maximum number of multilink fragments queued up. * This has to be large enough to cope with the maximum latency of * the slowest channel relative to the others. Strictly it should * depend on the number of channels and their characteristics. */ #define PPP_MP_MAX_QLEN 128 /* Multilink header bits. */ #define B 0x80 /* this fragment begins a packet */ #define E 0x40 /* this fragment ends a packet */ /* Compare multilink sequence numbers (assumed to be 32 bits wide) */ #define seq_before(a, b) ((s32)((a) - (b)) < 0) #define seq_after(a, b) ((s32)((a) - (b)) > 0) /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_receive_error(struct ppp *ppp); static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb); #ifdef CONFIG_PPP_MULTILINK static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_mp_reconstruct(struct ppp *ppp); static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb); #endif /* CONFIG_PPP_MULTILINK */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data); static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound); static void ppp_ccp_closed(struct ppp *ppp); static struct compressor *find_compressor(int type); static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st); static int ppp_create_interface(struct net *net, struct file *file, int *unit); static void init_ppp_file(struct ppp_file *pf, int kind); static void ppp_destroy_interface(struct ppp *ppp); static struct ppp *ppp_find_unit(struct ppp_net *pn, int unit); static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); static void ppp_setup(struct net_device *dev); static const struct net_device_ops ppp_netdev_ops; static const struct class ppp_class = { .name = "ppp", }; /* per net-namespace data */ static inline struct ppp_net *ppp_pernet(struct net *net) { return net_generic(net, ppp_net_id); } /* Translates a PPP protocol number to a NP index (NP == network protocol) */ static inline int proto_to_npindex(int proto) { switch (proto) { case PPP_IP: return NP_IP; case PPP_IPV6: return NP_IPV6; case PPP_IPX: return NP_IPX; case PPP_AT: return NP_AT; case PPP_MPLS_UC: return NP_MPLS_UC; case PPP_MPLS_MC: return NP_MPLS_MC; } return -EINVAL; } /* Translates an NP index into a PPP protocol number */ static const int npindex_to_proto[NUM_NP] = { PPP_IP, PPP_IPV6, PPP_IPX, PPP_AT, PPP_MPLS_UC, PPP_MPLS_MC, }; /* Translates an ethertype into an NP index */ static inline int ethertype_to_npindex(int ethertype) { switch (ethertype) { case ETH_P_IP: return NP_IP; case ETH_P_IPV6: return NP_IPV6; case ETH_P_IPX: return NP_IPX; case ETH_P_PPPTALK: case ETH_P_ATALK: return NP_AT; case ETH_P_MPLS_UC: return NP_MPLS_UC; case ETH_P_MPLS_MC: return NP_MPLS_MC; } return -1; } /* Translates an NP index into an ethertype */ static const int npindex_to_ethertype[NUM_NP] = { ETH_P_IP, ETH_P_IPV6, ETH_P_IPX, ETH_P_PPPTALK, ETH_P_MPLS_UC, ETH_P_MPLS_MC, }; /* * Locking shorthand. */ #define ppp_xmit_lock(ppp) spin_lock_bh(&(ppp)->wlock) #define ppp_xmit_unlock(ppp) spin_unlock_bh(&(ppp)->wlock) #define ppp_recv_lock(ppp) spin_lock_bh(&(ppp)->rlock) #define ppp_recv_unlock(ppp) spin_unlock_bh(&(ppp)->rlock) #define ppp_lock(ppp) do { ppp_xmit_lock(ppp); \ ppp_recv_lock(ppp); } while (0) #define ppp_unlock(ppp) do { ppp_recv_unlock(ppp); \ ppp_xmit_unlock(ppp); } while (0) /* * /dev/ppp device routines. * The /dev/ppp device is used by pppd to control the ppp unit. * It supports the read, write, ioctl and poll functions. * Open instances of /dev/ppp can be in one of three states: * unattached, attached to a ppp unit, or attached to a ppp channel. */ static int ppp_open(struct inode *inode, struct file *file) { /* * This could (should?) be enforced by the permissions on /dev/ppp. */ if (!ns_capable(file->f_cred->user_ns, CAP_NET_ADMIN)) return -EPERM; return 0; } static int ppp_release(struct inode *unused, struct file *file) { struct ppp_file *pf = file->private_data; struct ppp *ppp; if (pf) { file->private_data = NULL; if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); rtnl_lock(); if (file == ppp->owner) unregister_netdevice(ppp->dev); rtnl_unlock(); } if (refcount_dec_and_test(&pf->refcnt)) { switch (pf->kind) { case INTERFACE: ppp_destroy_interface(PF_TO_PPP(pf)); break; case CHANNEL: ppp_destroy_channel(PF_TO_CHANNEL(pf)); break; } } } return 0; } static ssize_t ppp_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; DECLARE_WAITQUEUE(wait, current); ssize_t ret; struct sk_buff *skb = NULL; struct iovec iov; struct iov_iter to; ret = count; if (!pf) return -ENXIO; add_wait_queue(&pf->rwait, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); skb = skb_dequeue(&pf->rq); if (skb) break; ret = 0; if (pf->dead) break; if (pf->kind == INTERFACE) { /* * Return 0 (EOF) on an interface that has no * channels connected, unless it is looping * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) { ppp_recv_unlock(ppp); break; } ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; schedule(); } set_current_state(TASK_RUNNING); remove_wait_queue(&pf->rwait, &wait); if (!skb) goto out; ret = -EOVERFLOW; if (skb->len > count) goto outf; ret = -EFAULT; iov.iov_base = buf; iov.iov_len = count; iov_iter_init(&to, ITER_DEST, &iov, 1, count); if (skb_copy_datagram_iter(skb, 0, &to, skb->len)) goto outf; ret = skb->len; outf: kfree_skb(skb); out: return ret; } static bool ppp_check_packet(struct sk_buff *skb, size_t count) { /* LCP packets must include LCP header which 4 bytes long: * 1-byte code, 1-byte identifier, and 2-byte length. */ return get_unaligned_be16(skb->data) != PPP_LCP || count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; } static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; struct sk_buff *skb; ssize_t ret; if (!pf) return -ENXIO; /* All PPP packets should start with the 2-byte protocol */ if (count < PPP_PROTO_LEN) return -EINVAL; ret = -ENOMEM; skb = alloc_skb(count + pf->hdrlen, GFP_KERNEL); if (!skb) goto out; skb_reserve(skb, pf->hdrlen); ret = -EFAULT; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); goto out; } ret = -EINVAL; if (unlikely(!ppp_check_packet(skb, count))) { kfree_skb(skb); goto out; } switch (pf->kind) { case INTERFACE: ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } ret = count; out: return ret; } /* No kernel lock - fine */ static __poll_t ppp_poll(struct file *file, poll_table *wait) { struct ppp_file *pf = file->private_data; __poll_t mask; if (!pf) return 0; poll_wait(file, &pf->rwait, wait); mask = EPOLLOUT | EPOLLWRNORM; if (skb_peek(&pf->rq)) mask |= EPOLLIN | EPOLLRDNORM; if (pf->dead) mask |= EPOLLHUP; else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= EPOLLIN | EPOLLRDNORM; ppp_recv_unlock(ppp); } return mask; } #ifdef CONFIG_PPP_FILTER static struct bpf_prog *get_filter(struct sock_fprog *uprog) { struct sock_fprog_kern fprog; struct bpf_prog *res = NULL; int err; if (!uprog->len) return NULL; /* uprog->len is unsigned short, so no overflow here */ fprog.len = uprog->len; fprog.filter = memdup_array_user(uprog->filter, uprog->len, sizeof(struct sock_filter)); if (IS_ERR(fprog.filter)) return ERR_CAST(fprog.filter); err = bpf_prog_create(&res, &fprog); kfree(fprog.filter); return err ? ERR_PTR(err) : res; } static struct bpf_prog *ppp_get_filter(struct sock_fprog __user *p) { struct sock_fprog uprog; if (copy_from_user(&uprog, p, sizeof(struct sock_fprog))) return ERR_PTR(-EFAULT); return get_filter(&uprog); } #ifdef CONFIG_COMPAT struct sock_fprog32 { unsigned short len; compat_caddr_t filter; }; #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) static struct bpf_prog *compat_ppp_get_filter(struct sock_fprog32 __user *p) { struct sock_fprog32 uprog32; struct sock_fprog uprog; if (copy_from_user(&uprog32, p, sizeof(struct sock_fprog32))) return ERR_PTR(-EFAULT); uprog.len = uprog32.len; uprog.filter = compat_ptr(uprog32.filter); return get_filter(&uprog); } #endif #endif /* Bridge one PPP channel to another. * When two channels are bridged, ppp_input on one channel is redirected to * the other's ops->start_xmit handler. * In order to safely bridge channels we must reject channels which are already * part of a bridge instance, or which form part of an existing unit. * Once successfully bridged, each channel holds a reference on the other * to prevent it being freed while the bridge is extant. */ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb) { write_lock_bh(&pch->upl); if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) { write_unlock_bh(&pch->upl); return -EALREADY; } refcount_inc(&pchb->file.refcnt); rcu_assign_pointer(pch->bridge, pchb); write_unlock_bh(&pch->upl); write_lock_bh(&pchb->upl); if (pchb->ppp || rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl))) { write_unlock_bh(&pchb->upl); goto err_unset; } refcount_inc(&pch->file.refcnt); rcu_assign_pointer(pchb->bridge, pch); write_unlock_bh(&pchb->upl); return 0; err_unset: write_lock_bh(&pch->upl); /* Re-read pch->bridge with upl held in case it was modified concurrently */ pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); synchronize_rcu(); if (pchb) if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return -EALREADY; } static int ppp_unbridge_channels(struct channel *pch) { struct channel *pchb, *pchbb; write_lock_bh(&pch->upl); pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); if (!pchb) { write_unlock_bh(&pch->upl); return -EINVAL; } RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); /* Only modify pchb if phcb->bridge points back to pch. * If not, it implies that there has been a race unbridging (and possibly * even rebridging) pchb. We should leave pchb alone to avoid either a * refcount underflow, or breaking another established bridge instance. */ write_lock_bh(&pchb->upl); pchbb = rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl)); if (pchbb == pch) RCU_INIT_POINTER(pchb->bridge, NULL); write_unlock_bh(&pchb->upl); synchronize_rcu(); if (pchbb == pch) if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return 0; } static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; struct ppp *ppp; int err = -EFAULT, val, val2, i; struct ppp_idle32 idle32; struct ppp_idle64 idle64; struct npioctl npi; int unit, cflags; struct slcompress *vj; void __user *argp = (void __user *)arg; int __user *p = argp; mutex_lock(&ppp_mutex); pf = file->private_data; if (!pf) { err = ppp_unattached_ioctl(current->nsproxy->net_ns, pf, file, cmd, arg); goto out; } if (cmd == PPPIOCDETACH) { /* * PPPIOCDETACH is no longer supported as it was heavily broken, * and is only known to have been used by pppd older than * ppp-2.4.2 (released November 2003). */ pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n", current->comm, current->pid); err = -EINVAL; goto out; } if (pf->kind == CHANNEL) { struct channel *pch, *pchb; struct ppp_channel *chan; struct ppp_net *pn; pch = PF_TO_CHANNEL(pf); switch (cmd) { case PPPIOCCONNECT: if (get_user(unit, p)) break; err = ppp_connect_channel(pch, unit); break; case PPPIOCDISCONN: err = ppp_disconnect_channel(pch); break; case PPPIOCBRIDGECHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(current->nsproxy->net_ns); spin_lock_bh(&pn->all_channels_lock); pchb = ppp_find_channel(pn, unit); /* Hold a reference to prevent pchb being freed while * we establish the bridge. */ if (pchb) refcount_inc(&pchb->file.refcnt); spin_unlock_bh(&pn->all_channels_lock); if (!pchb) break; err = ppp_bridge_channels(pch, pchb); /* Drop earlier refcount now bridge establishment is complete */ if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); break; case PPPIOCUNBRIDGECHAN: err = ppp_unbridge_channels(pch); break; default: down_read(&pch->chan_sem); chan = pch->chan; err = -ENOTTY; if (chan && chan->ops->ioctl) err = chan->ops->ioctl(chan, cmd, arg); up_read(&pch->chan_sem); } goto out; } if (pf->kind != INTERFACE) { /* can't happen */ pr_err("PPP: not interface or channel??\n"); err = -EINVAL; goto out; } ppp = PF_TO_PPP(pf); switch (cmd) { case PPPIOCSMRU: if (get_user(val, p)) break; ppp->mru = val; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; ppp_lock(ppp); cflags = ppp->flags & ~val; #ifdef CONFIG_PPP_MULTILINK if (!(ppp->flags & SC_MULTILINK) && (val & SC_MULTILINK)) ppp->nextseq = 0; #endif ppp->flags = val & SC_FLAG_BITS; ppp_unlock(ppp); if (cflags & SC_CCP_OPEN) ppp_ccp_closed(ppp); err = 0; break; case PPPIOCGFLAGS: val = ppp->flags | ppp->xstate | ppp->rstate; if (put_user(val, p)) break; err = 0; break; case PPPIOCSCOMPRESS: { struct ppp_option_data data; if (copy_from_user(&data, argp, sizeof(data))) err = -EFAULT; else err = ppp_set_compress(ppp, &data); break; } case PPPIOCGUNIT: if (put_user(ppp->file.index, p)) break; err = 0; break; case PPPIOCSDEBUG: if (get_user(val, p)) break; ppp->debug = val; err = 0; break; case PPPIOCGDEBUG: if (put_user(ppp->debug, p)) break; err = 0; break; case PPPIOCGIDLE32: idle32.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle32.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle32, sizeof(idle32))) break; err = 0; break; case PPPIOCGIDLE64: idle64.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle64.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle64, sizeof(idle64))) break; err = 0; break; case PPPIOCSMAXCID: if (get_user(val, p)) break; val2 = 15; if ((val >> 16) != 0) { val2 = val >> 16; val &= 0xffff; } vj = slhc_init(val2+1, val+1); if (IS_ERR(vj)) { err = PTR_ERR(vj); break; } ppp_lock(ppp); if (ppp->vj) slhc_free(ppp->vj); ppp->vj = vj; ppp_unlock(ppp); err = 0; break; case PPPIOCGNPMODE: case PPPIOCSNPMODE: if (copy_from_user(&npi, argp, sizeof(npi))) break; err = proto_to_npindex(npi.protocol); if (err < 0) break; i = err; if (cmd == PPPIOCGNPMODE) { err = -EFAULT; npi.mode = ppp->npmode[i]; if (copy_to_user(argp, &npi, sizeof(npi))) break; } else { ppp->npmode[i] = npi.mode; /* we may be able to transmit more packets now (??) */ netif_wake_queue(ppp->dev); } err = 0; break; #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS: case PPPIOCSACTIVE: { struct bpf_prog *filter = ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ #ifdef CONFIG_PPP_MULTILINK case PPPIOCSMRRU: if (get_user(val, p)) break; ppp_recv_lock(ppp); ppp->mrru = val; ppp_recv_unlock(ppp); err = 0; break; #endif /* CONFIG_PPP_MULTILINK */ default: err = -ENOTTY; } out: mutex_unlock(&ppp_mutex); return err; } #ifdef CONFIG_COMPAT struct ppp_option_data32 { compat_uptr_t ptr; u32 length; compat_int_t transmit; }; #define PPPIOCSCOMPRESS32 _IOW('t', 77, struct ppp_option_data32) static long ppp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; int err = -ENOIOCTLCMD; void __user *argp = (void __user *)arg; mutex_lock(&ppp_mutex); pf = file->private_data; if (pf && pf->kind == INTERFACE) { struct ppp *ppp = PF_TO_PPP(pf); switch (cmd) { #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS32: case PPPIOCSACTIVE32: { struct bpf_prog *filter = compat_ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS32) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ case PPPIOCSCOMPRESS32: { struct ppp_option_data32 data32; if (copy_from_user(&data32, argp, sizeof(data32))) { err = -EFAULT; } else { struct ppp_option_data data = { .ptr = compat_ptr(data32.ptr), .length = data32.length, .transmit = data32.transmit }; err = ppp_set_compress(ppp, &data); } break; } } } mutex_unlock(&ppp_mutex); /* all other commands have compatible arguments */ if (err == -ENOIOCTLCMD) err = ppp_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); return err; } #endif static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg) { int unit, err = -EFAULT; struct ppp *ppp; struct channel *chan; struct ppp_net *pn; int __user *p = (int __user *)arg; switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ if (get_user(unit, p)) break; err = ppp_create_interface(net, file, &unit); if (err < 0) break; err = -EFAULT; if (put_user(unit, p)) break; err = 0; break; case PPPIOCATTACH: /* Attach to an existing ppp unit */ if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (ppp) { refcount_inc(&ppp->file.refcnt); file->private_data = &ppp->file; err = 0; } mutex_unlock(&pn->all_ppp_mutex); break; case PPPIOCATTCHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); spin_lock_bh(&pn->all_channels_lock); chan = ppp_find_channel(pn, unit); if (chan) { refcount_inc(&chan->file.refcnt); file->private_data = &chan->file; err = 0; } spin_unlock_bh(&pn->all_channels_lock); break; default: err = -ENOTTY; } return err; } static const struct file_operations ppp_device_fops = { .owner = THIS_MODULE, .read = ppp_read, .write = ppp_write, .poll = ppp_poll, .unlocked_ioctl = ppp_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ppp_compat_ioctl, #endif .open = ppp_open, .release = ppp_release, .llseek = noop_llseek, }; static void ppp_nl_dellink(struct net_device *dev, struct list_head *head); static __net_init int ppp_init_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); idr_init(&pn->units_idr); mutex_init(&pn->all_ppp_mutex); INIT_LIST_HEAD(&pn->all_channels); INIT_LIST_HEAD(&pn->new_channels); spin_lock_init(&pn->all_channels_lock); return 0; } static __net_exit void ppp_exit_rtnl_net(struct net *net, struct list_head *dev_to_kill) { struct ppp_net *pn = net_generic(net, ppp_net_id); struct ppp *ppp; int id; idr_for_each_entry(&pn->units_idr, ppp, id) ppp_nl_dellink(ppp->dev, dev_to_kill); } static __net_exit void ppp_exit_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); mutex_destroy(&pn->all_ppp_mutex); idr_destroy(&pn->units_idr); WARN_ON_ONCE(!list_empty(&pn->all_channels)); WARN_ON_ONCE(!list_empty(&pn->new_channels)); } static struct pernet_operations ppp_net_ops = { .init = ppp_init_net, .exit_rtnl = ppp_exit_rtnl_net, .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) { struct ppp_net *pn = ppp_pernet(ppp->ppp_net); int ret; mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); if (!netdev_name_in_use(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); if (ret < 0) goto err; } } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST * too if idr allocation fails; this makes pppd retry without * requesting a specific unit number. */ if (unit_find(&pn->units_idr, unit)) { ret = -EEXIST; goto err; } ret = unit_set(&pn->units_idr, ppp, unit); if (ret < 0) { /* Rewrite error for backward compatibility */ ret = -EEXIST; goto err; } } ppp->file.index = ret; if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); return 0; err_unit: mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); return ret; } static int ppp_dev_configure(struct net *src_net, struct net_device *dev, const struct ppp_config *conf) { struct ppp *ppp = netdev_priv(dev); int indx; int err; int cpu; ppp->dev = dev; ppp->ppp_net = src_net; ppp->mru = PPP_MRU; ppp->owner = conf->file; init_ppp_file(&ppp->file, INTERFACE); ppp->file.hdrlen = PPP_HDRLEN - 2; /* don't count proto bytes */ for (indx = 0; indx < NUM_NP; ++indx) ppp->npmode[indx] = NPMODE_PASS; INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); ppp->xmit_recursion = alloc_percpu(int); if (!ppp->xmit_recursion) { err = -ENOMEM; goto err1; } for_each_possible_cpu(cpu) (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER ppp->pass_filter = NULL; ppp->active_filter = NULL; #endif /* CONFIG_PPP_FILTER */ err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) goto err2; conf->file->private_data = &ppp->file; return 0; err2: free_percpu(ppp->xmit_recursion); err1: return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { [IFLA_PPP_DEV_FD] = { .type = NLA_S32 }, }; static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return -EINVAL; if (!data[IFLA_PPP_DEV_FD]) return -EINVAL; if (nla_get_s32(data[IFLA_PPP_DEV_FD]) < 0) return -EBADF; return 0; } static int ppp_nl_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ppp_config conf = { .unit = -1, .ifname_is_set = true, }; struct file *file; int err; file = fget(nla_get_s32(data[IFLA_PPP_DEV_FD])); if (!file) return -EBADF; /* rtnl_lock is already held here, but ppp_create_interface() locks * ppp_mutex before holding rtnl_lock. Using mutex_trylock() avoids * possible deadlock due to lock order inversion, at the cost of * pushing the problem back to userspace. */ if (!mutex_trylock(&ppp_mutex)) { err = -EBUSY; goto out; } if (file->f_op != &ppp_device_fops || file->private_data) { err = -EBADF; goto out_unlock; } conf.file = file; /* Don't use device name generated by the rtnetlink layer when ifname * isn't specified. Let ppp_dev_configure() set the device name using * the PPP unit identifer as suffix (i.e. ppp<unit_id>). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(link_net, dev, &conf); out_unlock: mutex_unlock(&ppp_mutex); out: fput(file); return err; } static void ppp_nl_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static size_t ppp_nl_get_size(const struct net_device *dev) { return 0; } static int ppp_nl_fill_info(struct sk_buff *skb, const struct net_device *dev) { return 0; } static struct net *ppp_nl_get_link_net(const struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); return READ_ONCE(ppp->ppp_net); } static struct rtnl_link_ops ppp_link_ops __read_mostly = { .kind = "ppp", .maxtype = IFLA_PPP_MAX, .policy = ppp_nl_policy, .priv_size = sizeof(struct ppp), .setup = ppp_setup, .validate = ppp_nl_validate, .newlink = ppp_nl_newlink, .dellink = ppp_nl_dellink, .get_size = ppp_nl_get_size, .fill_info = ppp_nl_fill_info, .get_link_net = ppp_nl_get_link_net, }; #define PPP_MAJOR 108 /* Called at boot time if ppp is compiled into the kernel, or at module load time (from init_module) if compiled as a module. */ static int __init ppp_init(void) { int err; pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { pr_err("failed to register PPP device (%d)\n", err); goto out_net; } err = class_register(&ppp_class); if (err) goto out_chrdev; err = rtnl_link_register(&ppp_link_ops); if (err) { pr_err("failed to register rtnetlink PPP handler\n"); goto out_class; } /* not a big deal if we fail here :-) */ device_create(&ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); return 0; out_class: class_unregister(&ppp_class); out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: unregister_pernet_device(&ppp_net_ops); out: return err; } /* * Network interface unit routines. */ static netdev_tx_t ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); int npi, proto; unsigned char *pp; npi = ethertype_to_npindex(ntohs(skb->protocol)); if (npi < 0) goto outf; /* Drop, accept or reject the packet */ switch (ppp->npmode[npi]) { case NPMODE_PASS: break; case NPMODE_QUEUE: /* it would be nice to have a way to tell the network system to queue this one up for later. */ goto outf; case NPMODE_DROP: case NPMODE_ERROR: goto outf; } /* Put the 2-byte PPP protocol number on the front, making sure there is room for the address and control fields. */ if (skb_cow_head(skb, PPP_HDRLEN)) goto outf; pp = skb_push(skb, 2); proto = npindex_to_proto[npi]; put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); ppp_xmit_process(ppp, skb); return NETDEV_TX_OK; outf: kfree_skb(skb); ++dev->stats.tx_dropped; return NETDEV_TX_OK; } static int ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *addr, int cmd) { struct ppp *ppp = netdev_priv(dev); int err = -EFAULT; struct ppp_stats stats; struct ppp_comp_stats cstats; char *vers; switch (cmd) { case SIOCGPPPSTATS: ppp_get_stats(ppp, &stats); if (copy_to_user(addr, &stats, sizeof(stats))) break; err = 0; break; case SIOCGPPPCSTATS: memset(&cstats, 0, sizeof(cstats)); if (ppp->xc_state) ppp->xcomp->comp_stat(ppp->xc_state, &cstats.c); if (ppp->rc_state) ppp->rcomp->decomp_stat(ppp->rc_state, &cstats.d); if (copy_to_user(addr, &cstats, sizeof(cstats))) break; err = 0; break; case SIOCGPPPVER: vers = PPP_VERSION; if (copy_to_user(addr, vers, strlen(vers) + 1)) break; err = 0; break; default: err = -EINVAL; } return err; } static void ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) { struct ppp *ppp = netdev_priv(dev); ppp_recv_lock(ppp); stats64->rx_packets = ppp->stats64.rx_packets; stats64->rx_bytes = ppp->stats64.rx_bytes; ppp_recv_unlock(ppp); ppp_xmit_lock(ppp); stats64->tx_packets = ppp->stats64.tx_packets; stats64->tx_bytes = ppp->stats64.tx_bytes; ppp_xmit_unlock(ppp); stats64->rx_errors = dev->stats.rx_errors; stats64->tx_errors = dev->stats.tx_errors; stats64->rx_dropped = dev->stats.rx_dropped; stats64->tx_dropped = dev->stats.tx_dropped; stats64->rx_length_errors = dev->stats.rx_length_errors; } static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; netdev_lockdep_set_classes(dev); ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets * unregistered. */ refcount_inc(&ppp->file.refcnt); return 0; } static void ppp_dev_uninit(struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); struct ppp_net *pn = ppp_pernet(ppp->ppp_net); ppp_lock(ppp); ppp->closing = 1; ppp_unlock(ppp); mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ppp->owner = NULL; ppp->file.dead = 1; wake_up_interruptible(&ppp->file.rwait); } static void ppp_dev_priv_destructor(struct net_device *dev) { struct ppp *ppp; ppp = netdev_priv(dev); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); } static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ppp *ppp = netdev_priv(ctx->dev); struct ppp_channel *chan; struct channel *pch; if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; if (list_empty(&ppp->channels)) return -ENODEV; pch = list_first_entry(&ppp->channels, struct channel, clist); chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; return chan->ops->fill_forward_path(ctx, path, chan); } static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, .ndo_start_xmit = ppp_start_xmit, .ndo_siocdevprivate = ppp_net_siocdevprivate, .ndo_get_stats64 = ppp_get_stats64, .ndo_fill_forward_path = ppp_fill_forward_path, }; static const struct device_type ppp_type = { .name = "ppp", }; static void ppp_setup(struct net_device *dev) { dev->netdev_ops = &ppp_netdev_ops; SET_NETDEV_DEVTYPE(dev, &ppp_type); dev->lltx = true; dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; dev->addr_len = 0; dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } /* * Transmit-side routines. */ /* Called to do any work queued up on the transmit side that can now be done */ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); if (skb) skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) netif_wake_queue(ppp->dev); else netif_stop_queue(ppp->dev); } else { kfree_skb(skb); } ppp_xmit_unlock(ppp); } static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); return; err: local_bh_enable(); kfree_skb(skb); if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } static inline struct sk_buff * pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *new_skb; int len; int new_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + ppp->dev->hard_header_len; int compressor_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + PPP_HDRLEN; new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) skb_reserve(new_skb, ppp->dev->hard_header_len - PPP_HDRLEN); /* compressor still expects A/C bytes in hdr */ len = ppp->xcomp->compress(ppp->xc_state, skb->data - 2, new_skb->data, skb->len + 2, compressor_skb_size); if (len > 0 && (ppp->flags & SC_CCP_UP)) { consume_skb(skb); skb = new_skb; skb_put(skb, len); skb_pull(skb, 2); /* pull off A/C bytes */ } else if (len == 0) { /* didn't compress, or CCP not up yet */ consume_skb(new_skb); new_skb = skb; } else { /* * (len < 0) * MPPE requires that we do not send unencrypted * frames. The compressor will return -1 if we * should drop the frame. We cannot simply test * the compress_proto because MPPE and MPPC share * the same number. */ if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); consume_skb(new_skb); new_skb = NULL; } return new_skb; } /* * Compress and send a frame. * The caller should have locked the xmit path, * and xmit_pending should be 0. */ static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *new_skb; int len; unsigned char *cp; skb->dev = ppp->dev; if (proto < 0x8000) { #ifdef CONFIG_PPP_FILTER /* check if the packet passes the pass and active filters. * See comment for PPP_FILTER_OUTBOUND_TAG above. */ *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " "not passed\n"); kfree_skb(skb); return; } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else /* for data packets, record the time */ ppp->last_xmit = jiffies; #endif /* CONFIG_PPP_FILTER */ } ++ppp->stats64.tx_packets; ppp->stats64.tx_bytes += skb->len - PPP_PROTO_LEN; switch (proto) { case PPP_IP: if (!ppp->vj || (ppp->flags & SC_COMP_TCP) == 0) break; /* try to do VJ TCP header compression */ new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); cp = skb->data + 2; len = slhc_compress(ppp->vj, cp, skb->len - 2, new_skb->data + 2, &cp, !(ppp->flags & SC_NO_TCP_CCID)); if (cp == skb->data + 2) { /* didn't compress */ consume_skb(new_skb); } else { if (cp[0] & SL_TYPE_COMPRESSED_TCP) { proto = PPP_VJC_COMP; cp[0] &= ~SL_TYPE_COMPRESSED_TCP; } else { proto = PPP_VJC_UNCOMP; cp[0] = skb->data[2]; } consume_skb(skb); skb = new_skb; cp = skb_put(skb, len + 2); cp[0] = 0; cp[1] = proto; } break; case PPP_CCP: /* peek at outbound CCP frames */ ppp_ccp_peek(ppp, skb, 0); break; } /* try to do packet compression */ if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compression required but " "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); if (!skb) goto drop; } /* * If we are waiting for traffic (demand dialling), * queue it up for pppd to receive. */ if (ppp->flags & SC_LOOP_TRAFFIC) { if (ppp->file.rq.qlen > PPP_MAX_RQLEN) goto drop; skb_queue_tail(&ppp->file.rq, skb); wake_up_interruptible(&ppp->file.rwait); return; } ppp->xmit_pending = skb; ppp_push(ppp); return; drop: kfree_skb(skb); ++ppp->dev->stats.tx_errors; } /* * Try to send the frame in xmit_pending. * The caller should have the xmit path locked. */ static void ppp_push(struct ppp *ppp) { struct list_head *list; struct channel *pch; struct sk_buff *skb = ppp->xmit_pending; if (!skb) return; list = &ppp->channels; if (list_empty(list)) { /* nowhere to send the packet, just drop it */ ppp->xmit_pending = NULL; kfree_skb(skb); return; } if ((ppp->flags & SC_MULTILINK) == 0) { /* not doing multilink: send it down the first channel */ list = list->next; pch = list_entry(list, struct channel, clist); spin_lock(&pch->downl); if (pch->chan) { if (pch->chan->ops->start_xmit(pch->chan, skb)) ppp->xmit_pending = NULL; } else { /* channel got unregistered */ kfree_skb(skb); ppp->xmit_pending = NULL; } spin_unlock(&pch->downl); return; } #ifdef CONFIG_PPP_MULTILINK /* Multilink: fragment the packet over as many links as can take the packet at the moment. */ if (!ppp_mp_explode(ppp, skb)) return; #endif /* CONFIG_PPP_MULTILINK */ ppp->xmit_pending = NULL; kfree_skb(skb); } #ifdef CONFIG_PPP_MULTILINK static bool mp_protocol_compress __read_mostly = true; module_param(mp_protocol_compress, bool, 0644); MODULE_PARM_DESC(mp_protocol_compress, "compress protocol id in multilink fragments"); /* * Divide a packet to be transmitted into fragments and * send them out the individual links. */ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) { int len, totlen; int i, bits, hdrlen, mtu; int flen; int navail, nfree, nzero; int nbigger; int totspeed; int totfree; unsigned char *p, *q; struct list_head *list; struct channel *pch; struct sk_buff *frag; struct ppp_channel *chan; totspeed = 0; /*total bitrate of the bundle*/ nfree = 0; /* # channels which have no packet already queued */ navail = 0; /* total # of usable channels (not deregistered) */ nzero = 0; /* number of channels with zero speed associated*/ totfree = 0; /*total # of channels available and *having no queued packets before *starting the fragmentation*/ hdrlen = (ppp->flags & SC_MP_XSHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; i = 0; list_for_each_entry(pch, &ppp->channels, clist) { if (pch->chan) { pch->avail = 1; navail++; pch->speed = pch->chan->speed; } else { pch->avail = 0; } if (pch->avail) { if (skb_queue_empty(&pch->file.xq) || !pch->had_frag) { if (pch->speed == 0) nzero++; else totspeed += pch->speed; pch->avail = 2; ++nfree; ++totfree; } if (!pch->had_frag && i < ppp->nxchan) ppp->nxchan = i; } ++i; } /* * Don't start sending this packet unless at least half of * the channels are free. This gives much better TCP * performance if we have a lot of channels. */ if (nfree == 0 || nfree < navail / 2) return 0; /* can't take now, leave it in xmit_pending */ /* Do protocol field compression */ p = skb->data; len = skb->len; if (*p == 0 && mp_protocol_compress) { ++p; --len; } totlen = len; nbigger = len % nfree; /* skip to the channel after the one we last used and start at that one */ list = &ppp->channels; for (i = 0; i < ppp->nxchan; ++i) { list = list->next; if (list == &ppp->channels) { i = 0; break; } } /* create a fragment for each channel */ bits = B; while (len > 0) { list = list->next; if (list == &ppp->channels) { i = 0; continue; } pch = list_entry(list, struct channel, clist); ++i; if (!pch->avail) continue; /* * Skip this channel if it has a fragment pending already and * we haven't given a fragment to all of the free channels. */ if (pch->avail == 1) { if (nfree > 0) continue; } else { pch->avail = 1; } /* check the channel's mtu and whether it is still attached. */ spin_lock(&pch->downl); if (pch->chan == NULL) { /* can't use this channel, it's being deregistered */ if (pch->speed == 0) nzero--; else totspeed -= pch->speed; spin_unlock(&pch->downl); pch->avail = 0; totlen = len; totfree--; nfree--; if (--navail == 0) break; continue; } /* *if the channel speed is not set divide *the packet evenly among the free channels; *otherwise divide it according to the speed *of the channel we are going to transmit on */ flen = len; if (nfree > 0) { if (pch->speed == 0) { flen = len/nfree; if (nbigger > 0) { flen++; nbigger--; } } else { flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / ((totspeed*totfree)/pch->speed)) - hdrlen; if (nbigger > 0) { flen += ((totfree - nzero)*pch->speed)/totspeed; nbigger -= ((totfree - nzero)*pch->speed)/ totspeed; } } nfree--; } /* *check if we are on the last channel or *we exceded the length of the data to *fragment */ if ((nfree <= 0) || (flen > len)) flen = len; /* *it is not worth to tx on slow channels: *in that case from the resulting flen according to the *above formula will be equal or less than zero. *Skip the channel in this case */ if (flen <= 0) { pch->avail = 2; spin_unlock(&pch->downl); continue; } /* * hdrlen includes the 2-byte PPP protocol field, but the * MTU counts only the payload excluding the protocol field. * (RFC1661 Section 2) */ mtu = pch->chan->mtu - (hdrlen - 2); if (mtu < 4) mtu = 4; if (flen > mtu) flen = mtu; if (flen == len) bits |= E; frag = alloc_skb(flen + hdrlen + (flen == 0), GFP_ATOMIC); if (!frag) goto noskb; q = skb_put(frag, flen + hdrlen); /* make the MP header */ put_unaligned_be16(PPP_MP, q); if (ppp->flags & SC_MP_XSHORTSEQ) { q[2] = bits + ((ppp->nxseq >> 8) & 0xf); q[3] = ppp->nxseq; } else { q[2] = bits; q[3] = ppp->nxseq >> 16; q[4] = ppp->nxseq >> 8; q[5] = ppp->nxseq; } memcpy(q + hdrlen, p, flen); /* try to send it down the channel */ chan = pch->chan; if (!skb_queue_empty(&pch->file.xq) || !chan->ops->start_xmit(chan, frag)) skb_queue_tail(&pch->file.xq, frag); pch->had_frag = 1; p += flen; len -= flen; ++ppp->nxseq; bits = 0; spin_unlock(&pch->downl); } ppp->nxchan = i; return 1; noskb: spin_unlock(&pch->downl); if (ppp->debug & 1) netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ } #endif /* CONFIG_PPP_MULTILINK */ /* Try to send data out on a channel */ static void __ppp_channel_push(struct channel *pch) { struct sk_buff *skb; struct ppp *ppp; spin_lock(&pch->downl); if (pch->chan) { while (!skb_queue_empty(&pch->file.xq)) { skb = skb_dequeue(&pch->file.xq); if (!pch->chan->ops->start_xmit(pch->chan, skb)) { /* put the packet back and try again later */ skb_queue_head(&pch->file.xq, skb); break; } } } else { /* channel got deregistered */ skb_queue_purge(&pch->file.xq); } spin_unlock(&pch->downl); /* see if there is anything from the attached unit to be sent */ if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) __ppp_xmit_process(ppp, NULL); } } static void ppp_channel_push(struct channel *pch) { read_lock_bh(&pch->upl); if (pch->ppp) { (*this_cpu_ptr(pch->ppp->xmit_recursion))++; __ppp_channel_push(pch); (*this_cpu_ptr(pch->ppp->xmit_recursion))--; } else { __ppp_channel_push(pch); } read_unlock_bh(&pch->upl); } /* * Receive-side routines. */ struct ppp_mp_skb_parm { u32 sequence; u8 BEbits; }; #define PPP_MP_CB(skb) ((struct ppp_mp_skb_parm *)((skb)->cb)) static inline void ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { ppp_recv_lock(ppp); if (!ppp->closing) ppp_receive_frame(ppp, skb, pch); else kfree_skb(skb); ppp_recv_unlock(ppp); } /** * __ppp_decompress_proto - Decompress protocol field, slim version. * @skb: Socket buffer where protocol field should be decompressed. It must have * at least 1 byte of head room and 1 byte of linear data. First byte of * data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data * length are done in this function. */ static void __ppp_decompress_proto(struct sk_buff *skb) { if (skb->data[0] & 0x01) *(u8 *)skb_push(skb, 1) = 0x00; } /** * ppp_decompress_proto - Check skb data room and decompress protocol field. * @skb: Socket buffer where protocol field should be decompressed. First byte * of data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. This function also makes * sure that skb data room is sufficient for Protocol field, before and after * decompression. * * Return: true - decompressed successfully, false - not enough room in skb. */ static bool ppp_decompress_proto(struct sk_buff *skb) { /* At least one byte should be present (if protocol is compressed) */ if (!pskb_may_pull(skb, 1)) return false; __ppp_decompress_proto(skb); /* Protocol field should occupy 2 bytes when not compressed */ return pskb_may_pull(skb, 2); } /* Attempt to handle a frame via. a bridged channel, if one exists. * If the channel is bridged, the frame is consumed by the bridge. * If not, the caller must handle the frame by normal recv mechanisms. * Returns true if the frame is consumed, false otherwise. */ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) { struct channel *pchb; rcu_read_lock(); pchb = rcu_dereference(pch->bridge); if (!pchb) goto out_rcu; spin_lock_bh(&pchb->downl); if (!pchb->chan) { /* channel got unregistered */ kfree_skb(skb); goto outl; } skb_scrub_packet(skb, !net_eq(pch->chan_net, pchb->chan_net)); if (!pchb->chan->ops->start_xmit(pchb->chan, skb)) kfree_skb(skb); outl: spin_unlock_bh(&pchb->downl); out_rcu: rcu_read_unlock(); /* If pchb is set then we've consumed the packet */ return !!pchb; } void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { struct channel *pch = chan->ppp; int proto; if (!pch) { kfree_skb(skb); return; } /* If the channel is bridged, transmit via. bridge */ if (ppp_channel_bridge_input(pch, skb)) return; read_lock_bh(&pch->upl); if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (pch->ppp) { ++pch->ppp->dev->stats.rx_length_errors; ppp_receive_error(pch->ppp); } goto done; } proto = PPP_PROTO(skb); if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) { /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ while (pch->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { ppp_do_recv(pch->ppp, skb, pch); } done: read_unlock_bh(&pch->upl); } /* Put a 0-length skb in the receive queue as an error indication */ void ppp_input_error(struct ppp_channel *chan, int code) { struct channel *pch = chan->ppp; struct sk_buff *skb; if (!pch) return; read_lock_bh(&pch->upl); if (pch->ppp) { skb = alloc_skb(0, GFP_ATOMIC); if (skb) { skb->len = 0; /* probably unnecessary */ skb->cb[0] = code; ppp_do_recv(pch->ppp, skb, pch); } } read_unlock_bh(&pch->upl); } /* * We come in here to process a received frame. * The receive side of the ppp unit is locked. */ static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { /* note: a 0-length skb is used as an error indication */ if (skb->len > 0) { skb_checksum_complete_unset(skb); #ifdef CONFIG_PPP_MULTILINK /* XXX do channel-level decompression here */ if (PPP_PROTO(skb) == PPP_MP) ppp_receive_mp_frame(ppp, skb, pch); else #endif /* CONFIG_PPP_MULTILINK */ ppp_receive_nonmp_frame(ppp, skb); } else { kfree_skb(skb); ppp_receive_error(ppp); } } static void ppp_receive_error(struct ppp *ppp) { ++ppp->dev->stats.rx_errors; if (ppp->vj) slhc_toss(ppp->vj); } static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *ns; int proto, len, npi; /* * Decompress the frame, if compressed. * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) goto err; /* At this point the "Protocol" field MUST be decompressed, either in * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame(). */ proto = PPP_PROTO(skb); switch (proto) { case PPP_VJC_COMP: /* decompress VJ compressed packets */ if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; if (skb_tailroom(skb) < 124 || skb_cloned(skb)) { /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { netdev_err(ppp->dev, "PPP: no memory " "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); skb_copy_bits(skb, 0, skb_put(ns, skb->len), skb->len); consume_skb(skb); skb = ns; } else skb->ip_summed = CHECKSUM_NONE; len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { netdev_printk(KERN_DEBUG, ppp->dev, "PPP: VJ decompression error\n"); goto err; } len += 2; if (len > skb->len) skb_put(skb, len - skb->len); else if (len < skb->len) skb_trim(skb, len); proto = PPP_IP; break; case PPP_VJC_UNCOMP: if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; /* Until we fix the decompressor need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; break; case PPP_CCP: ppp_ccp_peek(ppp, skb, 1); break; } ++ppp->stats64.rx_packets; ppp->stats64.rx_bytes += skb->len - 2; npi = proto_to_npindex(proto); if (npi < 0) { /* control or unknown frame - pass it to pppd */ skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ while (ppp->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); } else { /* network protocol frame - give it to the kernel */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter || ppp->active_filter) { if (skb_unclone(skb, GFP_ATOMIC)) goto err; /* Check if the packet passes the pass and active filters. * See comment for PPP_FILTER_INBOUND_TAG above. */ *(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG); if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " "not passed\n"); kfree_skb(skb); return; } if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ ppp->last_recv = jiffies; if ((ppp->dev->flags & IFF_UP) == 0 || ppp->npmode[npi] != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ skb_pull_rcsum(skb, 2); skb->dev = ppp->dev; skb->protocol = htons(npindex_to_ethertype[npi]); skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(ppp->dev))); netif_rx(skb); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } static struct sk_buff * ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *ns; int len; /* Until we fix all the decompressor's need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (proto == PPP_COMP) { int obuff_size; switch(ppp->rcomp->compress_proto) { case CI_MPPE: obuff_size = ppp->mru + PPP_HDRLEN + 1; break; default: obuff_size = ppp->mru + PPP_HDRLEN; break; } ns = dev_alloc_skb(obuff_size); if (!ns) { netdev_err(ppp->dev, "ppp_decompress_frame: " "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ len = ppp->rcomp->decompress(ppp->rc_state, skb->data - 2, skb->len + 2, ns->data, obuff_size); if (len < 0) { /* Pass the compressed frame to pppd as an error indication. */ if (len == DECOMP_FATALERROR) ppp->rstate |= SC_DC_FERROR; kfree_skb(ns); goto err; } consume_skb(skb); skb = ns; skb_put(skb, len); skb_pull(skb, 2); /* pull off the A/C bytes */ /* Don't call __ppp_decompress_proto() here, but instead rely on * corresponding algo (mppe/bsd/deflate) to decompress it. */ } else { /* Uncompressed frame - pass to decompressor so it can update its dictionary if necessary. */ if (ppp->rcomp->incomp) ppp->rcomp->incomp(ppp->rc_state, skb->data - 2, skb->len + 2); } return skb; err: ppp->rstate |= SC_DC_ERROR; ppp_receive_error(ppp); return skb; } #ifdef CONFIG_PPP_MULTILINK /* * Receive a multilink frame. * We put it on the reconstruction queue and then pull off * as many completed frames as we can. */ static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { u32 mask, seq; struct channel *ch; int mphdrlen = (ppp->flags & SC_MP_SHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; if (!pskb_may_pull(skb, mphdrlen + 1) || ppp->mrru == 0) goto err; /* no good, throw it away */ /* Decode sequence number and begin/end bits */ if (ppp->flags & SC_MP_SHORTSEQ) { seq = ((skb->data[2] & 0x0f) << 8) | skb->data[3]; mask = 0xfff; } else { seq = (skb->data[3] << 16) | (skb->data[4] << 8)| skb->data[5]; mask = 0xffffff; } PPP_MP_CB(skb)->BEbits = skb->data[2]; skb_pull(skb, mphdrlen); /* pull off PPP and MP headers */ /* * Do protocol ID decompression on the first fragment of each packet. * We have to do that here, because ppp_receive_nonmp_frame() expects * decompressed protocol field. */ if (PPP_MP_CB(skb)->BEbits & B) __ppp_decompress_proto(skb); /* * Expand sequence number to 32 bits, making it as close * as possible to ppp->minseq. */ seq |= ppp->minseq & ~mask; if ((int)(ppp->minseq - seq) > (int)(mask >> 1)) seq += mask + 1; else if ((int)(seq - ppp->minseq) > (int)(mask >> 1)) seq -= mask + 1; /* should never happen */ PPP_MP_CB(skb)->sequence = seq; pch->lastseq = seq; /* * If this packet comes before the next one we were expecting, * drop it. */ if (seq_before(seq, ppp->nextseq)) { kfree_skb(skb); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); return; } /* * Reevaluate minseq, the minimum over all channels of the * last sequence number received on each channel. Because of * the increasing sequence number rule, we know that any fragment * before `minseq' which hasn't arrived is never going to arrive. * The list of channels can't change because we have the receive * side of the ppp unit locked. */ list_for_each_entry(ch, &ppp->channels, clist) { if (seq_before(ch->lastseq, seq)) seq = ch->lastseq; } if (seq_before(ppp->minseq, seq)) ppp->minseq = seq; /* Put the fragment on the reconstruction queue */ ppp_mp_insert(ppp, skb); /* If the queue is getting long, don't wait any longer for packets before the start of the queue. */ if (skb_queue_len(&ppp->mrq) >= PPP_MP_MAX_QLEN) { struct sk_buff *mskb = skb_peek(&ppp->mrq); if (seq_before(ppp->minseq, PPP_MP_CB(mskb)->sequence)) ppp->minseq = PPP_MP_CB(mskb)->sequence; } /* Pull completed packets off the queue and receive them. */ while ((skb = ppp_mp_reconstruct(ppp))) { if (pskb_may_pull(skb, 2)) ppp_receive_nonmp_frame(ppp, skb); else { ++ppp->dev->stats.rx_length_errors; kfree_skb(skb); ppp_receive_error(ppp); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } /* * Insert a fragment on the MP reconstruction queue. * The queue is ordered by increasing sequence number. */ static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *p; struct sk_buff_head *list = &ppp->mrq; u32 seq = PPP_MP_CB(skb)->sequence; /* N.B. we don't need to lock the list lock because we have the ppp unit receive-side lock. */ skb_queue_walk(list, p) { if (seq_before(seq, PPP_MP_CB(p)->sequence)) break; } __skb_queue_before(list, p, skb); } /* * Reconstruct a packet from the MP fragment queue. * We go through increasing sequence numbers until we find a * complete packet, or we get to the sequence number for a fragment * which hasn't arrived but might still do so. */ static struct sk_buff * ppp_mp_reconstruct(struct ppp *ppp) { u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ netdev_err(ppp->dev, "ppp_mp_reconstruct bad " "seq %u < %u\n", PPP_MP_CB(p)->sequence, seq); __skb_unlink(p, list); kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { u32 oldseq; /* Fragment `seq' is missing. If it is after minseq, it might arrive later, so stop here. */ if (seq_after(seq, minseq)) break; /* Fragment `seq' is lost, keep going. */ lost = 1; oldseq = seq; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "lost frag %u..%u\n", oldseq, seq-1); goto again; } /* * At this point we know that all the fragments from * ppp->nextseq to seq are either present or lost. * Also, there are no complete packets in the queue * that have no missing fragments and end before this * fragment. */ /* B bit set indicates this fragment starts a packet */ if (PPP_MP_CB(p)->BEbits & B) { head = p; lost = 0; len = 0; } len += p->len; /* Got a complete packet yet? */ if (lost == 0 && (PPP_MP_CB(p)->BEbits & E) && (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; netdev_printk(KERN_DEBUG, ppp->dev, "PPP: reconstructed packet" " is too long (%d)\n", len); } else { tail = p; break; } ppp->nextseq = seq + 1; } /* * If this is the ending fragment of a packet, * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ if (PPP_MP_CB(p)->BEbits & E) { struct sk_buff *tmp2; skb_queue_reverse_walk_from_safe(list, p, tmp2) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } head = skb_peek(list); if (!head) break; } ++seq; } /* If we have a complete packet, copy it all into one skb. */ if (tail != NULL) { /* If we have discarded any fragments, signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { skb_queue_walk_safe(list, p, tmp) { if (p == head) break; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, " missed pkts %u..%u\n", ppp->nextseq, PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } skb = head; if (head != tail) { struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; p = skb_queue_next(list, head); __skb_unlink(skb, list); skb_queue_walk_from_safe(list, p, tmp) { __skb_unlink(p, list); *fragpp = p; p->next = NULL; fragpp = &p->next; skb->len += p->len; skb->data_len += p->len; skb->truesize += p->truesize; if (p == tail) break; } } else { __skb_unlink(skb, list); } ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; } #endif /* CONFIG_PPP_MULTILINK */ /* * Channel interface. */ /* Create a new, unattached ppp channel. */ int ppp_register_channel(struct ppp_channel *chan) { return ppp_register_net_channel(current->nsproxy->net_ns, chan); } /* Create a new, unattached ppp channel for specified net. */ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) { struct channel *pch; struct ppp_net *pn; pch = kzalloc(sizeof(struct channel), GFP_KERNEL); if (!pch) return -ENOMEM; pn = ppp_pernet(net); pch->ppp = NULL; pch->chan = chan; pch->chan_net = get_net_track(net, &pch->ns_tracker, GFP_KERNEL); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; #ifdef CONFIG_PPP_MULTILINK pch->lastseq = -1; #endif /* CONFIG_PPP_MULTILINK */ init_rwsem(&pch->chan_sem); spin_lock_init(&pch->downl); rwlock_init(&pch->upl); spin_lock_bh(&pn->all_channels_lock); pch->file.index = ++pn->last_channel_index; list_add(&pch->list, &pn->new_channels); atomic_inc(&channel_count); spin_unlock_bh(&pn->all_channels_lock); return 0; } /* * Return the index of a channel. */ int ppp_channel_index(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (pch) return pch->file.index; return -1; } /* * Return the PPP unit number to which a channel is connected. */ int ppp_unit_number(struct ppp_channel *chan) { struct channel *pch = chan->ppp; int unit = -1; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp) unit = pch->ppp->file.index; read_unlock_bh(&pch->upl); } return unit; } /* * Return the PPP device interface name of a channel. */ char *ppp_dev_name(struct ppp_channel *chan) { struct channel *pch = chan->ppp; char *name = NULL; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp && pch->ppp->dev) name = pch->ppp->dev->name; read_unlock_bh(&pch->upl); } return name; } /* * Disconnect a channel from the generic layer. * This must be called in process context. */ void ppp_unregister_channel(struct ppp_channel *chan) { struct channel *pch = chan->ppp; struct ppp_net *pn; if (!pch) return; /* should never happen */ chan->ppp = NULL; /* * This ensures that we have returned from any calls into * the channel's start_xmit or ioctl routine before we proceed. */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); pch->chan = NULL; spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); pn = ppp_pernet(pch->chan_net); spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); ppp_unbridge_channels(pch); pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); } /* * Callback from a channel when it can accept more to transmit. * This should be called at BH/softirq level, not interrupt level. */ void ppp_output_wakeup(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (!pch) return; ppp_channel_push(pch); } /* * Compression control. */ /* Process the PPPIOCSCOMPRESS ioctl. */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data) { int err = -EFAULT; struct compressor *cp, *ocomp; void *state, *ostate; unsigned char ccp_option[CCP_MAX_OPTION_LENGTH]; if (data->length > CCP_MAX_OPTION_LENGTH) goto out; if (copy_from_user(ccp_option, data->ptr, data->length)) goto out; err = -EINVAL; if (data->length < 2 || ccp_option[1] < 2 || ccp_option[1] > data->length) goto out; cp = try_then_request_module( find_compressor(ccp_option[0]), "ppp-compress-%d", ccp_option[0]); if (!cp) goto out; err = -ENOBUFS; if (data->transmit) { state = cp->comp_alloc(ccp_option, data->length); if (state) { ppp_xmit_lock(ppp); ppp->xstate &= ~SC_COMP_RUN; ocomp = ppp->xcomp; ostate = ppp->xc_state; ppp->xcomp = cp; ppp->xc_state = state; ppp_xmit_unlock(ppp); if (ostate) { ocomp->comp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } else { state = cp->decomp_alloc(ccp_option, data->length); if (state) { ppp_recv_lock(ppp); ppp->rstate &= ~SC_DECOMP_RUN; ocomp = ppp->rcomp; ostate = ppp->rc_state; ppp->rcomp = cp; ppp->rc_state = state; ppp_recv_unlock(ppp); if (ostate) { ocomp->decomp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } out: return err; } /* * Look at a CCP packet and update our state accordingly. * We assume the caller has the xmit or recv path locked. */ static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) { unsigned char *dp; int len; if (!pskb_may_pull(skb, CCP_HDRLEN + 2)) return; /* no header */ dp = skb->data + 2; switch (CCP_CODE(dp)) { case CCP_CONFREQ: /* A ConfReq starts negotiation of compression * in one direction of transmission, * and hence brings it down...but which way? * * Remember: * A ConfReq indicates what the sender would like to receive */ if(inbound) /* He is proposing what I should send */ ppp->xstate &= ~SC_COMP_RUN; else /* I am proposing to what he should send */ ppp->rstate &= ~SC_DECOMP_RUN; break; case CCP_TERMREQ: case CCP_TERMACK: /* * CCP is going down, both directions of transmission */ ppp->rstate &= ~SC_DECOMP_RUN; ppp->xstate &= ~SC_COMP_RUN; break; case CCP_CONFACK: if ((ppp->flags & (SC_CCP_OPEN | SC_CCP_UP)) != SC_CCP_OPEN) break; len = CCP_LENGTH(dp); if (!pskb_may_pull(skb, len + 2)) return; /* too short */ dp += CCP_HDRLEN; len -= CCP_HDRLEN; if (len < CCP_OPT_MINLEN || len < CCP_OPT_LENGTH(dp)) break; if (inbound) { /* we will start receiving compressed packets */ if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, ppp->file.index, 0, ppp->mru, ppp->debug)) { ppp->rstate |= SC_DECOMP_RUN; ppp->rstate &= ~(SC_DC_ERROR | SC_DC_FERROR); } } else { /* we will soon start sending compressed packets */ if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, ppp->file.index, 0, ppp->debug)) ppp->xstate |= SC_COMP_RUN; } break; case CCP_RESETACK: /* reset the [de]compressor */ if ((ppp->flags & SC_CCP_UP) == 0) break; if (inbound) { if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN)) { ppp->rcomp->decomp_reset(ppp->rc_state); ppp->rstate &= ~SC_DC_ERROR; } } else { if (ppp->xc_state && (ppp->xstate & SC_COMP_RUN)) ppp->xcomp->comp_reset(ppp->xc_state); } break; } } /* Free up compression resources. */ static void ppp_ccp_closed(struct ppp *ppp) { void *xstate, *rstate; struct compressor *xcomp, *rcomp; ppp_lock(ppp); ppp->flags &= ~(SC_CCP_OPEN | SC_CCP_UP); ppp->xstate = 0; xcomp = ppp->xcomp; xstate = ppp->xc_state; ppp->xc_state = NULL; ppp->rstate = 0; rcomp = ppp->rcomp; rstate = ppp->rc_state; ppp->rc_state = NULL; ppp_unlock(ppp); if (xstate) { xcomp->comp_free(xstate); module_put(xcomp->owner); } if (rstate) { rcomp->decomp_free(rstate); module_put(rcomp->owner); } } /* List of compressors. */ static LIST_HEAD(compressor_list); static DEFINE_SPINLOCK(compressor_list_lock); struct compressor_entry { struct list_head list; struct compressor *comp; }; static struct compressor_entry * find_comp_entry(int proto) { struct compressor_entry *ce; list_for_each_entry(ce, &compressor_list, list) { if (ce->comp->compress_proto == proto) return ce; } return NULL; } /* Register a compressor */ int ppp_register_compressor(struct compressor *cp) { struct compressor_entry *ce; int ret; spin_lock(&compressor_list_lock); ret = -EEXIST; if (find_comp_entry(cp->compress_proto)) goto out; ret = -ENOMEM; ce = kmalloc(sizeof(struct compressor_entry), GFP_ATOMIC); if (!ce) goto out; ret = 0; ce->comp = cp; list_add(&ce->list, &compressor_list); out: spin_unlock(&compressor_list_lock); return ret; } /* Unregister a compressor */ void ppp_unregister_compressor(struct compressor *cp) { struct compressor_entry *ce; spin_lock(&compressor_list_lock); ce = find_comp_entry(cp->compress_proto); if (ce && ce->comp == cp) { list_del(&ce->list); kfree(ce); } spin_unlock(&compressor_list_lock); } /* Find a compressor. */ static struct compressor * find_compressor(int type) { struct compressor_entry *ce; struct compressor *cp = NULL; spin_lock(&compressor_list_lock); ce = find_comp_entry(type); if (ce) { cp = ce->comp; if (!try_module_get(cp->owner)) cp = NULL; } spin_unlock(&compressor_list_lock); return cp; } /* * Miscelleneous stuff. */ static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) { struct slcompress *vj = ppp->vj; memset(st, 0, sizeof(*st)); st->p.ppp_ipackets = ppp->stats64.rx_packets; st->p.ppp_ierrors = ppp->dev->stats.rx_errors; st->p.ppp_ibytes = ppp->stats64.rx_bytes; st->p.ppp_opackets = ppp->stats64.tx_packets; st->p.ppp_oerrors = ppp->dev->stats.tx_errors; st->p.ppp_obytes = ppp->stats64.tx_bytes; if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; st->vj.vjs_compressed = vj->sls_o_compressed; st->vj.vjs_searches = vj->sls_o_searches; st->vj.vjs_misses = vj->sls_o_misses; st->vj.vjs_errorin = vj->sls_i_error; st->vj.vjs_tossed = vj->sls_i_tossed; st->vj.vjs_uncompressedin = vj->sls_i_uncompressed; st->vj.vjs_compressedin = vj->sls_i_compressed; } /* * Stuff for handling the lists of ppp units and channels * and for initialization. */ /* * Create a new ppp interface unit. Fails if it can't allocate memory * or if there is already a unit with the requested number. * unit == -1 means allocate a new number. */ static int ppp_create_interface(struct net *net, struct file *file, int *unit) { struct ppp_config conf = { .file = file, .unit = *unit, .ifname_is_set = false, }; struct net_device *dev; struct ppp *ppp; int err; dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_ENUM, ppp_setup); if (!dev) { err = -ENOMEM; goto err; } dev_net_set(dev, net); dev->rtnl_link_ops = &ppp_link_ops; rtnl_lock(); err = ppp_dev_configure(net, dev, &conf); if (err < 0) goto err_dev; ppp = netdev_priv(dev); *unit = ppp->file.index; rtnl_unlock(); return 0; err_dev: rtnl_unlock(); free_netdev(dev); err: return err; } /* * Initialize a ppp_file structure. */ static void init_ppp_file(struct ppp_file *pf, int kind) { pf->kind = kind; skb_queue_head_init(&pf->xq); skb_queue_head_init(&pf->rq); refcount_set(&pf->refcnt, 1); init_waitqueue_head(&pf->rwait); } /* * Free the memory used by a ppp unit. This is only called once * there are no channels connected to the unit and no file structs * that reference the unit. */ static void ppp_destroy_interface(struct ppp *ppp) { atomic_dec(&ppp_unit_count); if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ netdev_err(ppp->dev, "ppp: destroying ppp struct %p " "but dead=%d n_channels=%d !\n", ppp, ppp->file.dead, ppp->n_channels); return; } ppp_ccp_closed(ppp); if (ppp->vj) { slhc_free(ppp->vj); ppp->vj = NULL; } skb_queue_purge(&ppp->file.xq); skb_queue_purge(&ppp->file.rq); #ifdef CONFIG_PPP_MULTILINK skb_queue_purge(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter) { bpf_prog_destroy(ppp->pass_filter); ppp->pass_filter = NULL; } if (ppp->active_filter) { bpf_prog_destroy(ppp->active_filter); ppp->active_filter = NULL; } #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } /* * Locate an existing ppp unit. * The caller should have locked the all_ppp_mutex. */ static struct ppp * ppp_find_unit(struct ppp_net *pn, int unit) { return unit_find(&pn->units_idr, unit); } /* * Locate an existing ppp channel. * The caller should have locked the all_channels_lock. * First we look in the new_channels list, then in the * all_channels list. If found in the new_channels list, * we move it to the all_channels list. This is for speed * when we have a lot of channels in use. */ static struct channel * ppp_find_channel(struct ppp_net *pn, int unit) { struct channel *pch; list_for_each_entry(pch, &pn->new_channels, list) { if (pch->file.index == unit) { list_move(&pch->list, &pn->all_channels); return pch; } } list_for_each_entry(pch, &pn->all_channels, list) { if (pch->file.index == unit) return pch; } return NULL; } /* * Connect a PPP channel to a PPP interface unit. */ static int ppp_connect_channel(struct channel *pch, int unit) { struct ppp *ppp; struct ppp_net *pn; int ret = -ENXIO; int hdrlen; pn = ppp_pernet(pch->chan_net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (!ppp) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) goto outl; ppp_lock(ppp); spin_lock_bh(&pch->downl); if (!pch->chan) { /* Don't connect unregistered channels */ spin_unlock_bh(&pch->downl); ppp_unlock(ppp); ret = -ENOTCONN; goto outl; } if (pch->chan->direct_xmit) ppp->dev->priv_flags |= IFF_NO_QUEUE; else ppp->dev->priv_flags &= ~IFF_NO_QUEUE; spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; list_add_tail(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); ppp_unlock(ppp); ret = 0; outl: write_unlock_bh(&pch->upl); out: mutex_unlock(&pn->all_ppp_mutex); return ret; } /* * Disconnect a channel from its ppp unit. */ static int ppp_disconnect_channel(struct channel *pch) { struct ppp *ppp; int err = -EINVAL; write_lock_bh(&pch->upl); ppp = pch->ppp; pch->ppp = NULL; write_unlock_bh(&pch->upl); if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); list_del(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; } return err; } /* * Free up the resources used by a ppp channel. */ static void ppp_destroy_channel(struct channel *pch) { put_net_track(pch->chan_net, &pch->ns_tracker); pch->chan_net = NULL; atomic_dec(&channel_count); if (!pch->file.dead) { /* "can't happen" */ pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); skb_queue_purge(&pch->file.rq); kfree(pch); } static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) pr_err("PPP: removing module but units remain!\n"); rtnl_link_unregister(&ppp_link_ops); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(&ppp_class, MKDEV(PPP_MAJOR, 0)); class_unregister(&ppp_class); unregister_pernet_device(&ppp_net_ops); } /* * Units handling. Caller must protect concurrent access * by holding all_ppp_mutex */ /* associate pointer with specified number */ static int unit_set(struct idr *p, void *ptr, int n) { int unit; unit = idr_alloc(p, ptr, n, n + 1, GFP_KERNEL); if (unit == -ENOSPC) unit = -EINVAL; return unit; } /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr, int min) { return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ static void unit_put(struct idr *p, int n) { idr_remove(p, n); } /* get pointer associated with the number */ static void *unit_find(struct idr *p, int n) { return idr_find(p, n); } /* Module/initialization stuff */ module_init(ppp_init); module_exit(ppp_cleanup); EXPORT_SYMBOL(ppp_register_net_channel); EXPORT_SYMBOL(ppp_register_channel); EXPORT_SYMBOL(ppp_unregister_channel); EXPORT_SYMBOL(ppp_channel_index); EXPORT_SYMBOL(ppp_unit_number); EXPORT_SYMBOL(ppp_dev_name); EXPORT_SYMBOL(ppp_input); EXPORT_SYMBOL(ppp_input_error); EXPORT_SYMBOL(ppp_output_wakeup); EXPORT_SYMBOL(ppp_register_compressor); EXPORT_SYMBOL(ppp_unregister_compressor); MODULE_DESCRIPTION("Generic PPP layer driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0); MODULE_ALIAS_RTNL_LINK("ppp"); MODULE_ALIAS("devname:ppp"); |
| 2 2 5 2 1 2 2 1 1 1 1 1 1 3 1 2 1 1 2 1 1 40 39 1 73 73 143 143 73 73 59 59 7 7 112 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NetLabel CALIPSO/IPv6 Support * * This file defines the CALIPSO/IPv6 functions for the NetLabel system. The * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and CALIPSO. * * Authors: Paul Moore <paul@paul-moore.com> * Huw Davies <huw@codeweavers.com> */ /* (c) Copyright Hewlett-Packard Development Company, L.P., 2006 * (c) Copyright Huw Davies <huw@codeweavers.com>, 2015 */ #include <linux/types.h> #include <linux/socket.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/audit.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/netlabel.h> #include <net/calipso.h> #include <linux/atomic.h> #include "netlabel_user.h" #include "netlabel_calipso.h" #include "netlabel_mgmt.h" #include "netlabel_domainhash.h" /* Argument struct for calipso_doi_walk() */ struct netlbl_calipso_doiwalk_arg { struct netlink_callback *nl_cb; struct sk_buff *skb; u32 seq; }; /* Argument struct for netlbl_domhsh_walk() */ struct netlbl_domhsh_walk_arg { struct netlbl_audit *audit_info; u32 doi; }; /* NetLabel Generic NETLINK CALIPSO family */ static struct genl_family netlbl_calipso_gnl_family; /* NetLabel Netlink attribute policy */ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = { [NLBL_CALIPSO_A_DOI] = { .type = NLA_U32 }, [NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 }, }; static const struct netlbl_calipso_ops *calipso_ops; /** * netlbl_calipso_ops_register - Register the CALIPSO operations * @ops: ops to register * * Description: * Register the CALIPSO packet engine operations. * */ const struct netlbl_calipso_ops * netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) { return xchg(&calipso_ops, ops); } EXPORT_SYMBOL(netlbl_calipso_ops_register); static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) { return READ_ONCE(calipso_ops); } /* NetLabel Command Handlers */ /** * netlbl_calipso_add_pass - Adds a CALIPSO pass DOI definition * @info: the Generic NETLINK info block * @audit_info: NetLabel audit information * * Description: * Create a new CALIPSO_MAP_PASS DOI definition based on the given ADD message * and add it to the CALIPSO engine. Return zero on success and non-zero on * error. * */ static int netlbl_calipso_add_pass(struct genl_info *info, struct netlbl_audit *audit_info) { int ret_val; struct calipso_doi *doi_def = NULL; doi_def = kmalloc(sizeof(*doi_def), GFP_KERNEL); if (!doi_def) return -ENOMEM; doi_def->type = CALIPSO_MAP_PASS; doi_def->doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); ret_val = calipso_doi_add(doi_def, audit_info); if (ret_val != 0) calipso_doi_free(doi_def); return ret_val; } /** * netlbl_calipso_add - Handle an ADD message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Create a new DOI definition based on the given ADD message and add it to the * CALIPSO engine. Returns zero on success, negative values on failure. * */ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct netlbl_audit audit_info; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (!info->attrs[NLBL_CALIPSO_A_DOI] || !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; if (!ops) return -EOPNOTSUPP; netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: ret_val = netlbl_calipso_add_pass(info, &audit_info); break; } if (ret_val == 0) atomic_inc(&netlabel_mgmt_protocount); return ret_val; } /** * netlbl_calipso_list - Handle a LIST message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated LIST message and respond accordingly. * Returns zero on success and negative values on error. * */ static int netlbl_calipso_list(struct sk_buff *skb, struct genl_info *info) { int ret_val; struct sk_buff *ans_skb = NULL; void *data; u32 doi; struct calipso_doi *doi_def; if (!info->attrs[NLBL_CALIPSO_A_DOI]) { ret_val = -EINVAL; goto list_failure; } doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); doi_def = calipso_doi_getdef(doi); if (!doi_def) { ret_val = -EINVAL; goto list_failure; } ans_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!ans_skb) { ret_val = -ENOMEM; goto list_failure_put; } data = genlmsg_put_reply(ans_skb, info, &netlbl_calipso_gnl_family, 0, NLBL_CALIPSO_C_LIST); if (!data) { ret_val = -ENOMEM; goto list_failure_put; } ret_val = nla_put_u32(ans_skb, NLBL_CALIPSO_A_MTYPE, doi_def->type); if (ret_val != 0) goto list_failure_put; calipso_doi_putdef(doi_def); genlmsg_end(ans_skb, data); return genlmsg_reply(ans_skb, info); list_failure_put: calipso_doi_putdef(doi_def); list_failure: kfree_skb(ans_skb); return ret_val; } /** * netlbl_calipso_listall_cb - calipso_doi_walk() callback for LISTALL * @doi_def: the CALIPSO DOI definition * @arg: the netlbl_calipso_doiwalk_arg structure * * Description: * This function is designed to be used as a callback to the * calipso_doi_walk() function for use in generating a response for a LISTALL * message. Returns the size of the message on success, negative values on * failure. * */ static int netlbl_calipso_listall_cb(struct calipso_doi *doi_def, void *arg) { int ret_val = -ENOMEM; struct netlbl_calipso_doiwalk_arg *cb_arg = arg; void *data; data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_calipso_gnl_family, NLM_F_MULTI, NLBL_CALIPSO_C_LISTALL); if (!data) goto listall_cb_failure; ret_val = nla_put_u32(cb_arg->skb, NLBL_CALIPSO_A_DOI, doi_def->doi); if (ret_val != 0) goto listall_cb_failure; ret_val = nla_put_u32(cb_arg->skb, NLBL_CALIPSO_A_MTYPE, doi_def->type); if (ret_val != 0) goto listall_cb_failure; genlmsg_end(cb_arg->skb, data); return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); return ret_val; } /** * netlbl_calipso_listall - Handle a LISTALL message * @skb: the NETLINK buffer * @cb: the NETLINK callback * * Description: * Process a user generated LISTALL message and respond accordingly. Returns * zero on success and negative values on error. * */ static int netlbl_calipso_listall(struct sk_buff *skb, struct netlink_callback *cb) { struct netlbl_calipso_doiwalk_arg cb_arg; u32 doi_skip = cb->args[0]; cb_arg.nl_cb = cb; cb_arg.skb = skb; cb_arg.seq = cb->nlh->nlmsg_seq; calipso_doi_walk(&doi_skip, netlbl_calipso_listall_cb, &cb_arg); cb->args[0] = doi_skip; return skb->len; } /** * netlbl_calipso_remove_cb - netlbl_calipso_remove() callback for REMOVE * @entry: LSM domain mapping entry * @arg: the netlbl_domhsh_walk_arg structure * * Description: * This function is intended for use by netlbl_calipso_remove() as the callback * for the netlbl_domhsh_walk() function; it removes LSM domain map entries * which are associated with the CALIPSO DOI specified in @arg. Returns zero on * success, negative values on failure. * */ static int netlbl_calipso_remove_cb(struct netlbl_dom_map *entry, void *arg) { struct netlbl_domhsh_walk_arg *cb_arg = arg; if (entry->def.type == NETLBL_NLTYPE_CALIPSO && entry->def.calipso->doi == cb_arg->doi) return netlbl_domhsh_remove_entry(entry, cb_arg->audit_info); return 0; } /** * netlbl_calipso_remove - Handle a REMOVE message * @skb: the NETLINK buffer * @info: the Generic NETLINK info block * * Description: * Process a user generated REMOVE message and respond accordingly. Returns * zero on success, negative values on failure. * */ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) { int ret_val = -EINVAL; struct netlbl_domhsh_walk_arg cb_arg; struct netlbl_audit audit_info; u32 skip_bkt = 0; u32 skip_chain = 0; if (!info->attrs[NLBL_CALIPSO_A_DOI]) return -EINVAL; netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, netlbl_calipso_remove_cb, &cb_arg); if (ret_val == 0 || ret_val == -ENOENT) { ret_val = calipso_doi_remove(cb_arg.doi, &audit_info); if (ret_val == 0) atomic_dec(&netlabel_mgmt_protocount); } return ret_val; } /* NetLabel Generic NETLINK Command Definitions */ static const struct genl_small_ops netlbl_calipso_ops[] = { { .cmd = NLBL_CALIPSO_C_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_calipso_add, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_REMOVE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = netlbl_calipso_remove, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LIST, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = netlbl_calipso_list, .dumpit = NULL, }, { .cmd = NLBL_CALIPSO_C_LISTALL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, .doit = NULL, .dumpit = netlbl_calipso_listall, }, }; static struct genl_family netlbl_calipso_gnl_family __ro_after_init = { .hdrsize = 0, .name = NETLBL_NLTYPE_CALIPSO_NAME, .version = NETLBL_PROTO_VERSION, .maxattr = NLBL_CALIPSO_A_MAX, .policy = calipso_genl_policy, .module = THIS_MODULE, .small_ops = netlbl_calipso_ops, .n_small_ops = ARRAY_SIZE(netlbl_calipso_ops), .resv_start_op = NLBL_CALIPSO_C_LISTALL + 1, }; /* NetLabel Generic NETLINK Protocol Functions */ /** * netlbl_calipso_genl_init - Register the CALIPSO NetLabel component * * Description: * Register the CALIPSO packet NetLabel component with the Generic NETLINK * mechanism. Returns zero on success, negative values on failure. * */ int __init netlbl_calipso_genl_init(void) { return genl_register_family(&netlbl_calipso_gnl_family); } /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure * @audit_info: NetLabel audit information * * Description: * The caller defines a new DOI for use by the CALIPSO engine and calls this * function to add it to the list of acceptable domains. The caller must * ensure that the mapping table specified in @doi_def->map meets all of the * requirements of the mapping type (see calipso.h for details). Returns * zero on success and non-zero on failure. * */ int calipso_doi_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_add(doi_def, audit_info); return ret_val; } /** * calipso_doi_free - Frees a DOI definition * @doi_def: the DOI definition * * Description: * This function frees all of the memory associated with a DOI definition. * */ void calipso_doi_free(struct calipso_doi *doi_def) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->doi_free(doi_def); } /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will * be called to release their own LSM domain mappings as well as our own * domain list. Returns zero on success and negative values on failure. * */ int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_remove(doi, audit_info); return ret_val; } /** * calipso_doi_getdef - Returns a reference to a valid DOI definition * @doi: the DOI value * * Description: * Searches for a valid DOI definition and if one is found it is returned to * the caller. Otherwise NULL is returned. The caller must ensure that * calipso_doi_putdef() is called when the caller is done. * */ struct calipso_doi *calipso_doi_getdef(u32 doi) { struct calipso_doi *ret_val = NULL; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_getdef(doi); return ret_val; } /** * calipso_doi_putdef - Releases a reference for the given DOI definition * @doi_def: the DOI definition * * Description: * Releases a DOI definition reference obtained from calipso_doi_getdef(). * */ void calipso_doi_putdef(struct calipso_doi *doi_def) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->doi_putdef(doi_def); } /** * calipso_doi_walk - Iterate through the DOI definitions * @skip_cnt: skip past this number of DOI definitions, updated * @callback: callback for each DOI definition * @cb_arg: argument for the callback function * * Description: * Iterate over the DOI definition list, skipping the first @skip_cnt entries. * For each entry call @callback, if @callback returns a negative value stop * 'walking' through the list and return. Updates the value in @skip_cnt upon * return. Returns zero on success, negative values on failure. * */ int calipso_doi_walk(u32 *skip_cnt, int (*callback)(struct calipso_doi *doi_def, void *arg), void *cb_arg) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->doi_walk(skip_cnt, callback, cb_arg); return ret_val; } /** * calipso_sock_getattr - Get the security attributes from a sock * @sk: the sock * @secattr: the security attributes * * Description: * Query @sk to see if there is a CALIPSO option attached to the sock and if * there is return the CALIPSO security attributes in @secattr. This function * requires that @sk be locked, or privately held, but it does not do any * locking itself. Returns zero on success and negative values on failure. * */ int calipso_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->sock_getattr(sk, secattr); return ret_val; } /** * calipso_sock_setattr - Add a CALIPSO option to a socket * @sk: the socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. This function requires * exclusive access to @sk, which means it either needs to be in the * process of being created or locked. Returns zero on success and negative * values on failure. * */ int calipso_sock_setattr(struct sock *sk, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->sock_setattr(sk, doi_def, secattr); return ret_val; } /** * calipso_sock_delattr - Delete the CALIPSO option from a socket * @sk: the socket * * Description: * Removes the CALIPSO option from a socket, if present. * */ void calipso_sock_delattr(struct sock *sk) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->sock_delattr(sk); } /** * calipso_req_setattr - Add a CALIPSO option to a connection request socket * @req: the connection request socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. Returns zero on success and * negative values on failure. * */ int calipso_req_setattr(struct request_sock *req, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->req_setattr(req, doi_def, secattr); return ret_val; } /** * calipso_req_delattr - Delete the CALIPSO option from a request socket * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. * */ void calipso_req_delattr(struct request_sock *req) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->req_delattr(req); } /** * calipso_optptr - Find the CALIPSO option in the packet * @skb: the packet * * Description: * Parse the packet's IP header looking for a CALIPSO option. Returns a pointer * to the start of the CALIPSO option on success, NULL if one if not found. * */ unsigned char *calipso_optptr(const struct sk_buff *skb) { unsigned char *ret_val = NULL; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_optptr(skb); return ret_val; } /** * calipso_getattr - Get the security attributes from a memory block. * @calipso: the CALIPSO option * @secattr: the security attributes * * Description: * Inspect @calipso and return the security attributes in @secattr. * Returns zero on success and negative values on failure. * */ int calipso_getattr(const unsigned char *calipso, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->opt_getattr(calipso, secattr); return ret_val; } /** * calipso_skbuff_setattr - Set the CALIPSO option on a packet * @skb: the packet * @doi_def: the CALIPSO DOI to use * @secattr: the security attributes * * Description: * Set the CALIPSO option on the given packet based on the security attributes. * Returns a pointer to the IP header on success and NULL on failure. * */ int calipso_skbuff_setattr(struct sk_buff *skb, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_setattr(skb, doi_def, secattr); return ret_val; } /** * calipso_skbuff_delattr - Delete any CALIPSO options from a packet * @skb: the packet * * Description: * Removes any and all CALIPSO options from the given packet. Returns zero on * success, negative values on failure. * */ int calipso_skbuff_delattr(struct sk_buff *skb) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->skbuff_delattr(skb); return ret_val; } /** * calipso_cache_invalidate - Invalidates the current CALIPSO cache * * Description: * Invalidates and frees any entries in the CALIPSO cache. Returns zero on * success and negative values on failure. * */ void calipso_cache_invalidate(void) { const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ops->cache_invalidate(); } /** * calipso_cache_add - Add an entry to the CALIPSO cache * @calipso_ptr: the CALIPSO option * @secattr: the packet's security attributes * * Description: * Add a new entry into the CALIPSO label mapping cache. * Returns zero on success, negative values on failure. * */ int calipso_cache_add(const unsigned char *calipso_ptr, const struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (ops) ret_val = ops->cache_add(calipso_ptr, secattr); return ret_val; } |
| 2 2 3 3 3 3 1 2 10 8 15 1 15 15 8 10 1 12 2 1 13 1 12 2 3 3 3 3 2 5 1 1 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/filter.h> #include <linux/kmod.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/netfilter/nf_bpf_link.h> #include <uapi/linux/netfilter_ipv4.h> static unsigned int nf_hook_run_bpf(void *bpf_prog, struct sk_buff *skb, const struct nf_hook_state *s) { const struct bpf_prog *prog = bpf_prog; struct bpf_nf_ctx ctx = { .state = s, .skb = skb, }; return bpf_prog_run(prog, &ctx); } struct bpf_nf_link { struct bpf_link link; struct nf_hook_ops hook_ops; netns_tracker ns_tracker; struct net *net; u32 dead; const struct nf_defrag_hook *defrag_hook; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static const struct nf_defrag_hook * get_proto_defrag_hook(struct bpf_nf_link *link, const struct nf_defrag_hook __rcu **ptr_global_hook, const char *mod) { const struct nf_defrag_hook *hook; int err; /* RCU protects us from races against module unloading */ rcu_read_lock(); hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); err = request_module("%s", mod); if (err) return ERR_PTR(err < 0 ? err : -EINVAL); rcu_read_lock(); hook = rcu_dereference(*ptr_global_hook); } if (hook && try_module_get(hook->owner)) { /* Once we have a refcnt on the module, we no longer need RCU */ hook = rcu_pointer_handoff(hook); } else { WARN_ONCE(!hook, "%s has bad registration", mod); hook = ERR_PTR(-ENOENT); } rcu_read_unlock(); if (!IS_ERR(hook)) { err = hook->enable(link->net); if (err) { module_put(hook->owner); hook = ERR_PTR(err); } } return hook; } #endif static int bpf_nf_enable_defrag(struct bpf_nf_link *link) { const struct nf_defrag_hook __maybe_unused *hook; switch (link->hook_ops.pf) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) case NFPROTO_IPV4: hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4"); if (IS_ERR(hook)) return PTR_ERR(hook); link->defrag_hook = hook; return 0; #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) case NFPROTO_IPV6: hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6"); if (IS_ERR(hook)) return PTR_ERR(hook); link->defrag_hook = hook; return 0; #endif default: return -EAFNOSUPPORT; } } static void bpf_nf_disable_defrag(struct bpf_nf_link *link) { const struct nf_defrag_hook *hook = link->defrag_hook; if (!hook) return; hook->disable(link->net); module_put(hook->owner); } static void bpf_nf_link_release(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); if (nf_link->dead) return; /* do not double release in case .detach was already called */ if (!cmpxchg(&nf_link->dead, 0, 1)) { nf_unregister_net_hook(nf_link->net, &nf_link->hook_ops); bpf_nf_disable_defrag(nf_link); put_net_track(nf_link->net, &nf_link->ns_tracker); } } static void bpf_nf_link_dealloc(struct bpf_link *link) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); kfree(nf_link); } static int bpf_nf_link_detach(struct bpf_link *link) { bpf_nf_link_release(link); return 0; } static void bpf_nf_link_show_info(const struct bpf_link *link, struct seq_file *seq) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); seq_printf(seq, "pf:\t%u\thooknum:\t%u\tprio:\t%d\n", nf_link->hook_ops.pf, nf_link->hook_ops.hooknum, nf_link->hook_ops.priority); } static int bpf_nf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); const struct nf_defrag_hook *hook = nf_link->defrag_hook; info->netfilter.pf = nf_link->hook_ops.pf; info->netfilter.hooknum = nf_link->hook_ops.hooknum; info->netfilter.priority = nf_link->hook_ops.priority; info->netfilter.flags = hook ? BPF_F_NETFILTER_IP_DEFRAG : 0; return 0; } static int bpf_nf_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static const struct bpf_link_ops bpf_nf_link_lops = { .release = bpf_nf_link_release, .dealloc = bpf_nf_link_dealloc, .detach = bpf_nf_link_detach, .show_fdinfo = bpf_nf_link_show_info, .fill_link_info = bpf_nf_link_fill_link_info, .update_prog = bpf_nf_link_update, }; static int bpf_nf_check_pf_and_hooks(const union bpf_attr *attr) { int prio; switch (attr->link_create.netfilter.pf) { case NFPROTO_IPV4: case NFPROTO_IPV6: if (attr->link_create.netfilter.hooknum >= NF_INET_NUMHOOKS) return -EPROTO; break; default: return -EAFNOSUPPORT; } if (attr->link_create.netfilter.flags & ~BPF_F_NETFILTER_IP_DEFRAG) return -EOPNOTSUPP; /* make sure conntrack confirm is always last */ prio = attr->link_create.netfilter.priority; if (prio == NF_IP_PRI_FIRST) return -ERANGE; /* sabotage_in and other warts */ else if (prio == NF_IP_PRI_LAST) return -ERANGE; /* e.g. conntrack confirm */ else if ((attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) && prio <= NF_IP_PRI_CONNTRACK_DEFRAG) return -ERANGE; /* cannot use defrag if prog runs before nf_defrag */ return 0; } int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct bpf_nf_link *link; int err; if (attr->link_create.flags) return -EINVAL; err = bpf_nf_check_pf_and_hooks(attr); if (err) return err; link = kzalloc(sizeof(*link), GFP_USER); if (!link) return -ENOMEM; bpf_link_init(&link->link, BPF_LINK_TYPE_NETFILTER, &bpf_nf_link_lops, prog); link->hook_ops.hook = nf_hook_run_bpf; link->hook_ops.hook_ops_type = NF_HOOK_OP_BPF; link->hook_ops.priv = prog; link->hook_ops.pf = attr->link_create.netfilter.pf; link->hook_ops.priority = attr->link_create.netfilter.priority; link->hook_ops.hooknum = attr->link_create.netfilter.hooknum; link->net = net; link->dead = false; link->defrag_hook = NULL; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); return err; } if (attr->link_create.netfilter.flags & BPF_F_NETFILTER_IP_DEFRAG) { err = bpf_nf_enable_defrag(link); if (err) { bpf_link_cleanup(&link_primer); return err; } } err = nf_register_net_hook(net, &link->hook_ops); if (err) { bpf_nf_disable_defrag(link); bpf_link_cleanup(&link_primer); return err; } get_net_track(net, &link->ns_tracker, GFP_KERNEL); return bpf_link_settle(&link_primer); } const struct bpf_prog_ops netfilter_prog_ops = { .test_run = bpf_prog_test_run_nf, }; static bool nf_ptr_to_btf_id(struct bpf_insn_access_aux *info, const char *name) { struct btf *btf; s32 type_id; btf = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(btf)) return false; type_id = btf_find_by_name_kind(btf, name, BTF_KIND_STRUCT); if (WARN_ON_ONCE(type_id < 0)) return false; info->btf = btf; info->btf_id = type_id; info->reg_type = PTR_TO_BTF_ID | PTR_TRUSTED; return true; } static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_nf_ctx)) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct bpf_nf_ctx, skb): if (size != sizeof_field(struct bpf_nf_ctx, skb)) return false; return nf_ptr_to_btf_id(info, "sk_buff"); case bpf_ctx_range(struct bpf_nf_ctx, state): if (size != sizeof_field(struct bpf_nf_ctx, state)) return false; return nf_ptr_to_btf_id(info, "nf_hook_state"); default: return false; } return false; } static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { .is_valid_access = nf_is_valid_access, .get_func_proto = bpf_nf_func_proto, }; |
| 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ #include <linux/static_key.h> #include <linux/objtool.h> #include <linux/linkage.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> /* * Call depth tracking for Intel SKL CPUs to address the RSB underflow * issue in software. * * The tracking does not use a counter. It uses uses arithmetic shift * right on call entry and logical shift left on return. * * The depth tracking variable is initialized to 0x8000.... when the call * depth is zero. The arithmetic shift right sign extends the MSB and * saturates after the 12th call. The shift count is 5 for both directions * so the tracking covers 12 nested calls. * * Call * 0: 0x8000000000000000 0x0000000000000000 * 1: 0xfc00000000000000 0xf000000000000000 * ... * 11: 0xfffffffffffffff8 0xfffffffffffffc00 * 12: 0xffffffffffffffff 0xffffffffffffffe0 * * After a return buffer fill the depth is credited 12 calls before the * next stuffing has to take place. * * There is a inaccuracy for situations like this: * * 10 calls * 5 returns * 3 calls * 4 returns * 3 calls * .... * * The shift count might cause this to be off by one in either direction, * but there is still a cushion vs. the RSB depth. The algorithm does not * claim to be perfect and it can be speculated around by the CPU, but it * is considered that it obfuscates the problem enough to make exploitation * extremely difficult. */ #define RET_DEPTH_SHIFT 5 #define RSB_RET_STUFF_LOOPS 16 #define RET_DEPTH_INIT 0x8000000000000000ULL #define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL #define RET_DEPTH_CREDIT 0xffffffffffffffffULL #ifdef CONFIG_CALL_THUNKS_DEBUG # define CALL_THUNKS_DEBUG_INC_CALLS \ incq PER_CPU_VAR(__x86_call_count); # define CALL_THUNKS_DEBUG_INC_RETS \ incq PER_CPU_VAR(__x86_ret_count); # define CALL_THUNKS_DEBUG_INC_STUFFS \ incq PER_CPU_VAR(__x86_stuffs_count); # define CALL_THUNKS_DEBUG_INC_CTXSW \ incq PER_CPU_VAR(__x86_ctxsw_count); #else # define CALL_THUNKS_DEBUG_INC_CALLS # define CALL_THUNKS_DEBUG_INC_RETS # define CALL_THUNKS_DEBUG_INC_STUFFS # define CALL_THUNKS_DEBUG_INC_CTXSW #endif #if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) #include <asm/asm-offsets.h> #define CREDIT_CALL_DEPTH \ movq $-1, PER_CPU_VAR(__x86_call_depth); #define RESET_CALL_DEPTH \ xor %eax, %eax; \ bts $63, %rax; \ movq %rax, PER_CPU_VAR(__x86_call_depth); #define RESET_CALL_DEPTH_FROM_CALL \ movb $0xfc, %al; \ shl $56, %rax; \ movq %rax, PER_CPU_VAR(__x86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ sarq $5, PER_CPU_VAR(__x86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #else #define CREDIT_CALL_DEPTH #define RESET_CALL_DEPTH #define RESET_CALL_DEPTH_FROM_CALL #define INCREMENT_CALL_DEPTH #endif /* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to * eliminate potentially bogus entries from the RSB, and sometimes * purely to ensure that it doesn't get empty, which on some CPUs would * allow predictions from other (unwanted!) sources to be used. * * We define a CPP macro such that it can be used from both .S files and * inline assembly. It's possible to do a .macro and then include that * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. */ #define RETPOLINE_THUNK_SIZE 32 #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. */ #define __FILL_RETURN_SLOT \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ int3; \ 772: /* * Stuff the entire RSB. * * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #ifdef CONFIG_X86_64 #define __FILL_RETURN_BUFFER(reg, nr) \ mov $(nr/2), reg; \ 771: \ __FILL_RETURN_SLOT \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ dec reg; \ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ CREDIT_CALL_DEPTH \ CALL_THUNKS_DEBUG_INC_CTXSW #else /* * i386 doesn't unconditionally have LFENCE, as such it can't * do a loop. */ #define __FILL_RETURN_BUFFER(reg, nr) \ .rept nr; \ __FILL_RETURN_SLOT; \ .endr; \ add $(BITS_PER_LONG/8) * nr, %_ASM_SP; #endif /* * Stuff a single RSB slot. * * To mitigate Post-Barrier RSB speculation, one CALL instruction must be * forced to retire before letting a RET instruction execute. * * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed * before this point. */ #define __FILL_ONE_RETURN \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLER__ /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into its own annotation. */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif .endm /* * Emits a conditional CS prefix that is compatible with * -mindirect-branch-cs-prefix. */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 .ifc \reg,\rs .byte 0x2e .endif .endr .endm /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. * * NOTE: these do not take kCFI into account and are thus not comparable to C * indirect calls, take care when using. The target of these should be an ENDBR * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else jmp *%\reg int3 #endif .endm .macro CALL_NOSPEC reg:req #ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else call *%\reg #endif .endm /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ __stringify(nop;nop;__FILL_ONE_RETURN), \ftr2 .Lskip_rsb_\@: .endm /* * The CALL to srso_alias_untrain_ret() must be patched in directly at * the spot where untraining must be done, ie., srso_alias_untrain_ret() * must be the target of a CALL instruction instead of indirectly * jumping to a wrapper which then calls it. Therefore, this macro is * called outside of __UNTRAIN_RET below, for the time being, before the * kernel can support nested alternatives with arbitrary nesting. */ .macro CALL_UNTRAIN_RET #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif .endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * * While retbleed_untrain_ret() doesn't clobber anything but requires stack, * write_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END CALL_UNTRAIN_RET ALTERNATIVE_2 "", \ "call write_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm #define UNTRAIN_RET \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_VM \ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_FROM_CALL \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) .macro CALL_DEPTH_ACCOUNT #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING ALTERNATIVE "", \ __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm /* * Macro to execute VERW instruction that mitigate transient data sampling * attacks such as MDS. On affected systems a microcode update overloaded VERW * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. * * Note: Only the memory operand variant of VERW clears the CPU buffers. */ .macro CLEAR_CPU_BUFFERS #ifdef CONFIG_X86_64 ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF #else /* * In 32bit mode, the memory operand must be a %cs reference. The data * segments may not be usable (vm86 mode), and the stack segment may not * be flat (ESPFIX32). */ ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF #endif .endm #ifdef CONFIG_X86_64 .macro CLEAR_BRANCH_HISTORY ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP .endm .macro CLEAR_BRANCH_HISTORY_VMEXIT ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT .endm #else #define CLEAR_BRANCH_HISTORY #define CLEAR_BRANCH_HISTORY_VMEXIT #endif #else /* __ASSEMBLER__ */ #define ITS_THUNK_SIZE 64 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; typedef u8 its_thunk_t[ITS_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; extern its_thunk_t __x86_indirect_its_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} #endif #ifdef CONFIG_MITIGATION_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} #endif extern void srso_alias_untrain_ret(void); #ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); #else static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif #ifdef CONFIG_MITIGATION_ITS extern void its_return_thunk(void); #else static inline void its_return_thunk(void) {} #endif extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void write_ibpb(void); #ifdef CONFIG_X86_64 extern void clear_bhb_loop(void); #endif extern void (*x86_return_thunk)(void); extern void __warn_thunk(void); #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ ALTERNATIVE("", \ __stringify(INCREMENT_CALL_DEPTH), \ X86_FEATURE_CALL_DEPTH) DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth); #ifdef CONFIG_CALL_THUNKS_DEBUG DECLARE_PER_CPU(u64, __x86_call_count); DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif #else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ #ifdef CONFIG_MITIGATION_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #ifdef CONFIG_X86_64 /* * Emits a conditional CS prefix that is compatible with * -mindirect-branch-cs-prefix. */ #define __CS_PREFIX(reg) \ ".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\rs," reg "\n" \ ".byte 0x2e\n" \ ".endif\n" \ ".endr\n" /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ #define CALL_NOSPEC __CS_PREFIX("%V[thunk_target]") \ "call __x86_indirect_thunk_%V[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "r" (addr) #else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, SPECTRE_V2_RETPOLINE, SPECTRE_V2_LFENCE, SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, SPEC_STORE_BYPASS_PRCTL, SPEC_STORE_BYPASS_SECCOMP, }; static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)), [feature] "i" (feature) : "memory"); } static inline void indirect_branch_prediction_barrier(void) { asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) : ASM_CALL_CONSTRAINT :: "rax", "rcx", "rdx", "memory"); } /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. * * (Implemented as CPP macros due to header hell.) */ #define firmware_restrict_branch_speculation_start() \ do { \ preempt_disable(); \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear); extern u16 mds_verw_sel; #include <asm/segment.h> /** * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; /* * Has to be the memory-operand variant because only that * guarantees the CPU buffer flush functionality according to * documentation. The register-operand variant does not. * Works with any segment selector, but a valid writable * data segment is the fastest variant. * * "cc" clobber is required because VERW modifies ZF. */ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); } #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ |
| 470 471 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/lockdep.h> #include <linux/sysfs.h> #include <linux/kobject.h> #include <linux/memory.h> #include <linux/memory-tiers.h> #include <linux/notifier.h> #include <linux/sched/sysctl.h> #include "internal.h" struct memory_tier { /* hierarchy of memory tiers */ struct list_head list; /* list of all memory types part of this tier */ struct list_head memory_types; /* * start value of abstract distance. memory tier maps * an abstract distance range, * adistance_start .. adistance_start + MEMTIER_CHUNK_SIZE */ int adistance_start; struct device dev; /* All the nodes that are part of all the lower memory tiers. */ nodemask_t lower_tier_mask; }; struct demotion_nodes { nodemask_t preferred; }; struct node_memory_type_map { struct memory_dev_type *memtype; int map_count; }; static DEFINE_MUTEX(memory_tier_lock); static LIST_HEAD(memory_tiers); /* * The list is used to store all memory types that are not created * by a device driver. */ static LIST_HEAD(default_memory_types); static struct node_memory_type_map node_memory_types[MAX_NUMNODES]; struct memory_dev_type *default_dram_type; nodemask_t default_dram_nodes __initdata = NODE_MASK_NONE; static const struct bus_type memory_tier_subsys = { .name = "memory_tiering", .dev_name = "memory_tier", }; #ifdef CONFIG_NUMA_BALANCING /** * folio_use_access_time - check if a folio reuses cpupid for page access time * @folio: folio to check * * folio's _last_cpupid field is repurposed by memory tiering. In memory * tiering mode, cpupid of slow memory folio (not toptier memory) is used to * record page access time. * * Return: the folio _last_cpupid is used to record page access time */ bool folio_use_access_time(struct folio *folio) { return (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && !node_is_toptier(folio_nid(folio)); } #endif #ifdef CONFIG_MIGRATION static int top_tier_adistance; /* * node_demotion[] examples: * * Example 1: * * Node 0 & 1 are CPU + DRAM nodes, node 2 & 3 are PMEM nodes. * * node distances: * node 0 1 2 3 * 0 10 20 30 40 * 1 20 10 40 30 * 2 30 40 10 40 * 3 40 30 40 10 * * memory_tiers0 = 0-1 * memory_tiers1 = 2-3 * * node_demotion[0].preferred = 2 * node_demotion[1].preferred = 3 * node_demotion[2].preferred = <empty> * node_demotion[3].preferred = <empty> * * Example 2: * * Node 0 & 1 are CPU + DRAM nodes, node 2 is memory-only DRAM node. * * node distances: * node 0 1 2 * 0 10 20 30 * 1 20 10 30 * 2 30 30 10 * * memory_tiers0 = 0-2 * * node_demotion[0].preferred = <empty> * node_demotion[1].preferred = <empty> * node_demotion[2].preferred = <empty> * * Example 3: * * Node 0 is CPU + DRAM nodes, Node 1 is HBM node, node 2 is PMEM node. * * node distances: * node 0 1 2 * 0 10 20 30 * 1 20 10 40 * 2 30 40 10 * * memory_tiers0 = 1 * memory_tiers1 = 0 * memory_tiers2 = 2 * * node_demotion[0].preferred = 2 * node_demotion[1].preferred = 0 * node_demotion[2].preferred = <empty> * */ static struct demotion_nodes *node_demotion __read_mostly; #endif /* CONFIG_MIGRATION */ static BLOCKING_NOTIFIER_HEAD(mt_adistance_algorithms); /* The lock is used to protect `default_dram_perf*` info and nid. */ static DEFINE_MUTEX(default_dram_perf_lock); static bool default_dram_perf_error; static struct access_coordinate default_dram_perf; static int default_dram_perf_ref_nid = NUMA_NO_NODE; static const char *default_dram_perf_ref_source; static inline struct memory_tier *to_memory_tier(struct device *device) { return container_of(device, struct memory_tier, dev); } static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memtier) { nodemask_t nodes = NODE_MASK_NONE; struct memory_dev_type *memtype; list_for_each_entry(memtype, &memtier->memory_types, tier_sibling) nodes_or(nodes, nodes, memtype->nodes); return nodes; } static void memory_tier_device_release(struct device *dev) { struct memory_tier *tier = to_memory_tier(dev); /* * synchronize_rcu in clear_node_memory_tier makes sure * we don't have rcu access to this memory tier. */ kfree(tier); } static ssize_t nodelist_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; nodemask_t nmask; mutex_lock(&memory_tier_lock); nmask = get_memtier_nodemask(to_memory_tier(dev)); ret = sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&nmask)); mutex_unlock(&memory_tier_lock); return ret; } static DEVICE_ATTR_RO(nodelist); static struct attribute *memtier_dev_attrs[] = { &dev_attr_nodelist.attr, NULL }; static const struct attribute_group memtier_dev_group = { .attrs = memtier_dev_attrs, }; static const struct attribute_group *memtier_dev_groups[] = { &memtier_dev_group, NULL }; static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype) { int ret; bool found_slot = false; struct memory_tier *memtier, *new_memtier; int adistance = memtype->adistance; unsigned int memtier_adistance_chunk_size = MEMTIER_CHUNK_SIZE; lockdep_assert_held_once(&memory_tier_lock); adistance = round_down(adistance, memtier_adistance_chunk_size); /* * If the memtype is already part of a memory tier, * just return that. */ if (!list_empty(&memtype->tier_sibling)) { list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) return memtier; } WARN_ON(1); return ERR_PTR(-EINVAL); } list_for_each_entry(memtier, &memory_tiers, list) { if (adistance == memtier->adistance_start) { goto link_memtype; } else if (adistance < memtier->adistance_start) { found_slot = true; break; } } new_memtier = kzalloc(sizeof(struct memory_tier), GFP_KERNEL); if (!new_memtier) return ERR_PTR(-ENOMEM); new_memtier->adistance_start = adistance; INIT_LIST_HEAD(&new_memtier->list); INIT_LIST_HEAD(&new_memtier->memory_types); if (found_slot) list_add_tail(&new_memtier->list, &memtier->list); else list_add_tail(&new_memtier->list, &memory_tiers); new_memtier->dev.id = adistance >> MEMTIER_CHUNK_BITS; new_memtier->dev.bus = &memory_tier_subsys; new_memtier->dev.release = memory_tier_device_release; new_memtier->dev.groups = memtier_dev_groups; ret = device_register(&new_memtier->dev); if (ret) { list_del(&new_memtier->list); put_device(&new_memtier->dev); return ERR_PTR(ret); } memtier = new_memtier; link_memtype: list_add(&memtype->tier_sibling, &memtier->memory_types); return memtier; } static struct memory_tier *__node_get_memory_tier(int node) { pg_data_t *pgdat; pgdat = NODE_DATA(node); if (!pgdat) return NULL; /* * Since we hold memory_tier_lock, we can avoid * RCU read locks when accessing the details. No * parallel updates are possible here. */ return rcu_dereference_check(pgdat->memtier, lockdep_is_held(&memory_tier_lock)); } #ifdef CONFIG_MIGRATION bool node_is_toptier(int node) { bool toptier; pg_data_t *pgdat; struct memory_tier *memtier; pgdat = NODE_DATA(node); if (!pgdat) return false; rcu_read_lock(); memtier = rcu_dereference(pgdat->memtier); if (!memtier) { toptier = true; goto out; } if (memtier->adistance_start <= top_tier_adistance) toptier = true; else toptier = false; out: rcu_read_unlock(); return toptier; } void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets) { struct memory_tier *memtier; /* * pg_data_t.memtier updates includes a synchronize_rcu() * which ensures that we either find NULL or a valid memtier * in NODE_DATA. protect the access via rcu_read_lock(); */ rcu_read_lock(); memtier = rcu_dereference(pgdat->memtier); if (memtier) *targets = memtier->lower_tier_mask; else *targets = NODE_MASK_NONE; rcu_read_unlock(); } /** * next_demotion_node() - Get the next node in the demotion path * @node: The starting node to lookup the next node * * Return: node id for next memory node in the demotion path hierarchy * from @node; NUMA_NO_NODE if @node is terminal. This does not keep * @node online or guarantee that it *continues* to be the next demotion * target. */ int next_demotion_node(int node) { struct demotion_nodes *nd; int target; if (!node_demotion) return NUMA_NO_NODE; nd = &node_demotion[node]; /* * node_demotion[] is updated without excluding this * function from running. * * Make sure to use RCU over entire code blocks if * node_demotion[] reads need to be consistent. */ rcu_read_lock(); /* * If there are multiple target nodes, just select one * target node randomly. * * In addition, we can also use round-robin to select * target node, but we should introduce another variable * for node_demotion[] to record last selected target node, * that may cause cache ping-pong due to the changing of * last target node. Or introducing per-cpu data to avoid * caching issue, which seems more complicated. So selecting * target node randomly seems better until now. */ target = node_random(&nd->preferred); rcu_read_unlock(); return target; } static void disable_all_demotion_targets(void) { struct memory_tier *memtier; int node; for_each_node_state(node, N_MEMORY) { node_demotion[node].preferred = NODE_MASK_NONE; /* * We are holding memory_tier_lock, it is safe * to access pgda->memtier. */ memtier = __node_get_memory_tier(node); if (memtier) memtier->lower_tier_mask = NODE_MASK_NONE; } /* * Ensure that the "disable" is visible across the system. * Readers will see either a combination of before+disable * state or disable+after. They will never see before and * after state together. */ synchronize_rcu(); } static void dump_demotion_targets(void) { int node; for_each_node_state(node, N_MEMORY) { struct memory_tier *memtier = __node_get_memory_tier(node); nodemask_t preferred = node_demotion[node].preferred; if (!memtier) continue; if (nodes_empty(preferred)) pr_info("Demotion targets for Node %d: null\n", node); else pr_info("Demotion targets for Node %d: preferred: %*pbl, fallback: %*pbl\n", node, nodemask_pr_args(&preferred), nodemask_pr_args(&memtier->lower_tier_mask)); } } /* * Find an automatic demotion target for all memory * nodes. Failing here is OK. It might just indicate * being at the end of a chain. */ static void establish_demotion_targets(void) { struct memory_tier *memtier; struct demotion_nodes *nd; int target = NUMA_NO_NODE, node; int distance, best_distance; nodemask_t tier_nodes, lower_tier; lockdep_assert_held_once(&memory_tier_lock); if (!node_demotion) return; disable_all_demotion_targets(); for_each_node_state(node, N_MEMORY) { best_distance = -1; nd = &node_demotion[node]; memtier = __node_get_memory_tier(node); if (!memtier || list_is_last(&memtier->list, &memory_tiers)) continue; /* * Get the lower memtier to find the demotion node list. */ memtier = list_next_entry(memtier, list); tier_nodes = get_memtier_nodemask(memtier); /* * find_next_best_node, use 'used' nodemask as a skip list. * Add all memory nodes except the selected memory tier * nodelist to skip list so that we find the best node from the * memtier nodelist. */ nodes_andnot(tier_nodes, node_states[N_MEMORY], tier_nodes); /* * Find all the nodes in the memory tier node list of same best distance. * add them to the preferred mask. We randomly select between nodes * in the preferred mask when allocating pages during demotion. */ do { target = find_next_best_node(node, &tier_nodes); if (target == NUMA_NO_NODE) break; distance = node_distance(node, target); if (distance == best_distance || best_distance == -1) { best_distance = distance; node_set(target, nd->preferred); } else { break; } } while (1); } /* * Promotion is allowed from a memory tier to higher * memory tier only if the memory tier doesn't include * compute. We want to skip promotion from a memory tier, * if any node that is part of the memory tier have CPUs. * Once we detect such a memory tier, we consider that tier * as top tiper from which promotion is not allowed. */ list_for_each_entry_reverse(memtier, &memory_tiers, list) { tier_nodes = get_memtier_nodemask(memtier); nodes_and(tier_nodes, node_states[N_CPU], tier_nodes); if (!nodes_empty(tier_nodes)) { /* * abstract distance below the max value of this memtier * is considered toptier. */ top_tier_adistance = memtier->adistance_start + MEMTIER_CHUNK_SIZE - 1; break; } } /* * Now build the lower_tier mask for each node collecting node mask from * all memory tier below it. This allows us to fallback demotion page * allocation to a set of nodes that is closer the above selected * preferred node. */ lower_tier = node_states[N_MEMORY]; list_for_each_entry(memtier, &memory_tiers, list) { /* * Keep removing current tier from lower_tier nodes, * This will remove all nodes in current and above * memory tier from the lower_tier mask. */ tier_nodes = get_memtier_nodemask(memtier); nodes_andnot(lower_tier, lower_tier, tier_nodes); memtier->lower_tier_mask = lower_tier; } dump_demotion_targets(); } #else static inline void establish_demotion_targets(void) {} #endif /* CONFIG_MIGRATION */ static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype) { if (!node_memory_types[node].memtype) node_memory_types[node].memtype = memtype; /* * for each device getting added in the same NUMA node * with this specific memtype, bump the map count. We * Only take memtype device reference once, so that * changing a node memtype can be done by droping the * only reference count taken here. */ if (node_memory_types[node].memtype == memtype) { if (!node_memory_types[node].map_count++) kref_get(&memtype->kref); } } static struct memory_tier *set_node_memory_tier(int node) { struct memory_tier *memtier; struct memory_dev_type *memtype = default_dram_type; int adist = MEMTIER_ADISTANCE_DRAM; pg_data_t *pgdat = NODE_DATA(node); lockdep_assert_held_once(&memory_tier_lock); if (!node_state(node, N_MEMORY)) return ERR_PTR(-EINVAL); mt_calc_adistance(node, &adist); if (!node_memory_types[node].memtype) { memtype = mt_find_alloc_memory_type(adist, &default_memory_types); if (IS_ERR(memtype)) { memtype = default_dram_type; pr_info("Failed to allocate a memory type. Fall back.\n"); } } __init_node_memory_type(node, memtype); memtype = node_memory_types[node].memtype; node_set(node, memtype->nodes); memtier = find_create_memory_tier(memtype); if (!IS_ERR(memtier)) rcu_assign_pointer(pgdat->memtier, memtier); return memtier; } static void destroy_memory_tier(struct memory_tier *memtier) { list_del(&memtier->list); device_unregister(&memtier->dev); } static bool clear_node_memory_tier(int node) { bool cleared = false; pg_data_t *pgdat; struct memory_tier *memtier; pgdat = NODE_DATA(node); if (!pgdat) return false; /* * Make sure that anybody looking at NODE_DATA who finds * a valid memtier finds memory_dev_types with nodes still * linked to the memtier. We achieve this by waiting for * rcu read section to finish using synchronize_rcu. * This also enables us to free the destroyed memory tier * with kfree instead of kfree_rcu */ memtier = __node_get_memory_tier(node); if (memtier) { struct memory_dev_type *memtype; rcu_assign_pointer(pgdat->memtier, NULL); synchronize_rcu(); memtype = node_memory_types[node].memtype; node_clear(node, memtype->nodes); if (nodes_empty(memtype->nodes)) { list_del_init(&memtype->tier_sibling); if (list_empty(&memtier->memory_types)) destroy_memory_tier(memtier); } cleared = true; } return cleared; } static void release_memtype(struct kref *kref) { struct memory_dev_type *memtype; memtype = container_of(kref, struct memory_dev_type, kref); kfree(memtype); } struct memory_dev_type *alloc_memory_type(int adistance) { struct memory_dev_type *memtype; memtype = kmalloc(sizeof(*memtype), GFP_KERNEL); if (!memtype) return ERR_PTR(-ENOMEM); memtype->adistance = adistance; INIT_LIST_HEAD(&memtype->tier_sibling); memtype->nodes = NODE_MASK_NONE; kref_init(&memtype->kref); return memtype; } EXPORT_SYMBOL_GPL(alloc_memory_type); void put_memory_type(struct memory_dev_type *memtype) { kref_put(&memtype->kref, release_memtype); } EXPORT_SYMBOL_GPL(put_memory_type); void init_node_memory_type(int node, struct memory_dev_type *memtype) { mutex_lock(&memory_tier_lock); __init_node_memory_type(node, memtype); mutex_unlock(&memory_tier_lock); } EXPORT_SYMBOL_GPL(init_node_memory_type); void clear_node_memory_type(int node, struct memory_dev_type *memtype) { mutex_lock(&memory_tier_lock); if (node_memory_types[node].memtype == memtype || !memtype) node_memory_types[node].map_count--; /* * If we umapped all the attached devices to this node, * clear the node memory type. */ if (!node_memory_types[node].map_count) { memtype = node_memory_types[node].memtype; node_memory_types[node].memtype = NULL; put_memory_type(memtype); } mutex_unlock(&memory_tier_lock); } EXPORT_SYMBOL_GPL(clear_node_memory_type); struct memory_dev_type *mt_find_alloc_memory_type(int adist, struct list_head *memory_types) { struct memory_dev_type *mtype; list_for_each_entry(mtype, memory_types, list) if (mtype->adistance == adist) return mtype; mtype = alloc_memory_type(adist); if (IS_ERR(mtype)) return mtype; list_add(&mtype->list, memory_types); return mtype; } EXPORT_SYMBOL_GPL(mt_find_alloc_memory_type); void mt_put_memory_types(struct list_head *memory_types) { struct memory_dev_type *mtype, *mtn; list_for_each_entry_safe(mtype, mtn, memory_types, list) { list_del(&mtype->list); put_memory_type(mtype); } } EXPORT_SYMBOL_GPL(mt_put_memory_types); /* * This is invoked via `late_initcall()` to initialize memory tiers for * memory nodes, both with and without CPUs. After the initialization of * firmware and devices, adistance algorithms are expected to be provided. */ static int __init memory_tier_late_init(void) { int nid; struct memory_tier *memtier; get_online_mems(); guard(mutex)(&memory_tier_lock); /* Assign each uninitialized N_MEMORY node to a memory tier. */ for_each_node_state(nid, N_MEMORY) { /* * Some device drivers may have initialized * memory tiers, potentially bringing memory nodes * online and configuring memory tiers. * Exclude them here. */ if (node_memory_types[nid].memtype) continue; memtier = set_node_memory_tier(nid); if (IS_ERR(memtier)) continue; } establish_demotion_targets(); put_online_mems(); return 0; } late_initcall(memory_tier_late_init); static void dump_hmem_attrs(struct access_coordinate *coord, const char *prefix) { pr_info( "%sread_latency: %u, write_latency: %u, read_bandwidth: %u, write_bandwidth: %u\n", prefix, coord->read_latency, coord->write_latency, coord->read_bandwidth, coord->write_bandwidth); } int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source) { guard(mutex)(&default_dram_perf_lock); if (default_dram_perf_error) return -EIO; if (perf->read_latency + perf->write_latency == 0 || perf->read_bandwidth + perf->write_bandwidth == 0) return -EINVAL; if (default_dram_perf_ref_nid == NUMA_NO_NODE) { default_dram_perf = *perf; default_dram_perf_ref_nid = nid; default_dram_perf_ref_source = kstrdup(source, GFP_KERNEL); return 0; } /* * The performance of all default DRAM nodes is expected to be * same (that is, the variation is less than 10%). And it * will be used as base to calculate the abstract distance of * other memory nodes. */ if (abs(perf->read_latency - default_dram_perf.read_latency) * 10 > default_dram_perf.read_latency || abs(perf->write_latency - default_dram_perf.write_latency) * 10 > default_dram_perf.write_latency || abs(perf->read_bandwidth - default_dram_perf.read_bandwidth) * 10 > default_dram_perf.read_bandwidth || abs(perf->write_bandwidth - default_dram_perf.write_bandwidth) * 10 > default_dram_perf.write_bandwidth) { pr_info( "memory-tiers: the performance of DRAM node %d mismatches that of the reference\n" "DRAM node %d.\n", nid, default_dram_perf_ref_nid); pr_info(" performance of reference DRAM node %d from %s:\n", default_dram_perf_ref_nid, default_dram_perf_ref_source); dump_hmem_attrs(&default_dram_perf, " "); pr_info(" performance of DRAM node %d from %s:\n", nid, source); dump_hmem_attrs(perf, " "); pr_info( " disable default DRAM node performance based abstract distance algorithm.\n"); default_dram_perf_error = true; return -EINVAL; } return 0; } int mt_perf_to_adistance(struct access_coordinate *perf, int *adist) { guard(mutex)(&default_dram_perf_lock); if (default_dram_perf_error) return -EIO; if (perf->read_latency + perf->write_latency == 0 || perf->read_bandwidth + perf->write_bandwidth == 0) return -EINVAL; if (default_dram_perf_ref_nid == NUMA_NO_NODE) return -ENOENT; /* * The abstract distance of a memory node is in direct proportion to * its memory latency (read + write) and inversely proportional to its * memory bandwidth (read + write). The abstract distance, memory * latency, and memory bandwidth of the default DRAM nodes are used as * the base. */ *adist = MEMTIER_ADISTANCE_DRAM * (perf->read_latency + perf->write_latency) / (default_dram_perf.read_latency + default_dram_perf.write_latency) * (default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) / (perf->read_bandwidth + perf->write_bandwidth); return 0; } EXPORT_SYMBOL_GPL(mt_perf_to_adistance); /** * register_mt_adistance_algorithm() - Register memory tiering abstract distance algorithm * @nb: The notifier block which describe the algorithm * * Return: 0 on success, errno on error. * * Every memory tiering abstract distance algorithm provider needs to * register the algorithm with register_mt_adistance_algorithm(). To * calculate the abstract distance for a specified memory node, the * notifier function will be called unless some high priority * algorithm has provided result. The prototype of the notifier * function is as follows, * * int (*algorithm_notifier)(struct notifier_block *nb, * unsigned long nid, void *data); * * Where "nid" specifies the memory node, "data" is the pointer to the * returned abstract distance (that is, "int *adist"). If the * algorithm provides the result, NOTIFY_STOP should be returned. * Otherwise, return_value & %NOTIFY_STOP_MASK == 0 to allow the next * algorithm in the chain to provide the result. */ int register_mt_adistance_algorithm(struct notifier_block *nb) { return blocking_notifier_chain_register(&mt_adistance_algorithms, nb); } EXPORT_SYMBOL_GPL(register_mt_adistance_algorithm); /** * unregister_mt_adistance_algorithm() - Unregister memory tiering abstract distance algorithm * @nb: the notifier block which describe the algorithm * * Return: 0 on success, errno on error. */ int unregister_mt_adistance_algorithm(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&mt_adistance_algorithms, nb); } EXPORT_SYMBOL_GPL(unregister_mt_adistance_algorithm); /** * mt_calc_adistance() - Calculate abstract distance with registered algorithms * @node: the node to calculate abstract distance for * @adist: the returned abstract distance * * Return: if return_value & %NOTIFY_STOP_MASK != 0, then some * abstract distance algorithm provides the result, and return it via * @adist. Otherwise, no algorithm can provide the result and @adist * will be kept as it is. */ int mt_calc_adistance(int node, int *adist) { return blocking_notifier_call_chain(&mt_adistance_algorithms, node, adist); } EXPORT_SYMBOL_GPL(mt_calc_adistance); static int __meminit memtier_hotplug_callback(struct notifier_block *self, unsigned long action, void *_arg) { struct memory_tier *memtier; struct memory_notify *arg = _arg; /* * Only update the node migration order when a node is * changing status, like online->offline. */ if (arg->status_change_nid < 0) return notifier_from_errno(0); switch (action) { case MEM_OFFLINE: mutex_lock(&memory_tier_lock); if (clear_node_memory_tier(arg->status_change_nid)) establish_demotion_targets(); mutex_unlock(&memory_tier_lock); break; case MEM_ONLINE: mutex_lock(&memory_tier_lock); memtier = set_node_memory_tier(arg->status_change_nid); if (!IS_ERR(memtier)) establish_demotion_targets(); mutex_unlock(&memory_tier_lock); break; } return notifier_from_errno(0); } static int __init memory_tier_init(void) { int ret; ret = subsys_virtual_register(&memory_tier_subsys, NULL); if (ret) panic("%s() failed to register memory tier subsystem\n", __func__); #ifdef CONFIG_MIGRATION node_demotion = kcalloc(nr_node_ids, sizeof(struct demotion_nodes), GFP_KERNEL); WARN_ON(!node_demotion); #endif mutex_lock(&memory_tier_lock); /* * For now we can have 4 faster memory tiers with smaller adistance * than default DRAM tier. */ default_dram_type = mt_find_alloc_memory_type(MEMTIER_ADISTANCE_DRAM, &default_memory_types); mutex_unlock(&memory_tier_lock); if (IS_ERR(default_dram_type)) panic("%s() failed to allocate default DRAM tier\n", __func__); /* Record nodes with memory and CPU to set default DRAM performance. */ nodes_and(default_dram_nodes, node_states[N_MEMORY], node_states[N_CPU]); hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRI); return 0; } subsys_initcall(memory_tier_init); bool numa_demotion_enabled = false; #ifdef CONFIG_MIGRATION #ifdef CONFIG_SYSFS static ssize_t demotion_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", str_true_false(numa_demotion_enabled)); } static ssize_t demotion_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { ssize_t ret; ret = kstrtobool(buf, &numa_demotion_enabled); if (ret) return ret; return count; } static struct kobj_attribute numa_demotion_enabled_attr = __ATTR_RW(demotion_enabled); static struct attribute *numa_attrs[] = { &numa_demotion_enabled_attr.attr, NULL, }; static const struct attribute_group numa_attr_group = { .attrs = numa_attrs, }; static int __init numa_init_sysfs(void) { int err; struct kobject *numa_kobj; numa_kobj = kobject_create_and_add("numa", mm_kobj); if (!numa_kobj) { pr_err("failed to create numa kobject\n"); return -ENOMEM; } err = sysfs_create_group(numa_kobj, &numa_attr_group); if (err) { pr_err("failed to register numa group\n"); goto delete_obj; } return 0; delete_obj: kobject_put(numa_kobj); return err; } subsys_initcall(numa_init_sysfs); #endif /* CONFIG_SYSFS */ #endif |
| 4 366 566 512 1473 1544 2150 416 133 397 131 656 365 291 649 105 701 472 138 335 278 1502 267 1229 1188 690 401 396 385 70 1185 216 277 644 345 114 81 1031 1030 1183 1108 72 66 30 72 51 51 1081 1079 15 4 1813 437 1814 436 1846 759 2232 4 8 233 329 1666 441 573 2 594 571 1 2138 1685 1891 746 746 2451 2458 19 19 121 37 37 26 46 46 26 12 1195 235 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ext4 #if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_EXT4_H #include <linux/writeback.h> #include <linux/tracepoint.h> struct ext4_allocation_context; struct ext4_allocation_request; struct ext4_extent; struct ext4_prealloc_space; struct ext4_inode_info; struct mpage_da_data; struct ext4_map_blocks; struct extent_status; struct ext4_fsmap; struct partial_cluster; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) #define show_mballoc_flags(flags) __print_flags(flags, "|", \ { EXT4_MB_HINT_MERGE, "HINT_MERGE" }, \ { EXT4_MB_HINT_RESERVED, "HINT_RESV" }, \ { EXT4_MB_HINT_METADATA, "HINT_MDATA" }, \ { EXT4_MB_HINT_FIRST, "HINT_FIRST" }, \ { EXT4_MB_HINT_BEST, "HINT_BEST" }, \ { EXT4_MB_HINT_DATA, "HINT_DATA" }, \ { EXT4_MB_HINT_NOPREALLOC, "HINT_NOPREALLOC" }, \ { EXT4_MB_HINT_GROUP_ALLOC, "HINT_GRP_ALLOC" }, \ { EXT4_MB_HINT_GOAL_ONLY, "HINT_GOAL_ONLY" }, \ { EXT4_MB_HINT_TRY_GOAL, "HINT_TRY_GOAL" }, \ { EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \ { EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \ { EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \ { EXT4_MB_USE_RESERVED, "USE_RESV" }, \ { EXT4_MB_STRICT_CHECK, "STRICT_CHECK" }) #define show_map_flags(flags) __print_flags(flags, "|", \ { EXT4_GET_BLOCKS_CREATE, "CREATE" }, \ { EXT4_GET_BLOCKS_UNWRIT_EXT, "UNWRIT" }, \ { EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \ { EXT4_GET_BLOCKS_PRE_IO, "PRE_IO" }, \ { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ { EXT4_GET_BLOCKS_CONVERT_UNWRITTEN, "CONVERT_UNWRITTEN" }, \ { EXT4_GET_BLOCKS_ZERO, "ZERO" }, \ { EXT4_GET_BLOCKS_IO_SUBMIT, "IO_SUBMIT" }, \ { EXT4_EX_NOCACHE, "EX_NOCACHE" }) /* * __print_flags() requires that all enum values be wrapped in the * TRACE_DEFINE_ENUM macro so that the enum value can be encoded in the ftrace * ring buffer. */ TRACE_DEFINE_ENUM(BH_New); TRACE_DEFINE_ENUM(BH_Mapped); TRACE_DEFINE_ENUM(BH_Unwritten); TRACE_DEFINE_ENUM(BH_Boundary); #define show_mflags(flags) __print_flags(flags, "", \ { EXT4_MAP_NEW, "N" }, \ { EXT4_MAP_MAPPED, "M" }, \ { EXT4_MAP_UNWRITTEN, "U" }, \ { EXT4_MAP_BOUNDARY, "B" }) #define show_free_flags(flags) __print_flags(flags, "|", \ { EXT4_FREE_BLOCKS_METADATA, "METADATA" }, \ { EXT4_FREE_BLOCKS_FORGET, "FORGET" }, \ { EXT4_FREE_BLOCKS_VALIDATED, "VALIDATED" }, \ { EXT4_FREE_BLOCKS_NO_QUOT_UPDATE, "NO_QUOTA" }, \ { EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\ { EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER, "LAST_CLUSTER" }) TRACE_DEFINE_ENUM(ES_WRITTEN_B); TRACE_DEFINE_ENUM(ES_UNWRITTEN_B); TRACE_DEFINE_ENUM(ES_DELAYED_B); TRACE_DEFINE_ENUM(ES_HOLE_B); TRACE_DEFINE_ENUM(ES_REFERENCED_B); #define show_extent_status(status) __print_flags(status, "", \ { EXTENT_STATUS_WRITTEN, "W" }, \ { EXTENT_STATUS_UNWRITTEN, "U" }, \ { EXTENT_STATUS_DELAYED, "D" }, \ { EXTENT_STATUS_HOLE, "H" }, \ { EXTENT_STATUS_REFERENCED, "R" }) #define show_falloc_mode(mode) __print_flags(mode, "|", \ { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_NOMEM); TRACE_DEFINE_ENUM(EXT4_FC_REASON_SWAP_BOOT); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RESIZE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_RENAME_DIR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_FALLOC_RANGE); TRACE_DEFINE_ENUM(EXT4_FC_REASON_INODE_JOURNAL_DATA); TRACE_DEFINE_ENUM(EXT4_FC_REASON_ENCRYPTED_FILENAME); TRACE_DEFINE_ENUM(EXT4_FC_REASON_MAX); #define show_fc_reason(reason) \ __print_symbolic(reason, \ { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}, \ { EXT4_FC_REASON_ENCRYPTED_FILENAME, "ENCRYPTED_FILENAME"}) TRACE_DEFINE_ENUM(CR_POWER2_ALIGNED); TRACE_DEFINE_ENUM(CR_GOAL_LEN_FAST); TRACE_DEFINE_ENUM(CR_BEST_AVAIL_LEN); TRACE_DEFINE_ENUM(CR_GOAL_LEN_SLOW); TRACE_DEFINE_ENUM(CR_ANY_FREE); #define show_criteria(cr) \ __print_symbolic(cr, \ { CR_POWER2_ALIGNED, "CR_POWER2_ALIGNED" }, \ { CR_GOAL_LEN_FAST, "CR_GOAL_LEN_FAST" }, \ { CR_BEST_AVAIL_LEN, "CR_BEST_AVAIL_LEN" }, \ { CR_GOAL_LEN_SLOW, "CR_GOAL_LEN_SLOW" }, \ { CR_ANY_FREE, "CR_ANY_FREE" }) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), TP_ARGS(inode, orig_ino), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, orig_ino ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u16, mode ) ), TP_fast_assign( __entry->orig_ino = orig_ino; __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d orig_ino %lu ino %lu mode 0%o uid %u gid %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->orig_ino, (unsigned long) __entry->ino, __entry->mode, __entry->uid, __entry->gid) ); TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( uid_t, uid ) __field( gid_t, gid ) __field( __u64, blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->uid = i_uid_read(inode); __entry->gid = i_gid_read(inode); __entry->blocks = inode->i_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->uid, __entry->gid, __entry->blocks) ); TRACE_EVENT(ext4_request_inode, TP_PROTO(struct inode *dir, int mode), TP_ARGS(dir, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, dir ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_allocate_inode, TP_PROTO(struct inode *inode, struct inode *dir, int mode), TP_ARGS(inode, dir, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, dir ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->dir, __entry->mode) ); TRACE_EVENT(ext4_evict_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, nlink ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nlink = inode->i_nlink; ), TP_printk("dev %d,%d ino %lu nlink %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nlink) ); TRACE_EVENT(ext4_drop_inode, TP_PROTO(struct inode *inode, int drop), TP_ARGS(inode, drop), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, drop ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->drop = drop; ), TP_printk("dev %d,%d ino %lu drop %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->drop) ); TRACE_EVENT(ext4_nfs_commit_metadata, 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) ); TRACE_EVENT(ext4_mark_inode_dirty, TP_PROTO(struct inode *inode, unsigned long IP), TP_ARGS(inode, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, ip ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ip = IP; ), TP_printk("dev %d,%d ino %lu caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_begin_ordered_truncate, TP_PROTO(struct inode *inode, loff_t new_size), TP_ARGS(inode, new_size), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, new_size ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->new_size = new_size; ), TP_printk("dev %d,%d ino %lu new_size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->new_size) ); DECLARE_EVENT_CLASS(ext4__write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; ), TP_printk("dev %d,%d ino %lu pos %lld len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len) ); DEFINE_EVENT(ext4__write_begin, ext4_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len) ); DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len), TP_ARGS(inode, pos, len) ); DECLARE_EVENT_CLASS(ext4__write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, len ) __field( unsigned int, copied ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->len = len; __entry->copied = copied; ), TP_printk("dev %d,%d ino %lu pos %lld len %u copied %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->copied) ); DEFINE_EVENT(ext4__write_end, ext4_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_PROTO(struct inode *inode, loff_t pos, unsigned int len, unsigned int copied), TP_ARGS(inode, pos, len, copied) ); TRACE_EVENT(ext4_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( loff_t, range_start ) __field( loff_t, range_end ) __field( pgoff_t, writeback_index ) __field( int, sync_mode ) __field( char, for_kupdate ) __field( char, range_cyclic ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->range_cyclic = wbc->range_cyclic; ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " "range_start %lld range_end %lld sync_mode %d " "for_kupdate %d range_cyclic %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, (unsigned long) __entry->writeback_index) ); TRACE_EVENT(ext4_da_write_pages, TP_PROTO(struct inode *inode, pgoff_t first_page, struct writeback_control *wbc), TP_ARGS(inode, first_page, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, first_page ) __field( long, nr_to_write ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->first_page = first_page; __entry->nr_to_write = wbc->nr_to_write; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %lu first_page %lu nr_to_write %ld " "sync_mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->first_page, __entry->nr_to_write, __entry->sync_mode) ); TRACE_EVENT(ext4_da_write_pages_extent, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map), TP_ARGS(inode, map), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, lblk ) __field( __u32, len ) __field( __u32, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->flags = map->m_flags; ), TP_printk("dev %d,%d ino %lu lblk %llu len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, show_mflags(__entry->flags)) ); TRACE_EVENT(ext4_writepages_result, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int ret, int pages_written), TP_ARGS(inode, wbc, ret, pages_written), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) __field( int, pages_written ) __field( long, pages_skipped ) __field( pgoff_t, writeback_index ) __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; __entry->pages_written = pages_written; __entry->pages_skipped = wbc->pages_skipped; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->sync_mode = wbc->sync_mode; ), TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld " "sync_mode %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret, __entry->pages_written, __entry->pages_skipped, __entry->sync_mode, (unsigned long) __entry->writeback_index) ); DECLARE_EVENT_CLASS(ext4__folio_op, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->index = folio->index; ), TP_printk("dev %d,%d ino %lu folio_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index) ); DEFINE_EVENT(ext4__folio_op, ext4_read_folio, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio) ); DEFINE_EVENT(ext4__folio_op, ext4_release_folio, TP_PROTO(struct inode *inode, struct folio *folio), TP_ARGS(inode, folio) ); DECLARE_EVENT_CLASS(ext4_invalidate_folio_op, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) __field( size_t, offset ) __field( size_t, length ) ), TP_fast_assign( __entry->dev = folio->mapping->host->i_sb->s_dev; __entry->ino = folio->mapping->host->i_ino; __entry->index = folio->index; __entry->offset = offset; __entry->length = length; ), TP_printk("dev %d,%d ino %lu folio_index %lu offset %zu length %zu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->index, __entry->offset, __entry->length) ); DEFINE_EVENT(ext4_invalidate_folio_op, ext4_invalidate_folio, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length) ); DEFINE_EVENT(ext4_invalidate_folio_op, ext4_journalled_invalidate_folio, TP_PROTO(struct folio *folio, size_t offset, size_t length), TP_ARGS(folio, offset, length) ); TRACE_EVENT(ext4_discard_blocks, TP_PROTO(struct super_block *sb, unsigned long long blk, unsigned long long count), TP_ARGS(sb, blk, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, blk ) __field( __u64, count ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->blk = blk; __entry->count = count; ), TP_printk("dev %d,%d blk %llu count %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blk, __entry->count) ); DECLARE_EVENT_CLASS(ext4__mb_new_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, pa_pstart ) __field( __u64, pa_lstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = ac->ac_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->pa_pstart = pa->pa_pstart; __entry->pa_lstart = pa->pa_lstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, TP_PROTO(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa), TP_ARGS(ac, pa) ); TRACE_EVENT(ext4_mb_release_inode_pa, TP_PROTO(struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), TP_ARGS(pa, block, count), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( __u32, count ) ), TP_fast_assign( __entry->dev = pa->pa_inode->i_sb->s_dev; __entry->ino = pa->pa_inode->i_ino; __entry->block = block; __entry->count = count; ), TP_printk("dev %d,%d ino %lu block %llu count %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->block, __entry->count) ); TRACE_EVENT(ext4_mb_release_group_pa, TP_PROTO(struct super_block *sb, struct ext4_prealloc_space *pa), TP_ARGS(sb, pa), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u64, pa_pstart ) __field( __u32, pa_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), TP_printk("dev %d,%d pstart %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->pa_pstart, __entry->pa_len) ); TRACE_EVENT(ext4_discard_preallocations, TP_PROTO(struct inode *inode, unsigned int len), TP_ARGS(inode, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->len = len; ), TP_printk("dev %d,%d ino %lu len: %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->len) ); TRACE_EVENT(ext4_mb_discard_preallocations, TP_PROTO(struct super_block *sb, int needed), TP_ARGS(sb, needed), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, needed ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->needed = needed; ), TP_printk("dev %d,%d needed %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->needed) ); TRACE_EVENT(ext4_request_blocks, TP_PROTO(struct ext4_allocation_request *ar), TP_ARGS(ar), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %lu flags %s len %u lblk %u goal %llu " "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_allocate_blocks, TP_PROTO(struct ext4_allocation_request *ar, unsigned long long block), TP_ARGS(ar, block), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned int, len ) __field( __u32, logical ) __field( __u32, lleft ) __field( __u32, lright ) __field( __u64, goal ) __field( __u64, pleft ) __field( __u64, pright ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = ar->inode->i_sb->s_dev; __entry->ino = ar->inode->i_ino; __entry->block = block; __entry->len = ar->len; __entry->logical = ar->logical; __entry->goal = ar->goal; __entry->lleft = ar->lleft; __entry->lright = ar->lright; __entry->pleft = ar->pleft; __entry->pright = ar->pright; __entry->flags = ar->flags; ), TP_printk("dev %d,%d ino %lu flags %s len %u block %llu lblk %u " "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->block, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_free_blocks, TP_PROTO(struct inode *inode, __u64 block, unsigned long count, int flags), TP_ARGS(inode, block, count, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( unsigned long, count ) __field( int, flags ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->count = count; __entry->flags = flags; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->block, __entry->count, show_free_flags(__entry->flags)) ); TRACE_EVENT(ext4_sync_file_enter, TP_PROTO(struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) ), TP_fast_assign( struct dentry *dentry = file->f_path.dentry; __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->datasync = datasync; __entry->parent = d_inode(dentry->d_parent)->i_ino; ), TP_printk("dev %d,%d ino %lu parent %lu datasync %d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) ); TRACE_EVENT(ext4_sync_file_exit, TP_PROTO(struct inode *inode, int ret), TP_ARGS(inode, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) ); TRACE_EVENT(ext4_sync_fs, TP_PROTO(struct super_block *sb, int wait), TP_ARGS(sb, wait), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, wait ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->wait = wait; ), TP_printk("dev %d,%d wait %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->wait) ); TRACE_EVENT(ext4_alloc_da_blocks, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, data_blocks ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks; ), TP_printk("dev %d,%d ino %lu reserved_data_blocks %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->data_blocks) ); TRACE_EVENT(ext4_mballoc_alloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, goal_logical ) __field( int, goal_start ) __field( __u32, goal_group ) __field( int, goal_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) __field( __u16, found ) __field( __u16, groups ) __field( __u16, buddy ) __field( __u16, flags ) __field( __u16, tail ) __field( __u8, cr ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->goal_logical = ac->ac_g_ex.fe_logical; __entry->goal_start = ac->ac_g_ex.fe_start; __entry->goal_group = ac->ac_g_ex.fe_group; __entry->goal_len = ac->ac_g_ex.fe_len; __entry->result_logical = ac->ac_f_ex.fe_logical; __entry->result_start = ac->ac_f_ex.fe_start; __entry->result_group = ac->ac_f_ex.fe_group; __entry->result_len = ac->ac_f_ex.fe_len; __entry->found = ac->ac_found; __entry->flags = ac->ac_flags; __entry->groups = ac->ac_groups_scanned; __entry->buddy = ac->ac_buddy; __entry->tail = ac->ac_tail; __entry->cr = ac->ac_criteria; ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " "result %u/%d/%u@%u blks %u grps %u cr %s flags %s " "tail %u broken %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->goal_group, __entry->goal_start, __entry->goal_len, __entry->goal_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical, __entry->found, __entry->groups, show_criteria(__entry->cr), show_mballoc_flags(__entry->flags), __entry->tail, __entry->buddy ? 1 << __entry->buddy : 0) ); TRACE_EVENT(ext4_mballoc_prealloc, TP_PROTO(struct ext4_allocation_context *ac), TP_ARGS(ac), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u32, orig_logical ) __field( int, orig_start ) __field( __u32, orig_group ) __field( int, orig_len ) __field( __u32, result_logical ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = ac->ac_inode->i_sb->s_dev; __entry->ino = ac->ac_inode->i_ino; __entry->orig_logical = ac->ac_o_ex.fe_logical; __entry->orig_start = ac->ac_o_ex.fe_start; __entry->orig_group = ac->ac_o_ex.fe_group; __entry->orig_len = ac->ac_o_ex.fe_len; __entry->result_logical = ac->ac_b_ex.fe_logical; __entry->result_start = ac->ac_b_ex.fe_start; __entry->result_group = ac->ac_b_ex.fe_group; __entry->result_len = ac->ac_b_ex.fe_len; ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->orig_group, __entry->orig_start, __entry->orig_len, __entry->orig_logical, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical) ); DECLARE_EVENT_CLASS(ext4__mballoc, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, result_start ) __field( __u32, result_group ) __field( int, result_len ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = inode ? inode->i_ino : 0; __entry->result_start = start; __entry->result_group = group; __entry->result_len = len; ), TP_printk("dev %d,%d inode %lu extent %u/%d/%d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, __entry->result_len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free, TP_PROTO(struct super_block *sb, struct inode *inode, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, inode, group, start, len) ); TRACE_EVENT(ext4_forget, TP_PROTO(struct inode *inode, int is_metadata, __u64 block), TP_ARGS(inode, is_metadata, block), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, block ) __field( int, is_metadata ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->block = block; __entry->is_metadata = is_metadata; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->is_metadata, __entry->block) ); TRACE_EVENT(ext4_da_update_reserve_space, TP_PROTO(struct inode *inode, int used_blocks, int quota_claim), TP_ARGS(inode, used_blocks, quota_claim), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, used_blocks ) __field( int, reserved_data_blocks ) __field( int, quota_claim ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->used_blocks = used_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->quota_claim = quota_claim; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " "reserved_data_blocks %d quota_claim %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->quota_claim) ); TRACE_EVENT(ext4_da_reserve_space, TP_PROTO(struct inode *inode, int nr_resv), TP_ARGS(inode, nr_resv), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, reserve_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->reserve_blocks = nr_resv; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu reserve_blocks %d" "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->reserve_blocks, __entry->reserved_data_blocks) ); TRACE_EVENT(ext4_da_release_space, TP_PROTO(struct inode *inode, int freed_blocks), TP_ARGS(inode, freed_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, i_blocks ) __field( int, freed_blocks ) __field( int, reserved_data_blocks ) __field( __u16, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->i_blocks = inode->i_blocks; __entry->freed_blocks = freed_blocks; __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; __entry->mode = inode->i_mode; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d " "reserved_data_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks) ); DECLARE_EVENT_CLASS(ext4__bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); TRACE_EVENT(ext4_read_block_bitmap_load, TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), TP_ARGS(sb, group, prefetch), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) __field( bool, prefetch ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; __entry->prefetch = prefetch; ), TP_printk("dev %d,%d group %u prefetch %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group, __entry->prefetch) ); DECLARE_EVENT_CLASS(ext4__fallocate_mode, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, offset ) __field( loff_t, len ) __field( int, mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu offset %lld len %lld mode %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->offset, __entry->len, show_falloc_mode(__entry->mode)) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_fallocate_enter, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_punch_hole, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); DEFINE_EVENT(ext4__fallocate_mode, ext4_zero_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len, int mode), TP_ARGS(inode, offset, len, mode) ); TRACE_EVENT(ext4_fallocate_exit, TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), TP_ARGS(inode, offset, max_blocks, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, pos ) __field( unsigned int, blocks ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = offset; __entry->blocks = max_blocks; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu pos %lld blocks %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->blocks, __entry->ret) ); TRACE_EVENT(ext4_unlink_enter, TP_PROTO(struct inode *parent, struct dentry *dentry), TP_ARGS(parent, dentry), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ino_t, parent ) __field( loff_t, size ) ), TP_fast_assign( __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->parent = parent->i_ino; __entry->size = d_inode(dentry)->i_size; ), TP_printk("dev %d,%d ino %lu size %lld parent %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->size, (unsigned long) __entry->parent) ); TRACE_EVENT(ext4_unlink_exit, TP_PROTO(struct dentry *dentry, int ret), TP_ARGS(dentry, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, ret ) ), TP_fast_assign( __entry->dev = dentry->d_sb->s_dev; __entry->ino = d_inode(dentry)->i_ino; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) ); DECLARE_EVENT_CLASS(ext4__truncate, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( __u64, blocks ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->blocks = inode->i_blocks; ), TP_printk("dev %d,%d ino %lu blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->blocks) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* 'ux' is the unwritten extent. */ TRACE_EVENT(ext4_ext_convert_to_initialized_enter, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, struct ext4_extent *ux), TP_ARGS(inode, map, ux), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, m_lblk ) __field( unsigned, m_len ) __field( ext4_lblk_t, u_lblk ) __field( unsigned, u_len ) __field( ext4_fsblk_t, u_pblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_len = map->m_len; __entry->u_lblk = le32_to_cpu(ux->ee_block); __entry->u_len = ext4_ext_get_actual_len(ux); __entry->u_pblk = ext4_ext_pblock(ux); ), TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u u_lblk %u u_len %u " "u_pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->m_lblk, __entry->m_len, __entry->u_lblk, __entry->u_len, __entry->u_pblk) ); /* * 'ux' is the unwritten extent. * 'ix' is the initialized extent to which blocks are transferred. */ TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, struct ext4_extent *ux, struct ext4_extent *ix), TP_ARGS(inode, map, ux, ix), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, m_lblk ) __field( unsigned, m_len ) __field( ext4_lblk_t, u_lblk ) __field( unsigned, u_len ) __field( ext4_fsblk_t, u_pblk ) __field( ext4_lblk_t, i_lblk ) __field( unsigned, i_len ) __field( ext4_fsblk_t, i_pblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->m_lblk = map->m_lblk; __entry->m_len = map->m_len; __entry->u_lblk = le32_to_cpu(ux->ee_block); __entry->u_len = ext4_ext_get_actual_len(ux); __entry->u_pblk = ext4_ext_pblock(ux); __entry->i_lblk = le32_to_cpu(ix->ee_block); __entry->i_len = ext4_ext_get_actual_len(ix); __entry->i_pblk = ext4_ext_pblock(ix); ), TP_printk("dev %d,%d ino %lu m_lblk %u m_len %u " "u_lblk %u u_len %u u_pblk %llu " "i_lblk %u i_len %u i_pblk %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->m_lblk, __entry->m_len, __entry->u_lblk, __entry->u_len, __entry->u_pblk, __entry->i_lblk, __entry->i_len, __entry->i_pblk) ); DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len, unsigned int flags), TP_ARGS(inode, lblk, len, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; __entry->len = len; __entry->flags = flags; ), TP_printk("dev %d,%d ino %lu lblk %u len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, show_map_flags(__entry->flags)) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned len, unsigned flags), TP_ARGS(inode, lblk, len, flags) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned len, unsigned flags), TP_ARGS(inode, lblk, len, flags) ); DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( unsigned int, flags ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) __field( unsigned int, mflags ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->flags = flags; __entry->pblk = map->m_pblk; __entry->lblk = map->m_lblk; __entry->len = map->m_len; __entry->mflags = map->m_flags; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu flags %s lblk %u pblk %llu len %u " "mflags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, show_map_flags(__entry->flags), __entry->lblk, __entry->pblk, __entry->len, show_mflags(__entry->mflags), __entry->ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, int ret), TP_ARGS(inode, flags, map, ret) ); TRACE_EVENT(ext4_ext_load_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk), TP_ARGS(inode, lblk, pblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %lu lblk %u pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->pblk) ); TRACE_EVENT(ext4_load_inode, TP_PROTO(struct super_block *sb, unsigned long ino), TP_ARGS(sb, ino), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ino = ino; ), TP_printk("dev %d,%d ino %ld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); TRACE_EVENT(ext4_journal_start_sb, TP_PROTO(struct super_block *sb, int blocks, int rsv_blocks, int revoke_creds, int type, unsigned long IP), TP_ARGS(sb, blocks, rsv_blocks, revoke_creds, type, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, ip ) __field( int, blocks ) __field( int, rsv_blocks ) __field( int, revoke_creds ) __field( int, type ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; __entry->rsv_blocks = rsv_blocks; __entry->revoke_creds = revoke_creds; __entry->type = type; ), TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d," " type %d, caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds, __entry->type, (void *)__entry->ip) ); TRACE_EVENT(ext4_journal_start_inode, TP_PROTO(struct inode *inode, int blocks, int rsv_blocks, int revoke_creds, int type, unsigned long IP), TP_ARGS(inode, blocks, rsv_blocks, revoke_creds, type, IP), TP_STRUCT__entry( __field( unsigned long, ino ) __field( dev_t, dev ) __field( unsigned long, ip ) __field( int, blocks ) __field( int, rsv_blocks ) __field( int, revoke_creds ) __field( int, type ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; __entry->rsv_blocks = rsv_blocks; __entry->revoke_creds = revoke_creds; __entry->type = type; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d," " type %d, ino %lu, caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds, __entry->type, __entry->ino, (void *)__entry->ip) ); TRACE_EVENT(ext4_journal_start_reserved, TP_PROTO(struct super_block *sb, int blocks, unsigned long IP), TP_ARGS(sb, blocks, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, ip ) __field( int, blocks ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->ip = IP; __entry->blocks = blocks; ), TP_printk("dev %d,%d blocks, %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blocks, (void *)__entry->ip) ); DECLARE_EVENT_CLASS(ext4__trim, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len), TP_STRUCT__entry( __field( int, dev_major ) __field( int, dev_minor ) __field( __u32, group ) __field( int, start ) __field( int, len ) ), TP_fast_assign( __entry->dev_major = MAJOR(sb->s_dev); __entry->dev_minor = MINOR(sb->s_dev); __entry->group = group; __entry->start = start; __entry->len = len; ), TP_printk("dev %d,%d group %u, start %d, len %d", __entry->dev_major, __entry->dev_minor, __entry->group, __entry->start, __entry->len) ); DEFINE_EVENT(ext4__trim, ext4_trim_extent, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len) ); DEFINE_EVENT(ext4__trim, ext4_trim_all_free, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t len), TP_ARGS(sb, group, start, len) ); TRACE_EVENT(ext4_ext_handle_unwritten_extents, TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags, unsigned int allocated, ext4_fsblk_t newblock), TP_ARGS(inode, map, flags, allocated, newblock), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( int, flags ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) __field( unsigned int, len ) __field( unsigned int, allocated ) __field( ext4_fsblk_t, newblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->flags = flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; __entry->allocated = allocated; __entry->newblk = newblock; ), TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %s " "allocated %d newblock %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, __entry->len, show_map_flags(__entry->flags), (unsigned int) __entry->allocated, (unsigned long long) __entry->newblk) ); TRACE_EVENT(ext4_get_implied_cluster_alloc_exit, TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret), TP_ARGS(sb, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned int, flags ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) __field( unsigned int, len ) __field( int, ret ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->flags = map->m_flags; __entry->lblk = map->m_lblk; __entry->pblk = map->m_pblk; __entry->len = map->m_len; __entry->ret = ret; ), TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lblk, (unsigned long long) __entry->pblk, __entry->len, show_mflags(__entry->flags), __entry->ret) ); TRACE_EVENT(ext4_ext_show_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, unsigned short len), TP_ARGS(inode, lblk, pblk, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) __field( unsigned short, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; __entry->lblk = lblk; __entry->len = len; ), TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, (unsigned short) __entry->len) ); TRACE_EVENT(ext4_remove_blocks, TP_PROTO(struct inode *inode, struct ext4_extent *ex, ext4_lblk_t from, ext4_fsblk_t to, struct partial_cluster *pc), TP_ARGS(inode, ex, from, to, pc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, from ) __field( ext4_lblk_t, to ) __field( ext4_fsblk_t, ee_pblk ) __field( ext4_lblk_t, ee_lblk ) __field( unsigned short, ee_len ) __field( ext4_fsblk_t, pc_pclu ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->from = from; __entry->to = to; __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_len = ext4_ext_get_actual_len(ex); __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]" "from %u to %u partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, (unsigned) __entry->from, (unsigned) __entry->to, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_leaf, TP_PROTO(struct inode *inode, ext4_lblk_t start, struct ext4_extent *ex, struct partial_cluster *pc), TP_ARGS(inode, start, ex, pc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, ee_lblk ) __field( ext4_fsblk_t, ee_pblk ) __field( short, ee_len ) __field( ext4_fsblk_t, pc_pclu ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->ee_lblk = le32_to_cpu(ex->ee_block); __entry->ee_pblk = ext4_ext_pblock(ex); __entry->ee_len = ext4_ext_get_actual_len(ex); __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; ), TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]" "partial [pclu %lld lblk %u state %d]", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->ee_lblk, (unsigned long long) __entry->ee_pblk, (unsigned short) __entry->ee_len, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state) ); TRACE_EVENT(ext4_ext_rm_idx, TP_PROTO(struct inode *inode, ext4_fsblk_t pblk), TP_ARGS(inode, pblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_fsblk_t, pblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pblk = pblk; ), TP_printk("dev %d,%d ino %lu index_pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long long) __entry->pblk) ); TRACE_EVENT(ext4_ext_remove_space, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, int depth), TP_ARGS(inode, start, end, depth), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->end = end; __entry->depth = depth; ), TP_printk("dev %d,%d ino %lu since %u end %u depth %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth) ); TRACE_EVENT(ext4_ext_remove_space_done, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, int depth, struct partial_cluster *pc, __le16 eh_entries), TP_ARGS(inode, start, end, depth, pc, eh_entries), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) __field( ext4_fsblk_t, pc_pclu ) __field( ext4_lblk_t, pc_lblk ) __field( int, pc_state ) __field( unsigned short, eh_entries ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; __entry->end = end; __entry->depth = depth; __entry->pc_pclu = pc->pclu; __entry->pc_lblk = pc->lblk; __entry->pc_state = pc->state; __entry->eh_entries = le16_to_cpu(eh_entries); ), TP_printk("dev %d,%d ino %lu since %u end %u depth %d " "partial [pclu %lld lblk %u state %d] " "remaining_entries %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth, (long long) __entry->pc_pclu, (unsigned int) __entry->pc_lblk, (int) __entry->pc_state, (unsigned short) __entry->eh_entries) ); DECLARE_EVENT_CLASS(ext4__es_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); ), TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status)) ); DEFINE_EVENT(ext4__es_extent, ext4_es_insert_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es) ); DEFINE_EVENT(ext4__es_extent, ext4_es_cache_extent, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es) ); TRACE_EVENT(ext4_es_remove_extent, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len), TP_ARGS(inode, lblk, len), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( loff_t, lblk ) __field( loff_t, len ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; __entry->len = len; ), TP_printk("dev %d,%d ino %lu es [%lld/%lld)", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len) ); TRACE_EVENT(ext4_es_find_extent_range_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %lu lblk %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk) ); TRACE_EVENT(ext4_es_find_extent_range_exit, TP_PROTO(struct inode *inode, struct extent_status *es), TP_ARGS(inode, es), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); ), TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status)) ); TRACE_EVENT(ext4_es_lookup_extent_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk), TP_ARGS(inode, lblk), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = lblk; ), TP_printk("dev %d,%d ino %lu lblk %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk) ); TRACE_EVENT(ext4_es_lookup_extent_exit, TP_PROTO(struct inode *inode, struct extent_status *es, int found), TP_ARGS(inode, es, found), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) __field( int, found ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->found = found; ), TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->found, __entry->lblk, __entry->len, __entry->found ? __entry->pblk : 0, show_extent_status(__entry->found ? __entry->status : 0)) ); DECLARE_EVENT_CLASS(ext4__es_shrink_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_to_scan ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_to_scan = nr_to_scan; __entry->cache_cnt = cache_cnt; ), TP_printk("dev %d,%d nr_to_scan %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_to_scan, __entry->cache_cnt) ); DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_count, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt) ); DEFINE_EVENT(ext4__es_shrink_enter, ext4_es_shrink_scan_enter, TP_PROTO(struct super_block *sb, int nr_to_scan, int cache_cnt), TP_ARGS(sb, nr_to_scan, cache_cnt) ); TRACE_EVENT(ext4_es_shrink_scan_exit, TP_PROTO(struct super_block *sb, int nr_shrunk, int cache_cnt), TP_ARGS(sb, nr_shrunk, cache_cnt), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_shrunk ) __field( int, cache_cnt ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_shrunk = nr_shrunk; __entry->cache_cnt = cache_cnt; ), TP_printk("dev %d,%d nr_shrunk %d cache_cnt %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, __entry->cache_cnt) ); TRACE_EVENT(ext4_collapse_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len), TP_ARGS(inode, offset, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, offset) __field(loff_t, len) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; ), TP_printk("dev %d,%d ino %lu offset %lld len %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->offset, __entry->len) ); TRACE_EVENT(ext4_insert_range, TP_PROTO(struct inode *inode, loff_t offset, loff_t len), TP_ARGS(inode, offset, len), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, offset) __field(loff_t, len) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->offset = offset; __entry->len = len; ), TP_printk("dev %d,%d ino %lu offset %lld len %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->offset, __entry->len) ); TRACE_EVENT(ext4_es_shrink, TP_PROTO(struct super_block *sb, int nr_shrunk, u64 scan_time, int nr_skipped, int retried), TP_ARGS(sb, nr_shrunk, scan_time, nr_skipped, retried), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, nr_shrunk ) __field( unsigned long long, scan_time ) __field( int, nr_skipped ) __field( int, retried ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nr_shrunk = nr_shrunk; __entry->scan_time = div_u64(scan_time, 1000); __entry->nr_skipped = nr_skipped; __entry->retried = retried; ), TP_printk("dev %d,%d nr_shrunk %d, scan_time %llu " "nr_skipped %d retried %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_shrunk, __entry->scan_time, __entry->nr_skipped, __entry->retried) ); TRACE_EVENT(ext4_es_insert_delayed_extent, TP_PROTO(struct inode *inode, struct extent_status *es, bool lclu_allocated, bool end_allocated), TP_ARGS(inode, es, lclu_allocated, end_allocated), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) __field( char, status ) __field( bool, lclu_allocated ) __field( bool, end_allocated ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_show_pblock(es); __entry->status = ext4_es_status(es); __entry->lclu_allocated = lclu_allocated; __entry->end_allocated = end_allocated; ), TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s " "allocated %d %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, __entry->pblk, show_extent_status(__entry->status), __entry->lclu_allocated, __entry->end_allocated) ); /* fsmap traces */ DECLARE_EVENT_CLASS(ext4_fsmap_class, TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, u64 owner), TP_ARGS(sb, keydev, agno, bno, len, owner), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(u32, agno) __field(u64, bno) __field(u64, len) __field(u64, owner) ), TP_fast_assign( __entry->dev = sb->s_bdev->bd_dev; __entry->keydev = new_decode_dev(keydev); __entry->agno = agno; __entry->bno = bno; __entry->len = len; __entry->owner = owner; ), TP_printk("dev %d:%d keydev %d:%d agno %u bno %llu len %llu owner %lld\n", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, __entry->bno, __entry->len, __entry->owner) ) #define DEFINE_FSMAP_EVENT(name) \ DEFINE_EVENT(ext4_fsmap_class, name, \ TP_PROTO(struct super_block *sb, u32 keydev, u32 agno, u64 bno, u64 len, \ u64 owner), \ TP_ARGS(sb, keydev, agno, bno, len, owner)) DEFINE_FSMAP_EVENT(ext4_fsmap_low_key); DEFINE_FSMAP_EVENT(ext4_fsmap_high_key); DEFINE_FSMAP_EVENT(ext4_fsmap_mapping); DECLARE_EVENT_CLASS(ext4_getfsmap_class, TP_PROTO(struct super_block *sb, struct ext4_fsmap *fsmap), TP_ARGS(sb, fsmap), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(u64, block) __field(u64, len) __field(u64, owner) __field(u64, flags) ), TP_fast_assign( __entry->dev = sb->s_bdev->bd_dev; __entry->keydev = new_decode_dev(fsmap->fmr_device); __entry->block = fsmap->fmr_physical; __entry->len = fsmap->fmr_length; __entry->owner = fsmap->fmr_owner; __entry->flags = fsmap->fmr_flags; ), TP_printk("dev %d:%d keydev %d:%d block %llu len %llu owner %lld flags 0x%llx\n", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->block, __entry->len, __entry->owner, __entry->flags) ) #define DEFINE_GETFSMAP_EVENT(name) \ DEFINE_EVENT(ext4_getfsmap_class, name, \ TP_PROTO(struct super_block *sb, struct ext4_fsmap *fsmap), \ TP_ARGS(sb, fsmap)) DEFINE_GETFSMAP_EVENT(ext4_getfsmap_low_key); DEFINE_GETFSMAP_EVENT(ext4_getfsmap_high_key); DEFINE_GETFSMAP_EVENT(ext4_getfsmap_mapping); TRACE_EVENT(ext4_shutdown, TP_PROTO(struct super_block *sb, unsigned long flags), TP_ARGS(sb, flags), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned, flags ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->flags = flags; ), TP_printk("dev %d,%d flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->flags) ); TRACE_EVENT(ext4_error, TP_PROTO(struct super_block *sb, const char *function, unsigned int line), TP_ARGS(sb, function, line), TP_STRUCT__entry( __field( dev_t, dev ) __field( const char *, function ) __field( unsigned, line ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->function = function; __entry->line = line; ), TP_printk("dev %d,%d function %s line %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->function, __entry->line) ); TRACE_EVENT(ext4_prefetch_bitmaps, TP_PROTO(struct super_block *sb, ext4_group_t group, ext4_group_t next, unsigned int prefetch_ios), TP_ARGS(sb, group, next, prefetch_ios), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) __field( __u32, next ) __field( __u32, ios ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; __entry->next = next; __entry->ios = prefetch_ios; ), TP_printk("dev %d,%d group %u next %u ios %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group, __entry->next, __entry->ios) ); TRACE_EVENT(ext4_lazy_itable_init, TP_PROTO(struct super_block *sb, ext4_group_t group), TP_ARGS(sb, group), TP_STRUCT__entry( __field( dev_t, dev ) __field( __u32, group ) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->group = group; ), TP_printk("dev %d,%d group %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) ); TRACE_EVENT(ext4_fc_replay_scan, TP_PROTO(struct super_block *sb, int error, int off), TP_ARGS(sb, error, off), TP_STRUCT__entry( __field(dev_t, dev) __field(int, error) __field(int, off) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->error = error; __entry->off = off; ), TP_printk("dev %d,%d error %d, off %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->error, __entry->off) ); TRACE_EVENT(ext4_fc_replay, TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2), TP_ARGS(sb, tag, ino, priv1, priv2), TP_STRUCT__entry( __field(dev_t, dev) __field(int, tag) __field(int, ino) __field(int, priv1) __field(int, priv2) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->tag = tag; __entry->ino = ino; __entry->priv1 = priv1; __entry->priv2 = priv2; ), TP_printk("dev %d,%d: tag %d, ino %d, data1 %d, data2 %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tag, __entry->ino, __entry->priv1, __entry->priv2) ); TRACE_EVENT(ext4_fc_commit_start, TP_PROTO(struct super_block *sb, tid_t commit_tid), TP_ARGS(sb, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->tid = commit_tid; ), TP_printk("dev %d,%d tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid) ); TRACE_EVENT(ext4_fc_commit_stop, TP_PROTO(struct super_block *sb, int nblks, int reason, tid_t commit_tid), TP_ARGS(sb, nblks, reason, commit_tid), TP_STRUCT__entry( __field(dev_t, dev) __field(int, nblks) __field(int, reason) __field(int, num_fc) __field(int, num_fc_ineligible) __field(int, nblks_agg) __field(tid_t, tid) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->nblks = nblks; __entry->reason = reason; __entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits; __entry->num_fc_ineligible = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks; __entry->tid = commit_tid; ), TP_printk("dev %d,%d nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nblks, __entry->reason, __entry->num_fc, __entry->num_fc_ineligible, __entry->nblks_agg, __entry->tid) ); #define FC_REASON_NAME_STAT(reason) \ show_fc_reason(reason), \ __entry->fc_ineligible_rc[reason] TRACE_EVENT(ext4_fc_stats, TP_PROTO(struct super_block *sb), TP_ARGS(sb), TP_STRUCT__entry( __field(dev_t, dev) __array(unsigned int, fc_ineligible_rc, EXT4_FC_REASON_MAX) __field(unsigned long, fc_commits) __field(unsigned long, fc_ineligible_commits) __field(unsigned long, fc_numblks) ), TP_fast_assign( int i; __entry->dev = sb->s_dev; for (i = 0; i < EXT4_FC_REASON_MAX; i++) { __entry->fc_ineligible_rc[i] = EXT4_SB(sb)->s_fc_stats.fc_ineligible_reason_count[i]; } __entry->fc_commits = EXT4_SB(sb)->s_fc_stats.fc_num_commits; __entry->fc_ineligible_commits = EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits; __entry->fc_numblks = EXT4_SB(sb)->s_fc_stats.fc_numblks; ), TP_printk("dev %d,%d fc ineligible reasons:\n" "%s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u, %s:%u" "num_commits:%lu, ineligible: %lu, numblks: %lu", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), FC_REASON_NAME_STAT(EXT4_FC_REASON_ENCRYPTED_FILENAME), __entry->fc_commits, __entry->fc_ineligible_commits, __entry->fc_numblks) ); DECLARE_EVENT_CLASS(ext4_fc_track_dentry, TP_PROTO(handle_t *handle, struct inode *inode, struct dentry *dentry, int ret), TP_ARGS(handle, inode, dentry, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, t_tid) __field(ino_t, i_ino) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), TP_printk("dev %d,%d, t_tid %u, ino %lu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error ) ); #define DEFINE_EVENT_CLASS_DENTRY(__type) \ DEFINE_EVENT(ext4_fc_track_dentry, ext4_fc_track_##__type, \ TP_PROTO(handle_t *handle, struct inode *inode, \ struct dentry *dentry, int ret), \ TP_ARGS(handle, inode, dentry, ret) \ ) DEFINE_EVENT_CLASS_DENTRY(create); DEFINE_EVENT_CLASS_DENTRY(link); DEFINE_EVENT_CLASS_DENTRY(unlink); TRACE_EVENT(ext4_fc_track_inode, TP_PROTO(handle_t *handle, struct inode *inode, int ret), TP_ARGS(handle, inode, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, t_tid) __field(ino_t, i_ino) __field(tid_t, i_sync_tid) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->error = ret; ), TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error) ); TRACE_EVENT(ext4_fc_track_range, TP_PROTO(handle_t *handle, struct inode *inode, long start, long end, int ret), TP_ARGS(handle, inode, start, end, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(tid_t, t_tid) __field(ino_t, i_ino) __field(tid_t, i_sync_tid) __field(long, start) __field(long, end) __field(int, error) ), TP_fast_assign( struct ext4_inode_info *ei = EXT4_I(inode); __entry->dev = inode->i_sb->s_dev; __entry->t_tid = handle->h_transaction->t_tid; __entry->i_ino = inode->i_ino; __entry->i_sync_tid = ei->i_sync_tid; __entry->start = start; __entry->end = end; __entry->error = ret; ), TP_printk("dev %d:%d, t_tid %u, inode %lu, i_sync_tid %u, error %d, start %ld, end %ld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->t_tid, __entry->i_ino, __entry->i_sync_tid, __entry->error, __entry->start, __entry->end) ); TRACE_EVENT(ext4_fc_cleanup, TP_PROTO(journal_t *journal, int full, tid_t tid), TP_ARGS(journal, full, tid), TP_STRUCT__entry( __field(dev_t, dev) __field(int, j_fc_off) __field(int, full) __field(tid_t, tid) ), TP_fast_assign( struct super_block *sb = journal->j_private; __entry->dev = sb->s_dev; __entry->j_fc_off = journal->j_fc_off; __entry->full = full; __entry->tid = tid; ), TP_printk("dev %d,%d, j_fc_off %d, full %d, tid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->j_fc_off, __entry->full, __entry->tid) ); TRACE_EVENT(ext4_update_sb, TP_PROTO(struct super_block *sb, ext4_fsblk_t fsblk, unsigned int flags), TP_ARGS(sb, fsblk, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(ext4_fsblk_t, fsblk) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = sb->s_dev; __entry->fsblk = fsblk; __entry->flags = flags; ), TP_printk("dev %d,%d fsblk %llu flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fsblk, __entry->flags) ); #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1476 1475 1476 1476 3129 3130 2500 2503 2502 2502 2502 2502 3132 3133 2503 3134 1475 1476 1474 1476 3126 3126 2496 2497 2498 2301 562 3134 3133 3131 2498 3134 1472 1366 126 1391 1391 31 30 30 626 3203 3204 1377 1377 3247 2479 1391 1390 1391 2477 2479 2479 15 15 489 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 | // 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/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/rps.h> #include "dev.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_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; /* Caller holds RTNL, netdev->lock or RCU */ static inline int dev_isalive(const struct net_device *dev) { return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; } /* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active, * when unregistering a net device and accessing associated sysfs files. The * potential deadlock is as follow: * * CPU 0 CPU 1 * * rtnl_lock vfs_read * unregister_netdevice_many kernfs_seq_start * device_del / kobject_put kernfs_get_active (kn->active++) * kernfs_drain sysfs_kf_seq_show * wait_event( rtnl_lock * kn->active == KN_DEACTIVATED_BIAS) -> waits on CPU 0 to release * -> waits on CPU 1 to decrease kn->active the rtnl lock. * * The historical fix was to use rtnl_trylock with restart_syscall to bail out * of sysfs operations when the lock couldn't be taken. This fixed the above * issue as it allowed CPU 1 to bail out of the ABBA situation. * * But it came with performances issues, as syscalls are being restarted in * loops when there was contention on the rtnl lock, with huge slow downs in * specific scenarios (e.g. lots of virtual interfaces created and userspace * daemons querying their attributes). * * The idea below is to bail out of the active kernfs_node protection * (kn->active) while trying to take the rtnl lock. * * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The * net device is guaranteed to be alive if this returns successfully. */ static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr, struct net_device *ndev) { struct kernfs_node *kn; int ret = 0; /* First, we hold a reference to the net device as the unregistration * path might run in parallel. This will ensure the net device and the * associated sysfs objects won't be freed while we try to take the rtnl * lock. */ dev_hold(ndev); /* sysfs_break_active_protection was introduced to allow self-removal of * devices and their associated sysfs files by bailing out of the * sysfs/kernfs protection. We do this here to allow the unregistration * path to complete in parallel. The following takes a reference on the * kobject and the kernfs_node being accessed. * * This works because we hold a reference onto the net device and the * unregistration path will wait for us eventually in netdev_run_todo * (outside an rtnl lock section). */ kn = sysfs_break_active_protection(kobj, attr); /* We can now try to take the rtnl lock. This can't deadlock us as the * unregistration path is able to drain sysfs files (kernfs_node) thanks * to the above dance. */ if (rtnl_lock_interruptible()) { ret = -ERESTARTSYS; goto unbreak; } /* Check dismantle on the device hasn't started, otherwise deny the * operation. */ if (!dev_isalive(ndev)) { rtnl_unlock(); ret = -ENODEV; goto unbreak; } /* We are now sure the device dismantle hasn't started nor that it can * start before we exit the locking section as we hold the rtnl lock. * There's no need to keep unbreaking the sysfs protection nor to hold * a net device reference from that point; that was only needed to take * the rtnl lock. */ unbreak: sysfs_unbreak_active_protection(kn); dev_put(ndev); return ret; } /* 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; rcu_read_lock(); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); rcu_read_unlock(); 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 sysfs_emit(buf, format_string, READ_ONCE(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; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) goto err; ret = (*set)(netdev, new); if (ret == 0) ret = len; rtnl_unlock(); err: return ret; } /* Same as netdev_store() but takes netdev_lock() instead of rtnl_lock() */ static ssize_t netdev_lock_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) return ret; netdev_lock(netdev); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } netdev_unlock(netdev); 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 sysfs_emit(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 sysfs_emit(buf, fmt_dec, READ_ONCE(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 (READ_ONCE(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 (dev_get_mac_address()) */ 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; down_read(&dev_addr_sem); rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); rcu_read_unlock(); up_read(&dev_addr_sem); 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); int ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); rcu_read_unlock(); return ret; } 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 locking section 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); int ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; if (netif_running(netdev)) { /* Synchronize carrier state with link watch, * see also rtnl_getlink(). */ linkwatch_sync_dev(netdev); ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); } rtnl_unlock(); return ret; } 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 locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) ret = sysfs_emit(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 locking section below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = -EINVAL; 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 = sysfs_emit(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 sysfs_emit(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 sysfs_emit(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; operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sysfs_emit(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 sysfs_emit(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 sysfs_emit(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 sysfs_emit(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) { netdev_set_gro_flush_timeout(dev, 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_lock_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) { if (val > S32_MAX) return -ERANGE; netdev_set_defer_hard_irqs(dev, (u32)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_lock_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); 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; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; 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; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) ret = sysfs_emit(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) { 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); struct netdev_phys_item_id ppid; ssize_t ret; /* The check is also done in dev_get_phys_port_id; this helps returning * early without hitting the locking section below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_get_phys_port_id(netdev, &ppid); if (!ret) ret = sysfs_emit(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); char name[IFNAMSIZ]; ssize_t ret; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the locking section below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->devlink_port) return -EOPNOTSUPP; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_get_phys_port_name(netdev, name, sizeof(name)); if (!ret) ret = sysfs_emit(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); struct netdev_phys_item_id ppid = { }; ssize_t ret; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the locking section below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->devlink_port) return -EOPNOTSUPP; ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev); if (ret) return ret; ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_switch_id); static ssize_t threaded_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(netdev)) ret = sysfs_emit(buf, fmt_dec, READ_ONCE(netdev->threaded)); rcu_read_unlock(); return ret; } static int modify_napi_threaded(struct net_device *dev, unsigned long val) { int ret; if (list_empty(&dev->napi_list)) return -EOPNOTSUPP; if (val != 0 && val != 1) return -EOPNOTSUPP; ret = dev_set_threaded(dev, val); return ret; } static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_lock_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); 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, &dev_attr_threaded.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); rcu_read_lock(); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } rcu_read_unlock(); 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, }; static struct attribute *wireless_attrs[] = { NULL }; static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; static bool wireless_group_needed(struct net_device *ndev) { #if IS_ENABLED(CONFIG_CFG80211) if (ndev->ieee80211_ptr) return true; #endif #if IS_ENABLED(CONFIG_WIRELESS_EXT) if (ndev->wireless_handlers) return true; #endif return false; } #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 = sysfs_emit(buf, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; } static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, cpumask_var_t mask) { static DEFINE_MUTEX(rps_map_mutex); struct rps_map *old_map, *map; int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) 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); return 0; } int rps_cpumask_housekeeping(struct cpumask *mask) { if (!cpumask_empty(mask)) { cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); if (cpumask_empty(mask)) return -EINVAL; } return 0; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, const char *buf, size_t len) { cpumask_var_t mask; int err; 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) goto out; err = rps_cpumask_housekeeping(mask); if (err) goto out; err = netdev_rx_queue_set_rps_mask(queue, mask); out: free_cpumask_var(mask); return err ? : 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 = 1UL << flow_table->log; rcu_read_unlock(); return sysfs_emit(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->log = ilog2(mask) + 1; 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)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *rx_queue_namespace(const 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->namespace) ns = dev->class->namespace(dev); return ns; } static void rx_queue_get_ownership(const 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 const struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; static int rx_queue_default_mask(struct net_device *dev, struct netdev_rx_queue *queue) { #if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) struct cpumask *rps_default_mask = READ_ONCE(dev_net(dev)->core.rps_default_mask); if (rps_default_mask && !cpumask_empty(rps_default_mask)) return netdev_rx_queue_set_rps_mask(queue, rps_default_mask); #endif return 0; } 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; /* Rx queues are cleared in rx_queue_release to allow later * re-registration. This is triggered when their kobj refcount is * dropped. * * If a queue is removed while both a read (or write) operation and a * the re-addition of the same queue are pending (waiting on rntl_lock) * it might happen that the re-addition will execute before the read, * making the initial removal to never happen (queue's kobj refcount * won't drop enough because of the pending read). In such rare case, * return to allow the removal operation to complete. */ if (unlikely(kobj->state_initialized)) { netdev_warn_once(dev, "Cannot re-add rx queues before their removal completed"); return -EAGAIN; } /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; queue->groups = rx_queue_default_groups; error = sysfs_create_groups(kobj, queue->groups); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err_default_groups; } error = rx_queue_default_mask(dev, queue); if (error) goto err_default_groups; kobject_uevent(kobj, KOBJ_ADD); return error; err_default_groups: sysfs_remove_groups(kobj, queue->groups); 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 netdev_rx_queue *queue = &dev->_rx[i]; struct kobject *kobj = &queue->kobj; if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); sysfs_remove_groups(kobj, queue->groups); 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf); ssize_t (*store)(struct kobject *kobj, struct attribute *attr, 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(kobj, attr, 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(kobj, attr, 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout); return sysfs_emit(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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int num_tc, tc, index, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; ret = sysfs_rtnl_lock(kobj, attr, queue->dev); if (ret) return ret; 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; num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); 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 num_tc < 0 ? sysfs_emit(buf, "%d%d\n", tc, num_tc) : sysfs_emit(buf, "%d\n", tc); } #ifdef CONFIG_XPS static ssize_t tx_maxrate_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { int err, index = get_netdev_queue_index(queue); struct net_device *dev = queue->dev; u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the locking section below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; err = sysfs_rtnl_lock(kobj, attr, dev); if (err) return err; err = -EOPNOTSUPP; netdev_lock_ops(dev); if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); netdev_unlock_ops(dev); if (!err) { queue->tx_maxrate = rate; rtnl_unlock(); return len; } rtnl_unlock(); 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 sysfs_emit(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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } static ssize_t bql_set_hold_time(struct kobject *kobj, struct attribute *attr, 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_stall_thrs(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); } static ssize_t bql_set_stall_thrs(struct kobject *kobj, struct attribute *attr, 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; value = msecs_to_jiffies(value); if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) return -ERANGE; if (!dql->stall_thrs && value) dql->last_reap = jiffies; /* Force last_reap to be live */ smp_wmb(); dql->stall_thrs = value; return len; } static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); static ssize_t bql_show_stall_max(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); } static ssize_t bql_set_stall_max(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { WRITE_ONCE(queue->dql.stall_max, 0); return len; } static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); static ssize_t bql_show_stall_cnt(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%lu\n", dql->stall_cnt); } static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); static ssize_t bql_show_inflight(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(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 kobject *kobj, \ struct attribute *attr, \ struct netdev_queue *queue, char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct kobject *kobj, \ struct attribute *attr, \ 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, &bql_stall_thrs_attribute.attr, &bql_stall_cnt_attribute.attr, &bql_stall_max_attribute.attr, NULL }; static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; #else /* Fake declaration, all the code using it should be dead */ static const struct attribute_group dql_group = {}; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS static ssize_t xps_queue_show(struct net_device *dev, unsigned int index, int tc, char *buf, enum xps_map_type type) { struct xps_dev_maps *dev_maps; unsigned long *mask; unsigned int nr_ids; int j, len; rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps[type]); /* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0 * when dev_maps hasn't been allocated yet, to be backward compatible. */ nr_ids = dev_maps ? dev_maps->nr_ids : (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues); mask = bitmap_zalloc(nr_ids, GFP_NOWAIT); if (!mask) { rcu_read_unlock(); return -ENOMEM; } if (!dev_maps || tc >= dev_maps->num_tc) goto out_no_maps; for (j = 0; j < nr_ids; j++) { int i, tci = j * dev_maps->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(); len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t xps_cpus_show(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int len, tc, ret; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); ret = sysfs_rtnl_lock(kobj, attr, queue->dev); if (ret) return ret; /* 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) { rtnl_unlock(); return -EINVAL; } /* Increase the net device refcnt to make sure it won't be freed while * xps_queue_show is running. */ dev_hold(dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); dev_put(dev); return len; } static ssize_t xps_cpus_store(struct kobject *kobj, struct attribute *attr, struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned int 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; } err = sysfs_rtnl_lock(kobj, attr, dev); if (err) { free_cpumask_var(mask); return err; } 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 kobject *kobj, struct attribute *attr, struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int tc, ret; index = get_netdev_queue_index(queue); ret = sysfs_rtnl_lock(kobj, attr, dev); if (ret) return ret; tc = netdev_txq_to_tc(dev, index); /* Increase the net device refcnt to make sure it won't be freed while * xps_queue_show is running. */ dev_hold(dev); rtnl_unlock(); ret = tc >= 0 ? xps_queue_show(dev, index, tc, buf, XPS_RXQS) : -EINVAL; dev_put(dev); return ret; } static ssize_t xps_rxqs_store(struct kobject *kobj, struct attribute *attr, 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; unsigned int 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; } err = sysfs_rtnl_lock(kobj, attr, dev); if (err) { bitmap_free(mask); return err; } cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS); 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)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *netdev_queue_namespace(const 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->namespace) ns = dev->class->namespace(dev); return ns; } static void netdev_queue_get_ownership(const 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 const struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; static bool netdev_uses_bql(const struct net_device *dev) { if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE)) return false; return IS_ENABLED(CONFIG_BQL); } 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; /* Tx queues are cleared in netdev_queue_release to allow later * re-registration. This is triggered when their kobj refcount is * dropped. * * If a queue is removed while both a read (or write) operation and a * the re-addition of the same queue are pending (waiting on rntl_lock) * it might happen that the re-addition will execute before the read, * making the initial removal to never happen (queue's kobj refcount * won't drop enough because of the pending read). In such rare case, * return to allow the removal operation to complete. */ if (unlikely(kobj->state_initialized)) { netdev_warn_once(dev, "Cannot re-add tx queues before their removal completed"); return -EAGAIN; } /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; queue->groups = netdev_queue_default_groups; error = sysfs_create_groups(kobj, queue->groups); if (error) goto err; if (netdev_uses_bql(dev)) { error = sysfs_create_group(kobj, &dql_group); if (error) goto err_default_groups; } kobject_uevent(kobj, KOBJ_ADD); return 0; err_default_groups: sysfs_remove_groups(kobj, queue->groups); 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; if (netdev_uses_bql(ndev)) error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); 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; /* Tx queue kobjects are allowed to be updated when a device is being * unregistered, but solely to remove queues from qdiscs. Any path * adding queues should be fixed. */ WARN(dev->reg_state == NETREG_UNREGISTERING && new_num > old_num, "New queues can't be registered after device unregistration."); 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)->ns.count)) queue->kobj.uevent_suppress = 1; if (netdev_uses_bql(dev)) sysfs_remove_group(&queue->kobj, &dql_group); sysfs_remove_groups(&queue->kobj, queue->groups); 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); netdev_lock_ops(dev); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; netdev_unlock_ops(dev); #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(const struct device *d, struct kobj_uevent_env *env) { const 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)); kvfree(dev); } static const void *net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d); return dev_net(dev); } static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid) { const struct net_device *dev = to_net_dev(d); const struct net *net = dev_net(dev); net_ns_get_ownership(net, uid, gid); } static const struct class net_class = { .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 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)->ns.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 (wireless_group_needed(ndev)) *groups++ = &wireless_group; #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); } |
| 7053 337 86 328 53 327 328 337 338 89 328 10 1 9 328 189 7 87 337 10 24 24 9 130 151 6 125 72 6 320 293 2 267 267 15 15 15 252 204 49 32 234 126 126 2 126 43 102 126 41 2 2 4 14 22 63 63 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* Clean up the remaining folios. */ while ((folio = readahead_folio(rac)) != NULL) { folio_get(folio); filemap_remove_folio(folio); folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { struct folio *folio; folio = filemap_alloc_folio(gfp_mask, order); if (folio && ractl->dropbehind) __folio_set_dropbehind(folio); return folio; } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = ractl_alloc_folio(ractl, gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t start = readahead_index(ractl); pgoff_t index = start; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); /* * Fallback when size < min_nrpages as each folio should be * at least min_nrpages anyway. */ if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < mapping_max_folio_order(mapping)) new_order += 2; new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation below. */ if (!err) return; fallback: /* * ->readahead() may have updated readahead window size so we have to * check there's still something to read. */ if (ra->size > index - start) do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, 0); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start; unsigned int order = folio_order(folio); /* no readahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected) { ra->start += ra->size; /* * In the case of MADV_HUGEPAGE, the actual size might exceed * the readahead window. */ ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { struct file *file; const struct inode *inode; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; file = fd_file(f); if (!(file->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!file->f_mapping) return -EINVAL; if (!file->f_mapping->a_ops) return -EINVAL; inode = file_inode(file); if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; if (IS_ANON_FILE(inode)) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 90 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BYTEORDER_GENERIC_H #define _LINUX_BYTEORDER_GENERIC_H /* * linux/byteorder/generic.h * Generic Byte-reordering support * * The "... p" macros, like le64_to_cpup, can be used with pointers * to unaligned data, but there will be a performance penalty on * some architectures. Use get_unaligned for unaligned data. * * Francois-Rene Rideau <fare@tunes.org> 19970707 * gathered all the good ideas from all asm-foo/byteorder.h into one file, * cleaned them up. * I hope it is compliant with non-GCC compilers. * I decided to put __BYTEORDER_HAS_U64__ in byteorder.h, * because I wasn't sure it would be ok to put it in types.h * Upgraded it to 2.1.43 * Francois-Rene Rideau <fare@tunes.org> 19971012 * Upgraded it to 2.1.57 * to please Linus T., replaced huge #ifdef's between little/big endian * by nestedly #include'd files. * Francois-Rene Rideau <fare@tunes.org> 19971205 * Made it to 2.1.71; now a facelift: * Put files under include/linux/byteorder/ * Split swab from generic support. * * TODO: * = Regular kernel maintainers could also replace all these manual * byteswap macros that remain, disseminated among drivers, * after some grep or the sources... * = Linus might want to rename all these macros and files to fit his taste, * to fit his personal naming scheme. * = it seems that a few drivers would also appreciate * nybble swapping support... * = every architecture could add their byteswap macro in asm/byteorder.h * see how some architectures already do (i386, alpha, ppc, etc) * = cpu_to_beXX and beXX_to_cpu might some day need to be well * distinguished throughout the kernel. This is not the case currently, * since little endian, big endian, and pdp endian machines needn't it. * But this might be the case for, say, a port of Linux to 20/21 bit * architectures (and F21 Linux addict around?). */ /* * The following macros are to be defined by <asm/byteorder.h>: * * Conversion of long and short int between network and host format * ntohl(__u32 x) * ntohs(__u16 x) * htonl(__u32 x) * htons(__u16 x) * It seems that some programs (which? where? or perhaps a standard? POSIX?) * might like the above to be functions, not macros (why?). * if that's true, then detect them, and take measures. * Anyway, the measure is: define only ___ntohl as a macro instead, * and in a separate file, have * unsigned long inline ntohl(x){return ___ntohl(x);} * * The same for constant arguments * __constant_ntohl(__u32 x) * __constant_ntohs(__u16 x) * __constant_htonl(__u32 x) * __constant_htons(__u16 x) * * Conversion of XX-bit integers (16- 32- or 64-) * between native CPU format and little/big endian format * 64-bit stuff only defined for proper architectures * cpu_to_[bl]eXX(__uXX x) * [bl]eXX_to_cpu(__uXX x) * * The same, but takes a pointer to the value to convert * cpu_to_[bl]eXXp(__uXX x) * [bl]eXX_to_cpup(__uXX x) * * The same, but change in situ * cpu_to_[bl]eXXs(__uXX x) * [bl]eXX_to_cpus(__uXX x) * * See asm-foo/byteorder.h for examples of how to provide * architecture-optimized versions * */ #define cpu_to_le64 __cpu_to_le64 #define le64_to_cpu __le64_to_cpu #define cpu_to_le32 __cpu_to_le32 #define le32_to_cpu __le32_to_cpu #define cpu_to_le16 __cpu_to_le16 #define le16_to_cpu __le16_to_cpu #define cpu_to_be64 __cpu_to_be64 #define be64_to_cpu __be64_to_cpu #define cpu_to_be32 __cpu_to_be32 #define be32_to_cpu __be32_to_cpu #define cpu_to_be16 __cpu_to_be16 #define be16_to_cpu __be16_to_cpu #define cpu_to_le64p __cpu_to_le64p #define le64_to_cpup __le64_to_cpup #define cpu_to_le32p __cpu_to_le32p #define le32_to_cpup __le32_to_cpup #define cpu_to_le16p __cpu_to_le16p #define le16_to_cpup __le16_to_cpup #define cpu_to_be64p __cpu_to_be64p #define be64_to_cpup __be64_to_cpup #define cpu_to_be32p __cpu_to_be32p #define be32_to_cpup __be32_to_cpup #define cpu_to_be16p __cpu_to_be16p #define be16_to_cpup __be16_to_cpup #define cpu_to_le64s __cpu_to_le64s #define le64_to_cpus __le64_to_cpus #define cpu_to_le32s __cpu_to_le32s #define le32_to_cpus __le32_to_cpus #define cpu_to_le16s __cpu_to_le16s #define le16_to_cpus __le16_to_cpus #define cpu_to_be64s __cpu_to_be64s #define be64_to_cpus __be64_to_cpus #define cpu_to_be32s __cpu_to_be32s #define be32_to_cpus __be32_to_cpus #define cpu_to_be16s __cpu_to_be16s #define be16_to_cpus __be16_to_cpus /* * They have to be macros in order to do the constant folding * correctly - if the argument passed into a inline function * it is no longer constant according to gcc.. */ #undef ntohl #undef ntohs #undef htonl #undef htons #define ___htonl(x) __cpu_to_be32(x) #define ___htons(x) __cpu_to_be16(x) #define ___ntohl(x) __be32_to_cpu(x) #define ___ntohs(x) __be16_to_cpu(x) #define htonl(x) ___htonl(x) #define ntohl(x) ___ntohl(x) #define htons(x) ___htons(x) #define ntohs(x) ___ntohs(x) static inline void le16_add_cpu(__le16 *var, u16 val) { *var = cpu_to_le16(le16_to_cpu(*var) + val); } static inline void le32_add_cpu(__le32 *var, u32 val) { *var = cpu_to_le32(le32_to_cpu(*var) + val); } static inline void le64_add_cpu(__le64 *var, u64 val) { *var = cpu_to_le64(le64_to_cpu(*var) + val); } /* XXX: this stuff can be optimized */ static inline void le32_to_cpu_array(u32 *buf, unsigned int words) { while (words--) { __le32_to_cpus(buf); buf++; } } static inline void cpu_to_le32_array(u32 *buf, unsigned int words) { while (words--) { __cpu_to_le32s(buf); buf++; } } static inline void be16_add_cpu(__be16 *var, u16 val) { *var = cpu_to_be16(be16_to_cpu(*var) + val); } static inline void be32_add_cpu(__be32 *var, u32 val) { *var = cpu_to_be32(be32_to_cpu(*var) + val); } static inline void be64_add_cpu(__be64 *var, u64 val) { *var = cpu_to_be64(be64_to_cpu(*var) + val); } static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) { size_t i; for (i = 0; i < len; i++) dst[i] = cpu_to_be32(src[i]); } static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) { size_t i; for (i = 0; i < len; i++) dst[i] = be32_to_cpu(src[i]); } #endif /* _LINUX_BYTEORDER_GENERIC_H */ |
| 1 5072 99 5129 2 4254 4500 861 1 5070 133 2 862 613 9 5067 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef INT_BLK_MQ_H #define INT_BLK_MQ_H #include <linux/blk-mq.h> #include "blk-stat.h" struct blk_mq_tag_set; struct blk_mq_ctxs { struct kobject kobj; struct blk_mq_ctx __percpu *queue_ctx; }; /** * struct blk_mq_ctx - State for a software queue facing the submitting CPUs */ struct blk_mq_ctx { struct { spinlock_t lock; struct list_head rq_lists[HCTX_MAX_TYPES]; } ____cacheline_aligned_in_smp; unsigned int cpu; unsigned short index_hw[HCTX_MAX_TYPES]; struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES]; struct request_queue *queue; struct blk_mq_ctxs *ctxs; struct kobject kobj; } ____cacheline_aligned_in_smp; enum { BLK_MQ_NO_TAG = -1U, BLK_MQ_TAG_MIN = 1, BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; #define BLK_MQ_CPU_WORK_BATCH (8) typedef unsigned int __bitwise blk_insert_t; #define BLK_MQ_INSERT_AT_HEAD ((__force blk_insert_t)0x01) void blk_mq_submit_bio(struct bio *bio); int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, unsigned int flags); void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, bool); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); void blk_mq_put_rq_ref(struct request *rq); /* * Internal helpers for allocating/freeing the request map */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); void blk_mq_free_rq_map(struct blk_mq_tags *tags); struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int depth); void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); /* * CPU -> queue mappings */ extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int); /* * blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue * @q: request queue * @type: the hctx type index * @cpu: CPU */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q, enum hctx_type type, unsigned int cpu) { return xa_load(&q->hctx_table, q->tag_set->map[type].mq_map[cpu]); } static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf) { enum hctx_type type = HCTX_TYPE_DEFAULT; /* * The caller ensure that if REQ_POLLED, poll must be enabled. */ if (opf & REQ_POLLED) type = HCTX_TYPE_POLL; else if ((opf & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; return type; } /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue * @opf: operation type (REQ_OP_*) and flags (e.g. REQ_POLLED). * @ctx: software queue cpu ctx */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(blk_opf_t opf, struct blk_mq_ctx *ctx) { return ctx->hctxs[blk_mq_get_hctx_type(opf)]; } /* * sysfs helpers */ extern void blk_mq_sysfs_init(struct request_queue *q); extern void blk_mq_sysfs_deinit(struct request_queue *q); int blk_mq_sysfs_register(struct gendisk *disk); void blk_mq_sysfs_unregister(struct gendisk *disk); int blk_mq_sysfs_register_hctxs(struct request_queue *q); void blk_mq_sysfs_unregister_hctxs(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_free_plug_rqs(struct blk_plug *plug); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_cancel_work_sync(struct request_queue *q); void blk_mq_release(struct request_queue *q); static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { return per_cpu_ptr(q->queue_ctx, cpu); } /* * This assumes per-cpu software queueing queues. They could be per-node * as well, for instance. For now this is hardcoded as-is. Note that we don't * care about preemption, since we know the ctx's are persistent. This does * mean that we can't rely on ctx always matching the currently running CPU. */ static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) { return __blk_mq_get_ctx(q, raw_smp_processor_id()); } struct blk_mq_alloc_data { /* input parameter */ struct request_queue *q; blk_mq_req_flags_t flags; unsigned int shallow_depth; blk_opf_t cmd_flags; req_flags_t rq_flags; /* allocate multiple requests/tags in one go */ unsigned int nr_tags; struct rq_list *cached_rqs; /* input & output parameter */ struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; }; struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, unsigned int flags, int node); void blk_mq_free_tags(struct blk_mq_tags *tags); unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, unsigned int *offset); void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags); int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size); void blk_mq_tag_update_sched_shared_tags(struct request_queue *q); void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, void *priv); void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); static inline struct sbq_wait_state *bt_wait_ptr(struct sbitmap_queue *bt, struct blk_mq_hw_ctx *hctx) { if (!hctx) return &bt->ws[0]; return sbq_wait_ptr(bt, &hctx->wait_index); } void __blk_mq_tag_busy(struct blk_mq_hw_ctx *); void __blk_mq_tag_idle(struct blk_mq_hw_ctx *); static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_tag_busy(hctx); } static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_tag_idle(hctx); } static inline bool blk_mq_tag_is_reserved(struct blk_mq_tags *tags, unsigned int tag) { return tag < tags->nr_reserved_tags; } static inline bool blk_mq_is_shared_tags(unsigned int flags) { return flags & BLK_MQ_F_TAG_HCTX_SHARED; } static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { if (data->rq_flags & RQF_SCHED_TAGS) return data->hctx->sched_tags; return data->hctx->tags; } static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { /* Fast path: hardware queue is not stopped most of the time. */ if (likely(!test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return false; /* * This barrier is used to order adding of dispatch list before and * the test of BLK_MQ_S_STOPPED below. Pairs with the memory barrier * in blk_mq_start_stopped_hw_queue() so that dispatch code could * either see BLK_MQ_S_STOPPED is cleared or dispatch list is not * empty to avoid missing dispatching requests. */ smp_mb(); return test_bit(BLK_MQ_S_STOPPED, &hctx->state); } static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) { return hctx->nr_ctx && hctx->tags; } void blk_mq_in_driver_rw(struct block_device *part, unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q, int budget_token) { if (q->mq_ops->put_budget) q->mq_ops->put_budget(q, budget_token); } static inline int blk_mq_get_dispatch_budget(struct request_queue *q) { if (q->mq_ops->get_budget) return q->mq_ops->get_budget(q); return 0; } static inline void blk_mq_set_rq_budget_token(struct request *rq, int token) { if (token < 0) return; if (rq->q->mq_ops->set_rq_budget_token) rq->q->mq_ops->set_rq_budget_token(rq, token); } static inline int blk_mq_get_rq_budget_token(struct request *rq) { if (rq->q->mq_ops->get_rq_budget_token) return rq->q->mq_ops->get_rq_budget_token(rq); return -1; } static inline void __blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx, int val) { if (blk_mq_is_shared_tags(hctx->flags)) atomic_add(val, &hctx->queue->nr_active_requests_shared_tags); else atomic_add(val, &hctx->nr_active); } static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) { __blk_mq_add_active_requests(hctx, 1); } static inline void __blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx, int val) { if (blk_mq_is_shared_tags(hctx->flags)) atomic_sub(val, &hctx->queue->nr_active_requests_shared_tags); else atomic_sub(val, &hctx->nr_active); } static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) { __blk_mq_sub_active_requests(hctx, 1); } static inline void blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx, int val) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_add_active_requests(hctx, val); } static inline void blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_inc_active_requests(hctx); } static inline void blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx, int val) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_sub_active_requests(hctx, val); } static inline void blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) { if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) __blk_mq_dec_active_requests(hctx); } static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_shared_tags(hctx->flags)) return atomic_read(&hctx->queue->nr_active_requests_shared_tags); return atomic_read(&hctx->nr_active); } static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_mq_dec_active_requests(hctx); blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = BLK_MQ_NO_TAG; } static inline void blk_mq_put_driver_tag(struct request *rq) { if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG) return; __blk_mq_put_driver_tag(rq->mq_hctx, rq); } bool __blk_mq_alloc_driver_tag(struct request *rq); static inline bool blk_mq_get_driver_tag(struct request *rq) { if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq)) return false; return true; } static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) { int cpu; for_each_possible_cpu(cpu) qmap->mq_map[cpu] = 0; } /* Free all requests on the list */ static inline void blk_mq_free_requests(struct list_head *list) { while (!list_empty(list)) { struct request *rq = list_entry_rq(list->next); list_del_init(&rq->queuelist); blk_mq_free_request(rq); } } /* * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. */ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt) { unsigned int depth, users; if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; /* * Don't try dividing an ant */ if (bt->sb.depth == 1) return true; if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return true; } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return true; } users = READ_ONCE(hctx->tags->active_queues); if (!users) return true; /* * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); return __blk_mq_active_requests(hctx) < depth; } /* run the code block in @dispatch_ops with rcu/srcu read lock held */ #define __blk_mq_run_dispatch_ops(q, check_sleep, dispatch_ops) \ do { \ if ((q)->tag_set->flags & BLK_MQ_F_BLOCKING) { \ struct blk_mq_tag_set *__tag_set = (q)->tag_set; \ int srcu_idx; \ \ might_sleep_if(check_sleep); \ srcu_idx = srcu_read_lock(__tag_set->srcu); \ (dispatch_ops); \ srcu_read_unlock(__tag_set->srcu, srcu_idx); \ } else { \ rcu_read_lock(); \ (dispatch_ops); \ rcu_read_unlock(); \ } \ } while (0) #define blk_mq_run_dispatch_ops(q, dispatch_ops) \ __blk_mq_run_dispatch_ops(q, true, dispatch_ops) \ static inline bool blk_mq_can_poll(struct request_queue *q) { return (q->limits.features & BLK_FEAT_POLL) && q->tag_set->map[HCTX_TYPE_POLL].nr_queues; } #endif |
| 313 312 146 174 254 6 231 229 171 25 2 81 7 4 248 246 2 128 128 20 127 11 9 102 82 102 2 80 19 112 24 653 549 179 40 144 561 561 560 558 559 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 | // SPDX-License-Identifier: GPL-2.0 /* * SUCS NET3: * * Generic stream handling routines. These are generic for most * protocols. Even IP. Tonight 8-). * This is used because TCP, LLC (others too) layer all have mostly * identical sendmsg() and recvmsg() code. * So we (will) share it here. * * Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br> * (from old tcp.c code) * Alan Cox <alan@lxorguk.ukuu.org.uk> (Borrowed comments 8-)) */ #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/net.h> #include <linux/signal.h> #include <linux/tcp.h> #include <linux/wait.h> #include <net/sock.h> /** * sk_stream_write_space - stream socket write_space callback. * @sk: socket * * FIXME: write proper description */ void sk_stream_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; struct socket_wq *wq; if (__sk_stream_is_writeable(sk, 1) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } } /** * sk_stream_wait_connect - Wait for a socket to get into the connected state * @sk: sock to wait on * @timeo_p: for how long to wait * * Must be called with the socket locked. */ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct task_struct *tsk = current; int done; do { int err = sock_error(sk); if (err) return err; if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) return -EPIPE; if (!*timeo_p) return -EAGAIN; if (signal_pending(tsk)) return sock_intr_errno(*timeo_p); add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, !READ_ONCE(sk->sk_err) && !((1 << READ_ONCE(sk->sk_state)) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); return done < 0 ? done : 0; } EXPORT_SYMBOL(sk_stream_wait_connect); /** * sk_stream_closing - Return 1 if we still have things to send in our buffers. * @sk: socket to verify */ static int sk_stream_closing(const struct sock *sk) { return (1 << READ_ONCE(sk->sk_state)) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK); } void sk_stream_wait_close(struct sock *sk, long timeout) { if (timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); do { if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk), &wait)) break; } while (!signal_pending(current) && timeout); remove_wait_queue(sk_sleep(sk), &wait); } } EXPORT_SYMBOL(sk_stream_wait_close); /** * sk_stream_wait_memory - Wait for more memory for a socket * @sk: socket to wait for memory * @timeo_p: for how long */ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) { int ret, err = 0; long vm_wait = 0; long current_timeo = *timeo_p; DEFINE_WAIT_FUNC(wait, woken_wake_function); if (sk_stream_memory_free(sk)) current_timeo = vm_wait = get_random_u32_below(HZ / 5) + 2; add_wait_queue(sk_sleep(sk), &wait); while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; if (!*timeo_p) goto do_eagain; if (signal_pending(current)) goto do_interrupted; sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk_stream_memory_free(sk) && !vm_wait) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; ret = sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || (sk_stream_memory_free(sk) && !vm_wait), &wait); sk->sk_write_pending--; if (ret < 0) goto do_error; if (vm_wait) { vm_wait -= current_timeo; current_timeo = *timeo_p; if (current_timeo != MAX_SCHEDULE_TIMEOUT && (current_timeo -= vm_wait) < 0) current_timeo = 0; vm_wait = 0; } *timeo_p = current_timeo; } out: if (!sock_flag(sk, SOCK_DEAD)) remove_wait_queue(sk_sleep(sk), &wait); return err; do_error: err = -EPIPE; goto out; do_eagain: /* Make sure that whenever EAGAIN is returned, EPOLLOUT event can * be generated later. * When TCP receives ACK packets that make room, tcp_check_space() * only calls tcp_new_space() if SOCK_NOSPACE is set. */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; goto out; do_interrupted: err = sock_intr_errno(*timeo_p); goto out; } EXPORT_SYMBOL(sk_stream_wait_memory); int sk_stream_error(struct sock *sk, int flags, int err) { if (err == -EPIPE) err = sock_error(sk) ? : -EPIPE; if (err == -EPIPE && !(flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); return err; } EXPORT_SYMBOL(sk_stream_error); void sk_stream_kill_queues(struct sock *sk) { /* First the read buffer. */ __skb_queue_purge(&sk->sk_receive_queue); /* Next, the error queue. * We need to use queue lock, because other threads might * add packets to the queue without socket lock being held. */ skb_queue_purge(&sk->sk_error_queue); /* Next, the write queue. */ WARN_ON_ONCE(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ sk_mem_reclaim_final(sk); WARN_ON_ONCE(sk->sk_wmem_queued); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket * have gone away, only the net layer knows can touch it. */ } EXPORT_SYMBOL(sk_stream_kill_queues); |
| 3 2 12 12 2 5 1 1 1 1 1 1 1 7 2 2 4 3 16 16 6 16 7 3183 1 1 3184 3 3178 3179 3 2 6 5 11 11 5 2 1 1 5 3 1 1 4 4 2568 2569 1377 1484 2466 2466 2465 1941 1940 230 1269 4264 2466 2465 3086 2441 1278 990 230 998 221 1378 108 108 6 6 27 2 4 8 5 3 3 6 6 5 1 1 52 2 2 3 4 3 4 3 2 2 27 27 1 8 4 2 5 1 2 1 2 25 22 3 27 23 4 58 58 20 6 32 15 28 1 5 20 5 5 11 1 2 6 5 4 4 26 26 2 5 2 489 489 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/types.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/sysctl.h> #include <linux/net.h> #include <linux/module.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/mpls.h> #include <linux/netconf.h> #include <linux/nospec.h> #include <linux/vmalloc.h> #include <linux/percpu.h> #include <net/gso.h> #include <net/ip.h> #include <net/dst.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/netevent.h> #include <net/ip_tunnels.h> #include <net/netns/generic.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #endif #include <net/ipv6_stubs.h> #include <net/rtnh.h> #include "internal.h" /* max memory we will use for mpls_route */ #define MAX_MPLS_ROUTE_MEM 4096 /* Maximum number of labels to look ahead at when selecting a path of * a multipath route */ #define MAX_MP_SELECT_LABELS 4 #define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1) static int label_limit = (1 << 20) - 1; static int ttl_max = 255; #if IS_ENABLED(CONFIG_NET_IP_TUNNEL) static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e) { return sizeof(struct mpls_shim_hdr); } static const struct ip_tunnel_encap_ops mpls_iptun_ops = { .encap_hlen = ipgre_mpls_encap_hlen, }; static int ipgre_tunnel_encap_add_mpls_ops(void) { return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); } static void ipgre_tunnel_encap_del_mpls_ops(void) { ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS); } #else static int ipgre_tunnel_encap_add_mpls_ops(void) { return 0; } static void ipgre_tunnel_encap_del_mpls_ops(void) { } #endif static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) { struct mpls_route *rt = NULL; if (index < net->mpls.platform_labels) { struct mpls_route __rcu **platform_label = rcu_dereference(net->mpls.platform_label); rt = rcu_dereference(platform_label[index]); } return rt; } bool mpls_output_possible(const struct net_device *dev) { return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev); } EXPORT_SYMBOL_GPL(mpls_output_possible); static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh) { return (u8 *)nh + rt->rt_via_offset; } static const u8 *mpls_nh_via(const struct mpls_route *rt, const struct mpls_nh *nh) { return __mpls_nh_via((struct mpls_route *)rt, (struct mpls_nh *)nh); } static unsigned int mpls_nh_header_size(const struct mpls_nh *nh) { /* The size of the layer 2.5 labels to be added for this route */ return nh->nh_labels * sizeof(struct mpls_shim_hdr); } unsigned int mpls_dev_mtu(const struct net_device *dev) { /* The amount of data the layer 2 frame can hold */ return dev->mtu; } EXPORT_SYMBOL_GPL(mpls_dev_mtu); bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); void mpls_stats_inc_outucastpkts(struct net_device *dev, const struct sk_buff *skb) { struct mpls_dev *mdev; if (skb->protocol == htons(ETH_P_MPLS_UC)) { mdev = mpls_dev_get(dev); if (mdev) MPLS_INC_STATS_LEN(mdev, skb->len, tx_packets, tx_bytes); } else if (skb->protocol == htons(ETH_P_IP)) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { struct inet6_dev *in6dev = __in6_dev_get(dev); if (in6dev) IP6_UPD_PO_STATS(dev_net(dev), in6dev, IPSTATS_MIB_OUT, skb->len); #endif } } EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts); static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb) { struct mpls_entry_decoded dec; unsigned int mpls_hdr_len = 0; struct mpls_shim_hdr *hdr; bool eli_seen = false; int label_index; u32 hash = 0; for (label_index = 0; label_index < MAX_MP_SELECT_LABELS; label_index++) { mpls_hdr_len += sizeof(*hdr); if (!pskb_may_pull(skb, mpls_hdr_len)) break; /* Read and decode the current label */ hdr = mpls_hdr(skb) + label_index; dec = mpls_entry_decode(hdr); /* RFC6790 - reserved labels MUST NOT be used as keys * for the load-balancing function */ if (likely(dec.label >= MPLS_LABEL_FIRST_UNRESERVED)) { hash = jhash_1word(dec.label, hash); /* The entropy label follows the entropy label * indicator, so this means that the entropy * label was just added to the hash - no need to * go any deeper either in the label stack or in the * payload */ if (eli_seen) break; } else if (dec.label == MPLS_LABEL_ENTROPY) { eli_seen = true; } if (!dec.bos) continue; /* found bottom label; does skb have room for a header? */ if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) { const struct iphdr *v4hdr; v4hdr = (const struct iphdr *)(hdr + 1); if (v4hdr->version == 4) { hash = jhash_3words(ntohl(v4hdr->saddr), ntohl(v4hdr->daddr), v4hdr->protocol, hash); } else if (v4hdr->version == 6 && pskb_may_pull(skb, mpls_hdr_len + sizeof(struct ipv6hdr))) { const struct ipv6hdr *v6hdr; v6hdr = (const struct ipv6hdr *)(hdr + 1); hash = __ipv6_addr_jhash(&v6hdr->saddr, hash); hash = __ipv6_addr_jhash(&v6hdr->daddr, hash); hash = jhash_1word(v6hdr->nexthdr, hash); } } break; } return hash; } static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index) { return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size); } /* number of alive nexthops (rt->rt_nhn_alive) and the flags for * a next hop (nh->nh_flags) are modified by netdev event handlers. * Since those fields can change at any moment, use READ_ONCE to * access both. */ static const struct mpls_nh *mpls_select_multipath(struct mpls_route *rt, struct sk_buff *skb) { u32 hash = 0; int nh_index = 0; int n = 0; u8 alive; /* No need to look further into packet if there's only * one path */ if (rt->rt_nhn == 1) return rt->rt_nh; alive = READ_ONCE(rt->rt_nhn_alive); if (alive == 0) return NULL; hash = mpls_multipath_hash(rt, skb); nh_index = hash % alive; if (alive == rt->rt_nhn) goto out; for_nexthops(rt) { unsigned int nh_flags = READ_ONCE(nh->nh_flags); if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) continue; if (n == nh_index) return nh; n++; } endfor_nexthops(rt); out: return mpls_get_nexthop(rt, nh_index); } static bool mpls_egress(struct net *net, struct mpls_route *rt, struct sk_buff *skb, struct mpls_entry_decoded dec) { enum mpls_payload_type payload_type; bool success = false; /* The IPv4 code below accesses through the IPv4 header * checksum, which is 12 bytes into the packet. * The IPv6 code below accesses through the IPv6 hop limit * which is 8 bytes into the packet. * * For all supported cases there should always be at least 12 * bytes of packet data present. The IPv4 header is 20 bytes * without options and the IPv6 header is always 40 bytes * long. */ if (!pskb_may_pull(skb, 12)) return false; payload_type = rt->rt_payload_type; if (payload_type == MPT_UNSPEC) payload_type = ip_hdr(skb)->version; switch (payload_type) { case MPT_IPV4: { struct iphdr *hdr4 = ip_hdr(skb); u8 new_ttl; skb->protocol = htons(ETH_P_IP); /* If propagating TTL, take the decremented TTL from * the incoming MPLS header, otherwise decrement the * TTL, but only if not 0 to avoid underflow. */ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && net->mpls.ip_ttl_propagate)) new_ttl = dec.ttl; else new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0; csum_replace2(&hdr4->check, htons(hdr4->ttl << 8), htons(new_ttl << 8)); hdr4->ttl = new_ttl; success = true; break; } case MPT_IPV6: { struct ipv6hdr *hdr6 = ipv6_hdr(skb); skb->protocol = htons(ETH_P_IPV6); /* If propagating TTL, take the decremented TTL from * the incoming MPLS header, otherwise decrement the * hop limit, but only if not 0 to avoid underflow. */ if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED || (rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT && net->mpls.ip_ttl_propagate)) hdr6->hop_limit = dec.ttl; else if (hdr6->hop_limit) hdr6->hop_limit = hdr6->hop_limit - 1; success = true; break; } case MPT_UNSPEC: /* Should have decided which protocol it is by now */ break; } return success; } static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct net *net = dev_net(dev); struct mpls_shim_hdr *hdr; const struct mpls_nh *nh; struct mpls_route *rt; struct mpls_entry_decoded dec; struct net_device *out_dev; struct mpls_dev *out_mdev; struct mpls_dev *mdev; unsigned int hh_len; unsigned int new_header_size; unsigned int mtu; int err; /* Careful this entire function runs inside of an rcu critical section */ mdev = mpls_dev_get(dev); if (!mdev) goto drop; MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets, rx_bytes); if (!mdev->input_enabled) { MPLS_INC_STATS(mdev, rx_dropped); goto drop; } if (skb->pkt_type != PACKET_HOST) goto err; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) goto err; if (!pskb_may_pull(skb, sizeof(*hdr))) goto err; skb_dst_drop(skb); /* Read and decode the label */ hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); rt = mpls_route_input_rcu(net, dec.label); if (!rt) { MPLS_INC_STATS(mdev, rx_noroute); goto drop; } nh = mpls_select_multipath(rt, skb); if (!nh) goto err; /* Pop the label */ skb_pull(skb, sizeof(*hdr)); skb_reset_network_header(skb); skb_orphan(skb); if (skb_warn_if_lro(skb)) goto err; skb_forward_csum(skb); /* Verify ttl is valid */ if (dec.ttl <= 1) goto err; /* Find the output device */ out_dev = nh->nh_dev; if (!mpls_output_possible(out_dev)) goto tx_err; /* Verify the destination can hold the packet */ new_header_size = mpls_nh_header_size(nh); mtu = mpls_dev_mtu(out_dev); if (mpls_pkt_too_big(skb, mtu - new_header_size)) goto tx_err; hh_len = LL_RESERVED_SPACE(out_dev); if (!out_dev->header_ops) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ if (skb_cow(skb, hh_len + new_header_size)) goto tx_err; skb->dev = out_dev; skb->protocol = htons(ETH_P_MPLS_UC); dec.ttl -= 1; if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) goto err; } else { bool bos; int i; skb_push(skb, new_header_size); skb_reset_network_header(skb); /* Push the new labels */ hdr = mpls_hdr(skb); bos = dec.bos; for (i = nh->nh_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(nh->nh_label[i], dec.ttl, 0, bos); bos = false; } } mpls_stats_inc_outucastpkts(out_dev, skb); /* If via wasn't specified then send out using device address */ if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) err = neigh_xmit(NEIGH_LINK_TABLE, out_dev, out_dev->dev_addr, skb); else err = neigh_xmit(nh->nh_via_table, out_dev, mpls_nh_via(rt, nh), skb); if (err) net_dbg_ratelimited("%s: packet transmission failed: %d\n", __func__, err); return 0; tx_err: out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; if (out_mdev) MPLS_INC_STATS(out_mdev, tx_errors); goto drop; err: MPLS_INC_STATS(mdev, rx_errors); drop: kfree_skb(skb); return NET_RX_DROP; } static struct packet_type mpls_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_MPLS_UC), .func = mpls_forward, }; static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_TTL_PROPAGATE] = { .type = NLA_U8 }, }; struct mpls_route_config { u32 rc_protocol; u32 rc_ifindex; u8 rc_via_table; u8 rc_via_alen; u8 rc_via[MAX_VIA_ALEN]; u32 rc_label; u8 rc_ttl_propagate; u8 rc_output_labels; u32 rc_output_label[MAX_NEW_LABELS]; u32 rc_nlflags; enum mpls_payload_type rc_payload_type; struct nl_info rc_nlinfo; struct rtnexthop *rc_mp; int rc_mp_len; }; /* all nexthops within a route have the same size based on max * number of labels and max via length for a hop */ static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels) { u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen); struct mpls_route *rt; size_t size; size = sizeof(*rt) + num_nh * nh_size; if (size > MAX_MPLS_ROUTE_MEM) return ERR_PTR(-EINVAL); rt = kzalloc(size, GFP_KERNEL); if (!rt) return ERR_PTR(-ENOMEM); rt->rt_nhn = num_nh; rt->rt_nhn_alive = num_nh; rt->rt_nh_size = nh_size; rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels); return rt; } static void mpls_rt_free(struct mpls_route *rt) { if (rt) kfree_rcu(rt, rt_rcu); } static void mpls_notify_route(struct net *net, unsigned index, struct mpls_route *old, struct mpls_route *new, const struct nl_info *info) { struct nlmsghdr *nlh = info ? info->nlh : NULL; unsigned portid = info ? info->portid : 0; int event = new ? RTM_NEWROUTE : RTM_DELROUTE; struct mpls_route *rt = new ? new : old; unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0; /* Ignore reserved labels for now */ if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED)) rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags); } static void mpls_route_update(struct net *net, unsigned index, struct mpls_route *new, const struct nl_info *info) { struct mpls_route __rcu **platform_label; struct mpls_route *rt; ASSERT_RTNL(); platform_label = rtnl_dereference(net->mpls.platform_label); rt = rtnl_dereference(platform_label[index]); rcu_assign_pointer(platform_label[index], new); mpls_notify_route(net, index, rt, new, info); /* If we removed a route free it now */ mpls_rt_free(rt); } static unsigned find_free_label(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels; index++) { if (!rtnl_dereference(platform_label[index])) return index; } return LABEL_NOT_SPECIFIED; } #if IS_ENABLED(CONFIG_INET) static struct net_device *inet_fib_lookup_dev(struct net *net, const void *addr) { struct net_device *dev; struct rtable *rt; struct in_addr daddr; memcpy(&daddr, addr, sizeof(struct in_addr)); rt = ip_route_output(net, daddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return ERR_CAST(rt); dev = rt->dst.dev; dev_hold(dev); ip_rt_put(rt); return dev; } #else static struct net_device *inet_fib_lookup_dev(struct net *net, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); } #endif #if IS_ENABLED(CONFIG_IPV6) static struct net_device *inet6_fib_lookup_dev(struct net *net, const void *addr) { struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); dst_release(dst); return dev; } #else static struct net_device *inet6_fib_lookup_dev(struct net *net, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); } #endif static struct net_device *find_outdev(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif) { struct net_device *dev = NULL; if (!oif) { switch (nh->nh_via_table) { case NEIGH_ARP_TABLE: dev = inet_fib_lookup_dev(net, mpls_nh_via(rt, nh)); break; case NEIGH_ND_TABLE: dev = inet6_fib_lookup_dev(net, mpls_nh_via(rt, nh)); break; case NEIGH_LINK_TABLE: break; } } else { dev = dev_get_by_index(net, oif); } if (!dev) return ERR_PTR(-ENODEV); if (IS_ERR(dev)) return dev; /* The caller is holding rtnl anyways, so release the dev reference */ dev_put(dev); return dev; } static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif) { struct net_device *dev = NULL; int err = -ENODEV; dev = find_outdev(net, rt, nh, oif); if (IS_ERR(dev)) { err = PTR_ERR(dev); dev = NULL; goto errout; } /* Ensure this is a supported device */ err = -EINVAL; if (!mpls_dev_get(dev)) goto errout; if ((nh->nh_via_table == NEIGH_LINK_TABLE) && (dev->addr_len != nh->nh_via_alen)) goto errout; nh->nh_dev = dev; if (!(dev->flags & IFF_UP)) { nh->nh_flags |= RTNH_F_DEAD; } else { unsigned int flags; flags = dev_get_flags(dev); if (!(flags & (IFF_RUNNING | IFF_LOWER_UP))) nh->nh_flags |= RTNH_F_LINKDOWN; } return 0; errout: return err; } static int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table, u8 via_addr[], struct netlink_ext_ack *extack) { struct rtvia *via = nla_data(nla); int err = -EINVAL; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid attribute length for RTA_VIA"); goto errout; } alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); if (alen > MAX_VIA_ALEN) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid address length for RTA_VIA"); goto errout; } /* Validate the address family */ switch (via->rtvia_family) { case AF_PACKET: *via_table = NEIGH_LINK_TABLE; break; case AF_INET: *via_table = NEIGH_ARP_TABLE; if (alen != 4) goto errout; break; case AF_INET6: *via_table = NEIGH_ND_TABLE; if (alen != 16) goto errout; break; default: /* Unsupported address family */ goto errout; } memcpy(via_addr, via->rtvia_addr, alen); *via_alen = alen; err = 0; errout: return err; } static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg, struct mpls_route *rt) { struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_nh *nh = rt->rt_nh; int err; int i; if (!nh) return -ENOMEM; nh->nh_labels = cfg->rc_output_labels; for (i = 0; i < nh->nh_labels; i++) nh->nh_label[i] = cfg->rc_output_label[i]; nh->nh_via_table = cfg->rc_via_table; memcpy(__mpls_nh_via(rt, nh), cfg->rc_via, cfg->rc_via_alen); nh->nh_via_alen = cfg->rc_via_alen; err = mpls_nh_assign_dev(net, rt, nh, cfg->rc_ifindex); if (err) goto errout; if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) rt->rt_nhn_alive--; return 0; errout: return err; } static int mpls_nh_build(struct net *net, struct mpls_route *rt, struct mpls_nh *nh, int oif, struct nlattr *via, struct nlattr *newdst, u8 max_labels, struct netlink_ext_ack *extack) { int err = -ENOMEM; if (!nh) goto errout; if (newdst) { err = nla_get_labels(newdst, max_labels, &nh->nh_labels, nh->nh_label, extack); if (err) goto errout; } if (via) { err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table, __mpls_nh_via(rt, nh), extack); if (err) goto errout; } else { nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC; } err = mpls_nh_assign_dev(net, rt, nh, oif); if (err) goto errout; return 0; errout: return err; } static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len, u8 cfg_via_alen, u8 *max_via_alen, u8 *max_labels) { int remaining = len; u8 nhs = 0; *max_via_alen = 0; *max_labels = 0; while (rtnh_ok(rtnh, remaining)) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); int attrlen; u8 n_labels = 0; attrlen = rtnh_attrlen(rtnh); nla = nla_find(attrs, attrlen, RTA_VIA); if (nla && nla_len(nla) >= offsetof(struct rtvia, rtvia_addr)) { int via_alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); if (via_alen <= MAX_VIA_ALEN) *max_via_alen = max_t(u16, *max_via_alen, via_alen); } nla = nla_find(attrs, attrlen, RTA_NEWDST); if (nla && nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL, NULL) != 0) return 0; *max_labels = max_t(u8, *max_labels, n_labels); /* number of nexthops is tracked by a u8. * Check for overflow. */ if (nhs == 255) return 0; nhs++; rtnh = rtnh_next(rtnh, &remaining); } /* leftover implies invalid nexthop configuration, discard it */ return remaining > 0 ? 0 : nhs; } static int mpls_nh_build_multi(struct mpls_route_config *cfg, struct mpls_route *rt, u8 max_labels, struct netlink_ext_ack *extack) { struct rtnexthop *rtnh = cfg->rc_mp; struct nlattr *nla_via, *nla_newdst; int remaining = cfg->rc_mp_len; int err = 0; u8 nhs = 0; change_nexthops(rt) { int attrlen; nla_via = NULL; nla_newdst = NULL; err = -EINVAL; if (!rtnh_ok(rtnh, remaining)) goto errout; /* neither weighted multipath nor any flags * are supported */ if (rtnh->rtnh_hops || rtnh->rtnh_flags) goto errout; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *attrs = rtnh_attrs(rtnh); nla_via = nla_find(attrs, attrlen, RTA_VIA); nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST); } err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh, rtnh->rtnh_ifindex, nla_via, nla_newdst, max_labels, extack); if (err) goto errout; if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) rt->rt_nhn_alive--; rtnh = rtnh_next(rtnh, &remaining); nhs++; } endfor_nexthops(rt); rt->rt_nhn = nhs; return 0; errout: return err; } static bool mpls_label_ok(struct net *net, unsigned int *index, struct netlink_ext_ack *extack) { bool is_ok = true; /* Reserved labels may not be set */ if (*index < MPLS_LABEL_FIRST_UNRESERVED) { NL_SET_ERR_MSG(extack, "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); is_ok = false; } /* The full 20 bit range may not be supported. */ if (is_ok && *index >= net->mpls.platform_labels) { NL_SET_ERR_MSG(extack, "Label >= configured maximum in platform_labels"); is_ok = false; } *index = array_index_nospec(*index, net->mpls.platform_labels); return is_ok; } static int mpls_route_add(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct mpls_route __rcu **platform_label; struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_route *rt, *old; int err = -EINVAL; u8 max_via_alen; unsigned index; u8 max_labels; u8 nhs; index = cfg->rc_label; /* If a label was not specified during insert pick one */ if ((index == LABEL_NOT_SPECIFIED) && (cfg->rc_nlflags & NLM_F_CREATE)) { index = find_free_label(net); } if (!mpls_label_ok(net, &index, extack)) goto errout; /* Append makes no sense with mpls */ err = -EOPNOTSUPP; if (cfg->rc_nlflags & NLM_F_APPEND) { NL_SET_ERR_MSG(extack, "MPLS does not support route append"); goto errout; } err = -EEXIST; platform_label = rtnl_dereference(net->mpls.platform_label); old = rtnl_dereference(platform_label[index]); if ((cfg->rc_nlflags & NLM_F_EXCL) && old) goto errout; err = -EEXIST; if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old) goto errout; err = -ENOENT; if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old) goto errout; err = -EINVAL; if (cfg->rc_mp) { nhs = mpls_count_nexthops(cfg->rc_mp, cfg->rc_mp_len, cfg->rc_via_alen, &max_via_alen, &max_labels); } else { max_via_alen = cfg->rc_via_alen; max_labels = cfg->rc_output_labels; nhs = 1; } if (nhs == 0) { NL_SET_ERR_MSG(extack, "Route does not contain a nexthop"); goto errout; } rt = mpls_rt_alloc(nhs, max_via_alen, max_labels); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto errout; } rt->rt_protocol = cfg->rc_protocol; rt->rt_payload_type = cfg->rc_payload_type; rt->rt_ttl_propagate = cfg->rc_ttl_propagate; if (cfg->rc_mp) err = mpls_nh_build_multi(cfg, rt, max_labels, extack); else err = mpls_nh_build_from_cfg(cfg, rt); if (err) goto freert; mpls_route_update(net, index, rt, &cfg->rc_nlinfo); return 0; freert: mpls_rt_free(rt); errout: return err; } static int mpls_route_del(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct net *net = cfg->rc_nlinfo.nl_net; unsigned index; int err = -EINVAL; index = cfg->rc_label; if (!mpls_label_ok(net, &index, extack)) goto errout; mpls_route_update(net, index, NULL, &cfg->rc_nlinfo); err = 0; errout: return err; } static void mpls_get_stats(struct mpls_dev *mdev, struct mpls_link_stats *stats) { struct mpls_pcpu_stats *p; int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { struct mpls_link_stats local; unsigned int start; p = per_cpu_ptr(mdev->stats, i); do { start = u64_stats_fetch_begin(&p->syncp); local = p->stats; } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += local.rx_packets; stats->rx_bytes += local.rx_bytes; stats->tx_packets += local.tx_packets; stats->tx_bytes += local.tx_bytes; stats->rx_errors += local.rx_errors; stats->tx_errors += local.tx_errors; stats->rx_dropped += local.rx_dropped; stats->tx_dropped += local.tx_dropped; stats->rx_noroute += local.rx_noroute; } } static int mpls_fill_stats_af(struct sk_buff *skb, const struct net_device *dev) { struct mpls_link_stats *stats; struct mpls_dev *mdev; struct nlattr *nla; mdev = mpls_dev_get(dev); if (!mdev) return -ENODATA; nla = nla_reserve_64bit(skb, MPLS_STATS_LINK, sizeof(struct mpls_link_stats), MPLS_STATS_UNSPEC); if (!nla) return -EMSGSIZE; stats = nla_data(nla); mpls_get_stats(mdev, stats); return 0; } static size_t mpls_get_stats_af_size(const struct net_device *dev) { struct mpls_dev *mdev; mdev = mpls_dev_get(dev); if (!mdev) return 0; return nla_total_size_64bit(sizeof(struct mpls_link_stats)); } static int mpls_netconf_fill_devconf(struct sk_buff *skb, struct mpls_dev *mdev, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_MPLS; if (nla_put_s32(skb, NETCONFA_IFINDEX, mdev->dev->ifindex) < 0) goto nla_put_failure; if ((all || type == NETCONFA_INPUT) && nla_put_s32(skb, NETCONFA_INPUT, READ_ONCE(mdev->input_enabled)) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mpls_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_INPUT) size += nla_total_size(4); return size; } static void mpls_netconf_notify_devconf(struct net *net, int event, int type, struct mpls_dev *mdev) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = mpls_netconf_fill_devconf(skb, mdev, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); } static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, }; static int mpls_netconf_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_mpls_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_mpls_policy, extack); if (err) return err; for (i = 0; i <= NETCONFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETCONFA_IFINDEX: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request"); return -EINVAL; } } return 0; } static int mpls_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; struct net_device *dev; struct mpls_dev *mdev; struct sk_buff *skb; int ifindex; int err; err = mpls_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); dev = __dev_get_by_index(net, ifindex); if (!dev) goto errout; mdev = mpls_dev_get(dev); if (!mdev) goto errout; err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } static int mpls_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct { unsigned long ifindex; } *ctx = (void *)cb->ctx; struct net_device *dev; struct mpls_dev *mdev; int err = 0; if (cb->strict_check) { struct netlink_ext_ack *extack = cb->extack; struct netconfmsg *ncm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ncm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header in netconf dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { mdev = mpls_dev_get(dev); if (!mdev) continue; err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL); if (err < 0) break; } rcu_read_unlock(); return err; } #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ (&((struct mpls_dev *)0)->field) static int mpls_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int oval = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write) { struct mpls_dev *mdev = ctl->extra1; int i = (int *)ctl->data - (int *)mdev; struct net *net = ctl->extra2; int val = *(int *)ctl->data; if (i == offsetof(struct mpls_dev, input_enabled) && val != oval) { mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_INPUT, mdev); } } return ret; } static const struct ctl_table mpls_dev_table[] = { { .procname = "input", .maxlen = sizeof(int), .mode = 0644, .proc_handler = mpls_conf_proc, .data = MPLS_PERDEV_SYSCTL_OFFSET(input_enabled), }, }; static int mpls_dev_sysctl_register(struct net_device *dev, struct mpls_dev *mdev) { char path[sizeof("net/mpls/conf/") + IFNAMSIZ]; size_t table_size = ARRAY_SIZE(mpls_dev_table); struct net *net = dev_net(dev); struct ctl_table *table; int i; table = kmemdup(&mpls_dev_table, sizeof(mpls_dev_table), GFP_KERNEL); if (!table) goto out; /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ for (i = 0; i < table_size; i++) { table[i].data = (char *)mdev + (uintptr_t)table[i].data; table[i].extra1 = mdev; table[i].extra2 = net; } snprintf(path, sizeof(path), "net/mpls/conf/%s", dev->name); mdev->sysctl = register_net_sysctl_sz(net, path, table, table_size); if (!mdev->sysctl) goto free; mpls_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, mdev); return 0; free: kfree(table); out: mdev->sysctl = NULL; return -ENOBUFS; } static void mpls_dev_sysctl_unregister(struct net_device *dev, struct mpls_dev *mdev) { struct net *net = dev_net(dev); const struct ctl_table *table; if (!mdev->sysctl) return; table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); mpls_netconf_notify_devconf(net, RTM_DELNETCONF, 0, mdev); } static struct mpls_dev *mpls_add_dev(struct net_device *dev) { struct mpls_dev *mdev; int err = -ENOMEM; int i; ASSERT_RTNL(); mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(err); mdev->stats = alloc_percpu(struct mpls_pcpu_stats); if (!mdev->stats) goto free; for_each_possible_cpu(i) { struct mpls_pcpu_stats *mpls_stats; mpls_stats = per_cpu_ptr(mdev->stats, i); u64_stats_init(&mpls_stats->syncp); } mdev->dev = dev; err = mpls_dev_sysctl_register(dev, mdev); if (err) goto free; rcu_assign_pointer(dev->mpls_ptr, mdev); return mdev; free: free_percpu(mdev->stats); kfree(mdev); return ERR_PTR(err); } static void mpls_dev_destroy_rcu(struct rcu_head *head) { struct mpls_dev *mdev = container_of(head, struct mpls_dev, rcu); free_percpu(mdev->stats); kfree(mdev); } static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); bool nh_del = false; u8 alive = 0; if (!rt) continue; if (event == NETDEV_UNREGISTER) { u8 deleted = 0; for_nexthops(rt) { if (!nh->nh_dev || nh->nh_dev == dev) deleted++; if (nh->nh_dev == dev) nh_del = true; } endfor_nexthops(rt); /* if there are no more nexthops, delete the route */ if (deleted == rt->rt_nhn) { mpls_route_update(net, index, NULL, NULL); continue; } if (nh_del) { size_t size = sizeof(*rt) + rt->rt_nhn * rt->rt_nh_size; struct mpls_route *orig = rt; rt = kmemdup(orig, size, GFP_KERNEL); if (!rt) return -ENOMEM; } } change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; if (nh->nh_dev != dev) goto next; switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nh_flags |= RTNH_F_DEAD; fallthrough; case NETDEV_CHANGE: nh_flags |= RTNH_F_LINKDOWN; break; } if (event == NETDEV_UNREGISTER) nh->nh_dev = NULL; if (nh->nh_flags != nh_flags) WRITE_ONCE(nh->nh_flags, nh_flags); next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); if (nh_del) mpls_route_update(net, index, rt, NULL); } return 0; } static void mpls_ifup(struct net_device *dev, unsigned int flags) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); unsigned index; u8 alive; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); if (!rt) continue; alive = 0; change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; if (!(nh_flags & flags)) { alive++; continue; } if (nh->nh_dev != dev) continue; alive++; nh_flags &= ~flags; WRITE_ONCE(nh->nh_flags, nh_flags); } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); } } static int mpls_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mpls_dev *mdev; unsigned int flags; int err; if (event == NETDEV_REGISTER) { mdev = mpls_add_dev(dev); if (IS_ERR(mdev)) return notifier_from_errno(PTR_ERR(mdev)); return NOTIFY_OK; } mdev = mpls_dev_get(dev); if (!mdev) return NOTIFY_OK; switch (event) { case NETDEV_DOWN: err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); else mpls_ifup(dev, RTNH_F_DEAD); break; case NETDEV_CHANGE: flags = dev_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); } else { err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); } break; case NETDEV_UNREGISTER: err = mpls_ifdown(dev, event); if (err) return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); RCU_INIT_POINTER(dev->mpls_ptr, NULL); call_rcu(&mdev->rcu, mpls_dev_destroy_rcu); } break; case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) return notifier_from_errno(err); } break; } return NOTIFY_OK; } static struct notifier_block mpls_dev_notifier = { .notifier_call = mpls_dev_notify, }; static int nla_put_via(struct sk_buff *skb, u8 table, const void *addr, int alen) { static const int table_to_family[NEIGH_NR_TABLES + 1] = { AF_INET, AF_INET6, AF_PACKET, }; struct nlattr *nla; struct rtvia *via; int family = AF_UNSPEC; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) return -EMSGSIZE; if (table <= NEIGH_NR_TABLES) family = table_to_family[table]; via = nla_data(nla); via->rtvia_family = family; memcpy(via->rtvia_addr, addr, alen); return 0; } int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, const u32 label[]) { struct nlattr *nla; struct mpls_shim_hdr *nla_label; bool bos; int i; nla = nla_reserve(skb, attrtype, labels*4); if (!nla) return -EMSGSIZE; nla_label = nla_data(nla); bos = true; for (i = labels - 1; i >= 0; i--) { nla_label[i] = mpls_entry_encode(label[i], 0, 0, bos); bos = false; } return 0; } EXPORT_SYMBOL_GPL(nla_put_labels); int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, u32 label[], struct netlink_ext_ack *extack) { unsigned len = nla_len(nla); struct mpls_shim_hdr *nla_label; u8 nla_labels; bool bos; int i; /* len needs to be an even multiple of 4 (the label size). Number * of labels is a u8 so check for overflow. */ if (len & 3 || len / 4 > 255) { NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid length for labels attribute"); return -EINVAL; } /* Limit the number of new labels allowed */ nla_labels = len/4; if (nla_labels > max_labels) { NL_SET_ERR_MSG(extack, "Too many labels"); return -EINVAL; } /* when label == NULL, caller wants number of labels */ if (!label) goto out; nla_label = nla_data(nla); bos = true; for (i = nla_labels - 1; i >= 0; i--, bos = false) { struct mpls_entry_decoded dec; dec = mpls_entry_decode(nla_label + i); /* Ensure the bottom of stack flag is properly set * and ttl and tc are both clear. */ if (dec.ttl) { NL_SET_ERR_MSG_ATTR(extack, nla, "TTL in label must be 0"); return -EINVAL; } if (dec.tc) { NL_SET_ERR_MSG_ATTR(extack, nla, "Traffic class in label must be 0"); return -EINVAL; } if (dec.bos != bos) { NL_SET_BAD_ATTR(extack, nla); if (bos) { NL_SET_ERR_MSG(extack, "BOS bit must be set in first label"); } else { NL_SET_ERR_MSG(extack, "BOS bit can only be set in first label"); } return -EINVAL; } switch (dec.label) { case MPLS_LABEL_IMPLNULL: /* RFC3032: This is a label that an LSR may * assign and distribute, but which never * actually appears in the encapsulation. */ NL_SET_ERR_MSG_ATTR(extack, nla, "Implicit NULL Label (3) can not be used in encapsulation"); return -EINVAL; } label[i] = dec.label; } out: *labels = nla_labels; return 0; } EXPORT_SYMBOL_GPL(nla_get_labels); static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; int index; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_family != AF_MPLS) { NL_SET_ERR_MSG(extack, "Invalid address family in rtmsg"); goto errout; } if (rtm->rtm_dst_len != 20) { NL_SET_ERR_MSG(extack, "rtm_dst_len must be 20 for MPLS"); goto errout; } if (rtm->rtm_src_len != 0) { NL_SET_ERR_MSG(extack, "rtm_src_len must be 0 for MPLS"); goto errout; } if (rtm->rtm_tos != 0) { NL_SET_ERR_MSG(extack, "rtm_tos must be 0 for MPLS"); goto errout; } if (rtm->rtm_table != RT_TABLE_MAIN) { NL_SET_ERR_MSG(extack, "MPLS only supports the main route table"); goto errout; } /* Any value is acceptable for rtm_protocol */ /* As mpls uses destination specific addresses * (or source specific address in the case of multicast) * all addresses have universal scope. */ if (rtm->rtm_scope != RT_SCOPE_UNIVERSE) { NL_SET_ERR_MSG(extack, "Invalid route scope - MPLS only supports UNIVERSE"); goto errout; } if (rtm->rtm_type != RTN_UNICAST) { NL_SET_ERR_MSG(extack, "Invalid route type - MPLS only supports UNICAST"); goto errout; } if (rtm->rtm_flags != 0) { NL_SET_ERR_MSG(extack, "rtm_flags must be 0 for MPLS"); goto errout; } cfg->rc_label = LABEL_NOT_SPECIFIED; cfg->rc_protocol = rtm->rtm_protocol; cfg->rc_via_table = MPLS_NEIGH_TABLE_UNSPEC; cfg->rc_ttl_propagate = MPLS_TTL_PROP_DEFAULT; cfg->rc_nlflags = nlh->nlmsg_flags; cfg->rc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->rc_nlinfo.nlh = nlh; cfg->rc_nlinfo.nl_net = sock_net(skb->sk); for (index = 0; index <= RTA_MAX; index++) { struct nlattr *nla = tb[index]; if (!nla) continue; switch (index) { case RTA_OIF: cfg->rc_ifindex = nla_get_u32(nla); break; case RTA_NEWDST: if (nla_get_labels(nla, MAX_NEW_LABELS, &cfg->rc_output_labels, cfg->rc_output_label, extack)) goto errout; break; case RTA_DST: { u8 label_count; if (nla_get_labels(nla, 1, &label_count, &cfg->rc_label, extack)) goto errout; if (!mpls_label_ok(cfg->rc_nlinfo.nl_net, &cfg->rc_label, extack)) goto errout; break; } case RTA_GATEWAY: NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, &cfg->rc_via_table, cfg->rc_via, extack)) goto errout; break; } case RTA_MULTIPATH: { cfg->rc_mp = nla_data(nla); cfg->rc_mp_len = nla_len(nla); break; } case RTA_TTL_PROPAGATE: { u8 ttl_propagate = nla_get_u8(nla); if (ttl_propagate > 1) { NL_SET_ERR_MSG_ATTR(extack, nla, "RTA_TTL_PROPAGATE can only be 0 or 1"); goto errout; } cfg->rc_ttl_propagate = ttl_propagate ? MPLS_TTL_PROP_ENABLED : MPLS_TTL_PROP_DISABLED; break; } default: NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute"); /* Unsupported attribute */ goto errout; } } err = 0; errout: return err; } static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct mpls_route_config *cfg; int err; cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; err = mpls_route_del(cfg, extack); out: kfree(cfg); return err; } static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct mpls_route_config *cfg; int err; cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); if (!cfg) return -ENOMEM; err = rtm_to_route_config(skb, nlh, cfg, extack); if (err < 0) goto out; err = mpls_route_add(cfg, extack); out: kfree(cfg); return err; } static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 label, struct mpls_route *rt, int flags) { struct net_device *dev; struct nlmsghdr *nlh; struct rtmsg *rtm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = AF_MPLS; rtm->rtm_dst_len = 20; rtm->rtm_src_len = 0; rtm->rtm_tos = 0; rtm->rtm_table = RT_TABLE_MAIN; rtm->rtm_protocol = rt->rt_protocol; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; if (nla_put_labels(skb, RTA_DST, 1, &label)) goto nla_put_failure; if (rt->rt_ttl_propagate != MPLS_TTL_PROP_DEFAULT) { bool ttl_propagate = rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED; if (nla_put_u8(skb, RTA_TTL_PROPAGATE, ttl_propagate)) goto nla_put_failure; } if (rt->rt_nhn == 1) { const struct mpls_nh *nh = rt->rt_nh; if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (nh->nh_flags & RTNH_F_LINKDOWN) rtm->rtm_flags |= RTNH_F_LINKDOWN; if (nh->nh_flags & RTNH_F_DEAD) rtm->rtm_flags |= RTNH_F_DEAD; } else { struct rtnexthop *rtnh; struct nlattr *mp; u8 linkdown = 0; u8 dead = 0; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; for_nexthops(rt) { dev = nh->nh_dev; if (!dev) continue; rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); if (!rtnh) goto nla_put_failure; rtnh->rtnh_ifindex = dev->ifindex; if (nh->nh_flags & RTNH_F_LINKDOWN) { rtnh->rtnh_flags |= RTNH_F_LINKDOWN; linkdown++; } if (nh->nh_flags & RTNH_F_DEAD) { rtnh->rtnh_flags |= RTNH_F_DEAD; dead++; } if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; } endfor_nexthops(rt); if (linkdown == rt->rt_nhn) rtm->rtm_flags |= RTNH_F_LINKDOWN; if (dead == rt->rt_nhn) rtm->rtm_flags |= RTNH_F_DEAD; nla_nest_end(skb, mp); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } #if IS_ENABLED(CONFIG_INET) static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { return ip_valid_fib_dump_req(net, nlh, filter, cb); } #else static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for FIB dump request"); return -EINVAL; } if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_protocol) { filter->protocol = rtm->rtm_protocol; filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (i == RTA_OIF) { ifindex = nla_get_u32(tb[i]); filter->dev = __dev_get_by_index(net, ifindex); if (!filter->dev) return -ENODEV; filter->filter_set = 1; } else if (tb[i]) { NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } #endif static bool mpls_rt_uses_dev(struct mpls_route *rt, const struct net_device *dev) { if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; if (nh->nh_dev == dev) return true; } else { for_nexthops(rt) { if (nh->nh_dev == dev) return true; } endfor_nexthops(rt); } return false; } static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct mpls_route __rcu **platform_label; struct fib_dump_filter filter = { .rtnl_held = true, }; unsigned int flags = NLM_F_MULTI; size_t platform_labels; unsigned int index; ASSERT_RTNL(); if (cb->strict_check) { int err; err = mpls_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) return err; /* for MPLS, there is only 1 table with fixed type and flags. * If either are set in the filter then return nothing. */ if ((filter.table_id && filter.table_id != RT_TABLE_MAIN) || (filter.rt_type && filter.rt_type != RTN_UNICAST) || filter.flags) return skb->len; } index = cb->args[0]; if (index < MPLS_LABEL_FIRST_UNRESERVED) index = MPLS_LABEL_FIRST_UNRESERVED; platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; if (filter.filter_set) flags |= NLM_F_DUMP_FILTERED; for (; index < platform_labels; index++) { struct mpls_route *rt; rt = rtnl_dereference(platform_label[index]); if (!rt) continue; if ((filter.dev && !mpls_rt_uses_dev(rt, filter.dev)) || (filter.protocol && rt->rt_protocol != filter.protocol)) continue; if (mpls_dump_route(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, index, rt, flags) < 0) break; } cb->args[0] = index; return skb->len; } static inline size_t lfib_nlmsg_size(struct mpls_route *rt) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_DST */ + nla_total_size(1); /* RTA_TTL_PROPAGATE */ if (rt->rt_nhn == 1) { struct mpls_nh *nh = rt->rt_nh; if (nh->nh_dev) payload += nla_total_size(4); /* RTA_OIF */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) /* RTA_VIA */ payload += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) /* RTA_NEWDST */ payload += nla_total_size(nh->nh_labels * 4); } else { /* each nexthop is packed in an attribute */ size_t nhsize = 0; for_nexthops(rt) { if (!nh->nh_dev) continue; nhsize += nla_total_size(sizeof(struct rtnexthop)); /* RTA_VIA */ if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC) nhsize += nla_total_size(2 + nh->nh_via_alen); if (nh->nh_labels) nhsize += nla_total_size(nh->nh_labels * 4); } endfor_nexthops(rt); /* nested attribute */ payload += nla_total_size(nhsize); } return payload; } static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags) { struct sk_buff *skb; u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); if (skb == NULL) goto errout; err = mpls_dump_route(skb, portid, seq, event, label, rt, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_MPLS_ROUTE, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } static int mpls_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if ((rtm->rtm_dst_len && rtm->rtm_dst_len != 20) || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_mpls_policy, extack); if (err) return err; if ((tb[RTA_DST] || tb[RTA_NEWDST]) && !rtm->rtm_dst_len) { NL_SET_ERR_MSG_MOD(extack, "rtm_dst_len must be 20 for MPLS"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_DST: case RTA_NEWDST: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); u32 portid = NETLINK_CB(in_skb).portid; u32 in_label = LABEL_NOT_SPECIFIED; struct nlattr *tb[RTA_MAX + 1]; u32 labels[MAX_NEW_LABELS]; struct mpls_shim_hdr *hdr; unsigned int hdr_size = 0; const struct mpls_nh *nh; struct net_device *dev; struct mpls_route *rt; struct rtmsg *rtm, *r; struct nlmsghdr *nlh; struct sk_buff *skb; u8 n_labels; int err; err = mpls_valid_getroute_req(in_skb, in_nlh, tb, extack); if (err < 0) goto errout; rtm = nlmsg_data(in_nlh); if (tb[RTA_DST]) { u8 label_count; if (nla_get_labels(tb[RTA_DST], 1, &label_count, &in_label, extack)) { err = -EINVAL; goto errout; } if (!mpls_label_ok(net, &in_label, extack)) { err = -EINVAL; goto errout; } } rt = mpls_route_input_rcu(net, in_label); if (!rt) { err = -ENETUNREACH; goto errout; } if (rtm->rtm_flags & RTM_F_FIB_MATCH) { skb = nlmsg_new(lfib_nlmsg_size(rt), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = mpls_dump_route(skb, portid, in_nlh->nlmsg_seq, RTM_NEWROUTE, in_label, rt, 0); if (err < 0) { /* -EMSGSIZE implies BUG in lfib_nlmsg_size */ WARN_ON(err == -EMSGSIZE); goto errout_free; } return rtnl_unicast(skb, net, portid); } if (tb[RTA_NEWDST]) { if (nla_get_labels(tb[RTA_NEWDST], MAX_NEW_LABELS, &n_labels, labels, extack) != 0) { err = -EINVAL; goto errout; } hdr_size = n_labels * sizeof(struct mpls_shim_hdr); } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } skb->protocol = htons(ETH_P_MPLS_UC); if (hdr_size) { bool bos; int i; if (skb_cow(skb, hdr_size)) { err = -ENOBUFS; goto errout_free; } skb_reserve(skb, hdr_size); skb_push(skb, hdr_size); skb_reset_network_header(skb); /* Push new labels */ hdr = mpls_hdr(skb); bos = true; for (i = n_labels - 1; i >= 0; i--) { hdr[i] = mpls_entry_encode(labels[i], 1, 0, bos); bos = false; } } nh = mpls_select_multipath(rt, skb); if (!nh) { err = -ENETUNREACH; goto errout_free; } if (hdr_size) { skb_pull(skb, hdr_size); skb_reset_network_header(skb); } nlh = nlmsg_put(skb, portid, in_nlh->nlmsg_seq, RTM_NEWROUTE, sizeof(*r), 0); if (!nlh) { err = -EMSGSIZE; goto errout_free; } r = nlmsg_data(nlh); r->rtm_family = AF_MPLS; r->rtm_dst_len = 20; r->rtm_src_len = 0; r->rtm_table = RT_TABLE_MAIN; r->rtm_type = RTN_UNICAST; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = rt->rt_protocol; r->rtm_flags = 0; if (nla_put_labels(skb, RTA_DST, 1, &in_label)) goto nla_put_failure; if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST, nh->nh_labels, nh->nh_label)) goto nla_put_failure; if (nh->nh_via_table != MPLS_NEIGH_TABLE_UNSPEC && nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh), nh->nh_via_alen)) goto nla_put_failure; dev = nh->nh_dev; if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; nlmsg_end(skb, nlh); err = rtnl_unicast(skb, net, portid); errout: return err; nla_put_failure: nlmsg_cancel(skb, nlh); err = -EMSGSIZE; errout_free: kfree_skb(skb); return err; } static int resize_platform_label_table(struct net *net, size_t limit) { size_t size = sizeof(struct mpls_route *) * limit; size_t old_limit; size_t cp_size; struct mpls_route __rcu **labels = NULL, **old; struct mpls_route *rt0 = NULL, *rt2 = NULL; unsigned index; if (size) { labels = kvzalloc(size, GFP_KERNEL); if (!labels) goto nolabels; } /* In case the predefined labels need to be populated */ if (limit > MPLS_LABEL_IPV4NULL) { struct net_device *lo = net->loopback_dev; rt0 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt0)) goto nort0; rt0->rt_nh->nh_dev = lo; rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt0->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt0->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt0, rt0->rt_nh), lo->dev_addr, lo->addr_len); } if (limit > MPLS_LABEL_IPV6NULL) { struct net_device *lo = net->loopback_dev; rt2 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt2)) goto nort2; rt2->rt_nh->nh_dev = lo; rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; rt2->rt_nh->nh_via_table = NEIGH_LINK_TABLE; rt2->rt_nh->nh_via_alen = lo->addr_len; memcpy(__mpls_nh_via(rt2, rt2->rt_nh), lo->dev_addr, lo->addr_len); } rtnl_lock(); /* Remember the original table */ old = rtnl_dereference(net->mpls.platform_label); old_limit = net->mpls.platform_labels; /* Free any labels beyond the new table */ for (index = limit; index < old_limit; index++) mpls_route_update(net, index, NULL, NULL); /* Copy over the old labels */ cp_size = size; if (old_limit < limit) cp_size = old_limit * sizeof(struct mpls_route *); memcpy(labels, old, cp_size); /* If needed set the predefined labels */ if ((old_limit <= MPLS_LABEL_IPV6NULL) && (limit > MPLS_LABEL_IPV6NULL)) { RCU_INIT_POINTER(labels[MPLS_LABEL_IPV6NULL], rt2); rt2 = NULL; } if ((old_limit <= MPLS_LABEL_IPV4NULL) && (limit > MPLS_LABEL_IPV4NULL)) { RCU_INIT_POINTER(labels[MPLS_LABEL_IPV4NULL], rt0); rt0 = NULL; } /* Update the global pointers */ net->mpls.platform_labels = limit; rcu_assign_pointer(net->mpls.platform_label, labels); rtnl_unlock(); mpls_rt_free(rt2); mpls_rt_free(rt0); if (old) { synchronize_rcu(); kvfree(old); } return 0; nort2: mpls_rt_free(rt0); nort0: kvfree(labels); nolabels: return -ENOMEM; } static int mpls_platform_labels(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = table->data; int platform_labels = net->mpls.platform_labels; int ret; struct ctl_table tmp = { .procname = table->procname, .data = &platform_labels, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = &label_limit, }; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = resize_platform_label_table(net, platform_labels); return ret; } #define MPLS_NS_SYSCTL_OFFSET(field) \ (&((struct net *)0)->field) static const struct ctl_table mpls_table[] = { { .procname = "platform_labels", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = mpls_platform_labels, }, { .procname = "ip_ttl_propagate", .data = MPLS_NS_SYSCTL_OFFSET(mpls.ip_ttl_propagate), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "default_ttl", .data = MPLS_NS_SYSCTL_OFFSET(mpls.default_ttl), .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = &ttl_max, }, }; static int mpls_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(mpls_table); struct ctl_table *table; int i; net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; net->mpls.default_ttl = 255; table = kmemdup(mpls_table, sizeof(mpls_table), GFP_KERNEL); if (table == NULL) return -ENOMEM; /* Table data contains only offsets relative to the base of * the mdev at this point, so make them absolute. */ for (i = 0; i < table_size; i++) table[i].data = (char *)net + (uintptr_t)table[i].data; net->mpls.ctl = register_net_sysctl_sz(net, "net/mpls", table, table_size); if (net->mpls.ctl == NULL) { kfree(table); return -ENOMEM; } return 0; } static void mpls_net_exit(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; const struct ctl_table *table; unsigned int index; table = net->mpls.ctl->ctl_table_arg; unregister_net_sysctl_table(net->mpls.ctl); kfree(table); /* An rcu grace period has passed since there was a device in * the network namespace (and thus the last in flight packet) * left this network namespace. This is because * unregister_netdevice_many and netdev_run_todo has completed * for each network device that was in this network namespace. * * As such no additional rcu synchronization is necessary when * freeing the platform_label table. */ rtnl_lock(); platform_label = rtnl_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; for (index = 0; index < platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); RCU_INIT_POINTER(platform_label[index], NULL); mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } rtnl_unlock(); kvfree(platform_label); } static struct pernet_operations mpls_net_ops = { .init = mpls_net_init, .exit = mpls_net_exit, }; static struct rtnl_af_ops mpls_af_ops __read_mostly = { .family = AF_MPLS, .fill_stats_af = mpls_fill_stats_af, .get_stats_af_size = mpls_get_stats_af_size, }; static const struct rtnl_msg_handler mpls_rtnl_msg_handlers[] __initdata_or_module = { {THIS_MODULE, PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, 0}, {THIS_MODULE, PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, 0}, {THIS_MODULE, PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, 0}, {THIS_MODULE, PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, RTNL_FLAG_DUMP_UNLOCKED}, }; static int __init mpls_init(void) { int err; BUILD_BUG_ON(sizeof(struct mpls_shim_hdr) != 4); err = register_pernet_subsys(&mpls_net_ops); if (err) goto out; err = register_netdevice_notifier(&mpls_dev_notifier); if (err) goto out_unregister_pernet; dev_add_pack(&mpls_packet_type); err = rtnl_af_register(&mpls_af_ops); if (err) goto out_unregister_dev_type; err = rtnl_register_many(mpls_rtnl_msg_handlers); if (err) goto out_unregister_rtnl_af; err = ipgre_tunnel_encap_add_mpls_ops(); if (err) { pr_err("Can't add mpls over gre tunnel ops\n"); goto out_unregister_rtnl; } err = 0; out: return err; out_unregister_rtnl: rtnl_unregister_many(mpls_rtnl_msg_handlers); out_unregister_rtnl_af: rtnl_af_unregister(&mpls_af_ops); out_unregister_dev_type: dev_remove_pack(&mpls_packet_type); out_unregister_pernet: unregister_pernet_subsys(&mpls_net_ops); goto out; } module_init(mpls_init); static void __exit mpls_exit(void) { rtnl_unregister_all(PF_MPLS); rtnl_af_unregister(&mpls_af_ops); dev_remove_pack(&mpls_packet_type); unregister_netdevice_notifier(&mpls_dev_notifier); unregister_pernet_subsys(&mpls_net_ops); ipgre_tunnel_encap_del_mpls_ops(); } module_exit(mpls_exit); MODULE_DESCRIPTION("MultiProtocol Label Switching"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_NETPROTO(PF_MPLS); |
| 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MSR_H #define _ASM_X86_MSR_H #include "msr-index.h" #ifndef __ASSEMBLER__ #include <asm/asm.h> #include <asm/errno.h> #include <asm/cpumask.h> #include <uapi/asm/msr.h> #include <asm/shared/msr.h> #include <linux/types.h> #include <linux/percpu.h> struct msr_info { u32 msr_no; struct msr reg; struct msr __percpu *msrs; int err; }; struct msr_regs_info { u32 *regs; int err; }; struct saved_msr { bool valid; struct msr_info info; }; struct saved_msrs { unsigned int num; struct saved_msr *array; }; /* * Be very careful with includes. This header is prone to include loops. */ #include <asm/atomic.h> #include <linux/tracepoint-defs.h> #ifdef CONFIG_TRACEPOINTS DECLARE_TRACEPOINT(read_msr); DECLARE_TRACEPOINT(write_msr); DECLARE_TRACEPOINT(rdpmc); extern void do_trace_write_msr(u32 msr, u64 val, int failed); extern void do_trace_read_msr(u32 msr, u64 val, int failed); extern void do_trace_rdpmc(u32 msr, u64 val, int failed); #else static inline void do_trace_write_msr(u32 msr, u64 val, int failed) {} static inline void do_trace_read_msr(u32 msr, u64 val, int failed) {} static inline void do_trace_rdpmc(u32 msr, u64 val, int failed) {} #endif /* * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR * accessors and should not have any tracing or other functionality piggybacking * on them - those are *purely* for accessing MSRs and nothing more. So don't even * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ static __always_inline u64 __rdmsr(u32 msr) { EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("1: rdmsr\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR) : EAX_EDX_RET(val, low, high) : "c" (msr)); return EAX_EDX_VAL(val, low, high); } static __always_inline void __wrmsrq(u32 msr, u64 val) { asm volatile("1: wrmsr\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)) : "memory"); } #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ (void)((val1) = (u32)__val); \ (void)((val2) = (u32)(__val >> 32)); \ } while (0) static __always_inline u64 native_rdmsrq(u32 msr) { return __rdmsr(msr); } #define native_wrmsr(msr, low, high) \ __wrmsrq((msr), (u64)(high) << 32 | (low)) #define native_wrmsrq(msr, val) \ __wrmsrq((msr), (val)) static inline u64 native_read_msr(u32 msr) { u64 val; val = __rdmsr(msr); if (tracepoint_enabled(read_msr)) do_trace_read_msr(msr, val, 0); return val; } static inline int native_read_msr_safe(u32 msr, u64 *p) { int err; EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("1: rdmsr ; xor %[err],%[err]\n" "2:\n\t" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err]) : [err] "=r" (err), EAX_EDX_RET(val, low, high) : "c" (msr)); if (tracepoint_enabled(read_msr)) do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), err); *p = EAX_EDX_VAL(val, low, high); return err; } /* Can be uninlined because referenced by paravirt */ static inline void notrace native_write_msr(u32 msr, u64 val) { native_wrmsrq(msr, val); if (tracepoint_enabled(write_msr)) do_trace_write_msr(msr, val, 0); } /* Can be uninlined because referenced by paravirt */ static inline int notrace native_write_msr_safe(u32 msr, u64 val) { int err; asm volatile("1: wrmsr ; xor %[err],%[err]\n" "2:\n\t" _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err]) : [err] "=a" (err) : "c" (msr), "0" ((u32)val), "d" ((u32)(val >> 32)) : "memory"); if (tracepoint_enabled(write_msr)) do_trace_write_msr(msr, val, err); return err; } extern int rdmsr_safe_regs(u32 regs[8]); extern int wrmsr_safe_regs(u32 regs[8]); static inline u64 native_read_pmc(int counter) { EAX_EDX_DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); if (tracepoint_enabled(rdpmc)) do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #include <linux/errno.h> /* * Access to machine-specific registers (available on 586 and better only) * Note: the rd* operations modify the parameters directly (without using * pointer indirection), this allows gcc to optimize better */ #define rdmsr(msr, low, high) \ do { \ u64 __val = native_read_msr((msr)); \ (void)((low) = (u32)__val); \ (void)((high) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(u32 msr, u32 low, u32 high) { native_write_msr(msr, (u64)high << 32 | low); } #define rdmsrq(msr, val) \ ((val) = native_read_msr((msr))) static inline void wrmsrq(u32 msr, u64 val) { native_write_msr(msr, val); } /* wrmsr with exception handling */ static inline int wrmsrq_safe(u32 msr, u64 val) { return native_write_msr_safe(msr, val); } /* rdmsr with exception handling */ #define rdmsr_safe(msr, low, high) \ ({ \ u64 __val; \ int __err = native_read_msr_safe((msr), &__val); \ (*low) = (u32)__val; \ (*high) = (u32)(__val >> 32); \ __err; \ }) static inline int rdmsrq_safe(u32 msr, u64 *p) { return native_read_msr_safe(msr, p); } static __always_inline u64 rdpmc(int counter) { return native_read_pmc(counter); } #endif /* !CONFIG_PARAVIRT_XXL */ /* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */ #define ASM_WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) /* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */ static __always_inline void wrmsrns(u32 msr, u64 val) { /* * WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant * DS prefix to avoid a trailing NOP. */ asm volatile("1: " ALTERNATIVE("ds wrmsr", ASM_WRMSRNS, X86_FEATURE_WRMSRNS) "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32))); } /* * Dual u32 version of wrmsrq_safe(): */ static inline int wrmsr_safe(u32 msr, u32 low, u32 high) { return wrmsrq_safe(msr, (u64)high << 32 | low); } struct msr __percpu *msrs_alloc(void); void msrs_free(struct msr __percpu *msrs); int msr_set_bit(u32 msr, u8 bit); int msr_clear_bit(u32 msr, u8 bit); #ifdef CONFIG_SMP int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q); void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { rdmsr(msr_no, *l, *h); return 0; } static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { wrmsr(msr_no, l, h); return 0; } static inline int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { rdmsrq(msr_no, *q); return 0; } static inline int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { wrmsrq(msr_no, q); return 0; } static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr __percpu *msrs) { rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h)); } static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, struct msr __percpu *msrs) { wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h)); } static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { return rdmsr_safe(msr_no, l, h); } static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } static inline int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) { return rdmsrq_safe(msr_no, q); } static inline int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) { return wrmsrq_safe(msr_no, q); } static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return rdmsr_safe_regs(regs); } static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { return wrmsr_safe_regs(regs); } #endif /* CONFIG_SMP */ /* Compatibility wrappers: */ #define rdmsrl(msr, val) rdmsrq(msr, val) #define wrmsrl(msr, val) wrmsrq(msr, val) #define rdmsrl_on_cpu(cpu, msr, q) rdmsrq_on_cpu(cpu, msr, q) #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_MSR_H */ |
| 2643 614 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FIB_LOOKUP_H #define _FIB_LOOKUP_H #include <linux/types.h> #include <linux/list.h> #include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/nexthop.h> struct fib_alias { struct hlist_node fa_list; struct fib_info *fa_info; dscp_t fa_dscp; u8 fa_type; u8 fa_state; u8 fa_slen; u32 tb_id; s16 fa_default; u8 offload; u8 trap; u8 offload_failed; struct rcu_head rcu; }; #define FA_S_ACCESSED 0x01 /* Don't write on fa_state unless needed, to keep it shared on all cpus */ static inline void fib_alias_accessed(struct fib_alias *fa) { if (!(fa->fa_state & FA_S_ACCESSED)) fa->fa_state |= FA_S_ACCESSED; } /* Exported by fib_semantics.c */ void fib_release_info(struct fib_info *); struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack); int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, const struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); size_t fib_nlmsg_size(struct fib_info *fi); static inline void fib_result_assign(struct fib_result *res, struct fib_info *fi) { /* we used to play games with refcounts, but we now use RCU */ res->fi = fi; res->nhc = fib_info_nhc(fi, 0); } struct fib_prop { int error; u8 scope; }; extern const struct fib_prop fib_props[RTN_MAX + 1]; #endif /* _FIB_LOOKUP_H */ |
| 4 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/build_bug.h> #include <linux/errno.h> #include <linux/errname.h> #include <linux/kernel.h> #include <linux/math.h> /* * Ensure these tables do not accidentally become gigantic if some * huge errno makes it in. On most architectures, the first table will * only have about 140 entries, but mips and parisc have more sparsely * allocated errnos (with EHWPOISON = 257 on parisc, and EDQUOT = 1133 * on mips), so this wastes a bit of space on those - though we * special case the EDQUOT case. */ #define E(err) [err + BUILD_BUG_ON_ZERO(err <= 0 || err > 300)] = "-" #err static const char *names_0[] = { E(E2BIG), E(EACCES), E(EADDRINUSE), E(EADDRNOTAVAIL), E(EADV), E(EAFNOSUPPORT), E(EAGAIN), /* EWOULDBLOCK */ E(EALREADY), E(EBADE), E(EBADF), E(EBADFD), E(EBADMSG), E(EBADR), E(EBADRQC), E(EBADSLT), E(EBFONT), E(EBUSY), E(ECANCELED), /* ECANCELLED */ E(ECHILD), E(ECHRNG), E(ECOMM), E(ECONNABORTED), E(ECONNREFUSED), /* EREFUSED */ E(ECONNRESET), E(EDEADLK), /* EDEADLOCK */ #if EDEADLK != EDEADLOCK /* mips, sparc, powerpc */ E(EDEADLOCK), #endif E(EDESTADDRREQ), E(EDOM), E(EDOTDOT), #ifndef CONFIG_MIPS E(EDQUOT), #endif E(EEXIST), E(EFAULT), E(EFBIG), E(EHOSTDOWN), E(EHOSTUNREACH), E(EHWPOISON), E(EIDRM), E(EILSEQ), #ifdef EINIT E(EINIT), #endif E(EINPROGRESS), E(EINTR), E(EINVAL), E(EIO), E(EISCONN), E(EISDIR), E(EISNAM), E(EKEYEXPIRED), E(EKEYREJECTED), E(EKEYREVOKED), E(EL2HLT), E(EL2NSYNC), E(EL3HLT), E(EL3RST), E(ELIBACC), E(ELIBBAD), E(ELIBEXEC), E(ELIBMAX), E(ELIBSCN), E(ELNRNG), E(ELOOP), E(EMEDIUMTYPE), E(EMFILE), E(EMLINK), E(EMSGSIZE), E(EMULTIHOP), E(ENAMETOOLONG), E(ENAVAIL), E(ENETDOWN), E(ENETRESET), E(ENETUNREACH), E(ENFILE), E(ENOANO), E(ENOBUFS), E(ENOCSI), E(ENODATA), E(ENODEV), E(ENOENT), E(ENOEXEC), E(ENOKEY), E(ENOLCK), E(ENOLINK), E(ENOMEDIUM), E(ENOMEM), E(ENOMSG), E(ENONET), E(ENOPKG), E(ENOPROTOOPT), E(ENOSPC), E(ENOSR), E(ENOSTR), E(ENOSYS), E(ENOTBLK), E(ENOTCONN), E(ENOTDIR), E(ENOTEMPTY), E(ENOTNAM), E(ENOTRECOVERABLE), E(ENOTSOCK), E(ENOTTY), E(ENOTUNIQ), E(ENXIO), E(EOPNOTSUPP), E(EOVERFLOW), E(EOWNERDEAD), E(EPERM), E(EPFNOSUPPORT), E(EPIPE), #ifdef EPROCLIM E(EPROCLIM), #endif E(EPROTO), E(EPROTONOSUPPORT), E(EPROTOTYPE), E(ERANGE), E(EREMCHG), #ifdef EREMDEV E(EREMDEV), #endif E(EREMOTE), E(EREMOTEIO), E(ERESTART), E(ERFKILL), E(EROFS), #ifdef ERREMOTE E(ERREMOTE), #endif E(ESHUTDOWN), E(ESOCKTNOSUPPORT), E(ESPIPE), E(ESRCH), E(ESRMNT), E(ESTALE), E(ESTRPIPE), E(ETIME), E(ETIMEDOUT), E(ETOOMANYREFS), E(ETXTBSY), E(EUCLEAN), E(EUNATCH), E(EUSERS), E(EXDEV), E(EXFULL), }; #undef E #ifdef EREFUSED /* parisc */ static_assert(EREFUSED == ECONNREFUSED); #endif #ifdef ECANCELLED /* parisc */ static_assert(ECANCELLED == ECANCELED); #endif static_assert(EAGAIN == EWOULDBLOCK); /* everywhere */ #define E(err) [err - 512 + BUILD_BUG_ON_ZERO(err < 512 || err > 550)] = "-" #err static const char *names_512[] = { E(ERESTARTSYS), E(ERESTARTNOINTR), E(ERESTARTNOHAND), E(ENOIOCTLCMD), E(ERESTART_RESTARTBLOCK), E(EPROBE_DEFER), E(EOPENSTALE), E(ENOPARAM), E(EBADHANDLE), E(ENOTSYNC), E(EBADCOOKIE), E(ENOTSUPP), E(ETOOSMALL), E(ESERVERFAULT), E(EBADTYPE), E(EJUKEBOX), E(EIOCBQUEUED), E(ERECALLCONFLICT), }; #undef E static const char *__errname(unsigned err) { if (err < ARRAY_SIZE(names_0)) return names_0[err]; if (err >= 512 && err - 512 < ARRAY_SIZE(names_512)) return names_512[err - 512]; /* But why? */ if (IS_ENABLED(CONFIG_MIPS) && err == EDQUOT) /* 1133 */ return "-EDQUOT"; return NULL; } /* * errname(EIO) -> "EIO" * errname(-EIO) -> "-EIO" */ const char *errname(int err) { const char *name = __errname(abs(err)); if (!name) return NULL; return err > 0 ? name + 1 : name; } EXPORT_SYMBOL(errname); |
| 12 116 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SHMEM_FS_H #define __SHMEM_FS_H #include <linux/file.h> #include <linux/swap.h> #include <linux/mempolicy.h> #include <linux/pagemap.h> #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> #include <linux/userfaultfd_k.h> /* inode in-kernel data */ #ifdef CONFIG_TMPFS_QUOTA #define SHMEM_MAXQUOTAS 2 #endif struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ union { struct offset_ctx dir_offsets; /* stable directory offsets */ struct { struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ }; }; struct timespec64 i_crtime; /* file creation time */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ pgoff_t fallocend; /* highest fallocate endindex */ unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */ atomic_t stop_eviction; /* hold when working on inode */ #ifdef CONFIG_TMPFS_QUOTA struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; }; #define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) #define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */ qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */ qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */ }; struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_ispace; /* How much ispace left for allocation */ raw_spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ unsigned long shrinklist_len; /* Length of shrinklist */ struct shmem_quota_limits qlimits; /* Default quota limits */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) { return container_of(inode, struct shmem_inode_info, vfs_inode); } /* * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM bool shmem_mapping(struct address_space *mapping); #else static inline bool shmem_mapping(struct address_space *mapping) { return false; } #endif /* CONFIG_SHMEM */ void shmem_unlock_mapping(struct address_space *mapping); struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int shmem_writeout(struct folio *folio, struct writeback_control *wbc); void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force); bool shmem_hpage_pmd_enabled(void); #else static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, loff_t write_end, bool shmem_huge_force) { return 0; } static inline bool shmem_hpage_pmd_enabled(void) { return false; } #endif #ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); #else static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) { return 0; } #endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); /* Flag allocation requirements to shmem_get_folio */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, struct folio **foliop, enum sgp_type sgp); struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp); static inline struct folio *shmem_read_folio(struct address_space *mapping, pgoff_t index) { return shmem_read_folio_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { return shmem_read_mapping_page_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline bool shmem_file(struct file *file) { if (!IS_ENABLED(CONFIG_SHMEM)) return false; if (!file || !file->f_mapping) return false; return shmem_mapping(file->f_mapping); } /* * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages * beyond i_size's notion of EOF, which fallocate has committed to reserving: * which split_huge_page() must therefore not delete. This use of a single * "fallocend" per inode errs on the side of not deleting a reservation when * in doubt: there are plenty of cases when it preserves unreserved pages. */ static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof) { return max(eof, SHMEM_I(inode)->fallocend); } extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #else /* !CONFIG_SHMEM */ #define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ #define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */ #define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL #ifdef CONFIG_TMPFS_QUOTA extern const struct dquot_operations shmem_quota_operations; extern struct quota_format_type shmem_quota_format; #endif /* CONFIG_TMPFS_QUOTA */ #endif |
| 2511 1684 17 13154 3295 163 2397 200 1 6 40 40 8831 13154 6926 40 7502 5258 7623 232 4806 5893 4828 4984 192 3972 7637 214 696 416 347 545 55 35 523 805 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> struct list_lru; /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Three common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] * * xa_limit_16b - [0 - USHRT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) #define xa_limit_16b XA_LIMIT(0, USHRT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Note that callers interested in whether wrapping has occurred should * use __xa_alloc_cyclic() instead. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err < 0 ? err : 0; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Note that callers interested in whether wrapping has occurred should * use __xa_alloc_cyclic() instead. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err < 0 ? err : 0; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Note that callers interested in whether wrapping has occurred should * use __xa_alloc_cyclic() instead. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err < 0 ? err : 0; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; struct list_lru *xa_lru; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL, \ .xa_lru = NULL, \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_destroy(struct xa_state *); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); void xas_try_split(struct xa_state *xas, void *entry, unsigned int order); unsigned int xas_try_split_min_order(unsigned int order); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline int xas_get_order(struct xa_state *xas) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } static inline void xas_try_split(struct xa_state *xas, void *entry, unsigned int order) { } static inline unsigned int xas_try_split_min_order(unsigned int order) { return 0; } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_advance() - Skip over sibling entries. * @xas: XArray operation state. * @index: Index of last sibling entry. * * Move the operation state to refer to the last sibling entry. * This is useful for loops that normally want to see sibling * entries but sometimes want to skip them. Use xas_set() if you * want to move to an index which is not part of this entry. */ static inline void xas_advance(struct xa_state *xas, unsigned long index) { unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; xas->xa_index = index; xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page * cache and swap cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) { xas->xa_lru = lru; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 35 2 33 1 28 11 39 39 39 34 7 29 98 3 3 1 3 1 36 1 39 3 3 6 33 12 1 75 4 41 9 35 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <net/sock.h> #include <linux/in.h> #include <linux/ipv6.h> #include <linux/if_arp.h> #include <linux/jhash.h> #include <linux/ratelimit.h> #include "rds.h" static struct rhashtable bind_hash_table; static const struct rhashtable_params ht_parms = { .nelem_hint = 768, .key_len = RDS_BOUND_KEY_LEN, .key_offset = offsetof(struct rds_sock, rs_bound_key), .head_offset = offsetof(struct rds_sock, rs_bound_node), .max_size = 16384, .min_size = 1024, }; /* Create a key for the bind hash table manipulation. Port is in network byte * order. */ static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr, __be16 port, __u32 scope_id) { memcpy(key, addr, sizeof(*addr)); key += sizeof(*addr); memcpy(key, &port, sizeof(port)); key += sizeof(port); memcpy(key, &scope_id, sizeof(scope_id)); } /* * Return the rds_sock bound at the given local address. * * The rx path can race with rds_release. We notice if rds_release() has * marked this socket and don't return a rs ref to the rx path. */ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __u32 scope_id) { u8 key[RDS_BOUND_KEY_LEN]; struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); return rs; } /* returns -ve errno or +ve port */ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, __be16 *port, __u32 scope_id) { int ret = -EADDRINUSE; u16 rover, last; u8 key[RDS_BOUND_KEY_LEN]; if (*port != 0) { rover = be16_to_cpu(*port); if (rover == RDS_FLAG_PROBE_PORT) return -EINVAL; last = rover; } else { rover = max_t(u16, get_random_u16(), 2); last = rover - 1; } do { if (rover == 0) rover++; if (rover == RDS_FLAG_PROBE_PORT) continue; __rds_create_bind_key(key, addr, cpu_to_be16(rover), scope_id); if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms)) continue; memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key)); rs->rs_bound_addr = *addr; net_get_random_once(&rs->rs_hash_initval, sizeof(rs->rs_hash_initval)); rs->rs_bound_port = cpu_to_be16(rover); rs->rs_bound_node.next = NULL; rds_sock_addref(rs); if (!rhashtable_insert_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms)) { *port = rs->rs_bound_port; rs->rs_bound_scope_id = scope_id; ret = 0; rdsdebug("rs %p binding to %pI6c:%d\n", rs, addr, (int)ntohs(*port)); break; } else { rs->rs_bound_addr = in6addr_any; rds_sock_put(rs); ret = -ENOMEM; break; } } while (rover++ != last); return ret; } void rds_remove_bound(struct rds_sock *rs) { if (ipv6_addr_any(&rs->rs_bound_addr)) return; rdsdebug("rs %p unbinding from %pI6c:%d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port)); rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms); rds_sock_put(rs); rs->rs_bound_addr = in6addr_any; } int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); struct in6_addr v6addr, *binding_addr; struct rds_transport *trans; __u32 scope_id = 0; int ret = 0; __be16 port; /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; if (addr_len < sizeof(struct sockaddr_in) || sin->sin_addr.s_addr == htonl(INADDR_ANY) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || ipv4_is_multicast(sin->sin_addr.s_addr)) return -EINVAL; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); binding_addr = &v6addr; port = sin->sin_port; #if IS_ENABLED(CONFIG_IPV6) } else if (uaddr->sa_family == AF_INET6) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr; int addr_type; if (addr_len < sizeof(struct sockaddr_in6)) return -EINVAL; addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) return -EINVAL; /* It is a mapped address. Need to do some sanity * checks. */ addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || ipv4_is_multicast(addr4)) return -EINVAL; } /* The scope ID must be specified for link local address. */ if (addr_type & IPV6_ADDR_LINKLOCAL) { if (sin6->sin6_scope_id == 0) return -EINVAL; scope_id = sin6->sin6_scope_id; } binding_addr = &sin6->sin6_addr; port = sin6->sin6_port; #endif } else { return -EINVAL; } lock_sock(sk); /* RDS socket does not allow re-binding. */ if (!ipv6_addr_any(&rs->rs_bound_addr)) { ret = -EINVAL; goto out; } /* Socket is connected. The binding address should have the same * scope ID as the connected address, except the case when one is * non-link local address (scope_id is 0). */ if (!ipv6_addr_any(&rs->rs_conn_addr) && scope_id && rs->rs_bound_scope_id && scope_id != rs->rs_bound_scope_id) { ret = -EINVAL; goto out; } /* The transport can be set using SO_RDS_TRANSPORT option before the * socket is bound. */ if (rs->rs_transport) { trans = rs->rs_transport; if (!trans->laddr_check || trans->laddr_check(sock_net(sock->sk), binding_addr, scope_id) != 0) { ret = -ENOPROTOOPT; goto out; } } else { trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr, scope_id); if (!trans) { ret = -EADDRNOTAVAIL; pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n", __func__, binding_addr); goto out; } rs->rs_transport = trans; } sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) rs->rs_transport = NULL; out: release_sock(sk); return ret; } void rds_bind_lock_destroy(void) { rhashtable_destroy(&bind_hash_table); } int rds_bind_lock_init(void) { return rhashtable_init(&bind_hash_table, &ht_parms); } |
| 18505 18503 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | // 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_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 */ 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); } |
| 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | #ifndef LLC_C_EV_H #define LLC_C_EV_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <net/sock.h> /* Connection component state transition event qualifiers */ /* Types of events (possible values in 'ev->type') */ #define LLC_CONN_EV_TYPE_SIMPLE 1 #define LLC_CONN_EV_TYPE_CONDITION 2 #define LLC_CONN_EV_TYPE_PRIM 3 #define LLC_CONN_EV_TYPE_PDU 4 /* command/response PDU */ #define LLC_CONN_EV_TYPE_ACK_TMR 5 #define LLC_CONN_EV_TYPE_P_TMR 6 #define LLC_CONN_EV_TYPE_REJ_TMR 7 #define LLC_CONN_EV_TYPE_BUSY_TMR 8 #define LLC_CONN_EV_TYPE_RPT_STATUS 9 #define LLC_CONN_EV_TYPE_SENDACK_TMR 10 #define NBR_CONN_EV 5 /* Connection events which cause state transitions when fully qualified */ #define LLC_CONN_EV_CONN_REQ 1 #define LLC_CONN_EV_CONN_RESP 2 #define LLC_CONN_EV_DATA_REQ 3 #define LLC_CONN_EV_DISC_REQ 4 #define LLC_CONN_EV_RESET_REQ 5 #define LLC_CONN_EV_RESET_RESP 6 #define LLC_CONN_EV_LOCAL_BUSY_DETECTED 7 #define LLC_CONN_EV_LOCAL_BUSY_CLEARED 8 #define LLC_CONN_EV_RX_BAD_PDU 9 #define LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X 10 #define LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X 11 #define LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X 12 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X 13 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_UNEXPD_Ns 14 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_INVAL_Ns 15 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X 16 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_UNEXPD_Ns 17 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_INVAL_Ns 18 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_X 19 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X 20 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_X 21 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_X 22 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_X 23 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_X 24 #define LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X 25 #define LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X 26 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_X 27 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_X 28 #define LLC_CONN_EV_RX_XXX_YYY 29 #define LLC_CONN_EV_RX_ZZZ_CMD_Pbit_SET_X_INVAL_Nr 30 #define LLC_CONN_EV_RX_ZZZ_RSP_Fbit_SET_X_INVAL_Nr 31 #define LLC_CONN_EV_P_TMR_EXP 32 #define LLC_CONN_EV_ACK_TMR_EXP 33 #define LLC_CONN_EV_REJ_TMR_EXP 34 #define LLC_CONN_EV_BUSY_TMR_EXP 35 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_1 36 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_0 37 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns 38 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns 39 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns 40 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns 41 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 42 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 43 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 44 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 45 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 46 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 47 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 48 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 49 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 50 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 51 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 52 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 53 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 54 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 55 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 56 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 57 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_1 58 #define LLC_CONN_EV_TX_BUFF_FULL 59 #define LLC_CONN_EV_INIT_P_F_CYCLE 100 /* * Connection event qualifiers; for some events a certain combination of * these qualifiers must be TRUE before event recognized valid for state; * these constants act as indexes into the Event Qualifier function * table */ #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_1 1 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_0 2 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_2 3 #define LLC_CONN_EV_QFY_P_FLAG_EQ_1 4 #define LLC_CONN_EV_QFY_P_FLAG_EQ_0 5 #define LLC_CONN_EV_QFY_P_FLAG_EQ_Fbit 6 #define LLC_CONN_EV_QFY_REMOTE_BUSY_EQ_0 7 #define LLC_CONN_EV_QFY_RETRY_CNT_LT_N2 8 #define LLC_CONN_EV_QFY_RETRY_CNT_GTE_N2 9 #define LLC_CONN_EV_QFY_S_FLAG_EQ_1 10 #define LLC_CONN_EV_QFY_S_FLAG_EQ_0 11 #define LLC_CONN_EV_QFY_INIT_P_F_CYCLE 12 struct llc_conn_state_ev { u8 type; u8 prim; u8 prim_type; u8 reason; u8 status; u8 ind_prim; u8 cfm_prim; }; static __inline__ struct llc_conn_state_ev *llc_conn_ev(struct sk_buff *skb) { return (struct llc_conn_state_ev *)skb->cb; } typedef int (*llc_conn_ev_t)(struct sock *sk, struct sk_buff *skb); typedef int (*llc_conn_ev_qfyr_t)(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_detected(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb); /* NOT_USED functions and their variations */ int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb); /* Available connection action qualifiers */ int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conn(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_disc(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_failed(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk, struct sk_buff *skb); static __inline__ int llc_conn_space(struct sock *sk, struct sk_buff *skb) { return atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned int)sk->sk_rcvbuf; } #endif /* LLC_C_EV_H */ |
| 70 70 31 31 70 70 70 70 36 70 70 70 70 70 70 70 70 70 70 70 68 69 36 8 8 31 31 31 31 31 31 31 31 31 30 31 70 69 70 8 70 70 69 31 31 31 31 31 31 31 70 70 31 31 31 70 69 70 31 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * DRBG: Deterministic Random Bits Generator * Based on NIST Recommended DRBG from NIST SP800-90A with the following * properties: * * CTR DRBG with DF with AES-128, AES-192, AES-256 cores * * Hash DRBG with DF with SHA-1, SHA-256, SHA-384, SHA-512 cores * * HMAC DRBG with DF with SHA-1, SHA-256, SHA-384, SHA-512 cores * * with and without prediction resistance * * Copyright Stephan Mueller <smueller@chronox.de>, 2014 * * 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, and the entire permission notice in its entirety, * including the disclaimer of warranties. * 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. The name of the author may not be used to endorse or promote * products derived from this software without specific prior * written permission. * * ALTERNATIVELY, this product may be distributed under the terms of * the GNU General Public License, in which case the provisions of the GPL are * required INSTEAD OF the above restrictions. (This clause is * necessary due to a potential bad interaction between the GPL and * the restrictions contained in a BSD-style copyright.) * * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF * WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR 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 NOT ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * * DRBG Usage * ========== * The SP 800-90A DRBG allows the user to specify a personalization string * for initialization as well as an additional information string for each * random number request. The following code fragments show how a caller * uses the kernel crypto API to use the full functionality of the DRBG. * * Usage without any additional data * --------------------------------- * struct crypto_rng *drng; * int err; * char data[DATALEN]; * * drng = crypto_alloc_rng(drng_name, 0, 0); * err = crypto_rng_get_bytes(drng, &data, DATALEN); * crypto_free_rng(drng); * * * Usage with personalization string during initialization * ------------------------------------------------------- * struct crypto_rng *drng; * int err; * char data[DATALEN]; * struct drbg_string pers; * char personalization[11] = "some-string"; * * drbg_string_fill(&pers, personalization, strlen(personalization)); * drng = crypto_alloc_rng(drng_name, 0, 0); * // The reset completely re-initializes the DRBG with the provided * // personalization string * err = crypto_rng_reset(drng, &personalization, strlen(personalization)); * err = crypto_rng_get_bytes(drng, &data, DATALEN); * crypto_free_rng(drng); * * * Usage with additional information string during random number request * --------------------------------------------------------------------- * struct crypto_rng *drng; * int err; * char data[DATALEN]; * char addtl_string[11] = "some-string"; * string drbg_string addtl; * * drbg_string_fill(&addtl, addtl_string, strlen(addtl_string)); * drng = crypto_alloc_rng(drng_name, 0, 0); * // The following call is a wrapper to crypto_rng_get_bytes() and returns * // the same error codes. * err = crypto_drbg_get_bytes_addtl(drng, &data, DATALEN, &addtl); * crypto_free_rng(drng); * * * Usage with personalization and additional information strings * ------------------------------------------------------------- * Just mix both scenarios above. */ #include <crypto/drbg.h> #include <crypto/internal/cipher.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string_choices.h> /*************************************************************** * Backend cipher definitions available to DRBG ***************************************************************/ /* * The order of the DRBG definitions here matter: every DRBG is registered * as stdrng. Each DRBG receives an increasing cra_priority values the later * they are defined in this array (see drbg_fill_array). * * HMAC DRBGs are favored over Hash DRBGs over CTR DRBGs, and the * HMAC-SHA512 / SHA256 / AES 256 over other ciphers. Thus, the * favored DRBGs are the latest entries in this array. */ static const struct drbg_core drbg_cores[] = { #ifdef CONFIG_CRYPTO_DRBG_CTR { .flags = DRBG_CTR | DRBG_STRENGTH128, .statelen = 32, /* 256 bits as defined in 10.2.1 */ .blocklen_bytes = 16, .cra_name = "ctr_aes128", .backend_cra_name = "aes", }, { .flags = DRBG_CTR | DRBG_STRENGTH192, .statelen = 40, /* 320 bits as defined in 10.2.1 */ .blocklen_bytes = 16, .cra_name = "ctr_aes192", .backend_cra_name = "aes", }, { .flags = DRBG_CTR | DRBG_STRENGTH256, .statelen = 48, /* 384 bits as defined in 10.2.1 */ .blocklen_bytes = 16, .cra_name = "ctr_aes256", .backend_cra_name = "aes", }, #endif /* CONFIG_CRYPTO_DRBG_CTR */ #ifdef CONFIG_CRYPTO_DRBG_HASH { .flags = DRBG_HASH | DRBG_STRENGTH256, .statelen = 111, /* 888 bits */ .blocklen_bytes = 48, .cra_name = "sha384", .backend_cra_name = "sha384", }, { .flags = DRBG_HASH | DRBG_STRENGTH256, .statelen = 111, /* 888 bits */ .blocklen_bytes = 64, .cra_name = "sha512", .backend_cra_name = "sha512", }, { .flags = DRBG_HASH | DRBG_STRENGTH256, .statelen = 55, /* 440 bits */ .blocklen_bytes = 32, .cra_name = "sha256", .backend_cra_name = "sha256", }, #endif /* CONFIG_CRYPTO_DRBG_HASH */ #ifdef CONFIG_CRYPTO_DRBG_HMAC { .flags = DRBG_HMAC | DRBG_STRENGTH256, .statelen = 48, /* block length of cipher */ .blocklen_bytes = 48, .cra_name = "hmac_sha384", .backend_cra_name = "hmac(sha384)", }, { .flags = DRBG_HMAC | DRBG_STRENGTH256, .statelen = 32, /* block length of cipher */ .blocklen_bytes = 32, .cra_name = "hmac_sha256", .backend_cra_name = "hmac(sha256)", }, { .flags = DRBG_HMAC | DRBG_STRENGTH256, .statelen = 64, /* block length of cipher */ .blocklen_bytes = 64, .cra_name = "hmac_sha512", .backend_cra_name = "hmac(sha512)", }, #endif /* CONFIG_CRYPTO_DRBG_HMAC */ }; static int drbg_uninstantiate(struct drbg_state *drbg); /****************************************************************** * Generic helper functions ******************************************************************/ /* * Return strength of DRBG according to SP800-90A section 8.4 * * @flags DRBG flags reference * * Return: normalized strength in *bytes* value or 32 as default * to counter programming errors */ static inline unsigned short drbg_sec_strength(drbg_flag_t flags) { switch (flags & DRBG_STRENGTH_MASK) { case DRBG_STRENGTH128: return 16; case DRBG_STRENGTH192: return 24; case DRBG_STRENGTH256: return 32; default: return 32; } } /* * FIPS 140-2 continuous self test for the noise source * The test is performed on the noise source input data. Thus, the function * implicitly knows the size of the buffer to be equal to the security * strength. * * Note, this function disregards the nonce trailing the entropy data during * initial seeding. * * drbg->drbg_mutex must have been taken. * * @drbg DRBG handle * @entropy buffer of seed data to be checked * * return: * 0 on success * -EAGAIN on when the CTRNG is not yet primed * < 0 on error */ static int drbg_fips_continuous_test(struct drbg_state *drbg, const unsigned char *entropy) { unsigned short entropylen = drbg_sec_strength(drbg->core->flags); int ret = 0; if (!IS_ENABLED(CONFIG_CRYPTO_FIPS)) return 0; /* skip test if we test the overall system */ if (list_empty(&drbg->test_data.list)) return 0; /* only perform test in FIPS mode */ if (!fips_enabled) return 0; if (!drbg->fips_primed) { /* Priming of FIPS test */ memcpy(drbg->prev, entropy, entropylen); drbg->fips_primed = true; /* priming: another round is needed */ return -EAGAIN; } ret = memcmp(drbg->prev, entropy, entropylen); if (!ret) panic("DRBG continuous self test failed\n"); memcpy(drbg->prev, entropy, entropylen); /* the test shall pass when the two values are not equal */ return 0; } /* * Convert an integer into a byte representation of this integer. * The byte representation is big-endian * * @val value to be converted * @buf buffer holding the converted integer -- caller must ensure that * buffer size is at least 32 bit */ #if (defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_CTR)) static inline void drbg_cpu_to_be32(__u32 val, unsigned char *buf) { struct s { __be32 conv; }; struct s *conversion = (struct s *) buf; conversion->conv = cpu_to_be32(val); } #endif /* defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_CTR) */ /****************************************************************** * CTR DRBG callback functions ******************************************************************/ #ifdef CONFIG_CRYPTO_DRBG_CTR #define CRYPTO_DRBG_CTR_STRING "CTR " MODULE_ALIAS_CRYPTO("drbg_pr_ctr_aes256"); MODULE_ALIAS_CRYPTO("drbg_nopr_ctr_aes256"); MODULE_ALIAS_CRYPTO("drbg_pr_ctr_aes192"); MODULE_ALIAS_CRYPTO("drbg_nopr_ctr_aes192"); MODULE_ALIAS_CRYPTO("drbg_pr_ctr_aes128"); MODULE_ALIAS_CRYPTO("drbg_nopr_ctr_aes128"); static void drbg_kcapi_symsetkey(struct drbg_state *drbg, const unsigned char *key); static int drbg_kcapi_sym(struct drbg_state *drbg, unsigned char *outval, const struct drbg_string *in); static int drbg_init_sym_kernel(struct drbg_state *drbg); static int drbg_fini_sym_kernel(struct drbg_state *drbg); static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *inbuf, u32 inbuflen, u8 *outbuf, u32 outlen); #define DRBG_OUTSCRATCHLEN 256 /* BCC function for CTR DRBG as defined in 10.4.3 */ static int drbg_ctr_bcc(struct drbg_state *drbg, unsigned char *out, const unsigned char *key, struct list_head *in) { int ret = 0; struct drbg_string *curr = NULL; struct drbg_string data; short cnt = 0; drbg_string_fill(&data, out, drbg_blocklen(drbg)); /* 10.4.3 step 2 / 4 */ drbg_kcapi_symsetkey(drbg, key); list_for_each_entry(curr, in, list) { const unsigned char *pos = curr->buf; size_t len = curr->len; /* 10.4.3 step 4.1 */ while (len) { /* 10.4.3 step 4.2 */ if (drbg_blocklen(drbg) == cnt) { cnt = 0; ret = drbg_kcapi_sym(drbg, out, &data); if (ret) return ret; } out[cnt] ^= *pos; pos++; cnt++; len--; } } /* 10.4.3 step 4.2 for last block */ if (cnt) ret = drbg_kcapi_sym(drbg, out, &data); return ret; } /* * scratchpad usage: drbg_ctr_update is interlinked with drbg_ctr_df * (and drbg_ctr_bcc, but this function does not need any temporary buffers), * the scratchpad is used as follows: * drbg_ctr_update: * temp * start: drbg->scratchpad * length: drbg_statelen(drbg) + drbg_blocklen(drbg) * note: the cipher writing into this variable works * blocklen-wise. Now, when the statelen is not a multiple * of blocklen, the generateion loop below "spills over" * by at most blocklen. Thus, we need to give sufficient * memory. * df_data * start: drbg->scratchpad + * drbg_statelen(drbg) + drbg_blocklen(drbg) * length: drbg_statelen(drbg) * * drbg_ctr_df: * pad * start: df_data + drbg_statelen(drbg) * length: drbg_blocklen(drbg) * iv * start: pad + drbg_blocklen(drbg) * length: drbg_blocklen(drbg) * temp * start: iv + drbg_blocklen(drbg) * length: drbg_satelen(drbg) + drbg_blocklen(drbg) * note: temp is the buffer that the BCC function operates * on. BCC operates blockwise. drbg_statelen(drbg) * is sufficient when the DRBG state length is a multiple * of the block size. For AES192 (and maybe other ciphers) * this is not correct and the length for temp is * insufficient (yes, that also means for such ciphers, * the final output of all BCC rounds are truncated). * Therefore, add drbg_blocklen(drbg) to cover all * possibilities. */ /* Derivation Function for CTR DRBG as defined in 10.4.2 */ static int drbg_ctr_df(struct drbg_state *drbg, unsigned char *df_data, size_t bytes_to_return, struct list_head *seedlist) { int ret = -EFAULT; unsigned char L_N[8]; /* S3 is input */ struct drbg_string S1, S2, S4, cipherin; LIST_HEAD(bcc_list); unsigned char *pad = df_data + drbg_statelen(drbg); unsigned char *iv = pad + drbg_blocklen(drbg); unsigned char *temp = iv + drbg_blocklen(drbg); size_t padlen = 0; unsigned int templen = 0; /* 10.4.2 step 7 */ unsigned int i = 0; /* 10.4.2 step 8 */ const unsigned char *K = (unsigned char *) "\x00\x01\x02\x03\x04\x05\x06\x07" "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" "\x10\x11\x12\x13\x14\x15\x16\x17" "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"; unsigned char *X; size_t generated_len = 0; size_t inputlen = 0; struct drbg_string *seed = NULL; memset(pad, 0, drbg_blocklen(drbg)); memset(iv, 0, drbg_blocklen(drbg)); /* 10.4.2 step 1 is implicit as we work byte-wise */ /* 10.4.2 step 2 */ if ((512/8) < bytes_to_return) return -EINVAL; /* 10.4.2 step 2 -- calculate the entire length of all input data */ list_for_each_entry(seed, seedlist, list) inputlen += seed->len; drbg_cpu_to_be32(inputlen, &L_N[0]); /* 10.4.2 step 3 */ drbg_cpu_to_be32(bytes_to_return, &L_N[4]); /* 10.4.2 step 5: length is L_N, input_string, one byte, padding */ padlen = (inputlen + sizeof(L_N) + 1) % (drbg_blocklen(drbg)); /* wrap the padlen appropriately */ if (padlen) padlen = drbg_blocklen(drbg) - padlen; /* * pad / padlen contains the 0x80 byte and the following zero bytes. * As the calculated padlen value only covers the number of zero * bytes, this value has to be incremented by one for the 0x80 byte. */ padlen++; pad[0] = 0x80; /* 10.4.2 step 4 -- first fill the linked list and then order it */ drbg_string_fill(&S1, iv, drbg_blocklen(drbg)); list_add_tail(&S1.list, &bcc_list); drbg_string_fill(&S2, L_N, sizeof(L_N)); list_add_tail(&S2.list, &bcc_list); list_splice_tail(seedlist, &bcc_list); drbg_string_fill(&S4, pad, padlen); list_add_tail(&S4.list, &bcc_list); /* 10.4.2 step 9 */ while (templen < (drbg_keylen(drbg) + (drbg_blocklen(drbg)))) { /* * 10.4.2 step 9.1 - the padding is implicit as the buffer * holds zeros after allocation -- even the increment of i * is irrelevant as the increment remains within length of i */ drbg_cpu_to_be32(i, iv); /* 10.4.2 step 9.2 -- BCC and concatenation with temp */ ret = drbg_ctr_bcc(drbg, temp + templen, K, &bcc_list); if (ret) goto out; /* 10.4.2 step 9.3 */ i++; templen += drbg_blocklen(drbg); } /* 10.4.2 step 11 */ X = temp + (drbg_keylen(drbg)); drbg_string_fill(&cipherin, X, drbg_blocklen(drbg)); /* 10.4.2 step 12: overwriting of outval is implemented in next step */ /* 10.4.2 step 13 */ drbg_kcapi_symsetkey(drbg, temp); while (generated_len < bytes_to_return) { short blocklen = 0; /* * 10.4.2 step 13.1: the truncation of the key length is * implicit as the key is only drbg_blocklen in size based on * the implementation of the cipher function callback */ ret = drbg_kcapi_sym(drbg, X, &cipherin); if (ret) goto out; blocklen = (drbg_blocklen(drbg) < (bytes_to_return - generated_len)) ? drbg_blocklen(drbg) : (bytes_to_return - generated_len); /* 10.4.2 step 13.2 and 14 */ memcpy(df_data + generated_len, X, blocklen); generated_len += blocklen; } ret = 0; out: memset(iv, 0, drbg_blocklen(drbg)); memset(temp, 0, drbg_statelen(drbg) + drbg_blocklen(drbg)); memset(pad, 0, drbg_blocklen(drbg)); return ret; } /* * update function of CTR DRBG as defined in 10.2.1.2 * * The reseed variable has an enhanced meaning compared to the update * functions of the other DRBGs as follows: * 0 => initial seed from initialization * 1 => reseed via drbg_seed * 2 => first invocation from drbg_ctr_update when addtl is present. In * this case, the df_data scratchpad is not deleted so that it is * available for another calls to prevent calling the DF function * again. * 3 => second invocation from drbg_ctr_update. When the update function * was called with addtl, the df_data memory already contains the * DFed addtl information and we do not need to call DF again. */ static int drbg_ctr_update(struct drbg_state *drbg, struct list_head *seed, int reseed) { int ret = -EFAULT; /* 10.2.1.2 step 1 */ unsigned char *temp = drbg->scratchpad; unsigned char *df_data = drbg->scratchpad + drbg_statelen(drbg) + drbg_blocklen(drbg); if (3 > reseed) memset(df_data, 0, drbg_statelen(drbg)); if (!reseed) { /* * The DRBG uses the CTR mode of the underlying AES cipher. The * CTR mode increments the counter value after the AES operation * but SP800-90A requires that the counter is incremented before * the AES operation. Hence, we increment it at the time we set * it by one. */ crypto_inc(drbg->V, drbg_blocklen(drbg)); ret = crypto_skcipher_setkey(drbg->ctr_handle, drbg->C, drbg_keylen(drbg)); if (ret) goto out; } /* 10.2.1.3.2 step 2 and 10.2.1.4.2 step 2 */ if (seed) { ret = drbg_ctr_df(drbg, df_data, drbg_statelen(drbg), seed); if (ret) goto out; } ret = drbg_kcapi_sym_ctr(drbg, df_data, drbg_statelen(drbg), temp, drbg_statelen(drbg)); if (ret) return ret; /* 10.2.1.2 step 5 */ ret = crypto_skcipher_setkey(drbg->ctr_handle, temp, drbg_keylen(drbg)); if (ret) goto out; /* 10.2.1.2 step 6 */ memcpy(drbg->V, temp + drbg_keylen(drbg), drbg_blocklen(drbg)); /* See above: increment counter by one to compensate timing of CTR op */ crypto_inc(drbg->V, drbg_blocklen(drbg)); ret = 0; out: memset(temp, 0, drbg_statelen(drbg) + drbg_blocklen(drbg)); if (2 != reseed) memset(df_data, 0, drbg_statelen(drbg)); return ret; } /* * scratchpad use: drbg_ctr_update is called independently from * drbg_ctr_extract_bytes. Therefore, the scratchpad is reused */ /* Generate function of CTR DRBG as defined in 10.2.1.5.2 */ static int drbg_ctr_generate(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen, struct list_head *addtl) { int ret; int len = min_t(int, buflen, INT_MAX); /* 10.2.1.5.2 step 2 */ if (addtl && !list_empty(addtl)) { ret = drbg_ctr_update(drbg, addtl, 2); if (ret) return 0; } /* 10.2.1.5.2 step 4.1 */ ret = drbg_kcapi_sym_ctr(drbg, NULL, 0, buf, len); if (ret) return ret; /* 10.2.1.5.2 step 6 */ ret = drbg_ctr_update(drbg, NULL, 3); if (ret) len = ret; return len; } static const struct drbg_state_ops drbg_ctr_ops = { .update = drbg_ctr_update, .generate = drbg_ctr_generate, .crypto_init = drbg_init_sym_kernel, .crypto_fini = drbg_fini_sym_kernel, }; #endif /* CONFIG_CRYPTO_DRBG_CTR */ /****************************************************************** * HMAC DRBG callback functions ******************************************************************/ #if defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_HMAC) static int drbg_kcapi_hash(struct drbg_state *drbg, unsigned char *outval, const struct list_head *in); static void drbg_kcapi_hmacsetkey(struct drbg_state *drbg, const unsigned char *key); static int drbg_init_hash_kernel(struct drbg_state *drbg); static int drbg_fini_hash_kernel(struct drbg_state *drbg); #endif /* (CONFIG_CRYPTO_DRBG_HASH || CONFIG_CRYPTO_DRBG_HMAC) */ #ifdef CONFIG_CRYPTO_DRBG_HMAC #define CRYPTO_DRBG_HMAC_STRING "HMAC " MODULE_ALIAS_CRYPTO("drbg_pr_hmac_sha512"); MODULE_ALIAS_CRYPTO("drbg_nopr_hmac_sha512"); MODULE_ALIAS_CRYPTO("drbg_pr_hmac_sha384"); MODULE_ALIAS_CRYPTO("drbg_nopr_hmac_sha384"); MODULE_ALIAS_CRYPTO("drbg_pr_hmac_sha256"); MODULE_ALIAS_CRYPTO("drbg_nopr_hmac_sha256"); /* update function of HMAC DRBG as defined in 10.1.2.2 */ static int drbg_hmac_update(struct drbg_state *drbg, struct list_head *seed, int reseed) { int ret = -EFAULT; int i = 0; struct drbg_string seed1, seed2, vdata; LIST_HEAD(seedlist); LIST_HEAD(vdatalist); if (!reseed) { /* 10.1.2.3 step 2 -- memset(0) of C is implicit with kzalloc */ memset(drbg->V, 1, drbg_statelen(drbg)); drbg_kcapi_hmacsetkey(drbg, drbg->C); } drbg_string_fill(&seed1, drbg->V, drbg_statelen(drbg)); list_add_tail(&seed1.list, &seedlist); /* buffer of seed2 will be filled in for loop below with one byte */ drbg_string_fill(&seed2, NULL, 1); list_add_tail(&seed2.list, &seedlist); /* input data of seed is allowed to be NULL at this point */ if (seed) list_splice_tail(seed, &seedlist); drbg_string_fill(&vdata, drbg->V, drbg_statelen(drbg)); list_add_tail(&vdata.list, &vdatalist); for (i = 2; 0 < i; i--) { /* first round uses 0x0, second 0x1 */ unsigned char prefix = DRBG_PREFIX0; if (1 == i) prefix = DRBG_PREFIX1; /* 10.1.2.2 step 1 and 4 -- concatenation and HMAC for key */ seed2.buf = &prefix; ret = drbg_kcapi_hash(drbg, drbg->C, &seedlist); if (ret) return ret; drbg_kcapi_hmacsetkey(drbg, drbg->C); /* 10.1.2.2 step 2 and 5 -- HMAC for V */ ret = drbg_kcapi_hash(drbg, drbg->V, &vdatalist); if (ret) return ret; /* 10.1.2.2 step 3 */ if (!seed) return ret; } return 0; } /* generate function of HMAC DRBG as defined in 10.1.2.5 */ static int drbg_hmac_generate(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen, struct list_head *addtl) { int len = 0; int ret = 0; struct drbg_string data; LIST_HEAD(datalist); /* 10.1.2.5 step 2 */ if (addtl && !list_empty(addtl)) { ret = drbg_hmac_update(drbg, addtl, 1); if (ret) return ret; } drbg_string_fill(&data, drbg->V, drbg_statelen(drbg)); list_add_tail(&data.list, &datalist); while (len < buflen) { unsigned int outlen = 0; /* 10.1.2.5 step 4.1 */ ret = drbg_kcapi_hash(drbg, drbg->V, &datalist); if (ret) return ret; outlen = (drbg_blocklen(drbg) < (buflen - len)) ? drbg_blocklen(drbg) : (buflen - len); /* 10.1.2.5 step 4.2 */ memcpy(buf + len, drbg->V, outlen); len += outlen; } /* 10.1.2.5 step 6 */ if (addtl && !list_empty(addtl)) ret = drbg_hmac_update(drbg, addtl, 1); else ret = drbg_hmac_update(drbg, NULL, 1); if (ret) return ret; return len; } static const struct drbg_state_ops drbg_hmac_ops = { .update = drbg_hmac_update, .generate = drbg_hmac_generate, .crypto_init = drbg_init_hash_kernel, .crypto_fini = drbg_fini_hash_kernel, }; #endif /* CONFIG_CRYPTO_DRBG_HMAC */ /****************************************************************** * Hash DRBG callback functions ******************************************************************/ #ifdef CONFIG_CRYPTO_DRBG_HASH #define CRYPTO_DRBG_HASH_STRING "HASH " MODULE_ALIAS_CRYPTO("drbg_pr_sha512"); MODULE_ALIAS_CRYPTO("drbg_nopr_sha512"); MODULE_ALIAS_CRYPTO("drbg_pr_sha384"); MODULE_ALIAS_CRYPTO("drbg_nopr_sha384"); MODULE_ALIAS_CRYPTO("drbg_pr_sha256"); MODULE_ALIAS_CRYPTO("drbg_nopr_sha256"); /* * Increment buffer * * @dst buffer to increment * @add value to add */ static inline void drbg_add_buf(unsigned char *dst, size_t dstlen, const unsigned char *add, size_t addlen) { /* implied: dstlen > addlen */ unsigned char *dstptr; const unsigned char *addptr; unsigned int remainder = 0; size_t len = addlen; dstptr = dst + (dstlen-1); addptr = add + (addlen-1); while (len) { remainder += *dstptr + *addptr; *dstptr = remainder & 0xff; remainder >>= 8; len--; dstptr--; addptr--; } len = dstlen - addlen; while (len && remainder > 0) { remainder = *dstptr + 1; *dstptr = remainder & 0xff; remainder >>= 8; len--; dstptr--; } } /* * scratchpad usage: as drbg_hash_update and drbg_hash_df are used * interlinked, the scratchpad is used as follows: * drbg_hash_update * start: drbg->scratchpad * length: drbg_statelen(drbg) * drbg_hash_df: * start: drbg->scratchpad + drbg_statelen(drbg) * length: drbg_blocklen(drbg) * * drbg_hash_process_addtl uses the scratchpad, but fully completes * before either of the functions mentioned before are invoked. Therefore, * drbg_hash_process_addtl does not need to be specifically considered. */ /* Derivation Function for Hash DRBG as defined in 10.4.1 */ static int drbg_hash_df(struct drbg_state *drbg, unsigned char *outval, size_t outlen, struct list_head *entropylist) { int ret = 0; size_t len = 0; unsigned char input[5]; unsigned char *tmp = drbg->scratchpad + drbg_statelen(drbg); struct drbg_string data; /* 10.4.1 step 3 */ input[0] = 1; drbg_cpu_to_be32((outlen * 8), &input[1]); /* 10.4.1 step 4.1 -- concatenation of data for input into hash */ drbg_string_fill(&data, input, 5); list_add(&data.list, entropylist); /* 10.4.1 step 4 */ while (len < outlen) { short blocklen = 0; /* 10.4.1 step 4.1 */ ret = drbg_kcapi_hash(drbg, tmp, entropylist); if (ret) goto out; /* 10.4.1 step 4.2 */ input[0]++; blocklen = (drbg_blocklen(drbg) < (outlen - len)) ? drbg_blocklen(drbg) : (outlen - len); memcpy(outval + len, tmp, blocklen); len += blocklen; } out: memset(tmp, 0, drbg_blocklen(drbg)); return ret; } /* update function for Hash DRBG as defined in 10.1.1.2 / 10.1.1.3 */ static int drbg_hash_update(struct drbg_state *drbg, struct list_head *seed, int reseed) { int ret = 0; struct drbg_string data1, data2; LIST_HEAD(datalist); LIST_HEAD(datalist2); unsigned char *V = drbg->scratchpad; unsigned char prefix = DRBG_PREFIX1; if (!seed) return -EINVAL; if (reseed) { /* 10.1.1.3 step 1 */ memcpy(V, drbg->V, drbg_statelen(drbg)); drbg_string_fill(&data1, &prefix, 1); list_add_tail(&data1.list, &datalist); drbg_string_fill(&data2, V, drbg_statelen(drbg)); list_add_tail(&data2.list, &datalist); } list_splice_tail(seed, &datalist); /* 10.1.1.2 / 10.1.1.3 step 2 and 3 */ ret = drbg_hash_df(drbg, drbg->V, drbg_statelen(drbg), &datalist); if (ret) goto out; /* 10.1.1.2 / 10.1.1.3 step 4 */ prefix = DRBG_PREFIX0; drbg_string_fill(&data1, &prefix, 1); list_add_tail(&data1.list, &datalist2); drbg_string_fill(&data2, drbg->V, drbg_statelen(drbg)); list_add_tail(&data2.list, &datalist2); /* 10.1.1.2 / 10.1.1.3 step 4 */ ret = drbg_hash_df(drbg, drbg->C, drbg_statelen(drbg), &datalist2); out: memset(drbg->scratchpad, 0, drbg_statelen(drbg)); return ret; } /* processing of additional information string for Hash DRBG */ static int drbg_hash_process_addtl(struct drbg_state *drbg, struct list_head *addtl) { int ret = 0; struct drbg_string data1, data2; LIST_HEAD(datalist); unsigned char prefix = DRBG_PREFIX2; /* 10.1.1.4 step 2 */ if (!addtl || list_empty(addtl)) return 0; /* 10.1.1.4 step 2a */ drbg_string_fill(&data1, &prefix, 1); drbg_string_fill(&data2, drbg->V, drbg_statelen(drbg)); list_add_tail(&data1.list, &datalist); list_add_tail(&data2.list, &datalist); list_splice_tail(addtl, &datalist); ret = drbg_kcapi_hash(drbg, drbg->scratchpad, &datalist); if (ret) goto out; /* 10.1.1.4 step 2b */ drbg_add_buf(drbg->V, drbg_statelen(drbg), drbg->scratchpad, drbg_blocklen(drbg)); out: memset(drbg->scratchpad, 0, drbg_blocklen(drbg)); return ret; } /* Hashgen defined in 10.1.1.4 */ static int drbg_hash_hashgen(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen) { int len = 0; int ret = 0; unsigned char *src = drbg->scratchpad; unsigned char *dst = drbg->scratchpad + drbg_statelen(drbg); struct drbg_string data; LIST_HEAD(datalist); /* 10.1.1.4 step hashgen 2 */ memcpy(src, drbg->V, drbg_statelen(drbg)); drbg_string_fill(&data, src, drbg_statelen(drbg)); list_add_tail(&data.list, &datalist); while (len < buflen) { unsigned int outlen = 0; /* 10.1.1.4 step hashgen 4.1 */ ret = drbg_kcapi_hash(drbg, dst, &datalist); if (ret) { len = ret; goto out; } outlen = (drbg_blocklen(drbg) < (buflen - len)) ? drbg_blocklen(drbg) : (buflen - len); /* 10.1.1.4 step hashgen 4.2 */ memcpy(buf + len, dst, outlen); len += outlen; /* 10.1.1.4 hashgen step 4.3 */ if (len < buflen) crypto_inc(src, drbg_statelen(drbg)); } out: memset(drbg->scratchpad, 0, (drbg_statelen(drbg) + drbg_blocklen(drbg))); return len; } /* generate function for Hash DRBG as defined in 10.1.1.4 */ static int drbg_hash_generate(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen, struct list_head *addtl) { int len = 0; int ret = 0; union { unsigned char req[8]; __be64 req_int; } u; unsigned char prefix = DRBG_PREFIX3; struct drbg_string data1, data2; LIST_HEAD(datalist); /* 10.1.1.4 step 2 */ ret = drbg_hash_process_addtl(drbg, addtl); if (ret) return ret; /* 10.1.1.4 step 3 */ len = drbg_hash_hashgen(drbg, buf, buflen); /* this is the value H as documented in 10.1.1.4 */ /* 10.1.1.4 step 4 */ drbg_string_fill(&data1, &prefix, 1); list_add_tail(&data1.list, &datalist); drbg_string_fill(&data2, drbg->V, drbg_statelen(drbg)); list_add_tail(&data2.list, &datalist); ret = drbg_kcapi_hash(drbg, drbg->scratchpad, &datalist); if (ret) { len = ret; goto out; } /* 10.1.1.4 step 5 */ drbg_add_buf(drbg->V, drbg_statelen(drbg), drbg->scratchpad, drbg_blocklen(drbg)); drbg_add_buf(drbg->V, drbg_statelen(drbg), drbg->C, drbg_statelen(drbg)); u.req_int = cpu_to_be64(drbg->reseed_ctr); drbg_add_buf(drbg->V, drbg_statelen(drbg), u.req, 8); out: memset(drbg->scratchpad, 0, drbg_blocklen(drbg)); return len; } /* * scratchpad usage: as update and generate are used isolated, both * can use the scratchpad */ static const struct drbg_state_ops drbg_hash_ops = { .update = drbg_hash_update, .generate = drbg_hash_generate, .crypto_init = drbg_init_hash_kernel, .crypto_fini = drbg_fini_hash_kernel, }; #endif /* CONFIG_CRYPTO_DRBG_HASH */ /****************************************************************** * Functions common for DRBG implementations ******************************************************************/ static inline int __drbg_seed(struct drbg_state *drbg, struct list_head *seed, int reseed, enum drbg_seed_state new_seed_state) { int ret = drbg->d_ops->update(drbg, seed, reseed); if (ret) return ret; drbg->seeded = new_seed_state; drbg->last_seed_time = jiffies; /* 10.1.1.2 / 10.1.1.3 step 5 */ drbg->reseed_ctr = 1; switch (drbg->seeded) { case DRBG_SEED_STATE_UNSEEDED: /* Impossible, but handle it to silence compiler warnings. */ fallthrough; case DRBG_SEED_STATE_PARTIAL: /* * Require frequent reseeds until the seed source is * fully initialized. */ drbg->reseed_threshold = 50; break; case DRBG_SEED_STATE_FULL: /* * Seed source has become fully initialized, frequent * reseeds no longer required. */ drbg->reseed_threshold = drbg_max_requests(drbg); break; } return ret; } static inline int drbg_get_random_bytes(struct drbg_state *drbg, unsigned char *entropy, unsigned int entropylen) { int ret; do { get_random_bytes(entropy, entropylen); ret = drbg_fips_continuous_test(drbg, entropy); if (ret && ret != -EAGAIN) return ret; } while (ret); return 0; } static int drbg_seed_from_random(struct drbg_state *drbg) { struct drbg_string data; LIST_HEAD(seedlist); unsigned int entropylen = drbg_sec_strength(drbg->core->flags); unsigned char entropy[32]; int ret; BUG_ON(!entropylen); BUG_ON(entropylen > sizeof(entropy)); drbg_string_fill(&data, entropy, entropylen); list_add_tail(&data.list, &seedlist); ret = drbg_get_random_bytes(drbg, entropy, entropylen); if (ret) goto out; ret = __drbg_seed(drbg, &seedlist, true, DRBG_SEED_STATE_FULL); out: memzero_explicit(entropy, entropylen); return ret; } static bool drbg_nopr_reseed_interval_elapsed(struct drbg_state *drbg) { unsigned long next_reseed; /* Don't ever reseed from get_random_bytes() in test mode. */ if (list_empty(&drbg->test_data.list)) return false; /* * Obtain fresh entropy for the nopr DRBGs after 300s have * elapsed in order to still achieve sort of partial * prediction resistance over the time domain at least. Note * that the period of 300s has been chosen to match the * CRNG_RESEED_INTERVAL of the get_random_bytes()' chacha * rngs. */ next_reseed = drbg->last_seed_time + 300 * HZ; return time_after(jiffies, next_reseed); } /* * Seeding or reseeding of the DRBG * * @drbg: DRBG state struct * @pers: personalization / additional information buffer * @reseed: 0 for initial seed process, 1 for reseeding * * return: * 0 on success * error value otherwise */ static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers, bool reseed) { int ret; unsigned char entropy[((32 + 16) * 2)]; unsigned int entropylen = drbg_sec_strength(drbg->core->flags); struct drbg_string data1; LIST_HEAD(seedlist); enum drbg_seed_state new_seed_state = DRBG_SEED_STATE_FULL; /* 9.1 / 9.2 / 9.3.1 step 3 */ if (pers && pers->len > (drbg_max_addtl(drbg))) { pr_devel("DRBG: personalization string too long %zu\n", pers->len); return -EINVAL; } if (list_empty(&drbg->test_data.list)) { drbg_string_fill(&data1, drbg->test_data.buf, drbg->test_data.len); pr_devel("DRBG: using test entropy\n"); } else { /* * Gather entropy equal to the security strength of the DRBG. * With a derivation function, a nonce is required in addition * to the entropy. A nonce must be at least 1/2 of the security * strength of the DRBG in size. Thus, entropy + nonce is 3/2 * of the strength. The consideration of a nonce is only * applicable during initial seeding. */ BUG_ON(!entropylen); if (!reseed) entropylen = ((entropylen + 1) / 2) * 3; BUG_ON((entropylen * 2) > sizeof(entropy)); /* Get seed from in-kernel /dev/urandom */ if (!rng_is_initialized()) new_seed_state = DRBG_SEED_STATE_PARTIAL; ret = drbg_get_random_bytes(drbg, entropy, entropylen); if (ret) goto out; if (!drbg->jent) { drbg_string_fill(&data1, entropy, entropylen); pr_devel("DRBG: (re)seeding with %u bytes of entropy\n", entropylen); } else { /* * Get seed from Jitter RNG, failures are * fatal only in FIPS mode. */ ret = crypto_rng_get_bytes(drbg->jent, entropy + entropylen, entropylen); if (fips_enabled && ret) { pr_devel("DRBG: jent failed with %d\n", ret); /* * Do not treat the transient failure of the * Jitter RNG as an error that needs to be * reported. The combined number of the * maximum reseed threshold times the maximum * number of Jitter RNG transient errors is * less than the reseed threshold required by * SP800-90A allowing us to treat the * transient errors as such. * * However, we mandate that at least the first * seeding operation must succeed with the * Jitter RNG. */ if (!reseed || ret != -EAGAIN) goto out; } drbg_string_fill(&data1, entropy, entropylen * 2); pr_devel("DRBG: (re)seeding with %u bytes of entropy\n", entropylen * 2); } } list_add_tail(&data1.list, &seedlist); /* * concatenation of entropy with personalization str / addtl input) * the variable pers is directly handed in by the caller, so check its * contents whether it is appropriate */ if (pers && pers->buf && 0 < pers->len) { list_add_tail(&pers->list, &seedlist); pr_devel("DRBG: using personalization string\n"); } if (!reseed) { memset(drbg->V, 0, drbg_statelen(drbg)); memset(drbg->C, 0, drbg_statelen(drbg)); } ret = __drbg_seed(drbg, &seedlist, reseed, new_seed_state); out: memzero_explicit(entropy, entropylen * 2); return ret; } /* Free all substructures in a DRBG state without the DRBG state structure */ static inline void drbg_dealloc_state(struct drbg_state *drbg) { if (!drbg) return; kfree_sensitive(drbg->Vbuf); drbg->Vbuf = NULL; drbg->V = NULL; kfree_sensitive(drbg->Cbuf); drbg->Cbuf = NULL; drbg->C = NULL; kfree_sensitive(drbg->scratchpadbuf); drbg->scratchpadbuf = NULL; drbg->reseed_ctr = 0; drbg->d_ops = NULL; drbg->core = NULL; if (IS_ENABLED(CONFIG_CRYPTO_FIPS)) { kfree_sensitive(drbg->prev); drbg->prev = NULL; drbg->fips_primed = false; } } /* * Allocate all sub-structures for a DRBG state. * The DRBG state structure must already be allocated. */ static inline int drbg_alloc_state(struct drbg_state *drbg) { int ret = -ENOMEM; unsigned int sb_size = 0; switch (drbg->core->flags & DRBG_TYPE_MASK) { #ifdef CONFIG_CRYPTO_DRBG_HMAC case DRBG_HMAC: drbg->d_ops = &drbg_hmac_ops; break; #endif /* CONFIG_CRYPTO_DRBG_HMAC */ #ifdef CONFIG_CRYPTO_DRBG_HASH case DRBG_HASH: drbg->d_ops = &drbg_hash_ops; break; #endif /* CONFIG_CRYPTO_DRBG_HASH */ #ifdef CONFIG_CRYPTO_DRBG_CTR case DRBG_CTR: drbg->d_ops = &drbg_ctr_ops; break; #endif /* CONFIG_CRYPTO_DRBG_CTR */ default: ret = -EOPNOTSUPP; goto err; } ret = drbg->d_ops->crypto_init(drbg); if (ret < 0) goto err; drbg->Vbuf = kmalloc(drbg_statelen(drbg) + ret, GFP_KERNEL); if (!drbg->Vbuf) { ret = -ENOMEM; goto fini; } drbg->V = PTR_ALIGN(drbg->Vbuf, ret + 1); drbg->Cbuf = kmalloc(drbg_statelen(drbg) + ret, GFP_KERNEL); if (!drbg->Cbuf) { ret = -ENOMEM; goto fini; } drbg->C = PTR_ALIGN(drbg->Cbuf, ret + 1); /* scratchpad is only generated for CTR and Hash */ if (drbg->core->flags & DRBG_HMAC) sb_size = 0; else if (drbg->core->flags & DRBG_CTR) sb_size = drbg_statelen(drbg) + drbg_blocklen(drbg) + /* temp */ drbg_statelen(drbg) + /* df_data */ drbg_blocklen(drbg) + /* pad */ drbg_blocklen(drbg) + /* iv */ drbg_statelen(drbg) + drbg_blocklen(drbg); /* temp */ else sb_size = drbg_statelen(drbg) + drbg_blocklen(drbg); if (0 < sb_size) { drbg->scratchpadbuf = kzalloc(sb_size + ret, GFP_KERNEL); if (!drbg->scratchpadbuf) { ret = -ENOMEM; goto fini; } drbg->scratchpad = PTR_ALIGN(drbg->scratchpadbuf, ret + 1); } if (IS_ENABLED(CONFIG_CRYPTO_FIPS)) { drbg->prev = kzalloc(drbg_sec_strength(drbg->core->flags), GFP_KERNEL); if (!drbg->prev) { ret = -ENOMEM; goto fini; } drbg->fips_primed = false; } return 0; fini: drbg->d_ops->crypto_fini(drbg); err: drbg_dealloc_state(drbg); return ret; } /************************************************************************* * DRBG interface functions *************************************************************************/ /* * DRBG generate function as required by SP800-90A - this function * generates random numbers * * @drbg DRBG state handle * @buf Buffer where to store the random numbers -- the buffer must already * be pre-allocated by caller * @buflen Length of output buffer - this value defines the number of random * bytes pulled from DRBG * @addtl Additional input that is mixed into state, may be NULL -- note * the entropy is pulled by the DRBG internally unconditionally * as defined in SP800-90A. The additional input is mixed into * the state in addition to the pulled entropy. * * return: 0 when all bytes are generated; < 0 in case of an error */ static int drbg_generate(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen, struct drbg_string *addtl) { int len = 0; LIST_HEAD(addtllist); if (!drbg->core) { pr_devel("DRBG: not yet seeded\n"); return -EINVAL; } if (0 == buflen || !buf) { pr_devel("DRBG: no output buffer provided\n"); return -EINVAL; } if (addtl && NULL == addtl->buf && 0 < addtl->len) { pr_devel("DRBG: wrong format of additional information\n"); return -EINVAL; } /* 9.3.1 step 2 */ len = -EINVAL; if (buflen > (drbg_max_request_bytes(drbg))) { pr_devel("DRBG: requested random numbers too large %u\n", buflen); goto err; } /* 9.3.1 step 3 is implicit with the chosen DRBG */ /* 9.3.1 step 4 */ if (addtl && addtl->len > (drbg_max_addtl(drbg))) { pr_devel("DRBG: additional information string too long %zu\n", addtl->len); goto err; } /* 9.3.1 step 5 is implicit with the chosen DRBG */ /* * 9.3.1 step 6 and 9 supplemented by 9.3.2 step c is implemented * here. The spec is a bit convoluted here, we make it simpler. */ if (drbg->reseed_threshold < drbg->reseed_ctr) drbg->seeded = DRBG_SEED_STATE_UNSEEDED; if (drbg->pr || drbg->seeded == DRBG_SEED_STATE_UNSEEDED) { pr_devel("DRBG: reseeding before generation (prediction " "resistance: %s, state %s)\n", str_true_false(drbg->pr), (drbg->seeded == DRBG_SEED_STATE_FULL ? "seeded" : "unseeded")); /* 9.3.1 steps 7.1 through 7.3 */ len = drbg_seed(drbg, addtl, true); if (len) goto err; /* 9.3.1 step 7.4 */ addtl = NULL; } else if (rng_is_initialized() && (drbg->seeded == DRBG_SEED_STATE_PARTIAL || drbg_nopr_reseed_interval_elapsed(drbg))) { len = drbg_seed_from_random(drbg); if (len) goto err; } if (addtl && 0 < addtl->len) list_add_tail(&addtl->list, &addtllist); /* 9.3.1 step 8 and 10 */ len = drbg->d_ops->generate(drbg, buf, buflen, &addtllist); /* 10.1.1.4 step 6, 10.1.2.5 step 7, 10.2.1.5.2 step 7 */ drbg->reseed_ctr++; if (0 >= len) goto err; /* * Section 11.3.3 requires to re-perform self tests after some * generated random numbers. The chosen value after which self * test is performed is arbitrary, but it should be reasonable. * However, we do not perform the self tests because of the following * reasons: it is mathematically impossible that the initial self tests * were successfully and the following are not. If the initial would * pass and the following would not, the kernel integrity is violated. * In this case, the entire kernel operation is questionable and it * is unlikely that the integrity violation only affects the * correct operation of the DRBG. * * Albeit the following code is commented out, it is provided in * case somebody has a need to implement the test of 11.3.3. */ #if 0 if (drbg->reseed_ctr && !(drbg->reseed_ctr % 4096)) { int err = 0; pr_devel("DRBG: start to perform self test\n"); if (drbg->core->flags & DRBG_HMAC) err = alg_test("drbg_pr_hmac_sha512", "drbg_pr_hmac_sha512", 0, 0); else if (drbg->core->flags & DRBG_CTR) err = alg_test("drbg_pr_ctr_aes256", "drbg_pr_ctr_aes256", 0, 0); else err = alg_test("drbg_pr_sha256", "drbg_pr_sha256", 0, 0); if (err) { pr_err("DRBG: periodical self test failed\n"); /* * uninstantiate implies that from now on, only errors * are returned when reusing this DRBG cipher handle */ drbg_uninstantiate(drbg); return 0; } else { pr_devel("DRBG: self test successful\n"); } } #endif /* * All operations were successful, return 0 as mandated by * the kernel crypto API interface. */ len = 0; err: return len; } /* * Wrapper around drbg_generate which can pull arbitrary long strings * from the DRBG without hitting the maximum request limitation. * * Parameters: see drbg_generate * Return codes: see drbg_generate -- if one drbg_generate request fails, * the entire drbg_generate_long request fails */ static int drbg_generate_long(struct drbg_state *drbg, unsigned char *buf, unsigned int buflen, struct drbg_string *addtl) { unsigned int len = 0; unsigned int slice = 0; do { int err = 0; unsigned int chunk = 0; slice = ((buflen - len) / drbg_max_request_bytes(drbg)); chunk = slice ? drbg_max_request_bytes(drbg) : (buflen - len); mutex_lock(&drbg->drbg_mutex); err = drbg_generate(drbg, buf + len, chunk, addtl); mutex_unlock(&drbg->drbg_mutex); if (0 > err) return err; len += chunk; } while (slice > 0 && (len < buflen)); return 0; } static int drbg_prepare_hrng(struct drbg_state *drbg) { /* We do not need an HRNG in test mode. */ if (list_empty(&drbg->test_data.list)) return 0; drbg->jent = crypto_alloc_rng("jitterentropy_rng", 0, 0); if (IS_ERR(drbg->jent)) { const int err = PTR_ERR(drbg->jent); drbg->jent = NULL; if (fips_enabled) return err; pr_info("DRBG: Continuing without Jitter RNG\n"); } return 0; } /* * DRBG instantiation function as required by SP800-90A - this function * sets up the DRBG handle, performs the initial seeding and all sanity * checks required by SP800-90A * * @drbg memory of state -- if NULL, new memory is allocated * @pers Personalization string that is mixed into state, may be NULL -- note * the entropy is pulled by the DRBG internally unconditionally * as defined in SP800-90A. The additional input is mixed into * the state in addition to the pulled entropy. * @coreref reference to core * @pr prediction resistance enabled * * return * 0 on success * error value otherwise */ static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers, int coreref, bool pr) { int ret; bool reseed = true; pr_devel("DRBG: Initializing DRBG core %d with prediction resistance " "%s\n", coreref, str_enabled_disabled(pr)); mutex_lock(&drbg->drbg_mutex); /* 9.1 step 1 is implicit with the selected DRBG type */ /* * 9.1 step 2 is implicit as caller can select prediction resistance * and the flag is copied into drbg->flags -- * all DRBG types support prediction resistance */ /* 9.1 step 4 is implicit in drbg_sec_strength */ if (!drbg->core) { drbg->core = &drbg_cores[coreref]; drbg->pr = pr; drbg->seeded = DRBG_SEED_STATE_UNSEEDED; drbg->last_seed_time = 0; drbg->reseed_threshold = drbg_max_requests(drbg); ret = drbg_alloc_state(drbg); if (ret) goto unlock; ret = drbg_prepare_hrng(drbg); if (ret) goto free_everything; reseed = false; } ret = drbg_seed(drbg, pers, reseed); if (ret && !reseed) goto free_everything; mutex_unlock(&drbg->drbg_mutex); return ret; unlock: mutex_unlock(&drbg->drbg_mutex); return ret; free_everything: mutex_unlock(&drbg->drbg_mutex); drbg_uninstantiate(drbg); return ret; } /* * DRBG uninstantiate function as required by SP800-90A - this function * frees all buffers and the DRBG handle * * @drbg DRBG state handle * * return * 0 on success */ static int drbg_uninstantiate(struct drbg_state *drbg) { if (!IS_ERR_OR_NULL(drbg->jent)) crypto_free_rng(drbg->jent); drbg->jent = NULL; if (drbg->d_ops) drbg->d_ops->crypto_fini(drbg); drbg_dealloc_state(drbg); /* no scrubbing of test_data -- this shall survive an uninstantiate */ return 0; } /* * Helper function for setting the test data in the DRBG * * @drbg DRBG state handle * @data test data * @len test data length */ static void drbg_kcapi_set_entropy(struct crypto_rng *tfm, const u8 *data, unsigned int len) { struct drbg_state *drbg = crypto_rng_ctx(tfm); mutex_lock(&drbg->drbg_mutex); drbg_string_fill(&drbg->test_data, data, len); mutex_unlock(&drbg->drbg_mutex); } /*************************************************************** * Kernel crypto API cipher invocations requested by DRBG ***************************************************************/ #if defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_HMAC) struct sdesc { struct shash_desc shash; char ctx[]; }; static int drbg_init_hash_kernel(struct drbg_state *drbg) { struct sdesc *sdesc; struct crypto_shash *tfm; tfm = crypto_alloc_shash(drbg->core->backend_cra_name, 0, 0); if (IS_ERR(tfm)) { pr_info("DRBG: could not allocate digest TFM handle: %s\n", drbg->core->backend_cra_name); return PTR_ERR(tfm); } BUG_ON(drbg_blocklen(drbg) != crypto_shash_digestsize(tfm)); sdesc = kzalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm), GFP_KERNEL); if (!sdesc) { crypto_free_shash(tfm); return -ENOMEM; } sdesc->shash.tfm = tfm; drbg->priv_data = sdesc; return 0; } static int drbg_fini_hash_kernel(struct drbg_state *drbg) { struct sdesc *sdesc = drbg->priv_data; if (sdesc) { crypto_free_shash(sdesc->shash.tfm); kfree_sensitive(sdesc); } drbg->priv_data = NULL; return 0; } static void drbg_kcapi_hmacsetkey(struct drbg_state *drbg, const unsigned char *key) { struct sdesc *sdesc = drbg->priv_data; crypto_shash_setkey(sdesc->shash.tfm, key, drbg_statelen(drbg)); } static int drbg_kcapi_hash(struct drbg_state *drbg, unsigned char *outval, const struct list_head *in) { struct sdesc *sdesc = drbg->priv_data; struct drbg_string *input = NULL; crypto_shash_init(&sdesc->shash); list_for_each_entry(input, in, list) crypto_shash_update(&sdesc->shash, input->buf, input->len); return crypto_shash_final(&sdesc->shash, outval); } #endif /* (CONFIG_CRYPTO_DRBG_HASH || CONFIG_CRYPTO_DRBG_HMAC) */ #ifdef CONFIG_CRYPTO_DRBG_CTR static int drbg_fini_sym_kernel(struct drbg_state *drbg) { struct crypto_cipher *tfm = (struct crypto_cipher *)drbg->priv_data; if (tfm) crypto_free_cipher(tfm); drbg->priv_data = NULL; if (drbg->ctr_handle) crypto_free_skcipher(drbg->ctr_handle); drbg->ctr_handle = NULL; if (drbg->ctr_req) skcipher_request_free(drbg->ctr_req); drbg->ctr_req = NULL; kfree(drbg->outscratchpadbuf); drbg->outscratchpadbuf = NULL; return 0; } static int drbg_init_sym_kernel(struct drbg_state *drbg) { struct crypto_cipher *tfm; struct crypto_skcipher *sk_tfm; struct skcipher_request *req; unsigned int alignmask; char ctr_name[CRYPTO_MAX_ALG_NAME]; tfm = crypto_alloc_cipher(drbg->core->backend_cra_name, 0, 0); if (IS_ERR(tfm)) { pr_info("DRBG: could not allocate cipher TFM handle: %s\n", drbg->core->backend_cra_name); return PTR_ERR(tfm); } BUG_ON(drbg_blocklen(drbg) != crypto_cipher_blocksize(tfm)); drbg->priv_data = tfm; if (snprintf(ctr_name, CRYPTO_MAX_ALG_NAME, "ctr(%s)", drbg->core->backend_cra_name) >= CRYPTO_MAX_ALG_NAME) { drbg_fini_sym_kernel(drbg); return -EINVAL; } sk_tfm = crypto_alloc_skcipher(ctr_name, 0, 0); if (IS_ERR(sk_tfm)) { pr_info("DRBG: could not allocate CTR cipher TFM handle: %s\n", ctr_name); drbg_fini_sym_kernel(drbg); return PTR_ERR(sk_tfm); } drbg->ctr_handle = sk_tfm; crypto_init_wait(&drbg->ctr_wait); req = skcipher_request_alloc(sk_tfm, GFP_KERNEL); if (!req) { pr_info("DRBG: could not allocate request queue\n"); drbg_fini_sym_kernel(drbg); return -ENOMEM; } drbg->ctr_req = req; skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &drbg->ctr_wait); alignmask = crypto_skcipher_alignmask(sk_tfm); drbg->outscratchpadbuf = kmalloc(DRBG_OUTSCRATCHLEN + alignmask, GFP_KERNEL); if (!drbg->outscratchpadbuf) { drbg_fini_sym_kernel(drbg); return -ENOMEM; } drbg->outscratchpad = (u8 *)PTR_ALIGN(drbg->outscratchpadbuf, alignmask + 1); sg_init_table(&drbg->sg_in, 1); sg_init_one(&drbg->sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN); return alignmask; } static void drbg_kcapi_symsetkey(struct drbg_state *drbg, const unsigned char *key) { struct crypto_cipher *tfm = drbg->priv_data; crypto_cipher_setkey(tfm, key, (drbg_keylen(drbg))); } static int drbg_kcapi_sym(struct drbg_state *drbg, unsigned char *outval, const struct drbg_string *in) { struct crypto_cipher *tfm = drbg->priv_data; /* there is only component in *in */ BUG_ON(in->len < drbg_blocklen(drbg)); crypto_cipher_encrypt_one(tfm, outval, in->buf); return 0; } static int drbg_kcapi_sym_ctr(struct drbg_state *drbg, u8 *inbuf, u32 inlen, u8 *outbuf, u32 outlen) { struct scatterlist *sg_in = &drbg->sg_in, *sg_out = &drbg->sg_out; u32 scratchpad_use = min_t(u32, outlen, DRBG_OUTSCRATCHLEN); int ret; if (inbuf) { /* Use caller-provided input buffer */ sg_set_buf(sg_in, inbuf, inlen); } else { /* Use scratchpad for in-place operation */ inlen = scratchpad_use; memset(drbg->outscratchpad, 0, scratchpad_use); sg_set_buf(sg_in, drbg->outscratchpad, scratchpad_use); } while (outlen) { u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN); /* Output buffer may not be valid for SGL, use scratchpad */ skcipher_request_set_crypt(drbg->ctr_req, sg_in, sg_out, cryptlen, drbg->V); ret = crypto_wait_req(crypto_skcipher_encrypt(drbg->ctr_req), &drbg->ctr_wait); if (ret) goto out; crypto_init_wait(&drbg->ctr_wait); memcpy(outbuf, drbg->outscratchpad, cryptlen); memzero_explicit(drbg->outscratchpad, cryptlen); outlen -= cryptlen; outbuf += cryptlen; } ret = 0; out: return ret; } #endif /* CONFIG_CRYPTO_DRBG_CTR */ /*************************************************************** * Kernel crypto API interface to register DRBG ***************************************************************/ /* * Look up the DRBG flags by given kernel crypto API cra_name * The code uses the drbg_cores definition to do this * * @cra_name kernel crypto API cra_name * @coreref reference to integer which is filled with the pointer to * the applicable core * @pr reference for setting prediction resistance * * return: flags */ static inline void drbg_convert_tfm_core(const char *cra_driver_name, int *coreref, bool *pr) { int i = 0; size_t start = 0; int len = 0; *pr = true; /* disassemble the names */ if (!memcmp(cra_driver_name, "drbg_nopr_", 10)) { start = 10; *pr = false; } else if (!memcmp(cra_driver_name, "drbg_pr_", 8)) { start = 8; } else { return; } /* remove the first part */ len = strlen(cra_driver_name) - start; for (i = 0; ARRAY_SIZE(drbg_cores) > i; i++) { if (!memcmp(cra_driver_name + start, drbg_cores[i].cra_name, len)) { *coreref = i; return; } } } static int drbg_kcapi_init(struct crypto_tfm *tfm) { struct drbg_state *drbg = crypto_tfm_ctx(tfm); mutex_init(&drbg->drbg_mutex); return 0; } static void drbg_kcapi_cleanup(struct crypto_tfm *tfm) { drbg_uninstantiate(crypto_tfm_ctx(tfm)); } /* * Generate random numbers invoked by the kernel crypto API: * The API of the kernel crypto API is extended as follows: * * src is additional input supplied to the RNG. * slen is the length of src. * dst is the output buffer where random data is to be stored. * dlen is the length of dst. */ static int drbg_kcapi_random(struct crypto_rng *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int dlen) { struct drbg_state *drbg = crypto_rng_ctx(tfm); struct drbg_string *addtl = NULL; struct drbg_string string; if (slen) { /* linked list variable is now local to allow modification */ drbg_string_fill(&string, src, slen); addtl = &string; } return drbg_generate_long(drbg, dst, dlen, addtl); } /* * Seed the DRBG invoked by the kernel crypto API */ static int drbg_kcapi_seed(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) { struct drbg_state *drbg = crypto_rng_ctx(tfm); struct crypto_tfm *tfm_base = crypto_rng_tfm(tfm); bool pr = false; struct drbg_string string; struct drbg_string *seed_string = NULL; int coreref = 0; drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm_base), &coreref, &pr); if (0 < slen) { drbg_string_fill(&string, seed, slen); seed_string = &string; } return drbg_instantiate(drbg, seed_string, coreref, pr); } /*************************************************************** * Kernel module: code to load the module ***************************************************************/ /* * Tests as defined in 11.3.2 in addition to the cipher tests: testing * of the error handling. * * Note: testing of failing seed source as defined in 11.3.2 is not applicable * as seed source of get_random_bytes does not fail. * * Note 2: There is no sensible way of testing the reseed counter * enforcement, so skip it. */ static inline int __init drbg_healthcheck_sanity(void) { int len = 0; #define OUTBUFLEN 16 unsigned char buf[OUTBUFLEN]; struct drbg_state *drbg = NULL; int ret; int rc = -EFAULT; bool pr = false; int coreref = 0; struct drbg_string addtl; size_t max_addtllen, max_request_bytes; /* only perform test in FIPS mode */ if (!fips_enabled) return 0; #ifdef CONFIG_CRYPTO_DRBG_CTR drbg_convert_tfm_core("drbg_nopr_ctr_aes256", &coreref, &pr); #endif #ifdef CONFIG_CRYPTO_DRBG_HASH drbg_convert_tfm_core("drbg_nopr_sha256", &coreref, &pr); #endif #ifdef CONFIG_CRYPTO_DRBG_HMAC drbg_convert_tfm_core("drbg_nopr_hmac_sha512", &coreref, &pr); #endif drbg = kzalloc(sizeof(struct drbg_state), GFP_KERNEL); if (!drbg) return -ENOMEM; mutex_init(&drbg->drbg_mutex); drbg->core = &drbg_cores[coreref]; drbg->reseed_threshold = drbg_max_requests(drbg); /* * if the following tests fail, it is likely that there is a buffer * overflow as buf is much smaller than the requested or provided * string lengths -- in case the error handling does not succeed * we may get an OOPS. And we want to get an OOPS as this is a * grave bug. */ max_addtllen = drbg_max_addtl(drbg); max_request_bytes = drbg_max_request_bytes(drbg); drbg_string_fill(&addtl, buf, max_addtllen + 1); /* overflow addtllen with additonal info string */ len = drbg_generate(drbg, buf, OUTBUFLEN, &addtl); BUG_ON(0 < len); /* overflow max_bits */ len = drbg_generate(drbg, buf, (max_request_bytes + 1), NULL); BUG_ON(0 < len); /* overflow max addtllen with personalization string */ ret = drbg_seed(drbg, &addtl, false); BUG_ON(0 == ret); /* all tests passed */ rc = 0; pr_devel("DRBG: Sanity tests for failure code paths successfully " "completed\n"); kfree(drbg); return rc; } static struct rng_alg drbg_algs[22]; /* * Fill the array drbg_algs used to register the different DRBGs * with the kernel crypto API. To fill the array, the information * from drbg_cores[] is used. */ static inline void __init drbg_fill_array(struct rng_alg *alg, const struct drbg_core *core, int pr) { int pos = 0; static int priority = 200; memcpy(alg->base.cra_name, "stdrng", 6); if (pr) { memcpy(alg->base.cra_driver_name, "drbg_pr_", 8); pos = 8; } else { memcpy(alg->base.cra_driver_name, "drbg_nopr_", 10); pos = 10; } memcpy(alg->base.cra_driver_name + pos, core->cra_name, strlen(core->cra_name)); alg->base.cra_priority = priority; priority++; /* * If FIPS mode enabled, the selected DRBG shall have the * highest cra_priority over other stdrng instances to ensure * it is selected. */ if (fips_enabled) alg->base.cra_priority += 200; alg->base.cra_ctxsize = sizeof(struct drbg_state); alg->base.cra_module = THIS_MODULE; alg->base.cra_init = drbg_kcapi_init; alg->base.cra_exit = drbg_kcapi_cleanup; alg->generate = drbg_kcapi_random; alg->seed = drbg_kcapi_seed; alg->set_ent = drbg_kcapi_set_entropy; alg->seedsize = 0; } static int __init drbg_init(void) { unsigned int i = 0; /* pointer to drbg_algs */ unsigned int j = 0; /* pointer to drbg_cores */ int ret; ret = drbg_healthcheck_sanity(); if (ret) return ret; if (ARRAY_SIZE(drbg_cores) * 2 > ARRAY_SIZE(drbg_algs)) { pr_info("DRBG: Cannot register all DRBG types" "(slots needed: %zu, slots available: %zu)\n", ARRAY_SIZE(drbg_cores) * 2, ARRAY_SIZE(drbg_algs)); return -EFAULT; } /* * each DRBG definition can be used with PR and without PR, thus * we instantiate each DRBG in drbg_cores[] twice. * * As the order of placing them into the drbg_algs array matters * (the later DRBGs receive a higher cra_priority) we register the * prediction resistance DRBGs first as the should not be too * interesting. */ for (j = 0; ARRAY_SIZE(drbg_cores) > j; j++, i++) drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 1); for (j = 0; ARRAY_SIZE(drbg_cores) > j; j++, i++) drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 0); return crypto_register_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2)); } static void __exit drbg_exit(void) { crypto_unregister_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2)); } module_init(drbg_init); module_exit(drbg_exit); #ifndef CRYPTO_DRBG_HASH_STRING #define CRYPTO_DRBG_HASH_STRING "" #endif #ifndef CRYPTO_DRBG_HMAC_STRING #define CRYPTO_DRBG_HMAC_STRING "" #endif #ifndef CRYPTO_DRBG_CTR_STRING #define CRYPTO_DRBG_CTR_STRING "" #endif MODULE_LICENSE("GPL"); MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>"); MODULE_DESCRIPTION("NIST SP800-90A Deterministic Random Bit Generator (DRBG) " "using following cores: " CRYPTO_DRBG_HASH_STRING CRYPTO_DRBG_HMAC_STRING CRYPTO_DRBG_CTR_STRING); MODULE_ALIAS_CRYPTO("stdrng"); MODULE_IMPORT_NS("CRYPTO_INTERNAL"); |
| 51 930 375 533 86 15 568 44 19 41 572 31 333 91 47 5 8 2 4 66 5 5 5 134 4 137 9 22 1577 1578 1567 598 287 287 47 43 3538 1217 2456 3064 204 1789 1499 122 681 183 318 1278 1278 935 157 7 408 25 7 2 128 2 861 1207 1 347 178 28 9 7 2 6 2 2 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IPV6_H #define _NET_IPV6_H #include <linux/ipv6.h> #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/inet_dscp.h> #include <net/snmp.h> #include <net/netns/hash.h> struct ip_tunnel_info; #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 /* * NextHeader field of IPv6 header */ #define NEXTHDR_HOP 0 /* Hop-by-hop option header. */ #define NEXTHDR_IPV4 4 /* IPv4 in IPv6 */ #define NEXTHDR_TCP 6 /* TCP segment. */ #define NEXTHDR_UDP 17 /* UDP message. */ #define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */ #define NEXTHDR_ROUTING 43 /* Routing header. */ #define NEXTHDR_FRAGMENT 44 /* Fragmentation/reassembly header. */ #define NEXTHDR_GRE 47 /* GRE header. */ #define NEXTHDR_ESP 50 /* Encapsulating security payload. */ #define NEXTHDR_AUTH 51 /* Authentication header. */ #define NEXTHDR_ICMP 58 /* ICMP for IPv6. */ #define NEXTHDR_NONE 59 /* No next header */ #define NEXTHDR_DEST 60 /* Destination options header. */ #define NEXTHDR_SCTP 132 /* SCTP message. */ #define NEXTHDR_MOBILITY 135 /* Mobility header. */ #define NEXTHDR_MAX 255 #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 /* Limits on Hop-by-Hop and Destination options. * * Per RFC8200 there is no limit on the maximum number or lengths of options in * Hop-by-Hop or Destination options other then the packet must fit in an MTU. * We allow configurable limits in order to mitigate potential denial of * service attacks. * * There are three limits that may be set: * - Limit the number of options in a Hop-by-Hop or Destination options * extension header * - Limit the byte length of a Hop-by-Hop or Destination options extension * header * - Disallow unknown options * * The limits are expressed in corresponding sysctls: * * ipv6.sysctl.max_dst_opts_cnt * ipv6.sysctl.max_hbh_opts_cnt * ipv6.sysctl.max_dst_opts_len * ipv6.sysctl.max_hbh_opts_len * * max_*_opts_cnt is the number of TLVs that are allowed for Destination * options or Hop-by-Hop options. If the number is less than zero then unknown * TLVs are disallowed and the number of known options that are allowed is the * absolute value. Setting the value to INT_MAX indicates no limit. * * max_*_opts_len is the length limit in bytes of a Destination or * Hop-by-Hop options extension header. Setting the value to INT_MAX * indicates no length limit. * * If a limit is exceeded when processing an extension header the packet is * silently discarded. */ /* Default limits for Hop-by-Hop and Destination options */ #define IP6_DEFAULT_MAX_DST_OPTS_CNT 8 #define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8 #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ /* * Addr type * * type - unicast | multicast * scope - local | site | global * v4 - compat * v4mapped * any * loopback */ #define IPV6_ADDR_ANY 0x0000U #define IPV6_ADDR_UNICAST 0x0001U #define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U #define IPV6_ADDR_SITELOCAL 0x0040U #define IPV6_ADDR_COMPATv4 0x0080U #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U /* * Addr scopes */ #define IPV6_ADDR_MC_SCOPE(a) \ ((a)->s6_addr[1] & 0x0f) /* nonstandard */ #define __IPV6_ADDR_SCOPE_INVALID -1 #define IPV6_ADDR_SCOPE_NODELOCAL 0x01 #define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 #define IPV6_ADDR_SCOPE_SITELOCAL 0x05 #define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* * Addr flags */ #define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ ((a)->s6_addr[1] & 0x10) #define IPV6_ADDR_MC_FLAG_PREFIX(a) \ ((a)->s6_addr[1] & 0x20) #define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ ((a)->s6_addr[1] & 0x40) /* * fragmentation header */ struct frag_hdr { __u8 nexthdr; __u8 reserved; __be16 frag_off; __be32 identification; }; /* * Jumbo payload option, as described in RFC 2675 2. */ struct hop_jumbo_hdr { u8 nexthdr; u8 hdrlen; u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ u8 tlv_len; /* 4 */ __be32 jumbo_payload_len; }; #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; struct sk_buff *frag; int offset; unsigned int hlen; __be32 frag_id; u8 nexthdr; }; int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip6_frag_state { u8 *prevhdr; unsigned int hlen; unsigned int mtu; unsigned int left; int offset; int ptr; int hroom; int troom; __be32 frag_id; u8 nexthdr; }; void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state); #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) #include <net/sock.h> /* sysctls */ extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; #define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ #define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ #define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ unsigned long _field = (field); \ unsigned long _val = (val); \ if (likely(_idev != NULL)) \ mod##SNMP_ADD_STATS((_idev)->stats.statname, _field, _val); \ mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, _field, _val);\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ unsigned long _val = (val); \ if (likely(_idev != NULL)) \ mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, _val); \ mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, _val);\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, , idev, field) #define __IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, , idev, field, val) #define __IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, , idev, field, val) #define __IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) #define __ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; void (*destructor)(struct sock *); }; extern struct ip6_ra_chain *ip6_ra_chain; extern rwlock_t ip6_ra_lock; /* This structure is prepared by protocol, when parsing ancillary data and passed to IPv6. */ struct ipv6_txoptions { refcount_t refcnt; /* Length of this structure */ int tot_len; /* length of extension headers */ __u16 opt_flen; /* after fragment hdr */ __u16 opt_nflen; /* before fragment hdr */ struct ipv6_opt_hdr *hopopt; struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; /* flowlabel_reflect sysctl values */ enum flowlabel_reflect { FLOWLABEL_REFLECT_ESTABLISHED = 1, FLOWLABEL_REFLECT_TCP_RESET = 2, FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, }; struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; struct ipv6_txoptions *opt; unsigned long linger; struct rcu_head rcu; u8 share; union { struct pid *pid; kuid_t uid; } owner; unsigned long lastuse; unsigned long expires; struct net *fl_net; }; #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) #define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 struct ipv6_fl_socklist { struct ipv6_fl_socklist __rcu *next; struct ip6_flowlabel *fl; struct rcu_head rcu; }; struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __u16 gso_size; __s8 dontfrag; struct ipv6_txoptions *opt; }; static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct sock *sk) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = inet6_sk(sk)->tclass, .dontfrag = inet6_test_bit(DONTFRAG, sk), }; sockcm_init(&ipc6->sockc, sk); } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); } rcu_read_unlock(); return opt; } static inline void txopt_put(struct ipv6_txoptions *opt) { if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } #if IS_ENABLED(CONFIG_IPV6) struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key) && READ_ONCE(sock_net(sk)->ipv6.flowlabel_has_excl)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } #endif struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); void fl6_free_socklist(struct sock *sk); int ipv6_flowlabel_opt(struct sock *sk, sockptr_t optval, int optlen); int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); bool ip6_autoflowlabel(struct net *net, const struct sock *sk); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { if (fl) atomic_dec(&fl->users); } enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); int ipv6_parse_hopopts(struct sk_buff *skb); struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt); struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); static inline struct ipv6_txoptions * ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { if (!opt) return NULL; return __ipv6_fixup_options(opt_space, opt); } bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); /* This helper is specialized for BIG TCP needs. * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. * It assumes headers are already in skb->head. * Returns: 0, or IPPROTO_TCP if a BIG TCP packet is there. */ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) { const struct hop_jumbo_hdr *jhdr; const struct ipv6hdr *nhdr; if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) return 0; if (skb->protocol != htons(ETH_P_IPV6)) return 0; if (skb_network_offset(skb) + sizeof(struct ipv6hdr) + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) return 0; nhdr = ipv6_hdr(skb); if (nhdr->nexthdr != NEXTHDR_HOP) return 0; jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || jhdr->nexthdr != IPPROTO_TCP) return 0; return jhdr->nexthdr; } /* Return 0 if HBH header is successfully removed * Or if HBH removal is unnecessary (packet is not big TCP) * Return error to indicate dropping the packet */ static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb) { const int hophdr_len = sizeof(struct hop_jumbo_hdr); int nexthdr = ipv6_has_hopopt_jumbo(skb); struct ipv6hdr *h6; if (!nexthdr) return 0; if (skb_cow_head(skb, 0)) return -1; /* Remove the HBH header. * Layout: [Ethernet header][IPv6 header][HBH][L4 Header] */ memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb), skb_network_header(skb) - skb_mac_header(skb) + sizeof(struct ipv6hdr)); __skb_pull(skb, hophdr_len); skb->network_header += hophdr_len; skb->mac_header += hophdr_len; h6 = ipv6_hdr(skb); h6->nexthdr = nexthdr; return 0; } static inline bool ipv6_accept_ra(const struct inet6_dev *idev) { s32 accept_ra = READ_ONCE(idev->cnf.accept_ra); /* If forwarding is enabled, RA are not accepted unless the special * hybrid mode (accept_ra=2) is enabled. */ return READ_ONCE(idev->cnf.forwarding) ? accept_ra == 2 : accept_ra; } #define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */ #define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */ #define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & 0xffff; } static inline int ipv6_addr_scope(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & IPV6_ADDR_SCOPE_MASK; } static inline int __ipv6_addr_src_scope(int type) { return (type == IPV6_ADDR_ANY) ? __IPV6_ADDR_SCOPE_INVALID : (type >> 16); } static inline int ipv6_addr_src_scope(const struct in6_addr *addr) { return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } static inline bool __ipv6_addr_needs_scope_id(int type) { return type & IPV6_ADDR_LINKLOCAL || (type & IPV6_ADDR_MULTICAST && (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); } static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) { return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; } static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); } static inline bool ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ulm = (const unsigned long *)m; const unsigned long *ul2 = (const unsigned long *)a2; return !!(((ul1[0] ^ ul2[0]) & ulm[0]) | ((ul1[1] ^ ul2[1]) & ulm[1])); #else return !!(((a1->s6_addr32[0] ^ a2->s6_addr32[0]) & m->s6_addr32[0]) | ((a1->s6_addr32[1] ^ a2->s6_addr32[1]) & m->s6_addr32[1]) | ((a1->s6_addr32[2] ^ a2->s6_addr32[2]) & m->s6_addr32[2]) | ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); #endif } static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memset(pfx->s6_addr, 0, sizeof(pfx->s6_addr)); memcpy(pfx->s6_addr, addr, o); if (b != 0) pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, const struct in6_addr *pfx, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memcpy(addr->s6_addr, pfx, o); if (b != 0) { addr->s6_addr[o] &= ~(0xff00 >> b); addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); } } static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #if defined(__BIG_ENDIAN) if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) { *(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl)); return; } #elif defined(__LITTLE_ENDIAN) if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) { *(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh)); return; } #endif #endif addr[0] = wh; addr[1] = wl; } static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { __ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2); __ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4); } static inline bool ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; #endif } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline bool __ipv6_prefix_equal64_half(const __be64 *a1, const __be64 *a2, unsigned int len) { if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len)))) return false; return true; } static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be64 *a1 = (const __be64 *)addr1; const __be64 *a2 = (const __be64 *)addr2; if (prefixlen >= 64) { if (a1[0] ^ a2[0]) return false; return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64); } return __ipv6_prefix_equal64_half(a1, a2, prefixlen); } #else static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be32 *a1 = addr1->s6_addr32; const __be32 *a2 = addr2->s6_addr32; unsigned int pdw, pbi; /* check complete u32 in prefix */ pdw = prefixlen >> 5; if (pdw && memcmp(a1, a2, pdw << 2)) return false; /* check incomplete u32 in prefix */ pbi = prefixlen & 0x1f; if (pbi && ((a1[pdw] ^ a2[pdw]) & htonl((0xffffffff) << (32 - pbi)))) return false; return true; } #endif static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; return (ul[0] | ul[1]) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | a->s6_addr32[3]) == 0; #endif } static inline u32 ipv6_addr_hash(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; unsigned long x = ul[0] ^ ul[1]; return (u32)(x ^ (x >> 32)); #else return (__force u32)(a->s6_addr32[0] ^ a->s6_addr32[1] ^ a->s6_addr32[2] ^ a->s6_addr32[3]); #endif } /* more secured version of ipv6_addr_hash() */ static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) { return jhash2((__force const u32 *)a->s6_addr32, ARRAY_SIZE(a->s6_addr32), initval); } static inline bool ipv6_addr_loopback(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *be = (const __be64 *)a; return (be[0] | (be[1] ^ cpu_to_be64(1))) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | (a->s6_addr32[3] ^ cpu_to_be32(1))) == 0; #endif } /* * Note that we must __force cast these to unsigned long to make sparse happy, * since all of the endian-annotated types are fixed size regardless of arch. */ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) { return ( #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 *(unsigned long *)a | #else (__force unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | #endif (__force unsigned long)(a->s6_addr32[2] ^ cpu_to_be32(0x0000ffff))) == 0UL; } static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]); } static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) { unsigned int hash, mix = net_hash_mix(net); if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) */ static inline bool ipv6_addr_orchid(const struct in6_addr *a) { return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010); } static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) { return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000); } static inline void ipv6_addr_set_v4mapped(const __be32 addr, struct in6_addr *v4mapped) { ipv6_addr_set(v4mapped, 0, 0, htonl(0x0000FFFF), addr); } /* * find the first different bit between two addresses * length of address must be a multiple of 32bits */ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen) { const __be32 *a1 = token1, *a2 = token2; int i; addrlen >>= 2; for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) return i * 32 + 31 - __fls(ntohl(xb)); } /* * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... * ip route add 1111::/64 via ... * and we are here. * * Ideally, this function should stop comparison * at prefix length. It does not, but it is still OK, * if returned value is greater than prefix length. * --ANK (980803) */ return addrlen << 5; } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen) { const __be64 *a1 = token1, *a2 = token2; int i; addrlen >>= 3; for (i = 0; i < addrlen; i++) { __be64 xb = a1[i] ^ a2[i]; if (xb) return i * 64 + 63 - __fls(be64_to_cpu(xb)); } return addrlen << 6; } #endif static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 if (__builtin_constant_p(addrlen) && !(addrlen & 7)) return __ipv6_addr_diff64(token1, token2, addrlen); #endif return __ipv6_addr_diff32(token1, token2, addrlen); } static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2) { return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, struct dst_entry *dst) { int hlimit; if (ipv6_addr_is_multicast(&fl6->daddr)) hlimit = READ_ONCE(np->mcast_hops); else hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); return hlimit; } /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, const struct ipv6hdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } #if IS_ENABLED(CONFIG_IPV6) static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 #define IP6_AUTO_FLOW_LABEL_OPTIN 2 #define IP6_AUTO_FLOW_LABEL_FORCED 3 #define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. * Here we want only the flow label value. */ flowlabel &= IPV6_FLOWLABEL_MASK; if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; if (net->ipv6.sysctl.flowlabel_state_ranges) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { switch (net->ipv6.sysctl.auto_flowlabels) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: return 0; case IP6_AUTO_FLOW_LABEL_OPTOUT: case IP6_AUTO_FLOW_LABEL_FORCED: return 1; } } #else static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { return 0; } #endif #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return net->ipv6.sysctl.multipath_hash_fields; } #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } static inline u32 ip6_multipath_hash_fields(const struct net *net) { return 0; } #endif /* * Header manipulation */ static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass, __be32 flowlabel) { *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel; } static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWINFO_MASK; } static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; } static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } static inline dscp_t ip6_dscp(__be32 flowinfo) { return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); } static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; } static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) { return fl6->flowlabel & IPV6_FLOWLABEL_MASK; } /* * Prototypes exported by ipv6 */ /* * rcv function (called from netdevice level) */ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); /* * skb processing functions */ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing */ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr_p, struct in6_addr *saddr); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); bool ipv6_ext_hdr(u8 nexthdr); enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), IP6_FH_F_SKIP_RH = (1 << 2), }; /* find specified header and get offset to it */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); /* * socket options (ipv6_sockglue.c) */ DECLARE_STATIC_KEY_FALSE(ip6_min_hopcount); int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); int do_ipv6_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); /* * reassembly.c */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr); int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); void ac6_proc_exit(struct net *net); int raw6_proc_init(void); void raw6_proc_exit(void); int tcp6_proc_init(struct net *net); void tcp6_proc_exit(struct net *net); int udp6_proc_init(struct net *net); void udp6_proc_exit(struct net *net); int udplite6_proc_init(void); void udplite6_proc_exit(void); int ipv6_misc_proc_init(void); void ipv6_misc_proc_exit(void); int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); #else static inline int ac6_proc_init(struct net *net) { return 0; } static inline void ac6_proc_exit(struct net *net) { } static inline int snmp6_register_dev(struct inet6_dev *idev) { return 0; } static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; } #endif #ifdef CONFIG_SYSCTL struct ctl_table *ipv6_icmp_sysctl_init(struct net *net); size_t ipv6_icmp_sysctl_table_size(void); struct ctl_table *ipv6_route_sysctl_init(struct net *net); size_t ipv6_route_sysctl_table_size(struct net *net); int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); static inline int ip6_sock_set_v6only(struct sock *sk) { if (inet_sk(sk)->inet_num) return -EINVAL; lock_sock(sk); sk->sk_ipv6only = true; release_sock(sk); return 0; } static inline void ip6_sock_set_recverr(struct sock *sk) { inet6_set_bit(RECVERR6, sk); } #define IPV6_PREFER_SRC_MASK (IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBLIC | \ IPV6_PREFER_SRC_COA) static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val) { unsigned int prefmask = ~IPV6_PREFER_SRC_MASK; unsigned int pref = 0; /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ switch (val & (IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP | IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { case IPV6_PREFER_SRC_PUBLIC: pref |= IPV6_PREFER_SRC_PUBLIC; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_TMP: pref |= IPV6_PREFER_SRC_TMP; prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case IPV6_PREFER_SRC_PUBTMP_DEFAULT: prefmask &= ~(IPV6_PREFER_SRC_PUBLIC | IPV6_PREFER_SRC_TMP); break; case 0: break; default: return -EINVAL; } /* check HOME/COA conflicts */ switch (val & (IPV6_PREFER_SRC_HOME | IPV6_PREFER_SRC_COA)) { case IPV6_PREFER_SRC_HOME: prefmask &= ~IPV6_PREFER_SRC_COA; break; case IPV6_PREFER_SRC_COA: pref |= IPV6_PREFER_SRC_COA; break; case 0: break; default: return -EINVAL; } /* check CGA/NONCGA conflicts */ switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { case IPV6_PREFER_SRC_CGA: case IPV6_PREFER_SRC_NONCGA: case 0: break; default: return -EINVAL; } WRITE_ONCE(inet6_sk(sk)->srcprefs, (READ_ONCE(inet6_sk(sk)->srcprefs) & prefmask) | pref); return 0; } static inline void ip6_sock_set_recvpktinfo(struct sock *sk) { lock_sock(sk); inet6_sk(sk)->rxopt.bits.rxinfo = true; release_sock(sk); } #define IPV6_ADDR_WORDS 4 static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) { cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); } static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) { be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); } #endif /* _NET_IPV6_H */ |
| 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2018 Intel Corporation. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ib_mad #if !defined(_TRACE_IB_MAD_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IB_MAD_H #include <linux/tracepoint.h> #include <rdma/ib_mad.h> #ifdef CONFIG_TRACEPOINTS struct trace_event_raw_ib_mad_send_template; static void create_mad_addr_info(struct ib_mad_send_wr_private *mad_send_wr, struct ib_mad_qp_info *qp_info, struct trace_event_raw_ib_mad_send_template *entry); #endif DECLARE_EVENT_CLASS(ib_mad_send_template, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info), TP_STRUCT__entry( __field(u8, base_version) __field(u8, mgmt_class) __field(u8, class_version) __field(u8, port_num) __field(u32, qp_num) __field(u8, method) __field(u8, sl) __field(u16, attr_id) __field(u32, attr_mod) __field(u64, wrtid) __field(u64, tid) __field(u16, status) __field(u16, class_specific) __field(u32, length) __field(u32, dlid) __field(u32, rqpn) __field(u32, rqkey) __field(u32, dev_index) __field(void *, agent_priv) __field(unsigned long, timeout) __field(int, retries_left) __field(int, max_retries) __field(int, retry) ), TP_fast_assign( __entry->dev_index = wr->mad_agent_priv->agent.device->index; __entry->port_num = wr->mad_agent_priv->agent.port_num; __entry->qp_num = wr->mad_agent_priv->qp_info->qp->qp_num; __entry->agent_priv = wr->mad_agent_priv; __entry->wrtid = wr->tid; __entry->max_retries = wr->max_retries; __entry->retries_left = wr->retries_left; __entry->retry = wr->retry; __entry->timeout = wr->timeout; __entry->length = wr->send_buf.hdr_len + wr->send_buf.data_len; __entry->base_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->base_version; __entry->mgmt_class = ((struct ib_mad_hdr *)wr->send_buf.mad)->mgmt_class; __entry->class_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->class_version; __entry->method = ((struct ib_mad_hdr *)wr->send_buf.mad)->method; __entry->status = ((struct ib_mad_hdr *)wr->send_buf.mad)->status; __entry->class_specific = ((struct ib_mad_hdr *)wr->send_buf.mad)->class_specific; __entry->tid = ((struct ib_mad_hdr *)wr->send_buf.mad)->tid; __entry->attr_id = ((struct ib_mad_hdr *)wr->send_buf.mad)->attr_id; __entry->attr_mod = ((struct ib_mad_hdr *)wr->send_buf.mad)->attr_mod; create_mad_addr_info(wr, qp_info, __entry); ), TP_printk("%d:%d QP%d agent %p: " \ "wrtid 0x%llx; %d/%d retries(%d); timeout %lu length %d : " \ "hdr : base_ver 0x%x class 0x%x class_ver 0x%x " \ "method 0x%x status 0x%x class_specific 0x%x tid 0x%llx " \ "attr_id 0x%x attr_mod 0x%x => dlid 0x%08x sl %d "\ "rpqn 0x%x rqpkey 0x%x", __entry->dev_index, __entry->port_num, __entry->qp_num, __entry->agent_priv, be64_to_cpu(__entry->wrtid), __entry->retries_left, __entry->max_retries, __entry->retry, __entry->timeout, __entry->length, __entry->base_version, __entry->mgmt_class, __entry->class_version, __entry->method, be16_to_cpu(__entry->status), be16_to_cpu(__entry->class_specific), be64_to_cpu(__entry->tid), be16_to_cpu(__entry->attr_id), be32_to_cpu(__entry->attr_mod), be32_to_cpu(__entry->dlid), __entry->sl, __entry->rqpn, __entry->rqkey ) ); DEFINE_EVENT(ib_mad_send_template, ib_mad_error_handler, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info)); DEFINE_EVENT(ib_mad_send_template, ib_mad_ib_send_mad, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info)); DEFINE_EVENT(ib_mad_send_template, ib_mad_send_done_resend, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_mad_qp_info *qp_info), TP_ARGS(wr, qp_info)); TRACE_EVENT(ib_mad_send_done_handler, TP_PROTO(struct ib_mad_send_wr_private *wr, struct ib_wc *wc), TP_ARGS(wr, wc), TP_STRUCT__entry( __field(u8, port_num) __field(u8, base_version) __field(u8, mgmt_class) __field(u8, class_version) __field(u32, qp_num) __field(u64, wrtid) __field(u16, status) __field(u16, wc_status) __field(u32, length) __field(void *, agent_priv) __field(unsigned long, timeout) __field(u32, dev_index) __field(int, retries_left) __field(int, max_retries) __field(int, retry) __field(u8, method) ), TP_fast_assign( __entry->dev_index = wr->mad_agent_priv->agent.device->index; __entry->port_num = wr->mad_agent_priv->agent.port_num; __entry->qp_num = wr->mad_agent_priv->qp_info->qp->qp_num; __entry->agent_priv = wr->mad_agent_priv; __entry->wrtid = wr->tid; __entry->max_retries = wr->max_retries; __entry->retries_left = wr->retries_left; __entry->retry = wr->retry; __entry->timeout = wr->timeout; __entry->base_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->base_version; __entry->mgmt_class = ((struct ib_mad_hdr *)wr->send_buf.mad)->mgmt_class; __entry->class_version = ((struct ib_mad_hdr *)wr->send_buf.mad)->class_version; __entry->method = ((struct ib_mad_hdr *)wr->send_buf.mad)->method; __entry->status = ((struct ib_mad_hdr *)wr->send_buf.mad)->status; __entry->wc_status = wc->status; __entry->length = wc->byte_len; ), TP_printk("%d:%d QP%d : SEND WC Status %d : agent %p: " \ "wrtid 0x%llx %d/%d retries(%d) timeout %lu length %d: " \ "hdr : base_ver 0x%x class 0x%x class_ver 0x%x " \ "method 0x%x status 0x%x", __entry->dev_index, __entry->port_num, __entry->qp_num, __entry->wc_status, __entry->agent_priv, be64_to_cpu(__entry->wrtid), __entry->retries_left, __entry->max_retries, __entry->retry, __entry->timeout, __entry->length, __entry->base_version, __entry->mgmt_class, __entry->class_version, __entry->method, be16_to_cpu(__entry->status) ) ); TRACE_EVENT(ib_mad_recv_done_handler, TP_PROTO(struct ib_mad_qp_info *qp_info, struct ib_wc *wc, struct ib_mad_hdr *mad_hdr), TP_ARGS(qp_info, wc, mad_hdr), TP_STRUCT__entry( __field(u8, base_version) __field(u8, mgmt_class) __field(u8, class_version) __field(u8, port_num) __field(u32, qp_num) __field(u16, status) __field(u16, class_specific) __field(u32, length) __field(u64, tid) __field(u8, method) __field(u8, sl) __field(u16, attr_id) __field(u32, attr_mod) __field(u16, src_qp) __field(u16, wc_status) __field(u32, slid) __field(u32, dev_index) ), TP_fast_assign( __entry->dev_index = qp_info->port_priv->device->index; __entry->port_num = qp_info->port_priv->port_num; __entry->qp_num = qp_info->qp->qp_num; __entry->length = wc->byte_len; __entry->base_version = mad_hdr->base_version; __entry->mgmt_class = mad_hdr->mgmt_class; __entry->class_version = mad_hdr->class_version; __entry->method = mad_hdr->method; __entry->status = mad_hdr->status; __entry->class_specific = mad_hdr->class_specific; __entry->tid = mad_hdr->tid; __entry->attr_id = mad_hdr->attr_id; __entry->attr_mod = mad_hdr->attr_mod; __entry->slid = wc->slid; __entry->src_qp = wc->src_qp; __entry->sl = wc->sl; __entry->wc_status = wc->status; ), TP_printk("%d:%d QP%d : RECV WC Status %d : length %d : hdr : " \ "base_ver 0x%02x class 0x%02x class_ver 0x%02x " \ "method 0x%02x status 0x%04x class_specific 0x%04x " \ "tid 0x%016llx attr_id 0x%04x attr_mod 0x%08x " \ "slid 0x%08x src QP%d, sl %d", __entry->dev_index, __entry->port_num, __entry->qp_num, __entry->wc_status, __entry->length, __entry->base_version, __entry->mgmt_class, __entry->class_version, __entry->method, be16_to_cpu(__entry->status), be16_to_cpu(__entry->class_specific), be64_to_cpu(__entry->tid), be16_to_cpu(__entry->attr_id), be32_to_cpu(__entry->attr_mod), __entry->slid, __entry->src_qp, __entry->sl ) ); DECLARE_EVENT_CLASS(ib_mad_agent_template, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent), TP_STRUCT__entry( __field(u32, dev_index) __field(u32, hi_tid) __field(u8, port_num) __field(u8, mgmt_class) __field(u8, mgmt_class_version) ), TP_fast_assign( __entry->dev_index = agent->agent.device->index; __entry->port_num = agent->agent.port_num; __entry->hi_tid = agent->agent.hi_tid; if (agent->reg_req) { __entry->mgmt_class = agent->reg_req->mgmt_class; __entry->mgmt_class_version = agent->reg_req->mgmt_class_version; } else { __entry->mgmt_class = 0; __entry->mgmt_class_version = 0; } ), TP_printk("%d:%d mad agent : hi_tid 0x%08x class 0x%02x class_ver 0x%02x", __entry->dev_index, __entry->port_num, __entry->hi_tid, __entry->mgmt_class, __entry->mgmt_class_version ) ); DEFINE_EVENT(ib_mad_agent_template, ib_mad_recv_done_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DEFINE_EVENT(ib_mad_agent_template, ib_mad_send_done_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DEFINE_EVENT(ib_mad_agent_template, ib_mad_create_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DEFINE_EVENT(ib_mad_agent_template, ib_mad_unregister_agent, TP_PROTO(struct ib_mad_agent_private *agent), TP_ARGS(agent)); DECLARE_EVENT_CLASS(ib_mad_opa_smi_template, TP_PROTO(struct opa_smp *smp), TP_ARGS(smp), TP_STRUCT__entry( __field(u64, mkey) __field(u32, dr_slid) __field(u32, dr_dlid) __field(u8, hop_ptr) __field(u8, hop_cnt) __array(u8, initial_path, OPA_SMP_MAX_PATH_HOPS) __array(u8, return_path, OPA_SMP_MAX_PATH_HOPS) ), TP_fast_assign( __entry->hop_ptr = smp->hop_ptr; __entry->hop_cnt = smp->hop_cnt; __entry->mkey = smp->mkey; __entry->dr_slid = smp->route.dr.dr_slid; __entry->dr_dlid = smp->route.dr.dr_dlid; memcpy(__entry->initial_path, smp->route.dr.initial_path, OPA_SMP_MAX_PATH_HOPS); memcpy(__entry->return_path, smp->route.dr.return_path, OPA_SMP_MAX_PATH_HOPS); ), TP_printk("OPA SMP: hop_ptr %d hop_cnt %d " \ "mkey 0x%016llx dr_slid 0x%08x dr_dlid 0x%08x " \ "initial_path %*ph return_path %*ph ", __entry->hop_ptr, __entry->hop_cnt, be64_to_cpu(__entry->mkey), be32_to_cpu(__entry->dr_slid), be32_to_cpu(__entry->dr_dlid), OPA_SMP_MAX_PATH_HOPS, __entry->initial_path, OPA_SMP_MAX_PATH_HOPS, __entry->return_path ) ); DEFINE_EVENT(ib_mad_opa_smi_template, ib_mad_handle_opa_smi, TP_PROTO(struct opa_smp *smp), TP_ARGS(smp)); DEFINE_EVENT(ib_mad_opa_smi_template, ib_mad_handle_out_opa_smi, TP_PROTO(struct opa_smp *smp), TP_ARGS(smp)); DECLARE_EVENT_CLASS(ib_mad_opa_ib_template, TP_PROTO(struct ib_smp *smp), TP_ARGS(smp), TP_STRUCT__entry( __field(u64, mkey) __field(u32, dr_slid) __field(u32, dr_dlid) __field(u8, hop_ptr) __field(u8, hop_cnt) __array(u8, initial_path, IB_SMP_MAX_PATH_HOPS) __array(u8, return_path, IB_SMP_MAX_PATH_HOPS) ), TP_fast_assign( __entry->hop_ptr = smp->hop_ptr; __entry->hop_cnt = smp->hop_cnt; __entry->mkey = smp->mkey; __entry->dr_slid = smp->dr_slid; __entry->dr_dlid = smp->dr_dlid; memcpy(__entry->initial_path, smp->initial_path, IB_SMP_MAX_PATH_HOPS); memcpy(__entry->return_path, smp->return_path, IB_SMP_MAX_PATH_HOPS); ), TP_printk("OPA SMP: hop_ptr %d hop_cnt %d " \ "mkey 0x%016llx dr_slid 0x%04x dr_dlid 0x%04x " \ "initial_path %*ph return_path %*ph ", __entry->hop_ptr, __entry->hop_cnt, be64_to_cpu(__entry->mkey), be16_to_cpu(__entry->dr_slid), be16_to_cpu(__entry->dr_dlid), IB_SMP_MAX_PATH_HOPS, __entry->initial_path, IB_SMP_MAX_PATH_HOPS, __entry->return_path ) ); DEFINE_EVENT(ib_mad_opa_ib_template, ib_mad_handle_ib_smi, TP_PROTO(struct ib_smp *smp), TP_ARGS(smp)); DEFINE_EVENT(ib_mad_opa_ib_template, ib_mad_handle_out_ib_smi, TP_PROTO(struct ib_smp *smp), TP_ARGS(smp)); #endif /* _TRACE_IB_MAD_H */ #include <trace/define_trace.h> |
| 515 516 22 238 265 238 243 82 36 82 82 82 82 82 82 82 27 17 11 513 19 562 8 43 48 115 31 67 67 35 35 58 58 26 2 2 22 12 7 7 9 8 22 26 44 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 | // SPDX-License-Identifier: GPL-2.0 /* * High-level sync()-related operations */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/namei.h> #include <linux/sched.h> #include <linux/writeback.h> #include <linux/syscalls.h> #include <linux/linkage.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/backing-dev.h> #include "internal.h" #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER) /* * Write out and wait upon all dirty data associated with this * superblock. Filesystem data as well as the underlying block * device. Takes the superblock lock. */ int sync_filesystem(struct super_block *sb) { int ret = 0; /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* * No point in syncing out anything if the filesystem is read-only. */ if (sb_rdonly(sb)) return 0; /* * Do the filesystem syncing work. For simple filesystems * writeback_inodes_sb(sb) just dirties buffers with inodes so we have * to submit I/O for these buffers via sync_blockdev(). This also * speeds up the wait == 1 case since in that case write_inode() * methods call sync_dirty_buffer() and thus effectively write one block * at a time. */ writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 0); if (ret) return ret; } ret = sync_blockdev_nowait(sb->s_bdev); if (ret) return ret; sync_inodes_sb(sb); if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 1); if (ret) return ret; } return sync_blockdev(sb->s_bdev); } EXPORT_SYMBOL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!sb_rdonly(sb)) sync_inodes_sb(sb); } static void sync_fs_one_sb(struct super_block *sb, void *arg) { if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) && sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg); } /* * Sync everything. We start by waking flusher threads so that most of * writeback runs on all devices in parallel. Then we sync all inodes reliably * which effectively also waits for all flusher threads to finish doing * writeback. At this point all data is on disk so metadata should be stable * and we tell filesystems to sync their metadata via ->sync_fs() calls. * Finally, we writeout all block devices because some filesystems (e.g. ext2) * just write metadata (such as inodes or bitmaps) to block device page cache * and do not sync it on their own in ->sync_fs(). */ void ksys_sync(void) { int nowait = 0, wait = 1; wakeup_flusher_threads(WB_REASON_SYNC); iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); sync_bdevs(false); sync_bdevs(true); if (unlikely(laptop_mode)) laptop_sync_completion(); } SYSCALL_DEFINE0(sync) { ksys_sync(); return 0; } static void do_sync_work(struct work_struct *work) { int nowait = 0; /* * Sync twice to reduce the possibility we skipped some inodes / pages * because they were temporarily locked */ iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); sync_bdevs(false); iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); sync_bdevs(false); printk("Emergency Sync complete\n"); kfree(work); } void emergency_sync(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_sync_work); schedule_work(work); } } /* * sync a single super */ SYSCALL_DEFINE1(syncfs, int, fd) { CLASS(fd, f)(fd); struct super_block *sb; int ret, ret2; if (fd_empty(f)) return -EBADF; sb = fd_file(f)->f_path.dentry->d_sb; down_read(&sb->s_umount); ret = sync_filesystem(sb); up_read(&sb->s_umount); ret2 = errseq_check_and_advance(&sb->s_wb_err, &fd_file(f)->f_sb_err); return ret ? ret : ret2; } /** * vfs_fsync_range - helper to sync a range of data & metadata to disk * @file: file to sync * @start: offset in bytes of the beginning of data range to sync * @end: offset in bytes of the end of data range (inclusive) * @datasync: perform only datasync * * Write back data in range @start..@end and metadata for @file to disk. If * @datasync is set only metadata needed to access modified file data is * written. */ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; if (!file->f_op->fsync) return -EINVAL; if (!datasync && (inode->i_state & I_DIRTY_TIME)) mark_inode_dirty_sync(inode); return file->f_op->fsync(file, start, end, datasync); } EXPORT_SYMBOL(vfs_fsync_range); /** * vfs_fsync - perform a fsync or fdatasync on a file * @file: file to sync * @datasync: only perform a fdatasync operation * * Write back data and metadata for @file to disk. If @datasync is * set only metadata needed to access modified file data is written. */ int vfs_fsync(struct file *file, int datasync) { return vfs_fsync_range(file, 0, LLONG_MAX, datasync); } EXPORT_SYMBOL(vfs_fsync); static int do_fsync(unsigned int fd, int datasync) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_fsync(fd_file(f), datasync); } SYSCALL_DEFINE1(fsync, unsigned int, fd) { return do_fsync(fd, 0); } SYSCALL_DEFINE1(fdatasync, unsigned int, fd) { return do_fsync(fd, 1); } int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags) { int ret; struct address_space *mapping; loff_t endbyte; /* inclusive */ umode_t i_mode; ret = -EINVAL; if (flags & ~VALID_FLAGS) goto out; endbyte = offset + nbytes; if ((s64)offset < 0) goto out; if ((s64)endbyte < 0) goto out; if (endbyte < offset) goto out; if (sizeof(pgoff_t) == 4) { if (offset >= (0x100000000ULL << PAGE_SHIFT)) { /* * The range starts outside a 32 bit machine's * pagecache addressing capabilities. Let it "succeed" */ ret = 0; goto out; } if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) { /* * Out to EOF */ nbytes = 0; } } if (nbytes == 0) endbyte = LLONG_MAX; else endbyte--; /* inclusive */ i_mode = file_inode(file)->i_mode; ret = -ESPIPE; if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) && !S_ISLNK(i_mode)) goto out; mapping = file->f_mapping; ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { ret = file_fdatawait_range(file, offset, endbyte); if (ret < 0) goto out; } if (flags & SYNC_FILE_RANGE_WRITE) { int sync_mode = WB_SYNC_NONE; if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) == SYNC_FILE_RANGE_WRITE_AND_WAIT) sync_mode = WB_SYNC_ALL; ret = __filemap_fdatawrite_range(mapping, offset, endbyte, sync_mode); if (ret < 0) goto out; } if (flags & SYNC_FILE_RANGE_WAIT_AFTER) ret = file_fdatawait_range(file, offset, endbyte); out: return ret; } /* * ksys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is * zero then ksys_sync_file_range() will operate from offset out to EOF. * * The flag bits are: * * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range * before performing the write. * * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the * range which are not presently under writeback. Note that this may block for * significant periods due to exhaustion of disk request structures. * * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range * after performing the write. * * Useful combinations of the flag bits are: * * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages * in the range which were dirty on entry to ksys_sync_file_range() are placed * under writeout. This is a start-write-for-data-integrity operation. * * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which * are not presently under writeout. This is an asynchronous flush-to-disk * operation. Not suitable for data integrity operations. * * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for * completion of writeout of all pages in the range. This will be used after an * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait * for that operation to complete and to return the result. * * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER * (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT): * a traditional sync() operation. This is a write-for-data-integrity operation * which will ensure that all pages in the range which were dirty on entry to * ksys_sync_file_range() are written to disk. It should be noted that disk * caches are not flushed by this call, so there are no guarantees here that the * data will be available on disk after a crash. * * * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any * I/O errors or ENOSPC conditions and will return those to the caller, after * clearing the EIO and ENOSPC flags in the address_space. * * It should be noted that none of these operations write out the file's * metadata. So unless the application is strictly performing overwrites of * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, unsigned int flags) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return sync_file_range(fd_file(f), offset, nbytes, flags); } SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, unsigned int, flags) { return ksys_sync_file_range(fd, offset, nbytes, flags); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_SYNC_FILE_RANGE) COMPAT_SYSCALL_DEFINE6(sync_file_range, int, fd, compat_arg_u64_dual(offset), compat_arg_u64_dual(nbytes), unsigned int, flags) { return ksys_sync_file_range(fd, compat_arg_u64_glue(offset), compat_arg_u64_glue(nbytes), flags); } #endif /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags, loff_t, offset, loff_t, nbytes) { return ksys_sync_file_range(fd, offset, nbytes, flags); } |
| 13 13 1 12 12 12 12 12 12 7 5 12 12 12 12 29 1 28 2 24 2 19 3 15 5 4 19 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * GRE GSO support */ #include <linux/skbuff.h> #include <linux/init.h> #include <net/protocol.h> #include <net/gre.h> #include <net/gro.h> #include <net/gso.h> static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool need_csum, offload_csum, gso_partial, need_ipsec; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; if (!skb->encapsulation) goto out; if (unlikely(tnl_hlen < sizeof(struct gre_base_hdr))) goto out; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & NETIF_F_HW_CSUM)); /* segment inner packet. */ segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); gre_offset = outer_hlen - tnl_hlen; skb = segs; do { struct gre_base_hdr *greh; __sum16 *pcsum; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, gre_offset); if (!need_csum) continue; greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that * the partial checksum is based on actual size * whereas headers should be based on MSS size. */ partial_adj = skb->len + skb_headroom(skb) - SKB_GSO_CB(skb)->data_offset - skb_shinfo(skb)->gso_size; *pcsum = ~csum_fold((__force __wsum)htonl(partial_adj)); } else { *pcsum = 0; } *(pcsum + 1) = 0; if (skb->encapsulation || !offload_csum) { *pcsum = gso_make_checksum(skb, 0); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } while ((skb = skb->next)); out: return segs; } static struct sk_buff *gre_gro_receive(struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; const struct gre_base_hdr *greh; unsigned int hlen, grehlen; unsigned int off; int flush = 1; struct packet_offload *ptype; __be16 type; if (NAPI_GRO_CB(skb)->encap_mark) goto out; NAPI_GRO_CB(skb)->encap_mark = 1; off = skb_gro_offset(skb); hlen = off + sizeof(*greh); greh = skb_gro_header(skb, hlen, off); if (unlikely(!greh)) goto out; /* Only support version 0 and K (key), C (csum) flags. Note that * although the support for the S (seq#) flag can be added easily * for GRO, this is problematic for GSO hence can not be enabled * here because a GRO pkt may end up in the forwarding path, thus * requiring GSO support to break it up correctly. */ if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0) goto out; /* We can only support GRE_CSUM if we can track the location of * the GRE header. In the case of FOU/GUE we cannot because the * outer UDP header displaces the GRE header leaving us in a state * of limbo. */ if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou) goto out; type = greh->protocol; ptype = gro_find_receive_by_type(type); if (!ptype) goto out; grehlen = GRE_HEADER_SECTION; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; if (greh->flags & GRE_CSUM) grehlen += GRE_HEADER_SECTION; hlen = off + grehlen; if (!skb_gro_may_pull(skb, hlen)) { greh = skb_gro_header_slow(skb, hlen, off); if (unlikely(!greh)) goto out; } /* Don't bother verifying checksum if we're going to flush anyway. */ if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) { if (skb_gro_checksum_simple_validate(skb)) goto out; skb_gro_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); } list_for_each_entry(p, head, list) { const struct gre_base_hdr *greh2; if (!NAPI_GRO_CB(p)->same_flow) continue; /* The following checks are needed to ensure only pkts * from the same tunnel are considered for aggregation. * The criteria for "the same tunnel" includes: * 1) same version (we only support version 0 here) * 2) same protocol (we only support ETH_P_IP for now) * 3) same set of flags * 4) same key if the key field is present. */ greh2 = (struct gre_base_hdr *)(p->data + off); if (greh2->flags != greh->flags || greh2->protocol != greh->protocol) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (greh->flags & GRE_KEY) { /* compare keys */ if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } } skb_gro_pull(skb, grehlen); /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ skb_gro_postpull_rcsum(skb, greh, grehlen); pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int gre_gro_complete(struct sk_buff *skb, int nhoff) { struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff); struct packet_offload *ptype; unsigned int grehlen = sizeof(*greh); int err = -ENOENT; __be16 type; skb->encapsulation = 1; skb_shinfo(skb)->gso_type = SKB_GSO_GRE; type = greh->protocol; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; if (greh->flags & GRE_CSUM) grehlen += GRE_HEADER_SECTION; ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); skb_set_inner_mac_header(skb, nhoff + grehlen); return err; } static const struct net_offload gre_offload = { .callbacks = { .gso_segment = gre_gso_segment, .gro_receive = gre_gro_receive, .gro_complete = gre_gro_complete, }, }; static int __init gre_offload_init(void) { int err; err = inet_add_offload(&gre_offload, IPPROTO_GRE); #if IS_ENABLED(CONFIG_IPV6) if (err) return err; err = inet6_add_offload(&gre_offload, IPPROTO_GRE); if (err) inet_del_offload(&gre_offload, IPPROTO_GRE); #endif return err; } device_initcall(gre_offload_init); |
| 7 8 7 7 19 2 97 97 1 1 1 1 1 97 1 1 1 64 97 39 2 156 40 52 64 1 97 3 8 6 4 2 2 1 2 32 21 3 2 1 7 21 6 1 5 151 151 24 24 24 128 128 97 97 97 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2011 Intel Corporation. All rights reserved. * Copyright (C) 2014 Marvell International Ltd. */ #define pr_fmt(fmt) "llcp: %s: " fmt, __func__ #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/nfc.h> #include "nfc.h" #include "llcp.h" static u8 llcp_magic[3] = {0x46, 0x66, 0x6d}; static LIST_HEAD(llcp_devices); /* Protects llcp_devices list */ static DEFINE_SPINLOCK(llcp_devices_lock); static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb); void nfc_llcp_sock_link(struct llcp_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_add_node(sk, &l->head); write_unlock(&l->lock); } void nfc_llcp_sock_unlink(struct llcp_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_del_node_init(sk); write_unlock(&l->lock); } void nfc_llcp_socket_remote_param_init(struct nfc_llcp_sock *sock) { sock->remote_rw = LLCP_DEFAULT_RW; sock->remote_miu = LLCP_MAX_MIU + 1; } static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local = sock->local; struct sk_buff *s, *tmp; skb_queue_purge(&sock->tx_queue); skb_queue_purge(&sock->tx_pending_queue); if (local == NULL) return; /* Search for local pending SKBs that are related to this socket */ skb_queue_walk_safe(&local->tx_queue, s, tmp) { if (s->sk != &sock->sk) continue; skb_unlink(s, &local->tx_queue); kfree_skb(s); } } static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, int err) { struct sock *sk; struct hlist_node *tmp; struct nfc_llcp_sock *llcp_sock; skb_queue_purge(&local->tx_queue); write_lock(&local->sockets.lock); sk_for_each_safe(sk, tmp, &local->sockets.head) { llcp_sock = nfc_llcp_sock(sk); bh_lock_sock(sk); nfc_llcp_socket_purge(llcp_sock); if (sk->sk_state == LLCP_CONNECTED) nfc_put_device(llcp_sock->dev); if (sk->sk_state == LLCP_LISTEN) { struct nfc_llcp_sock *lsk, *n; struct sock *accept_sk; list_for_each_entry_safe(lsk, n, &llcp_sock->accept_queue, accept_queue) { accept_sk = &lsk->sk; bh_lock_sock(accept_sk); nfc_llcp_accept_unlink(accept_sk); if (err) accept_sk->sk_err = err; accept_sk->sk_state = LLCP_CLOSED; accept_sk->sk_state_change(sk); bh_unlock_sock(accept_sk); } } if (err) sk->sk_err = err; sk->sk_state = LLCP_CLOSED; sk->sk_state_change(sk); bh_unlock_sock(sk); sk_del_node_init(sk); } write_unlock(&local->sockets.lock); /* If we still have a device, we keep the RAW sockets alive */ if (device == true) return; write_lock(&local->raw_sockets.lock); sk_for_each_safe(sk, tmp, &local->raw_sockets.head) { llcp_sock = nfc_llcp_sock(sk); bh_lock_sock(sk); nfc_llcp_socket_purge(llcp_sock); if (err) sk->sk_err = err; sk->sk_state = LLCP_CLOSED; sk->sk_state_change(sk); bh_unlock_sock(sk); sk_del_node_init(sk); } write_unlock(&local->raw_sockets.lock); } static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever * we hold a reference to local, we also need to hold a reference to * the device to avoid UAF. */ if (!nfc_get_device(local->dev->idx)) return NULL; kref_get(&local->ref); return local; } static void local_cleanup(struct nfc_llcp_local *local) { nfc_llcp_socket_release(local, false, ENXIO); timer_delete_sync(&local->link_timer); skb_queue_purge(&local->tx_queue); cancel_work_sync(&local->tx_work); cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); local->rx_pending = NULL; timer_delete_sync(&local->sdreq_timer); cancel_work_sync(&local->sdreq_timeout_work); nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs); } static void local_release(struct kref *ref) { struct nfc_llcp_local *local; local = container_of(ref, struct nfc_llcp_local, ref); local_cleanup(local); kfree(local); } int nfc_llcp_local_put(struct nfc_llcp_local *local) { struct nfc_dev *dev; int ret; if (local == NULL) return 0; dev = local->dev; ret = kref_put(&local->ref, local_release); nfc_put_device(dev); return ret; } static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, u8 ssap, u8 dsap) { struct sock *sk; struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("ssap dsap %d %d\n", ssap, dsap); if (ssap == 0 && dsap == 0) return NULL; read_lock(&local->sockets.lock); llcp_sock = NULL; sk_for_each(sk, &local->sockets.head) { tmp_sock = nfc_llcp_sock(sk); if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) { llcp_sock = tmp_sock; sock_hold(&llcp_sock->sk); break; } } read_unlock(&local->sockets.lock); return llcp_sock; } static void nfc_llcp_sock_put(struct nfc_llcp_sock *sock) { sock_put(&sock->sk); } static void nfc_llcp_timeout_work(struct work_struct *work) { struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, timeout_work); nfc_dep_link_down(local->dev); } static void nfc_llcp_symm_timer(struct timer_list *t) { struct nfc_llcp_local *local = timer_container_of(local, t, link_timer); pr_err("SYMM timeout\n"); schedule_work(&local->timeout_work); } static void nfc_llcp_sdreq_timeout_work(struct work_struct *work) { unsigned long time; HLIST_HEAD(nl_sdres_list); struct hlist_node *n; struct nfc_llcp_sdp_tlv *sdp; struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, sdreq_timeout_work); mutex_lock(&local->sdreq_lock); time = jiffies - msecs_to_jiffies(3 * local->remote_lto); hlist_for_each_entry_safe(sdp, n, &local->pending_sdreqs, node) { if (time_after(sdp->time, time)) continue; sdp->sap = LLCP_SDP_UNBOUND; hlist_del(&sdp->node); hlist_add_head(&sdp->node, &nl_sdres_list); } if (!hlist_empty(&local->pending_sdreqs)) mod_timer(&local->sdreq_timer, jiffies + msecs_to_jiffies(3 * local->remote_lto)); mutex_unlock(&local->sdreq_lock); if (!hlist_empty(&nl_sdres_list)) nfc_genl_llc_send_sdres(local->dev, &nl_sdres_list); } static void nfc_llcp_sdreq_timer(struct timer_list *t) { struct nfc_llcp_local *local = timer_container_of(local, t, sdreq_timer); schedule_work(&local->sdreq_timeout_work); } struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev) { struct nfc_llcp_local *local; struct nfc_llcp_local *res = NULL; spin_lock(&llcp_devices_lock); list_for_each_entry(local, &llcp_devices, list) if (local->dev == dev) { res = nfc_llcp_local_get(local); break; } spin_unlock(&llcp_devices_lock); return res; } static struct nfc_llcp_local *nfc_llcp_remove_local(struct nfc_dev *dev) { struct nfc_llcp_local *local, *tmp; spin_lock(&llcp_devices_lock); list_for_each_entry_safe(local, tmp, &llcp_devices, list) if (local->dev == dev) { list_del(&local->list); spin_unlock(&llcp_devices_lock); return local; } spin_unlock(&llcp_devices_lock); pr_warn("Shutting down device not found\n"); return NULL; } static char *wks[] = { NULL, NULL, /* SDP */ "urn:nfc:sn:ip", "urn:nfc:sn:obex", "urn:nfc:sn:snep", }; static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len) { int sap, num_wks; pr_debug("%s\n", service_name); if (service_name == NULL) return -EINVAL; num_wks = ARRAY_SIZE(wks); for (sap = 0; sap < num_wks; sap++) { if (wks[sap] == NULL) continue; if (strncmp(wks[sap], service_name, service_name_len) == 0) return sap; } return -EINVAL; } static struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, const u8 *sn, size_t sn_len, bool needref) { struct sock *sk; struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("sn %zd %p\n", sn_len, sn); if (sn == NULL || sn_len == 0) return NULL; read_lock(&local->sockets.lock); llcp_sock = NULL; sk_for_each(sk, &local->sockets.head) { tmp_sock = nfc_llcp_sock(sk); pr_debug("llcp sock %p\n", tmp_sock); if (tmp_sock->sk.sk_type == SOCK_STREAM && tmp_sock->sk.sk_state != LLCP_LISTEN) continue; if (tmp_sock->sk.sk_type == SOCK_DGRAM && tmp_sock->sk.sk_state != LLCP_BOUND) continue; if (tmp_sock->service_name == NULL || tmp_sock->service_name_len == 0) continue; if (tmp_sock->service_name_len != sn_len) continue; if (memcmp(sn, tmp_sock->service_name, sn_len) == 0) { llcp_sock = tmp_sock; if (needref) sock_hold(&llcp_sock->sk); break; } } read_unlock(&local->sockets.lock); pr_debug("Found llcp sock %p\n", llcp_sock); return llcp_sock; } u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, struct nfc_llcp_sock *sock) { mutex_lock(&local->sdp_lock); if (sock->service_name != NULL && sock->service_name_len > 0) { int ssap = nfc_llcp_wks_sap(sock->service_name, sock->service_name_len); if (ssap > 0) { pr_debug("WKS %d\n", ssap); /* This is a WKS, let's check if it's free */ if (test_bit(ssap, &local->local_wks)) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; } set_bit(ssap, &local->local_wks); mutex_unlock(&local->sdp_lock); return ssap; } /* * Check if there already is a non WKS socket bound * to this service name. */ if (nfc_llcp_sock_from_sn(local, sock->service_name, sock->service_name_len, false) != NULL) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; } mutex_unlock(&local->sdp_lock); return LLCP_SDP_UNBOUND; } else if (sock->ssap != 0 && sock->ssap < LLCP_WKS_NUM_SAP) { if (!test_bit(sock->ssap, &local->local_wks)) { set_bit(sock->ssap, &local->local_wks); mutex_unlock(&local->sdp_lock); return sock->ssap; } } mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; } u8 nfc_llcp_get_local_ssap(struct nfc_llcp_local *local) { u8 local_ssap; mutex_lock(&local->sdp_lock); local_ssap = find_first_zero_bit(&local->local_sap, LLCP_LOCAL_NUM_SAP); if (local_ssap == LLCP_LOCAL_NUM_SAP) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; } set_bit(local_ssap, &local->local_sap); mutex_unlock(&local->sdp_lock); return local_ssap + LLCP_LOCAL_SAP_OFFSET; } void nfc_llcp_put_ssap(struct nfc_llcp_local *local, u8 ssap) { u8 local_ssap; unsigned long *sdp; if (ssap < LLCP_WKS_NUM_SAP) { local_ssap = ssap; sdp = &local->local_wks; } else if (ssap < LLCP_LOCAL_NUM_SAP) { atomic_t *client_cnt; local_ssap = ssap - LLCP_WKS_NUM_SAP; sdp = &local->local_sdp; client_cnt = &local->local_sdp_cnt[local_ssap]; pr_debug("%d clients\n", atomic_read(client_cnt)); mutex_lock(&local->sdp_lock); if (atomic_dec_and_test(client_cnt)) { struct nfc_llcp_sock *l_sock; pr_debug("No more clients for SAP %d\n", ssap); clear_bit(local_ssap, sdp); /* Find the listening sock and set it back to UNBOUND */ l_sock = nfc_llcp_sock_get(local, ssap, LLCP_SAP_SDP); if (l_sock) { l_sock->ssap = LLCP_SDP_UNBOUND; nfc_llcp_sock_put(l_sock); } } mutex_unlock(&local->sdp_lock); return; } else if (ssap < LLCP_MAX_SAP) { local_ssap = ssap - LLCP_LOCAL_NUM_SAP; sdp = &local->local_sap; } else { return; } mutex_lock(&local->sdp_lock); clear_bit(local_ssap, sdp); mutex_unlock(&local->sdp_lock); } static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) { u8 ssap; mutex_lock(&local->sdp_lock); ssap = find_first_zero_bit(&local->local_sdp, LLCP_SDP_NUM_SAP); if (ssap == LLCP_SDP_NUM_SAP) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; } pr_debug("SDP ssap %d\n", LLCP_WKS_NUM_SAP + ssap); set_bit(ssap, &local->local_sdp); mutex_unlock(&local->sdp_lock); return LLCP_WKS_NUM_SAP + ssap; } static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { u8 *gb_cur, version, version_length; u8 lto_length, wks_length, miux_length; const u8 *version_tlv = NULL, *lto_tlv = NULL, *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; int ret = 0; version = LLCP_VERSION_11; version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version, 1, &version_length); if (!version_tlv) { ret = -ENOMEM; goto out; } gb_len += version_length; lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, <o_length); if (!lto_tlv) { ret = -ENOMEM; goto out; } gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length); if (!wks_tlv) { ret = -ENOMEM; goto out; } gb_len += wks_length; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_length); if (!miux_tlv) { ret = -ENOMEM; goto out; } gb_len += miux_length; gb_len += ARRAY_SIZE(llcp_magic); if (gb_len > NFC_MAX_GT_LEN) { ret = -EINVAL; goto out; } gb_cur = local->gb; memcpy(gb_cur, llcp_magic, ARRAY_SIZE(llcp_magic)); gb_cur += ARRAY_SIZE(llcp_magic); memcpy(gb_cur, version_tlv, version_length); gb_cur += version_length; memcpy(gb_cur, lto_tlv, lto_length); gb_cur += lto_length; memcpy(gb_cur, wks_tlv, wks_length); gb_cur += wks_length; memcpy(gb_cur, miux_tlv, miux_length); gb_cur += miux_length; local->gb_len = gb_len; out: kfree(version_tlv); kfree(lto_tlv); kfree(wks_tlv); kfree(miux_tlv); return ret; } u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) { struct nfc_llcp_local *local; local = nfc_llcp_find_local(dev); if (local == NULL) { *general_bytes_len = 0; return NULL; } nfc_llcp_build_gb(local); *general_bytes_len = local->gb_len; nfc_llcp_local_put(local); return local->gb; } int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; int err; if (gb_len < 3 || gb_len > NFC_MAX_GT_LEN) return -EINVAL; local = nfc_llcp_find_local(dev); if (local == NULL) { pr_err("No LLCP device\n"); return -ENODEV; } memset(local->remote_gb, 0, NFC_MAX_GT_LEN); memcpy(local->remote_gb, gb, gb_len); local->remote_gb_len = gb_len; if (memcmp(local->remote_gb, llcp_magic, 3)) { pr_err("MAC does not support LLCP\n"); err = -EINVAL; goto out; } err = nfc_llcp_parse_gb_tlv(local, &local->remote_gb[3], local->remote_gb_len - 3); out: nfc_llcp_local_put(local); return err; } static u8 nfc_llcp_dsap(const struct sk_buff *pdu) { return (pdu->data[0] & 0xfc) >> 2; } static u8 nfc_llcp_ptype(const struct sk_buff *pdu) { return ((pdu->data[0] & 0x03) << 2) | ((pdu->data[1] & 0xc0) >> 6); } static u8 nfc_llcp_ssap(const struct sk_buff *pdu) { return pdu->data[1] & 0x3f; } static u8 nfc_llcp_ns(const struct sk_buff *pdu) { return pdu->data[2] >> 4; } static u8 nfc_llcp_nr(const struct sk_buff *pdu) { return pdu->data[2] & 0xf; } static void nfc_llcp_set_nrns(struct nfc_llcp_sock *sock, struct sk_buff *pdu) { pdu->data[2] = (sock->send_n << 4) | (sock->recv_n); sock->send_n = (sock->send_n + 1) % 16; sock->recv_ack_n = (sock->recv_n - 1) % 16; } void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local, struct sk_buff *skb, u8 direction) { struct sk_buff *skb_copy = NULL, *nskb; struct sock *sk; u8 *data; read_lock(&local->raw_sockets.lock); sk_for_each(sk, &local->raw_sockets.head) { if (sk->sk_state != LLCP_BOUND) continue; if (skb_copy == NULL) { skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE, GFP_ATOMIC, true); if (skb_copy == NULL) continue; data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE); data[0] = local->dev ? local->dev->idx : 0xFF; data[1] = direction & 0x01; data[1] |= (RAW_PAYLOAD_LLCP << 1); } nskb = skb_clone(skb_copy, GFP_ATOMIC); if (!nskb) continue; if (sock_queue_rcv_skb(sk, nskb)) kfree_skb(nskb); } read_unlock(&local->raw_sockets.lock); kfree_skb(skb_copy); } static void nfc_llcp_tx_work(struct work_struct *work) { struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, tx_work); struct sk_buff *skb; struct sock *sk; struct nfc_llcp_sock *llcp_sock; skb = skb_dequeue(&local->tx_queue); if (skb != NULL) { sk = skb->sk; llcp_sock = nfc_llcp_sock(sk); if (llcp_sock == NULL && nfc_llcp_ptype(skb) == LLCP_PDU_I) { kfree_skb(skb); nfc_llcp_send_symm(local->dev); } else if (llcp_sock && !llcp_sock->remote_ready) { skb_queue_head(&local->tx_queue, skb); nfc_llcp_send_symm(local->dev); } else { struct sk_buff *copy_skb = NULL; u8 ptype = nfc_llcp_ptype(skb); int ret; pr_debug("Sending pending skb\n"); print_hex_dump_debug("LLCP Tx: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, true); if (ptype == LLCP_PDU_I) copy_skb = skb_copy(skb, GFP_ATOMIC); __net_timestamp(skb); nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX); ret = nfc_data_exchange(local->dev, local->target_idx, skb, nfc_llcp_recv, local); if (ret) { kfree_skb(copy_skb); goto out; } if (ptype == LLCP_PDU_I && copy_skb) skb_queue_tail(&llcp_sock->tx_pending_queue, copy_skb); } } else { nfc_llcp_send_symm(local->dev); } out: mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(2 * local->remote_lto)); } static struct nfc_llcp_sock *nfc_llcp_connecting_sock_get(struct nfc_llcp_local *local, u8 ssap) { struct sock *sk; struct nfc_llcp_sock *llcp_sock; read_lock(&local->connecting_sockets.lock); sk_for_each(sk, &local->connecting_sockets.head) { llcp_sock = nfc_llcp_sock(sk); if (llcp_sock->ssap == ssap) { sock_hold(&llcp_sock->sk); goto out; } } llcp_sock = NULL; out: read_unlock(&local->connecting_sockets.lock); return llcp_sock; } static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, const u8 *sn, size_t sn_len) { return nfc_llcp_sock_from_sn(local, sn, sn_len, true); } static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len) { u8 type, length; const u8 *tlv = &skb->data[2]; size_t tlv_array_len = skb->len - LLCP_HEADER_SIZE, offset = 0; while (offset < tlv_array_len) { type = tlv[0]; length = tlv[1]; pr_debug("type 0x%x length %d\n", type, length); if (type == LLCP_TLV_SN) { *sn_len = length; return &tlv[2]; } offset += length + 2; tlv += length + 2; } return NULL; } static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct nfc_llcp_ui_cb *ui_cb; u8 dsap, ssap; dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); ui_cb = nfc_llcp_ui_skb_cb(skb); ui_cb->dsap = dsap; ui_cb->ssap = ssap; pr_debug("%d %d\n", dsap, ssap); /* We're looking for a bound socket, not a client one */ llcp_sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP); if (llcp_sock == NULL || llcp_sock->sk.sk_type != SOCK_DGRAM) return; /* There is no sequence with UI frames */ skb_pull(skb, LLCP_HEADER_SIZE); if (!sock_queue_rcv_skb(&llcp_sock->sk, skb)) { /* * UI frames will be freed from the socket layer, so we * need to keep them alive until someone receives them. */ skb_get(skb); } else { pr_err("Receive queue is full\n"); } nfc_llcp_sock_put(llcp_sock); } static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, const struct sk_buff *skb) { struct sock *new_sk, *parent; struct nfc_llcp_sock *sock, *new_sock; u8 dsap, ssap, reason; dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); pr_debug("%d %d\n", dsap, ssap); if (dsap != LLCP_SAP_SDP) { sock = nfc_llcp_sock_get(local, dsap, LLCP_SAP_SDP); if (sock == NULL || sock->sk.sk_state != LLCP_LISTEN) { reason = LLCP_DM_NOBOUND; goto fail; } } else { const u8 *sn; size_t sn_len; sn = nfc_llcp_connect_sn(skb, &sn_len); if (sn == NULL) { reason = LLCP_DM_NOBOUND; goto fail; } pr_debug("Service name length %zu\n", sn_len); sock = nfc_llcp_sock_get_sn(local, sn, sn_len); if (sock == NULL) { reason = LLCP_DM_NOBOUND; goto fail; } } lock_sock(&sock->sk); parent = &sock->sk; if (sk_acceptq_is_full(parent)) { reason = LLCP_DM_REJ; release_sock(&sock->sk); sock_put(&sock->sk); goto fail; } if (sock->ssap == LLCP_SDP_UNBOUND) { u8 ssap = nfc_llcp_reserve_sdp_ssap(local); pr_debug("First client, reserving %d\n", ssap); if (ssap == LLCP_SAP_MAX) { reason = LLCP_DM_REJ; release_sock(&sock->sk); sock_put(&sock->sk); goto fail; } sock->ssap = ssap; } new_sk = nfc_llcp_sock_alloc(NULL, parent->sk_type, GFP_ATOMIC, 0); if (new_sk == NULL) { reason = LLCP_DM_REJ; release_sock(&sock->sk); sock_put(&sock->sk); goto fail; } new_sock = nfc_llcp_sock(new_sk); new_sock->local = nfc_llcp_local_get(local); if (!new_sock->local) { reason = LLCP_DM_REJ; sock_put(&new_sock->sk); release_sock(&sock->sk); sock_put(&sock->sk); goto fail; } new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; new_sock->dsap = ssap; new_sock->target_idx = local->target_idx; new_sock->parent = parent; new_sock->ssap = sock->ssap; if (sock->ssap < LLCP_LOCAL_NUM_SAP && sock->ssap >= LLCP_WKS_NUM_SAP) { atomic_t *client_count; pr_debug("reserved_ssap %d for %p\n", sock->ssap, new_sock); client_count = &local->local_sdp_cnt[sock->ssap - LLCP_WKS_NUM_SAP]; atomic_inc(client_count); new_sock->reserved_ssap = sock->ssap; } nfc_llcp_parse_connection_tlv(new_sock, &skb->data[LLCP_HEADER_SIZE], skb->len - LLCP_HEADER_SIZE); pr_debug("new sock %p sk %p\n", new_sock, &new_sock->sk); nfc_llcp_sock_link(&local->sockets, new_sk); nfc_llcp_accept_enqueue(&sock->sk, new_sk); nfc_get_device(local->dev->idx); new_sk->sk_state = LLCP_CONNECTED; /* Wake the listening processes */ parent->sk_data_ready(parent); /* Send CC */ nfc_llcp_send_cc(new_sock); release_sock(&sock->sk); sock_put(&sock->sk); return; fail: /* Send DM */ nfc_llcp_send_dm(local, dsap, ssap, reason); } int nfc_llcp_queue_i_frames(struct nfc_llcp_sock *sock) { int nr_frames = 0; struct nfc_llcp_local *local = sock->local; pr_debug("Remote ready %d tx queue len %d remote rw %d", sock->remote_ready, skb_queue_len(&sock->tx_pending_queue), sock->remote_rw); /* Try to queue some I frames for transmission */ while (sock->remote_ready && skb_queue_len(&sock->tx_pending_queue) < sock->remote_rw) { struct sk_buff *pdu; pdu = skb_dequeue(&sock->tx_queue); if (pdu == NULL) break; /* Update N(S)/N(R) */ nfc_llcp_set_nrns(sock, pdu); skb_queue_tail(&local->tx_queue, pdu); nr_frames++; } return nr_frames; } static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; u8 dsap, ssap, ptype, ns, nr; ptype = nfc_llcp_ptype(skb); dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); ns = nfc_llcp_ns(skb); nr = nfc_llcp_nr(skb); pr_debug("%d %d R %d S %d\n", dsap, ssap, nr, ns); llcp_sock = nfc_llcp_sock_get(local, dsap, ssap); if (llcp_sock == NULL) { nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN); return; } sk = &llcp_sock->sk; lock_sock(sk); if (sk->sk_state == LLCP_CLOSED) { release_sock(sk); nfc_llcp_sock_put(llcp_sock); } /* Pass the payload upstream */ if (ptype == LLCP_PDU_I) { pr_debug("I frame, queueing on %p\n", &llcp_sock->sk); if (ns == llcp_sock->recv_n) llcp_sock->recv_n = (llcp_sock->recv_n + 1) % 16; else pr_err("Received out of sequence I PDU\n"); skb_pull(skb, LLCP_HEADER_SIZE + LLCP_SEQUENCE_SIZE); if (!sock_queue_rcv_skb(&llcp_sock->sk, skb)) { /* * I frames will be freed from the socket layer, so we * need to keep them alive until someone receives them. */ skb_get(skb); } else { pr_err("Receive queue is full\n"); } } /* Remove skbs from the pending queue */ if (llcp_sock->send_ack_n != nr) { struct sk_buff *s, *tmp; u8 n; llcp_sock->send_ack_n = nr; /* Remove and free all skbs until ns == nr */ skb_queue_walk_safe(&llcp_sock->tx_pending_queue, s, tmp) { n = nfc_llcp_ns(s); skb_unlink(s, &llcp_sock->tx_pending_queue); kfree_skb(s); if (n == nr) break; } /* Re-queue the remaining skbs for transmission */ skb_queue_reverse_walk_safe(&llcp_sock->tx_pending_queue, s, tmp) { skb_unlink(s, &llcp_sock->tx_pending_queue); skb_queue_head(&local->tx_queue, s); } } if (ptype == LLCP_PDU_RR) llcp_sock->remote_ready = true; else if (ptype == LLCP_PDU_RNR) llcp_sock->remote_ready = false; if (nfc_llcp_queue_i_frames(llcp_sock) == 0 && ptype == LLCP_PDU_I) nfc_llcp_send_rr(llcp_sock); release_sock(sk); nfc_llcp_sock_put(llcp_sock); } static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; u8 dsap, ssap; dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); if ((dsap == 0) && (ssap == 0)) { pr_debug("Connection termination"); nfc_dep_link_down(local->dev); return; } llcp_sock = nfc_llcp_sock_get(local, dsap, ssap); if (llcp_sock == NULL) { nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN); return; } sk = &llcp_sock->sk; lock_sock(sk); nfc_llcp_socket_purge(llcp_sock); if (sk->sk_state == LLCP_CLOSED) { release_sock(sk); nfc_llcp_sock_put(llcp_sock); } if (sk->sk_state == LLCP_CONNECTED) { nfc_put_device(local->dev); sk->sk_state = LLCP_CLOSED; sk->sk_state_change(sk); } nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_DISC); release_sock(sk); nfc_llcp_sock_put(llcp_sock); } static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; u8 dsap, ssap; dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); llcp_sock = nfc_llcp_connecting_sock_get(local, dsap); if (llcp_sock == NULL) { pr_err("Invalid CC\n"); nfc_llcp_send_dm(local, dsap, ssap, LLCP_DM_NOCONN); return; } sk = &llcp_sock->sk; /* Unlink from connecting and link to the client array */ nfc_llcp_sock_unlink(&local->connecting_sockets, sk); nfc_llcp_sock_link(&local->sockets, sk); llcp_sock->dsap = ssap; nfc_llcp_parse_connection_tlv(llcp_sock, &skb->data[LLCP_HEADER_SIZE], skb->len - LLCP_HEADER_SIZE); sk->sk_state = LLCP_CONNECTED; sk->sk_state_change(sk); nfc_llcp_sock_put(llcp_sock); } static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; u8 dsap, ssap, reason; dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); reason = skb->data[2]; pr_debug("%d %d reason %d\n", ssap, dsap, reason); switch (reason) { case LLCP_DM_NOBOUND: case LLCP_DM_REJ: llcp_sock = nfc_llcp_connecting_sock_get(local, dsap); break; default: llcp_sock = nfc_llcp_sock_get(local, dsap, ssap); break; } if (llcp_sock == NULL) { pr_debug("Already closed\n"); return; } sk = &llcp_sock->sk; sk->sk_err = ENXIO; sk->sk_state = LLCP_CLOSED; sk->sk_state_change(sk); nfc_llcp_sock_put(llcp_sock); } static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; u8 dsap, ssap, type, length, tid, sap; const u8 *tlv; u16 tlv_len, offset; const char *service_name; size_t service_name_len; struct nfc_llcp_sdp_tlv *sdp; HLIST_HEAD(llc_sdres_list); size_t sdres_tlvs_len; HLIST_HEAD(nl_sdres_list); dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); pr_debug("%d %d\n", dsap, ssap); if (dsap != LLCP_SAP_SDP || ssap != LLCP_SAP_SDP) { pr_err("Wrong SNL SAP\n"); return; } tlv = &skb->data[LLCP_HEADER_SIZE]; tlv_len = skb->len - LLCP_HEADER_SIZE; offset = 0; sdres_tlvs_len = 0; while (offset < tlv_len) { type = tlv[0]; length = tlv[1]; switch (type) { case LLCP_TLV_SDREQ: tid = tlv[2]; service_name = (char *) &tlv[3]; service_name_len = length - 1; pr_debug("Looking for %.16s\n", service_name); if (service_name_len == strlen("urn:nfc:sn:sdp") && !strncmp(service_name, "urn:nfc:sn:sdp", service_name_len)) { sap = 1; goto add_snl; } llcp_sock = nfc_llcp_sock_from_sn(local, service_name, service_name_len, true); if (!llcp_sock) { sap = 0; goto add_snl; } /* * We found a socket but its ssap has not been reserved * yet. We need to assign it for good and send a reply. * The ssap will be freed when the socket is closed. */ if (llcp_sock->ssap == LLCP_SDP_UNBOUND) { atomic_t *client_count; sap = nfc_llcp_reserve_sdp_ssap(local); pr_debug("Reserving %d\n", sap); if (sap == LLCP_SAP_MAX) { sap = 0; nfc_llcp_sock_put(llcp_sock); goto add_snl; } client_count = &local->local_sdp_cnt[sap - LLCP_WKS_NUM_SAP]; atomic_inc(client_count); llcp_sock->ssap = sap; llcp_sock->reserved_ssap = sap; } else { sap = llcp_sock->ssap; } pr_debug("%p %d\n", llcp_sock, sap); nfc_llcp_sock_put(llcp_sock); add_snl: sdp = nfc_llcp_build_sdres_tlv(tid, sap); if (sdp == NULL) goto exit; sdres_tlvs_len += sdp->tlv_len; hlist_add_head(&sdp->node, &llc_sdres_list); break; case LLCP_TLV_SDRES: mutex_lock(&local->sdreq_lock); pr_debug("LLCP_TLV_SDRES: searching tid %d\n", tlv[2]); hlist_for_each_entry(sdp, &local->pending_sdreqs, node) { if (sdp->tid != tlv[2]) continue; sdp->sap = tlv[3]; pr_debug("Found: uri=%s, sap=%d\n", sdp->uri, sdp->sap); hlist_del(&sdp->node); hlist_add_head(&sdp->node, &nl_sdres_list); break; } mutex_unlock(&local->sdreq_lock); break; default: pr_err("Invalid SNL tlv value 0x%x\n", type); break; } offset += length + 2; tlv += length + 2; } exit: if (!hlist_empty(&nl_sdres_list)) nfc_genl_llc_send_sdres(local->dev, &nl_sdres_list); if (!hlist_empty(&llc_sdres_list)) nfc_llcp_send_snl_sdres(local, &llc_sdres_list, sdres_tlvs_len); } static void nfc_llcp_recv_agf(struct nfc_llcp_local *local, struct sk_buff *skb) { u8 ptype; u16 pdu_len; struct sk_buff *new_skb; if (skb->len <= LLCP_HEADER_SIZE) { pr_err("Malformed AGF PDU\n"); return; } skb_pull(skb, LLCP_HEADER_SIZE); while (skb->len > LLCP_AGF_PDU_HEADER_SIZE) { pdu_len = skb->data[0] << 8 | skb->data[1]; skb_pull(skb, LLCP_AGF_PDU_HEADER_SIZE); if (pdu_len < LLCP_HEADER_SIZE || pdu_len > skb->len) { pr_err("Malformed AGF PDU\n"); return; } ptype = nfc_llcp_ptype(skb); if (ptype == LLCP_PDU_SYMM || ptype == LLCP_PDU_AGF) goto next; new_skb = nfc_alloc_recv_skb(pdu_len, GFP_KERNEL); if (new_skb == NULL) { pr_err("Could not allocate PDU\n"); return; } skb_put_data(new_skb, skb->data, pdu_len); nfc_llcp_rx_skb(local, new_skb); kfree_skb(new_skb); next: skb_pull(skb, pdu_len); } } static void nfc_llcp_rx_skb(struct nfc_llcp_local *local, struct sk_buff *skb) { u8 dsap, ssap, ptype; ptype = nfc_llcp_ptype(skb); dsap = nfc_llcp_dsap(skb); ssap = nfc_llcp_ssap(skb); pr_debug("ptype 0x%x dsap 0x%x ssap 0x%x\n", ptype, dsap, ssap); if (ptype != LLCP_PDU_SYMM) print_hex_dump_debug("LLCP Rx: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, true); switch (ptype) { case LLCP_PDU_SYMM: pr_debug("SYMM\n"); break; case LLCP_PDU_UI: pr_debug("UI\n"); nfc_llcp_recv_ui(local, skb); break; case LLCP_PDU_CONNECT: pr_debug("CONNECT\n"); nfc_llcp_recv_connect(local, skb); break; case LLCP_PDU_DISC: pr_debug("DISC\n"); nfc_llcp_recv_disc(local, skb); break; case LLCP_PDU_CC: pr_debug("CC\n"); nfc_llcp_recv_cc(local, skb); break; case LLCP_PDU_DM: pr_debug("DM\n"); nfc_llcp_recv_dm(local, skb); break; case LLCP_PDU_SNL: pr_debug("SNL\n"); nfc_llcp_recv_snl(local, skb); break; case LLCP_PDU_I: case LLCP_PDU_RR: case LLCP_PDU_RNR: pr_debug("I frame\n"); nfc_llcp_recv_hdlc(local, skb); break; case LLCP_PDU_AGF: pr_debug("AGF frame\n"); nfc_llcp_recv_agf(local, skb); break; } } static void nfc_llcp_rx_work(struct work_struct *work) { struct nfc_llcp_local *local = container_of(work, struct nfc_llcp_local, rx_work); struct sk_buff *skb; skb = local->rx_pending; if (skb == NULL) { pr_debug("No pending SKB\n"); return; } __net_timestamp(skb); nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_RX); nfc_llcp_rx_skb(local, skb); schedule_work(&local->tx_work); kfree_skb(local->rx_pending); local->rx_pending = NULL; } static void __nfc_llcp_recv(struct nfc_llcp_local *local, struct sk_buff *skb) { local->rx_pending = skb; timer_delete(&local->link_timer); schedule_work(&local->rx_work); } void nfc_llcp_recv(void *data, struct sk_buff *skb, int err) { struct nfc_llcp_local *local = (struct nfc_llcp_local *) data; if (err < 0) { pr_err("LLCP PDU receive err %d\n", err); return; } __nfc_llcp_recv(local, skb); } int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb) { struct nfc_llcp_local *local; local = nfc_llcp_find_local(dev); if (local == NULL) { kfree_skb(skb); return -ENODEV; } __nfc_llcp_recv(local, skb); nfc_llcp_local_put(local); return 0; } void nfc_llcp_mac_is_down(struct nfc_dev *dev) { struct nfc_llcp_local *local; local = nfc_llcp_find_local(dev); if (local == NULL) return; local->remote_miu = LLCP_DEFAULT_MIU; local->remote_lto = LLCP_DEFAULT_LTO; /* Close and purge all existing sockets */ nfc_llcp_socket_release(local, true, 0); nfc_llcp_local_put(local); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode) { struct nfc_llcp_local *local; pr_debug("rf mode %d\n", rf_mode); local = nfc_llcp_find_local(dev); if (local == NULL) return; local->target_idx = target_idx; local->comm_mode = comm_mode; local->rf_mode = rf_mode; if (rf_mode == NFC_RF_INITIATOR) { pr_debug("Queueing Tx work\n"); schedule_work(&local->tx_work); } else { mod_timer(&local->link_timer, jiffies + msecs_to_jiffies(local->remote_lto)); } nfc_llcp_local_put(local); } int nfc_llcp_register_device(struct nfc_dev *ndev) { struct nfc_llcp_local *local; local = kzalloc(sizeof(struct nfc_llcp_local), GFP_KERNEL); if (local == NULL) return -ENOMEM; /* As we are going to initialize local's refcount, we need to get the * nfc_dev to avoid UAF, otherwise there is no point in continuing. * See nfc_llcp_local_get(). */ local->dev = nfc_get_device(ndev->idx); if (!local->dev) { kfree(local); return -ENODEV; } INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); timer_setup(&local->link_timer, nfc_llcp_symm_timer, 0); skb_queue_head_init(&local->tx_queue); INIT_WORK(&local->tx_work, nfc_llcp_tx_work); local->rx_pending = NULL; INIT_WORK(&local->rx_work, nfc_llcp_rx_work); INIT_WORK(&local->timeout_work, nfc_llcp_timeout_work); rwlock_init(&local->sockets.lock); rwlock_init(&local->connecting_sockets.lock); rwlock_init(&local->raw_sockets.lock); local->lto = 150; /* 1500 ms */ local->rw = LLCP_MAX_RW; local->miux = cpu_to_be16(LLCP_MAX_MIUX); local->local_wks = 0x1; /* LLC Link Management */ nfc_llcp_build_gb(local); local->remote_miu = LLCP_DEFAULT_MIU; local->remote_lto = LLCP_DEFAULT_LTO; mutex_init(&local->sdreq_lock); INIT_HLIST_HEAD(&local->pending_sdreqs); timer_setup(&local->sdreq_timer, nfc_llcp_sdreq_timer, 0); INIT_WORK(&local->sdreq_timeout_work, nfc_llcp_sdreq_timeout_work); spin_lock(&llcp_devices_lock); list_add(&local->list, &llcp_devices); spin_unlock(&llcp_devices_lock); return 0; } void nfc_llcp_unregister_device(struct nfc_dev *dev) { struct nfc_llcp_local *local = nfc_llcp_remove_local(dev); if (local == NULL) { pr_debug("No such device\n"); return; } local_cleanup(local); nfc_llcp_local_put(local); } int __init nfc_llcp_init(void) { return nfc_llcp_sock_init(); } void nfc_llcp_exit(void) { nfc_llcp_sock_exit(); } |
| 168 167 168 166 166 166 114 114 114 114 114 114 114 114 114 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | // SPDX-License-Identifier: GPL-2.0-only // Copyright (c) 2020 Facebook Inc. #include <linux/debugfs.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/udp_tunnel.h> #include "netdevsim.h" static int nsim_udp_tunnel_set_port(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti) { struct netdevsim *ns = netdev_priv(dev); int ret; ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error = 0; if (ns->udp_ports.sleep) msleep(ns->udp_ports.sleep); if (!ret) { if (ns->udp_ports.ports[table][entry]) { WARN(1, "entry already in use\n"); ret = -EBUSY; } else { ns->udp_ports.ports[table][entry] = be16_to_cpu(ti->port) << 16 | ti->type; } } netdev_info(dev, "set [%d, %d] type %d family %d port %d - %d\n", table, entry, ti->type, ti->sa_family, ntohs(ti->port), ret); return ret; } static int nsim_udp_tunnel_unset_port(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti) { struct netdevsim *ns = netdev_priv(dev); int ret; ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error = 0; if (ns->udp_ports.sleep) msleep(ns->udp_ports.sleep); if (!ret) { u32 val = be16_to_cpu(ti->port) << 16 | ti->type; if (val == ns->udp_ports.ports[table][entry]) { ns->udp_ports.ports[table][entry] = 0; } else { WARN(1, "entry not installed %x vs %x\n", val, ns->udp_ports.ports[table][entry]); ret = -ENOENT; } } netdev_info(dev, "unset [%d, %d] type %d family %d port %d - %d\n", table, entry, ti->type, ti->sa_family, ntohs(ti->port), ret); return ret; } static int nsim_udp_tunnel_sync_table(struct net_device *dev, unsigned int table) { struct netdevsim *ns = netdev_priv(dev); struct udp_tunnel_info ti; unsigned int i; int ret; ret = -ns->udp_ports.inject_error; ns->udp_ports.inject_error = 0; for (i = 0; i < NSIM_UDP_TUNNEL_N_PORTS; i++) { udp_tunnel_nic_get_port(dev, table, i, &ti); ns->udp_ports.ports[table][i] = be16_to_cpu(ti.port) << 16 | ti.type; } return ret; } static const struct udp_tunnel_nic_info nsim_udp_tunnel_info = { .set_port = nsim_udp_tunnel_set_port, .unset_port = nsim_udp_tunnel_unset_port, .sync_table = nsim_udp_tunnel_sync_table, .tables = { { .n_entries = NSIM_UDP_TUNNEL_N_PORTS, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, { .n_entries = NSIM_UDP_TUNNEL_N_PORTS, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE | UDP_TUNNEL_TYPE_VXLAN_GPE, }, }, }; static ssize_t nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct net_device *dev = file->private_data; struct netdevsim *ns = netdev_priv(dev); rtnl_lock(); if (dev->reg_state == NETREG_REGISTERED) { memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); udp_tunnel_nic_reset_ntf(dev); } rtnl_unlock(); return count; } static const struct file_operations nsim_udp_tunnels_info_reset_fops = { .open = simple_open, .write = nsim_udp_tunnels_info_reset_write, .llseek = generic_file_llseek, .owner = THIS_MODULE, }; int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); struct udp_tunnel_nic_info *info; if (nsim_dev->udp_ports.shared && nsim_dev->udp_ports.open_only) { dev_err(&nsim_dev->nsim_bus_dev->dev, "shared can't be used in conjunction with open_only\n"); return -EINVAL; } if (!nsim_dev->udp_ports.shared) ns->udp_ports.ports = ns->udp_ports.__ports; else ns->udp_ports.ports = nsim_dev->udp_ports.__ports; ns->udp_ports.ddir = debugfs_create_dir("udp_ports", ns->nsim_dev_port->ddir); debugfs_create_u32("inject_error", 0600, ns->udp_ports.ddir, &ns->udp_ports.inject_error); ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0]; ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS; debugfs_create_u32_array("table0", 0400, ns->udp_ports.ddir, &ns->udp_ports.dfs_ports[0]); ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1]; ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS; debugfs_create_u32_array("table1", 0400, ns->udp_ports.ddir, &ns->udp_ports.dfs_ports[1]); debugfs_create_file("reset", 0200, ns->udp_ports.ddir, dev, &nsim_udp_tunnels_info_reset_fops); /* Note: it's not normal to allocate the info struct like this! * Drivers are expected to use a static const one, here we're testing. */ info = kmemdup(&nsim_udp_tunnel_info, sizeof(nsim_udp_tunnel_info), GFP_KERNEL); if (!info) return -ENOMEM; ns->udp_ports.sleep = nsim_dev->udp_ports.sleep; if (nsim_dev->udp_ports.sync_all) { info->set_port = NULL; info->unset_port = NULL; } else { info->sync_table = NULL; } if (ns->udp_ports.sleep) info->flags |= UDP_TUNNEL_NIC_INFO_MAY_SLEEP; if (nsim_dev->udp_ports.open_only) info->flags |= UDP_TUNNEL_NIC_INFO_OPEN_ONLY; if (nsim_dev->udp_ports.ipv4_only) info->flags |= UDP_TUNNEL_NIC_INFO_IPV4_ONLY; if (nsim_dev->udp_ports.shared) info->shared = &nsim_dev->udp_ports.utn_shared; if (nsim_dev->udp_ports.static_iana_vxlan) info->flags |= UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN; dev->udp_tunnel_nic_info = info; return 0; } void nsim_udp_tunnels_info_destroy(struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); debugfs_remove_recursive(ns->udp_ports.ddir); kfree(dev->udp_tunnel_nic_info); dev->udp_tunnel_nic_info = NULL; } void nsim_udp_tunnels_debugfs_create(struct nsim_dev *nsim_dev) { debugfs_create_bool("udp_ports_sync_all", 0600, nsim_dev->ddir, &nsim_dev->udp_ports.sync_all); debugfs_create_bool("udp_ports_open_only", 0600, nsim_dev->ddir, &nsim_dev->udp_ports.open_only); debugfs_create_bool("udp_ports_ipv4_only", 0600, nsim_dev->ddir, &nsim_dev->udp_ports.ipv4_only); debugfs_create_bool("udp_ports_shared", 0600, nsim_dev->ddir, &nsim_dev->udp_ports.shared); debugfs_create_bool("udp_ports_static_iana_vxlan", 0600, nsim_dev->ddir, &nsim_dev->udp_ports.static_iana_vxlan); debugfs_create_u32("udp_ports_sleep", 0600, nsim_dev->ddir, &nsim_dev->udp_ports.sleep); } |
| 4 4 8 3 4 4 1 4 3 4 4 8 3 5 4 20 21 1 20 6 3 1 2 7 3 4 3 5 1 4 7 7 5 1 1 3 14 14 1 9 3 10 2 7 3 1 2 19 1 2 4 3 2 1 5 3 1 1 2 2 1 1 3 2 1 1 1 1 14 4 1 3 3 1 1 1 2 1 7 7 1 6 4 2 7 9 5 4 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 | /* 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 SCO sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/sco.h> static bool disable_esco; static const struct proto_ops sco_sock_ops; static struct bt_sock_list sco_sk_list = { .lock = __RW_LOCK_UNLOCKED(sco_sk_list.lock) }; /* ---- SCO connections ---- */ struct sco_conn { struct hci_conn *hcon; spinlock_t lock; struct sock *sk; struct delayed_work timeout_work; unsigned int mtu; struct kref ref; }; #define sco_conn_lock(c) spin_lock(&c->lock) #define sco_conn_unlock(c) spin_unlock(&c->lock) static void sco_sock_close(struct sock *sk); static void sco_sock_kill(struct sock *sk); /* ----- SCO socket info ----- */ #define sco_pi(sk) ((struct sco_pinfo *) sk) struct sco_pinfo { struct bt_sock bt; bdaddr_t src; bdaddr_t dst; __u32 flags; __u16 setting; struct bt_codec codec; struct sco_conn *conn; }; /* ---- SCO timers ---- */ #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) static void sco_conn_free(struct kref *ref) { struct sco_conn *conn = container_of(ref, struct sco_conn, ref); BT_DBG("conn %p", conn); if (conn->sk) sco_pi(conn->sk)->conn = NULL; if (conn->hcon) { conn->hcon->sco_data = NULL; hci_conn_drop(conn->hcon); } /* Ensure no more work items will run since hci_conn has been dropped */ disable_delayed_work_sync(&conn->timeout_work); kfree(conn); } static void sco_conn_put(struct sco_conn *conn) { if (!conn) return; BT_DBG("conn %p refcnt %d", conn, kref_read(&conn->ref)); kref_put(&conn->ref, sco_conn_free); } static struct sco_conn *sco_conn_hold(struct sco_conn *conn) { BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); kref_get(&conn->ref); return conn; } static struct sco_conn *sco_conn_hold_unless_zero(struct sco_conn *conn) { if (!conn) return NULL; BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); if (!kref_get_unless_zero(&conn->ref)) return NULL; return conn; } static struct sock *sco_sock_hold(struct sco_conn *conn) { if (!conn || !bt_sock_linked(&sco_sk_list, conn->sk)) return NULL; sock_hold(conn->sk); return conn->sk; } static void sco_sock_timeout(struct work_struct *work) { struct sco_conn *conn = container_of(work, struct sco_conn, timeout_work.work); struct sock *sk; conn = sco_conn_hold_unless_zero(conn); if (!conn) return; sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); sco_conn_put(conn); return; } sk = sco_sock_hold(conn); sco_conn_unlock(conn); sco_conn_put(conn); if (!sk) return; BT_DBG("sock %p state %d", sk, sk->sk_state); lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); release_sock(sk); sock_put(sk); } static void sco_sock_set_timer(struct sock *sk, long timeout) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout); } static void sco_sock_clear_timer(struct sock *sk) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d", sk, sk->sk_state); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); } /* ---- SCO connections ---- */ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) { struct sco_conn *conn = hcon->sco_data; conn = sco_conn_hold_unless_zero(conn); if (conn) { if (!conn->hcon) { sco_conn_lock(conn); conn->hcon = hcon; sco_conn_unlock(conn); } return conn; } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) return NULL; kref_init(&conn->ref); spin_lock_init(&conn->lock); INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout); hcon->sco_data = conn; conn->hcon = hcon; conn->mtu = hcon->mtu; if (hcon->mtu > 0) conn->mtu = hcon->mtu; else conn->mtu = 60; BT_DBG("hcon %p conn %p", hcon, conn); return conn; } /* Delete channel. * Must be called on the locked socket. */ static void sco_chan_del(struct sock *sk, int err) { struct sco_conn *conn; conn = sco_pi(sk)->conn; sco_pi(sk)->conn = NULL; BT_DBG("sk %p, conn %p, err %d", sk, conn, err); if (conn) { sco_conn_lock(conn); conn->sk = NULL; sco_conn_unlock(conn); sco_conn_put(conn); } sk->sk_state = BT_CLOSED; sk->sk_err = err; sk->sk_state_change(sk); sock_set_flag(sk, SOCK_ZAPPED); } static void sco_conn_del(struct hci_conn *hcon, int err) { struct sco_conn *conn = hcon->sco_data; struct sock *sk; conn = sco_conn_hold_unless_zero(conn); if (!conn) return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); sco_conn_lock(conn); sk = sco_sock_hold(conn); sco_conn_unlock(conn); sco_conn_put(conn); if (!sk) { sco_conn_put(conn); return; } /* Kill socket */ lock_sock(sk); sco_sock_clear_timer(sk); sco_chan_del(sk, err); release_sock(sk); sock_put(sk); } static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { BT_DBG("conn %p", conn); sco_pi(sk)->conn = conn; conn->sk = sk; if (parent) bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { int err = 0; sco_conn_lock(conn); if (conn->sk) err = -EBUSY; else __sco_chan_add(conn, sk, parent); sco_conn_unlock(conn); return err; } static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)) { err = -EOPNOTSUPP; goto unlock; } break; } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec, sk->sk_sndtimeo); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } lock_sock(sk); err = sco_chan_add(conn, sk, NULL); if (err) { release_sock(sk); goto unlock; } /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else { sk->sk_state = BT_CONNECT; sco_sock_set_timer(sk, sk->sk_sndtimeo); } release_sock(sk); unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int sco_send_frame(struct sock *sk, struct sk_buff *skb, const struct sockcm_cookie *sockc) { struct sco_conn *conn = sco_pi(sk)->conn; int len = skb->len; /* Check outgoing MTU */ if (len > conn->mtu) return -EINVAL; BT_DBG("sk %p len %d", sk, len); hci_setup_tx_timestamp(skb, 1, sockc); hci_send_sco(conn->hcon, skb); return len; } static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) { struct sock *sk; sco_conn_lock(conn); sk = conn->sk; sco_conn_unlock(conn); if (!sk) goto drop; BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; if (!sock_queue_rcv_skb(sk, skb)) return; drop: kfree_skb(skb); } /* -------- Socket interface ---------- */ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) { struct sock *sk; sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, ba)) return sk; } return NULL; } /* Find socket listening on source bdaddr. * Returns closest match. */ static struct sock *sco_get_sock_listen(bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; /* Exact match. */ if (!bacmp(&sco_pi(sk)->src, src)) break; /* Closest match */ if (!bacmp(&sco_pi(sk)->src, BDADDR_ANY)) sk1 = sk; } read_unlock(&sco_sk_list.lock); return sk ? sk : sk1; } static void sco_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); sco_conn_put(sco_pi(sk)->conn); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); } static void sco_sock_cleanup_listen(struct sock *parent) { struct sock *sk; BT_DBG("parent %p", parent); /* Close not yet accepted channels */ while ((sk = bt_accept_dequeue(parent, NULL))) { sco_sock_close(sk); sco_sock_kill(sk); } parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ static void sco_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); /* Kill poor orphan */ bt_sock_unlink(&sco_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } static void __sco_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: sco_sock_cleanup_listen(sk); break; case BT_CONNECTED: case BT_CONFIG: case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); break; default: sock_set_flag(sk, SOCK_ZAPPED); break; } } /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { lock_sock(sk); sco_sock_clear_timer(sk); __sco_sock_close(sk); release_sock(sk); } static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); if (parent) { sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } static struct proto sco_proto = { .name = "SCO", .owner = THIS_MODULE, .obj_size = sizeof(struct sco_pinfo) }; static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; sk = bt_sock_alloc(net, sock, &sco_proto, proto, prio, kern); if (!sk) return NULL; sk->sk_destruct = sco_sock_destruct; sk->sk_sndtimeo = SCO_CONN_TIMEOUT; sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; sco_pi(sk)->codec.id = BT_CODEC_CVSD; sco_pi(sk)->codec.cid = 0xffff; sco_pi(sk)->codec.vid = 0xffff; sco_pi(sk)->codec.data_path = 0x00; bt_sock_link(&sco_sk_list, sk); return sk; } static int sco_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET) return -ESOCKTNOSUPPORT; sock->ops = &sco_sock_ops; sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; sco_sock_init(sk, NULL); return 0; } static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err = 0; if (!addr || addr_len < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); lock_sock(sk); if (sk->sk_state != BT_OPEN) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } bacpy(&sco_pi(sk)->src, &sa->sco_bdaddr); sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err; BT_DBG("sk %p", sk); if (alen < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) return -EBADFD; if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); release_sock(sk); err = sco_connect(sk); if (err) return err; lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); release_sock(sk); return err; } static int sco_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; bdaddr_t *src = &sco_pi(sk)->src; int err = 0; BT_DBG("sk %p backlog %d", sk, backlog); lock_sock(sk); if (sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } write_lock(&sco_sk_list.lock); if (__sco_get_sock_listen_by_addr(src)) { err = -EADDRINUSE; goto unlock; } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = BT_LISTEN; unlock: write_unlock(&sco_sk_list.lock); done: release_sock(sk); return err; } static int sco_sock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; } ch = bt_accept_dequeue(sk, newsock); if (ch) break; if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); } remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; newsock->state = SS_CONNECTED; BT_DBG("new socket %p", ch); done: release_sock(sk); return err; } static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; if (peer) bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst); else bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src); return sizeof(struct sockaddr_sco); } static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb; struct sockcm_cookie sockc; int err; BT_DBG("sock %p, sk %p", sock, sk); err = sock_error(sk); if (err) return err; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; hci_sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (err) return err; } skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); if (IS_ERR(skb)) return PTR_ERR(skb); lock_sock(sk); if (sk->sk_state == BT_CONNECTED) err = sco_send_frame(sk, skb, &sockc); else err = -ENOTCONN; release_sock(sk); if (err < 0) kfree_skb(skb); return err; } static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) { struct hci_dev *hdev = conn->hdev; BT_DBG("conn %p", conn); conn->state = BT_CONFIG; if (!lmp_esco_capable(hdev)) { struct hci_cp_accept_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.role = 0x00; /* Ignored */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else { struct hci_cp_accept_sync_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.pkt_type = cpu_to_le16(conn->pkt_type); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.content_format = cpu_to_le16(setting); switch (setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (conn->pkt_type & ESCO_2EV3) cp.max_latency = cpu_to_le16(0x0008); else cp.max_latency = cpu_to_le16(0x000D); cp.retrans_effort = 0x02; break; case SCO_AIRMODE_CVSD: cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; default: /* use CVSD settings as fallback */ cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), &cp); } } static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sco_pinfo *pi = sco_pi(sk); if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_BLUETOOTH, BT_SCM_ERROR); lock_sock(sk); if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, pi->setting); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; } release_sock(sk); return bt_sock_recvmsg(sock, msg, len, flags); } static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; struct bt_voice voice; u32 opt; struct bt_codecs *codecs; struct hci_dev *hdev; __u8 buffer[255]; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); else clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; case BT_VOICE: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } voice.setting = sco_pi(sk)->setting; err = copy_safe_from_sockptr(&voice, sizeof(voice), optval, optlen); if (err) break; sco_pi(sk)->setting = voice.setting; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (enhanced_sync_conn_capable(hdev)) sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; break; } hci_dev_put(hdev); break; case BT_PKT_STATUS: err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_CODEC: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (!hci_dev_test_flag(hdev, HCI_OFFLOAD_CODECS_ENABLED)) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (!hdev->get_data_path_id) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (optlen < sizeof(struct bt_codecs) || optlen > sizeof(buffer)) { hci_dev_put(hdev); err = -EINVAL; break; } err = copy_struct_from_sockptr(buffer, sizeof(buffer), optval, optlen); if (err) { hci_dev_put(hdev); break; } codecs = (void *)buffer; if (codecs->num_codecs > 1) { hci_dev_put(hdev); err = -EINVAL; break; } sco_pi(sk)->codec = codecs->codecs[0]; hci_dev_put(hdev); break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; int err = 0; size_t len; BT_DBG("sk %p", sk); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case SCO_OPTIONS: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } opts.mtu = sco_pi(sk)->conn->mtu; BT_DBG("mtu %u", opts.mtu); len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; break; case SCO_CONNINFO: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_voice voice; u32 phys; int buf_len; struct codec_list *c; u8 num_codecs, i, __user *ptr; struct hci_dev *hdev; struct hci_codec_caps *caps; struct bt_codec codec; BT_DBG("sk %p", sk); if (level == SOL_SCO) return sco_sock_getsockopt_old(sock, optname, optval, optlen); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), (u32 __user *)optval)) err = -EFAULT; break; case BT_VOICE: voice.setting = sco_pi(sk)->setting; len = min_t(unsigned int, len, sizeof(voice)); if (copy_to_user(optval, (char *)&voice, len)) err = -EFAULT; break; case BT_PHY: if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; break; } phys = hci_conn_get_phy(sco_pi(sk)->conn->hcon); if (put_user(phys, (u32 __user *) optval)) err = -EFAULT; break; case BT_PKT_STATUS: if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), (int __user *)optval)) err = -EFAULT; break; case BT_SNDMTU: case BT_RCVMTU: if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; break; } if (put_user(sco_pi(sk)->conn->mtu, (u32 __user *)optval)) err = -EFAULT; break; case BT_CODEC: num_codecs = 0; buf_len = 0; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (!hci_dev_test_flag(hdev, HCI_OFFLOAD_CODECS_ENABLED)) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (!hdev->get_data_path_id) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } release_sock(sk); /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { if (c->transport != HCI_TRANSPORT_SCO_ESCO) continue; num_codecs++; for (i = 0, caps = c->caps; i < c->num_caps; i++) { buf_len += 1 + caps->len; caps = (void *)&caps->data[caps->len]; } buf_len += sizeof(struct bt_codec); } hci_dev_unlock(hdev); buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); return -EFAULT; } ptr += sizeof(num_codecs); /* Iterate all the codecs supported over SCO and populate * codec data */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { if (c->transport != HCI_TRANSPORT_SCO_ESCO) continue; codec.id = c->id; codec.cid = c->cid; codec.vid = c->vid; err = hdev->get_data_path_id(hdev, &codec.data_path); if (err < 0) break; codec.num_caps = c->num_caps; if (copy_to_user(ptr, &codec, sizeof(codec))) { err = -EFAULT; break; } ptr += sizeof(codec); /* find codec capabilities data length */ len = 0; for (i = 0, caps = c->caps; i < c->num_caps; i++) { len += 1 + caps->len; caps = (void *)&caps->data[caps->len]; } /* copy codec capabilities data */ if (len && copy_to_user(ptr, c->caps, len)) { err = -EFAULT; break; } ptr += len; } hci_dev_unlock(hdev); hci_dev_put(hdev); lock_sock(sk); if (!err && put_user(buf_len, optlen)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sock_hold(sk); lock_sock(sk); if (!sk->sk_shutdown) { sk->sk_shutdown = SHUTDOWN_MASK; sco_sock_clear_timer(sk); __sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); sock_put(sk); return err; } static int sco_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); } sock_orphan(sk); sco_sock_kill(sk); return err; } static void sco_conn_ready(struct sco_conn *conn) { struct sock *parent; struct sock *sk = conn->sk; BT_DBG("conn %p", conn); if (sk) { lock_sock(sk); sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); release_sock(sk); } else { sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); return; } parent = sco_get_sock_listen(&conn->hcon->src); if (!parent) { sco_conn_unlock(conn); return; } lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC, 0); if (!sk) { release_sock(parent); sco_conn_unlock(conn); return; } sco_sock_init(sk, parent); bacpy(&sco_pi(sk)->src, &conn->hcon->src); bacpy(&sco_pi(sk)->dst, &conn->hcon->dst); sco_conn_hold(conn); hci_conn_hold(conn->hcon); __sco_chan_add(conn, sk, parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent); release_sock(parent); sco_conn_unlock(conn); } } /* ----- SCO interface with lower layer (HCI) ----- */ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; int lm = 0; BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, &hdev->bdaddr) || !bacmp(&sco_pi(sk)->src, BDADDR_ANY)) { lm |= HCI_LM_ACCEPT; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; break; } } read_unlock(&sco_sk_list.lock); return lm; } static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; conn = sco_conn_add(hcon); if (conn) { sco_conn_ready(conn); sco_conn_put(conn); } } else sco_conn_del(hcon, bt_to_errno(status)); } static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); } void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) { struct sco_conn *conn = hcon->sco_data; if (!conn) goto drop; BT_DBG("conn %p len %u", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); return; } drop: kfree_skb(skb); } static struct hci_cb sco_cb = { .name = "SCO", .connect_cfm = sco_connect_cfm, .disconn_cfm = sco_disconn_cfm, }; static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &sco_pi(sk)->src, &sco_pi(sk)->dst, sk->sk_state); } read_unlock(&sco_sk_list.lock); return 0; } DEFINE_SHOW_ATTRIBUTE(sco_debugfs); static struct dentry *sco_debugfs; static const struct proto_ops sco_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = sco_sock_release, .bind = sco_sock_bind, .connect = sco_sock_connect, .listen = sco_sock_listen, .accept = sco_sock_accept, .getname = sco_sock_getname, .sendmsg = sco_sock_sendmsg, .recvmsg = sco_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .gettstamp = sock_gettstamp, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = sco_sock_shutdown, .setsockopt = sco_sock_setsockopt, .getsockopt = sco_sock_getsockopt }; static const struct net_proto_family sco_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = sco_sock_create, }; int __init sco_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_sco) > sizeof(struct sockaddr)); err = proto_register(&sco_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_SCO, &sco_sock_family_ops); if (err < 0) { BT_ERR("SCO socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "sco", &sco_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create SCO proc file"); bt_sock_unregister(BTPROTO_SCO); goto error; } BT_INFO("SCO socket layer initialized"); hci_register_cb(&sco_cb); if (IS_ERR_OR_NULL(bt_debugfs)) return 0; sco_debugfs = debugfs_create_file("sco", 0444, bt_debugfs, NULL, &sco_debugfs_fops); return 0; error: proto_unregister(&sco_proto); return err; } void sco_exit(void) { bt_procfs_cleanup(&init_net, "sco"); debugfs_remove(sco_debugfs); hci_unregister_cb(&sco_cb); bt_sock_unregister(BTPROTO_SCO); proto_unregister(&sco_proto); } module_param(disable_esco, bool, 0644); MODULE_PARM_DESC(disable_esco, "Disable eSCO connection creation"); |
| 30 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * i8042 keyboard and mouse controller driver for Linux * * Copyright (c) 1999-2004 Vojtech Pavlik */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/delay.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/serio.h> #include <linux/err.h> #include <linux/rcupdate.h> #include <linux/platform_device.h> #include <linux/i8042.h> #include <linux/slab.h> #include <linux/suspend.h> #include <linux/property.h> #include <asm/io.h> MODULE_AUTHOR("Vojtech Pavlik <vojtech@suse.cz>"); MODULE_DESCRIPTION("i8042 keyboard and mouse controller driver"); MODULE_LICENSE("GPL"); static bool i8042_nokbd; module_param_named(nokbd, i8042_nokbd, bool, 0); MODULE_PARM_DESC(nokbd, "Do not probe or use KBD port."); static bool i8042_noaux; module_param_named(noaux, i8042_noaux, bool, 0); MODULE_PARM_DESC(noaux, "Do not probe or use AUX (mouse) port."); static bool i8042_nomux; module_param_named(nomux, i8042_nomux, bool, 0); MODULE_PARM_DESC(nomux, "Do not check whether an active multiplexing controller is present."); static bool i8042_unlock; module_param_named(unlock, i8042_unlock, bool, 0); MODULE_PARM_DESC(unlock, "Ignore keyboard lock."); static bool i8042_probe_defer; module_param_named(probe_defer, i8042_probe_defer, bool, 0); MODULE_PARM_DESC(probe_defer, "Allow deferred probing."); enum i8042_controller_reset_mode { I8042_RESET_NEVER, I8042_RESET_ALWAYS, I8042_RESET_ON_S2RAM, #define I8042_RESET_DEFAULT I8042_RESET_ON_S2RAM }; static enum i8042_controller_reset_mode i8042_reset = I8042_RESET_DEFAULT; static int i8042_set_reset(const char *val, const struct kernel_param *kp) { enum i8042_controller_reset_mode *arg = kp->arg; int error; bool reset; if (val) { error = kstrtobool(val, &reset); if (error) return error; } else { reset = true; } *arg = reset ? I8042_RESET_ALWAYS : I8042_RESET_NEVER; return 0; } static const struct kernel_param_ops param_ops_reset_param = { .flags = KERNEL_PARAM_OPS_FL_NOARG, .set = i8042_set_reset, }; #define param_check_reset_param(name, p) \ __param_check(name, p, enum i8042_controller_reset_mode) module_param_named(reset, i8042_reset, reset_param, 0); MODULE_PARM_DESC(reset, "Reset controller on resume, cleanup or both"); static bool i8042_direct; module_param_named(direct, i8042_direct, bool, 0); MODULE_PARM_DESC(direct, "Put keyboard port into non-translated mode."); static bool i8042_dumbkbd; module_param_named(dumbkbd, i8042_dumbkbd, bool, 0); MODULE_PARM_DESC(dumbkbd, "Pretend that controller can only read data from keyboard"); static bool i8042_noloop; module_param_named(noloop, i8042_noloop, bool, 0); MODULE_PARM_DESC(noloop, "Disable the AUX Loopback command while probing for the AUX port"); static bool i8042_notimeout; module_param_named(notimeout, i8042_notimeout, bool, 0); MODULE_PARM_DESC(notimeout, "Ignore timeouts signalled by i8042"); static bool i8042_kbdreset; module_param_named(kbdreset, i8042_kbdreset, bool, 0); MODULE_PARM_DESC(kbdreset, "Reset device connected to KBD port"); #ifdef CONFIG_X86 static bool i8042_dritek; module_param_named(dritek, i8042_dritek, bool, 0); MODULE_PARM_DESC(dritek, "Force enable the Dritek keyboard extension"); #endif #ifdef CONFIG_PNP static bool i8042_nopnp; module_param_named(nopnp, i8042_nopnp, bool, 0); MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings"); #endif static bool i8042_forcenorestore; module_param_named(forcenorestore, i8042_forcenorestore, bool, 0); MODULE_PARM_DESC(forcenorestore, "Force no restore on s3 resume, copying s2idle behaviour"); #define DEBUG #ifdef DEBUG static bool i8042_debug; module_param_named(debug, i8042_debug, bool, 0600); MODULE_PARM_DESC(debug, "Turn i8042 debugging mode on and off"); static bool i8042_unmask_kbd_data; module_param_named(unmask_kbd_data, i8042_unmask_kbd_data, bool, 0600); MODULE_PARM_DESC(unmask_kbd_data, "Unconditional enable (may reveal sensitive data) of normally sanitize-filtered kbd data traffic debug log [pre-condition: i8042.debug=1 enabled]"); #endif static bool i8042_present; static bool i8042_bypass_aux_irq_test; static char i8042_kbd_firmware_id[128]; static char i8042_aux_firmware_id[128]; static struct fwnode_handle *i8042_kbd_fwnode; #include "i8042.h" /* * i8042_lock protects serialization between i8042_command and * the interrupt handler. */ static DEFINE_SPINLOCK(i8042_lock); /* * Writers to AUX and KBD ports as well as users issuing i8042_command * directly should acquire i8042_mutex (by means of calling * i8042_lock_chip() and i8042_unlock_chip() helpers) to ensure that * they do not disturb each other (unfortunately in many i8042 * implementations write to one of the ports will immediately abort * command that is being processed by another port). */ static DEFINE_MUTEX(i8042_mutex); struct i8042_port { struct serio *serio; int irq; bool exists; bool driver_bound; signed char mux; }; #define I8042_KBD_PORT_NO 0 #define I8042_AUX_PORT_NO 1 #define I8042_MUX_PORT_NO 2 #define I8042_NUM_PORTS (I8042_NUM_MUX_PORTS + 2) static struct i8042_port i8042_ports[I8042_NUM_PORTS]; static unsigned char i8042_initial_ctr; static unsigned char i8042_ctr; static bool i8042_mux_present; static bool i8042_kbd_irq_registered; static bool i8042_aux_irq_registered; static unsigned char i8042_suppress_kbd_ack; static struct platform_device *i8042_platform_device; static struct notifier_block i8042_kbd_bind_notifier_block; static bool i8042_handle_data(int irq); static i8042_filter_t i8042_platform_filter; static void *i8042_platform_filter_context; void i8042_lock_chip(void) { mutex_lock(&i8042_mutex); } EXPORT_SYMBOL(i8042_lock_chip); void i8042_unlock_chip(void) { mutex_unlock(&i8042_mutex); } EXPORT_SYMBOL(i8042_unlock_chip); int i8042_install_filter(i8042_filter_t filter, void *context) { guard(spinlock_irqsave)(&i8042_lock); if (i8042_platform_filter) return -EBUSY; i8042_platform_filter = filter; i8042_platform_filter_context = context; return 0; } EXPORT_SYMBOL(i8042_install_filter); int i8042_remove_filter(i8042_filter_t filter) { guard(spinlock_irqsave)(&i8042_lock); if (i8042_platform_filter != filter) return -EINVAL; i8042_platform_filter = NULL; i8042_platform_filter_context = NULL; return 0; } EXPORT_SYMBOL(i8042_remove_filter); /* * The i8042_wait_read() and i8042_wait_write functions wait for the i8042 to * be ready for reading values from it / writing values to it. * Called always with i8042_lock held. */ static int i8042_wait_read(void) { int i = 0; while ((~i8042_read_status() & I8042_STR_OBF) && (i < I8042_CTL_TIMEOUT)) { udelay(50); i++; } return -(i == I8042_CTL_TIMEOUT); } static int i8042_wait_write(void) { int i = 0; while ((i8042_read_status() & I8042_STR_IBF) && (i < I8042_CTL_TIMEOUT)) { udelay(50); i++; } return -(i == I8042_CTL_TIMEOUT); } /* * i8042_flush() flushes all data that may be in the keyboard and mouse buffers * of the i8042 down the toilet. */ static int i8042_flush(void) { unsigned char data, str; int count = 0; guard(spinlock_irqsave)(&i8042_lock); while ((str = i8042_read_status()) & I8042_STR_OBF) { if (count++ >= I8042_BUFFER_SIZE) return -EIO; udelay(50); data = i8042_read_data(); dbg("%02x <- i8042 (flush, %s)\n", data, str & I8042_STR_AUXDATA ? "aux" : "kbd"); } return 0; } /* * i8042_command() executes a command on the i8042. It also sends the input * parameter(s) of the commands to it, and receives the output value(s). The * parameters are to be stored in the param array, and the output is placed * into the same array. The number of the parameters and output values is * encoded in bits 8-11 of the command number. */ static int __i8042_command(unsigned char *param, int command) { int i, error; if (i8042_noloop && command == I8042_CMD_AUX_LOOP) return -1; error = i8042_wait_write(); if (error) return error; dbg("%02x -> i8042 (command)\n", command & 0xff); i8042_write_command(command & 0xff); for (i = 0; i < ((command >> 12) & 0xf); i++) { error = i8042_wait_write(); if (error) { dbg(" -- i8042 (wait write timeout)\n"); return error; } dbg("%02x -> i8042 (parameter)\n", param[i]); i8042_write_data(param[i]); } for (i = 0; i < ((command >> 8) & 0xf); i++) { error = i8042_wait_read(); if (error) { dbg(" -- i8042 (wait read timeout)\n"); return error; } if (command == I8042_CMD_AUX_LOOP && !(i8042_read_status() & I8042_STR_AUXDATA)) { dbg(" -- i8042 (auxerr)\n"); return -1; } param[i] = i8042_read_data(); dbg("%02x <- i8042 (return)\n", param[i]); } return 0; } int i8042_command(unsigned char *param, int command) { if (!i8042_present) return -1; guard(spinlock_irqsave)(&i8042_lock); return __i8042_command(param, command); } EXPORT_SYMBOL(i8042_command); /* * i8042_kbd_write() sends a byte out through the keyboard interface. */ static int i8042_kbd_write(struct serio *port, unsigned char c) { int error; guard(spinlock_irqsave)(&i8042_lock); error = i8042_wait_write(); if (error) return error; dbg("%02x -> i8042 (kbd-data)\n", c); i8042_write_data(c); return 0; } /* * i8042_aux_write() sends a byte out through the aux interface. */ static int i8042_aux_write(struct serio *serio, unsigned char c) { struct i8042_port *port = serio->port_data; return i8042_command(&c, port->mux == -1 ? I8042_CMD_AUX_SEND : I8042_CMD_MUX_SEND + port->mux); } /* * i8042_port_close attempts to clear AUX or KBD port state by disabling * and then re-enabling it. */ static void i8042_port_close(struct serio *serio) { int irq_bit; int disable_bit; const char *port_name; if (serio == i8042_ports[I8042_AUX_PORT_NO].serio) { irq_bit = I8042_CTR_AUXINT; disable_bit = I8042_CTR_AUXDIS; port_name = "AUX"; } else { irq_bit = I8042_CTR_KBDINT; disable_bit = I8042_CTR_KBDDIS; port_name = "KBD"; } i8042_ctr &= ~irq_bit; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) pr_warn("Can't write CTR while closing %s port\n", port_name); udelay(50); i8042_ctr &= ~disable_bit; i8042_ctr |= irq_bit; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) pr_err("Can't reactivate %s port\n", port_name); /* * See if there is any data appeared while we were messing with * port state. */ i8042_handle_data(0); } /* * i8042_start() is called by serio core when port is about to finish * registering. It will mark port as existing so i8042_interrupt can * start sending data through it. */ static int i8042_start(struct serio *serio) { struct i8042_port *port = serio->port_data; device_set_wakeup_capable(&serio->dev, true); /* * On platforms using suspend-to-idle, allow the keyboard to * wake up the system from sleep by enabling keyboard wakeups * by default. This is consistent with keyboard wakeup * behavior on many platforms using suspend-to-RAM (ACPI S3) * by default. */ if (pm_suspend_default_s2idle() && serio == i8042_ports[I8042_KBD_PORT_NO].serio) { device_set_wakeup_enable(&serio->dev, true); } guard(spinlock_irq)(&i8042_lock); port->exists = true; return 0; } /* * i8042_stop() marks serio port as non-existing so i8042_interrupt * will not try to send data to the port that is about to go away. * The function is called by serio core as part of unregister procedure. */ static void i8042_stop(struct serio *serio) { struct i8042_port *port = serio->port_data; scoped_guard(spinlock_irq, &i8042_lock) { port->exists = false; port->serio = NULL; } /* * We need to make sure that interrupt handler finishes using * our serio port before we return from this function. * We synchronize with both AUX and KBD IRQs because there is * a (very unlikely) chance that AUX IRQ is raised for KBD port * and vice versa. */ synchronize_irq(I8042_AUX_IRQ); synchronize_irq(I8042_KBD_IRQ); } /* * i8042_filter() filters out unwanted bytes from the input data stream. * It is called from i8042_interrupt and thus is running with interrupts * off and i8042_lock held. */ static bool i8042_filter(unsigned char data, unsigned char str, struct serio *serio) { if (unlikely(i8042_suppress_kbd_ack)) { if ((~str & I8042_STR_AUXDATA) && (data == 0xfa || data == 0xfe)) { i8042_suppress_kbd_ack--; dbg("Extra keyboard ACK - filtered out\n"); return true; } } if (!i8042_platform_filter) return false; if (i8042_platform_filter(data, str, serio, i8042_platform_filter_context)) { dbg("Filtered out by platform filter\n"); return true; } return false; } /* * i8042_handle_mux() handles case when data is coming from one of * the multiplexed ports. It would be simple if not for quirks with * handling errors: * * When MUXERR condition is signalled the data register can only contain * 0xfd, 0xfe or 0xff if implementation follows the spec. Unfortunately * it is not always the case. Some KBCs also report 0xfc when there is * nothing connected to the port while others sometimes get confused which * port the data came from and signal error leaving the data intact. They * _do not_ revert to legacy mode (actually I've never seen KBC reverting * to legacy mode yet, when we see one we'll add proper handling). * Anyway, we process 0xfc, 0xfd, 0xfe and 0xff as timeouts, and for the * rest assume that the data came from the same serio last byte * was transmitted (if transmission happened not too long ago). */ static int i8042_handle_mux(u8 str, u8 *data, unsigned int *dfl) { static unsigned long last_transmit; static unsigned long last_port; unsigned int mux_port; mux_port = (str >> 6) & 3; *dfl = 0; if (str & I8042_STR_MUXERR) { dbg("MUX error, status is %02x, data is %02x\n", str, *data); switch (*data) { default: if (time_before(jiffies, last_transmit + HZ/10)) { mux_port = last_port; break; } fallthrough; /* report timeout */ case 0xfc: case 0xfd: case 0xfe: *dfl = SERIO_TIMEOUT; *data = 0xfe; break; case 0xff: *dfl = SERIO_PARITY; *data = 0xfe; break; } } last_port = mux_port; last_transmit = jiffies; return I8042_MUX_PORT_NO + mux_port; } /* * i8042_handle_data() is the most important function in this driver - * it reads the data from the i8042, determines its destination serio * port, and sends received byte to the upper layers. * * Returns true if there was data waiting, false otherwise. */ static bool i8042_handle_data(int irq) { struct i8042_port *port; struct serio *serio; unsigned char str, data; unsigned int dfl; unsigned int port_no; bool filtered; scoped_guard(spinlock_irqsave, &i8042_lock) { str = i8042_read_status(); if (unlikely(~str & I8042_STR_OBF)) return false; data = i8042_read_data(); if (i8042_mux_present && (str & I8042_STR_AUXDATA)) { port_no = i8042_handle_mux(str, &data, &dfl); } else { dfl = (str & I8042_STR_PARITY) ? SERIO_PARITY : 0; if ((str & I8042_STR_TIMEOUT) && !i8042_notimeout) dfl |= SERIO_TIMEOUT; port_no = (str & I8042_STR_AUXDATA) ? I8042_AUX_PORT_NO : I8042_KBD_PORT_NO; } port = &i8042_ports[port_no]; serio = port->exists ? port->serio : NULL; filter_dbg(port->driver_bound, data, "<- i8042 (interrupt, %d, %d%s%s)\n", port_no, irq, dfl & SERIO_PARITY ? ", bad parity" : "", dfl & SERIO_TIMEOUT ? ", timeout" : ""); filtered = i8042_filter(data, str, serio); } if (likely(serio && !filtered)) serio_interrupt(serio, data, dfl); return true; } static irqreturn_t i8042_interrupt(int irq, void *dev_id) { if (unlikely(!i8042_handle_data(irq))) { dbg("Interrupt %d, without any data\n", irq); return IRQ_NONE; } return IRQ_HANDLED; } /* * i8042_enable_kbd_port enables keyboard port on chip */ static int i8042_enable_kbd_port(void) { i8042_ctr &= ~I8042_CTR_KBDDIS; i8042_ctr |= I8042_CTR_KBDINT; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { i8042_ctr &= ~I8042_CTR_KBDINT; i8042_ctr |= I8042_CTR_KBDDIS; pr_err("Failed to enable KBD port\n"); return -EIO; } return 0; } /* * i8042_enable_aux_port enables AUX (mouse) port on chip */ static int i8042_enable_aux_port(void) { i8042_ctr &= ~I8042_CTR_AUXDIS; i8042_ctr |= I8042_CTR_AUXINT; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { i8042_ctr &= ~I8042_CTR_AUXINT; i8042_ctr |= I8042_CTR_AUXDIS; pr_err("Failed to enable AUX port\n"); return -EIO; } return 0; } /* * i8042_enable_mux_ports enables 4 individual AUX ports after * the controller has been switched into Multiplexed mode */ static int i8042_enable_mux_ports(void) { unsigned char param; int i; for (i = 0; i < I8042_NUM_MUX_PORTS; i++) { i8042_command(¶m, I8042_CMD_MUX_PFX + i); i8042_command(¶m, I8042_CMD_AUX_ENABLE); } return i8042_enable_aux_port(); } /* * i8042_set_mux_mode checks whether the controller has an * active multiplexor and puts the chip into Multiplexed (true) * or Legacy (false) mode. */ static int i8042_set_mux_mode(bool multiplex, unsigned char *mux_version) { unsigned char param, val; /* * Get rid of bytes in the queue. */ i8042_flush(); /* * Internal loopback test - send three bytes, they should come back from the * mouse interface, the last should be version. */ param = val = 0xf0; if (i8042_command(¶m, I8042_CMD_AUX_LOOP) || param != val) return -1; param = val = multiplex ? 0x56 : 0xf6; if (i8042_command(¶m, I8042_CMD_AUX_LOOP) || param != val) return -1; param = val = multiplex ? 0xa4 : 0xa5; if (i8042_command(¶m, I8042_CMD_AUX_LOOP) || param == val) return -1; /* * Workaround for interference with USB Legacy emulation * that causes a v10.12 MUX to be found. */ if (param == 0xac) return -1; if (mux_version) *mux_version = param; return 0; } /* * i8042_check_mux() checks whether the controller supports the PS/2 Active * Multiplexing specification by Synaptics, Phoenix, Insyde and * LCS/Telegraphics. */ static int i8042_check_mux(void) { unsigned char mux_version; if (i8042_set_mux_mode(true, &mux_version)) return -1; pr_info("Detected active multiplexing controller, rev %d.%d\n", (mux_version >> 4) & 0xf, mux_version & 0xf); /* * Disable all muxed ports by disabling AUX. */ i8042_ctr |= I8042_CTR_AUXDIS; i8042_ctr &= ~I8042_CTR_AUXINT; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { pr_err("Failed to disable AUX port, can't use MUX\n"); return -EIO; } i8042_mux_present = true; return 0; } /* * The following is used to test AUX IRQ delivery. */ static struct completion i8042_aux_irq_delivered; static bool i8042_irq_being_tested; static irqreturn_t i8042_aux_test_irq(int irq, void *dev_id) { unsigned char str, data; guard(spinlock_irqsave)(&i8042_lock); str = i8042_read_status(); if (!(str & I8042_STR_OBF)) return IRQ_NONE; data = i8042_read_data(); dbg("%02x <- i8042 (aux_test_irq, %s)\n", data, str & I8042_STR_AUXDATA ? "aux" : "kbd"); if (i8042_irq_being_tested && data == 0xa5 && (str & I8042_STR_AUXDATA)) complete(&i8042_aux_irq_delivered); return IRQ_HANDLED; } /* * i8042_toggle_aux - enables or disables AUX port on i8042 via command and * verifies success by readinng CTR. Used when testing for presence of AUX * port. */ static int i8042_toggle_aux(bool on) { unsigned char param; int i; if (i8042_command(¶m, on ? I8042_CMD_AUX_ENABLE : I8042_CMD_AUX_DISABLE)) return -1; /* some chips need some time to set the I8042_CTR_AUXDIS bit */ for (i = 0; i < 100; i++) { udelay(50); if (i8042_command(¶m, I8042_CMD_CTL_RCTR)) return -1; if (!(param & I8042_CTR_AUXDIS) == on) return 0; } return -1; } /* * i8042_check_aux() applies as much paranoia as it can at detecting * the presence of an AUX interface. */ static int i8042_check_aux(void) { int retval = -1; bool irq_registered = false; bool aux_loop_broken = false; unsigned char param; /* * Get rid of bytes in the queue. */ i8042_flush(); /* * Internal loopback test - filters out AT-type i8042's. Unfortunately * SiS screwed up and their 5597 doesn't support the LOOP command even * though it has an AUX port. */ param = 0x5a; retval = i8042_command(¶m, I8042_CMD_AUX_LOOP); if (retval || param != 0x5a) { /* * External connection test - filters out AT-soldered PS/2 i8042's * 0x00 - no error, 0x01-0x03 - clock/data stuck, 0xff - general error * 0xfa - no error on some notebooks which ignore the spec * Because it's common for chipsets to return error on perfectly functioning * AUX ports, we test for this only when the LOOP command failed. */ if (i8042_command(¶m, I8042_CMD_AUX_TEST) || (param && param != 0xfa && param != 0xff)) return -1; /* * If AUX_LOOP completed without error but returned unexpected data * mark it as broken */ if (!retval) aux_loop_broken = true; } /* * Bit assignment test - filters out PS/2 i8042's in AT mode */ if (i8042_toggle_aux(false)) { pr_warn("Failed to disable AUX port, but continuing anyway... Is this a SiS?\n"); pr_warn("If AUX port is really absent please use the 'i8042.noaux' option\n"); } if (i8042_toggle_aux(true)) return -1; /* * Reset keyboard (needed on some laptops to successfully detect * touchpad, e.g., some Gigabyte laptop models with Elantech * touchpads). */ if (i8042_kbdreset) { pr_warn("Attempting to reset device connected to KBD port\n"); i8042_kbd_write(NULL, (unsigned char) 0xff); } /* * Test AUX IRQ delivery to make sure BIOS did not grab the IRQ and * used it for a PCI card or somethig else. */ if (i8042_noloop || i8042_bypass_aux_irq_test || aux_loop_broken) { /* * Without LOOP command we can't test AUX IRQ delivery. Assume the port * is working and hope we are right. */ retval = 0; goto out; } if (request_irq(I8042_AUX_IRQ, i8042_aux_test_irq, IRQF_SHARED, "i8042", i8042_platform_device)) goto out; irq_registered = true; if (i8042_enable_aux_port()) goto out; scoped_guard(spinlock_irqsave, &i8042_lock) { init_completion(&i8042_aux_irq_delivered); i8042_irq_being_tested = true; param = 0xa5; retval = __i8042_command(¶m, I8042_CMD_AUX_LOOP & 0xf0ff); if (retval) goto out; } if (wait_for_completion_timeout(&i8042_aux_irq_delivered, msecs_to_jiffies(250)) == 0) { /* * AUX IRQ was never delivered so we need to flush the controller to * get rid of the byte we put there; otherwise keyboard may not work. */ dbg(" -- i8042 (aux irq test timeout)\n"); i8042_flush(); retval = -1; } out: /* * Disable the interface. */ i8042_ctr |= I8042_CTR_AUXDIS; i8042_ctr &= ~I8042_CTR_AUXINT; if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) retval = -1; if (irq_registered) free_irq(I8042_AUX_IRQ, i8042_platform_device); return retval; } static int i8042_controller_check(void) { if (i8042_flush()) { pr_info("No controller found\n"); return -ENODEV; } return 0; } static int i8042_controller_selftest(void) { unsigned char param; int i = 0; /* * We try this 5 times; on some really fragile systems this does not * take the first time... */ do { if (i8042_command(¶m, I8042_CMD_CTL_TEST)) { pr_err("i8042 controller selftest timeout\n"); return -ENODEV; } if (param == I8042_RET_CTL_TEST) return 0; dbg("i8042 controller selftest: %#x != %#x\n", param, I8042_RET_CTL_TEST); msleep(50); } while (i++ < 5); #ifdef CONFIG_X86 /* * On x86, we don't fail entire i8042 initialization if controller * reset fails in hopes that keyboard port will still be functional * and user will still get a working keyboard. This is especially * important on netbooks. On other arches we trust hardware more. */ pr_info("giving up on controller selftest, continuing anyway...\n"); return 0; #else pr_err("i8042 controller selftest failed\n"); return -EIO; #endif } /* * i8042_controller_init initializes the i8042 controller, and, * most importantly, sets it into non-xlated mode if that's * desired. */ static int i8042_controller_init(void) { int n = 0; unsigned char ctr[2]; /* * Save the CTR for restore on unload / reboot. */ do { if (n >= 10) { pr_err("Unable to get stable CTR read\n"); return -EIO; } if (n != 0) udelay(50); if (i8042_command(&ctr[n++ % 2], I8042_CMD_CTL_RCTR)) { pr_err("Can't read CTR while initializing i8042\n"); return i8042_probe_defer ? -EPROBE_DEFER : -EIO; } } while (n < 2 || ctr[0] != ctr[1]); i8042_initial_ctr = i8042_ctr = ctr[0]; /* * Disable the keyboard interface and interrupt. */ i8042_ctr |= I8042_CTR_KBDDIS; i8042_ctr &= ~I8042_CTR_KBDINT; /* * Handle keylock. */ scoped_guard(spinlock_irqsave, &i8042_lock) { if (~i8042_read_status() & I8042_STR_KEYLOCK) { if (i8042_unlock) i8042_ctr |= I8042_CTR_IGNKEYLOCK; else pr_warn("Warning: Keylock active\n"); } } /* * If the chip is configured into nontranslated mode by the BIOS, don't * bother enabling translating and be happy. */ if (~i8042_ctr & I8042_CTR_XLATE) i8042_direct = true; /* * Set nontranslated mode for the kbd interface if requested by an option. * After this the kbd interface becomes a simple serial in/out, like the aux * interface is. We don't do this by default, since it can confuse notebook * BIOSes. */ if (i8042_direct) i8042_ctr &= ~I8042_CTR_XLATE; /* * Write CTR back. */ if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { pr_err("Can't write CTR while initializing i8042\n"); return -EIO; } /* * Flush whatever accumulated while we were disabling keyboard port. */ i8042_flush(); return 0; } /* * Reset the controller and reset CRT to the original value set by BIOS. */ static void i8042_controller_reset(bool s2r_wants_reset) { i8042_flush(); /* * Disable both KBD and AUX interfaces so they don't get in the way */ i8042_ctr |= I8042_CTR_KBDDIS | I8042_CTR_AUXDIS; i8042_ctr &= ~(I8042_CTR_KBDINT | I8042_CTR_AUXINT); if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) pr_warn("Can't write CTR while resetting\n"); /* * Disable MUX mode if present. */ if (i8042_mux_present) i8042_set_mux_mode(false, NULL); /* * Reset the controller if requested. */ if (i8042_reset == I8042_RESET_ALWAYS || (i8042_reset == I8042_RESET_ON_S2RAM && s2r_wants_reset)) { i8042_controller_selftest(); } /* * Restore the original control register setting. */ if (i8042_command(&i8042_initial_ctr, I8042_CMD_CTL_WCTR)) pr_warn("Can't restore CTR\n"); } /* * i8042_panic_blink() will turn the keyboard LEDs on or off and is called * when kernel panics. Flashing LEDs is useful for users running X who may * not see the console and will help distinguishing panics from "real" * lockups. * * Note that DELAY has a limit of 10ms so we will not get stuck here * waiting for KBC to free up even if KBD interrupt is off */ #define DELAY do { mdelay(1); if (++delay > 10) return delay; } while(0) static long i8042_panic_blink(int state) { long delay = 0; char led; led = (state) ? 0x01 | 0x04 : 0; while (i8042_read_status() & I8042_STR_IBF) DELAY; dbg("%02x -> i8042 (panic blink)\n", 0xed); i8042_suppress_kbd_ack = 2; i8042_write_data(0xed); /* set leds */ DELAY; while (i8042_read_status() & I8042_STR_IBF) DELAY; DELAY; dbg("%02x -> i8042 (panic blink)\n", led); i8042_write_data(led); DELAY; return delay; } #undef DELAY #ifdef CONFIG_X86 static void i8042_dritek_enable(void) { unsigned char param = 0x90; int error; error = i8042_command(¶m, 0x1059); if (error) pr_warn("Failed to enable DRITEK extension: %d\n", error); } #endif #ifdef CONFIG_PM /* * Here we try to reset everything back to a state we had * before suspending. */ static int i8042_controller_resume(bool s2r_wants_reset) { int error; error = i8042_controller_check(); if (error) return error; if (i8042_reset == I8042_RESET_ALWAYS || (i8042_reset == I8042_RESET_ON_S2RAM && s2r_wants_reset)) { error = i8042_controller_selftest(); if (error) return error; } /* * Restore original CTR value and disable all ports */ i8042_ctr = i8042_initial_ctr; if (i8042_direct) i8042_ctr &= ~I8042_CTR_XLATE; i8042_ctr |= I8042_CTR_AUXDIS | I8042_CTR_KBDDIS; i8042_ctr &= ~(I8042_CTR_AUXINT | I8042_CTR_KBDINT); if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { pr_warn("Can't write CTR to resume, retrying...\n"); msleep(50); if (i8042_command(&i8042_ctr, I8042_CMD_CTL_WCTR)) { pr_err("CTR write retry failed\n"); return -EIO; } } #ifdef CONFIG_X86 if (i8042_dritek) i8042_dritek_enable(); #endif if (i8042_mux_present) { if (i8042_set_mux_mode(true, NULL) || i8042_enable_mux_ports()) pr_warn("failed to resume active multiplexor, mouse won't work\n"); } else if (i8042_ports[I8042_AUX_PORT_NO].serio) { i8042_enable_aux_port(); } if (i8042_ports[I8042_KBD_PORT_NO].serio) i8042_enable_kbd_port(); i8042_handle_data(0); return 0; } /* * Here we try to restore the original BIOS settings to avoid * upsetting it. */ static int i8042_pm_suspend(struct device *dev) { int i; if (!i8042_forcenorestore && pm_suspend_via_firmware()) i8042_controller_reset(true); /* Set up serio interrupts for system wakeup. */ for (i = 0; i < I8042_NUM_PORTS; i++) { struct serio *serio = i8042_ports[i].serio; if (serio && device_may_wakeup(&serio->dev)) enable_irq_wake(i8042_ports[i].irq); } return 0; } static int i8042_pm_resume_noirq(struct device *dev) { if (i8042_forcenorestore || !pm_resume_via_firmware()) i8042_handle_data(0); return 0; } static int i8042_pm_resume(struct device *dev) { bool want_reset; int i; for (i = 0; i < I8042_NUM_PORTS; i++) { struct serio *serio = i8042_ports[i].serio; if (serio && device_may_wakeup(&serio->dev)) disable_irq_wake(i8042_ports[i].irq); } /* * If platform firmware was not going to be involved in suspend, we did * not restore the controller state to whatever it had been at boot * time, so we do not need to do anything. */ if (i8042_forcenorestore || !pm_suspend_via_firmware()) return 0; /* * We only need to reset the controller if we are resuming after handing * off control to the platform firmware, otherwise we can simply restore * the mode. */ want_reset = pm_resume_via_firmware(); return i8042_controller_resume(want_reset); } static int i8042_pm_thaw(struct device *dev) { i8042_handle_data(0); return 0; } static int i8042_pm_reset(struct device *dev) { i8042_controller_reset(false); return 0; } static int i8042_pm_restore(struct device *dev) { return i8042_controller_resume(false); } static const struct dev_pm_ops i8042_pm_ops = { .suspend = i8042_pm_suspend, .resume_noirq = i8042_pm_resume_noirq, .resume = i8042_pm_resume, .thaw = i8042_pm_thaw, .poweroff = i8042_pm_reset, .restore = i8042_pm_restore, }; #endif /* CONFIG_PM */ /* * We need to reset the 8042 back to original mode on system shutdown, * because otherwise BIOSes will be confused. */ static void i8042_shutdown(struct platform_device *dev) { i8042_controller_reset(false); } static int i8042_create_kbd_port(void) { struct serio *serio; struct i8042_port *port = &i8042_ports[I8042_KBD_PORT_NO]; serio = kzalloc(sizeof(*serio), GFP_KERNEL); if (!serio) return -ENOMEM; serio->id.type = i8042_direct ? SERIO_8042 : SERIO_8042_XL; serio->write = i8042_dumbkbd ? NULL : i8042_kbd_write; serio->start = i8042_start; serio->stop = i8042_stop; serio->close = i8042_port_close; serio->ps2_cmd_mutex = &i8042_mutex; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; strscpy(serio->name, "i8042 KBD port", sizeof(serio->name)); strscpy(serio->phys, I8042_KBD_PHYS_DESC, sizeof(serio->phys)); strscpy(serio->firmware_id, i8042_kbd_firmware_id, sizeof(serio->firmware_id)); set_primary_fwnode(&serio->dev, i8042_kbd_fwnode); port->serio = serio; port->irq = I8042_KBD_IRQ; return 0; } static int i8042_create_aux_port(int idx) { struct serio *serio; int port_no = idx < 0 ? I8042_AUX_PORT_NO : I8042_MUX_PORT_NO + idx; struct i8042_port *port = &i8042_ports[port_no]; serio = kzalloc(sizeof(*serio), GFP_KERNEL); if (!serio) return -ENOMEM; serio->id.type = SERIO_8042; serio->write = i8042_aux_write; serio->start = i8042_start; serio->stop = i8042_stop; serio->ps2_cmd_mutex = &i8042_mutex; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; if (idx < 0) { strscpy(serio->name, "i8042 AUX port", sizeof(serio->name)); strscpy(serio->phys, I8042_AUX_PHYS_DESC, sizeof(serio->phys)); strscpy(serio->firmware_id, i8042_aux_firmware_id, sizeof(serio->firmware_id)); serio->close = i8042_port_close; } else { snprintf(serio->name, sizeof(serio->name), "i8042 AUX%d port", idx); snprintf(serio->phys, sizeof(serio->phys), I8042_MUX_PHYS_DESC, idx + 1); strscpy(serio->firmware_id, i8042_aux_firmware_id, sizeof(serio->firmware_id)); } port->serio = serio; port->mux = idx; port->irq = I8042_AUX_IRQ; return 0; } static void i8042_free_kbd_port(void) { kfree(i8042_ports[I8042_KBD_PORT_NO].serio); i8042_ports[I8042_KBD_PORT_NO].serio = NULL; } static void i8042_free_aux_ports(void) { int i; for (i = I8042_AUX_PORT_NO; i < I8042_NUM_PORTS; i++) { kfree(i8042_ports[i].serio); i8042_ports[i].serio = NULL; } } static void i8042_register_ports(void) { int i; for (i = 0; i < I8042_NUM_PORTS; i++) { struct serio *serio = i8042_ports[i].serio; if (!serio) continue; printk(KERN_INFO "serio: %s at %#lx,%#lx irq %d\n", serio->name, (unsigned long) I8042_DATA_REG, (unsigned long) I8042_COMMAND_REG, i8042_ports[i].irq); serio_register_port(serio); } } static void i8042_unregister_ports(void) { int i; for (i = 0; i < I8042_NUM_PORTS; i++) { if (i8042_ports[i].serio) { serio_unregister_port(i8042_ports[i].serio); i8042_ports[i].serio = NULL; } } } static void i8042_free_irqs(void) { if (i8042_aux_irq_registered) free_irq(I8042_AUX_IRQ, i8042_platform_device); if (i8042_kbd_irq_registered) free_irq(I8042_KBD_IRQ, i8042_platform_device); i8042_aux_irq_registered = i8042_kbd_irq_registered = false; } static int i8042_setup_aux(void) { int (*aux_enable)(void); int error; int i; if (i8042_check_aux()) return -ENODEV; if (i8042_nomux || i8042_check_mux()) { error = i8042_create_aux_port(-1); if (error) goto err_free_ports; aux_enable = i8042_enable_aux_port; } else { for (i = 0; i < I8042_NUM_MUX_PORTS; i++) { error = i8042_create_aux_port(i); if (error) goto err_free_ports; } aux_enable = i8042_enable_mux_ports; } error = request_irq(I8042_AUX_IRQ, i8042_interrupt, IRQF_SHARED, "i8042", i8042_platform_device); if (error) goto err_free_ports; error = aux_enable(); if (error) goto err_free_irq; i8042_aux_irq_registered = true; return 0; err_free_irq: free_irq(I8042_AUX_IRQ, i8042_platform_device); err_free_ports: i8042_free_aux_ports(); return error; } static int i8042_setup_kbd(void) { int error; error = i8042_create_kbd_port(); if (error) return error; error = request_irq(I8042_KBD_IRQ, i8042_interrupt, IRQF_SHARED, "i8042", i8042_platform_device); if (error) goto err_free_port; error = i8042_enable_kbd_port(); if (error) goto err_free_irq; i8042_kbd_irq_registered = true; return 0; err_free_irq: free_irq(I8042_KBD_IRQ, i8042_platform_device); err_free_port: i8042_free_kbd_port(); return error; } static int i8042_kbd_bind_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct device *dev = data; struct serio *serio = to_serio_port(dev); struct i8042_port *port = serio->port_data; if (serio != i8042_ports[I8042_KBD_PORT_NO].serio) return 0; switch (action) { case BUS_NOTIFY_BOUND_DRIVER: port->driver_bound = true; break; case BUS_NOTIFY_UNBIND_DRIVER: port->driver_bound = false; break; } return 0; } static int i8042_probe(struct platform_device *dev) { int error; if (i8042_reset == I8042_RESET_ALWAYS) { error = i8042_controller_selftest(); if (error) return error; } error = i8042_controller_init(); if (error) return error; #ifdef CONFIG_X86 if (i8042_dritek) i8042_dritek_enable(); #endif if (!i8042_noaux) { error = i8042_setup_aux(); if (error && error != -ENODEV && error != -EBUSY) goto out_fail; } if (!i8042_nokbd) { error = i8042_setup_kbd(); if (error) goto out_fail; } /* * Ok, everything is ready, let's register all serio ports */ i8042_register_ports(); return 0; out_fail: i8042_free_aux_ports(); /* in case KBD failed but AUX not */ i8042_free_irqs(); i8042_controller_reset(false); return error; } static void i8042_remove(struct platform_device *dev) { i8042_unregister_ports(); i8042_free_irqs(); i8042_controller_reset(false); } static struct platform_driver i8042_driver = { .driver = { .name = "i8042", #ifdef CONFIG_PM .pm = &i8042_pm_ops, #endif }, .probe = i8042_probe, .remove = i8042_remove, .shutdown = i8042_shutdown, }; static struct notifier_block i8042_kbd_bind_notifier_block = { .notifier_call = i8042_kbd_bind_notifier, }; static int __init i8042_init(void) { int err; dbg_init(); err = i8042_platform_init(); if (err) return (err == -ENODEV) ? 0 : err; err = i8042_controller_check(); if (err) goto err_platform_exit; /* Set this before creating the dev to allow i8042_command to work right away */ i8042_present = true; err = platform_driver_register(&i8042_driver); if (err) goto err_platform_exit; i8042_platform_device = platform_device_alloc("i8042", -1); if (!i8042_platform_device) { err = -ENOMEM; goto err_unregister_driver; } err = platform_device_add(i8042_platform_device); if (err) goto err_free_device; bus_register_notifier(&serio_bus, &i8042_kbd_bind_notifier_block); panic_blink = i8042_panic_blink; return 0; err_free_device: platform_device_put(i8042_platform_device); err_unregister_driver: platform_driver_unregister(&i8042_driver); err_platform_exit: i8042_platform_exit(); return err; } static void __exit i8042_exit(void) { if (!i8042_present) return; platform_device_unregister(i8042_platform_device); platform_driver_unregister(&i8042_driver); i8042_platform_exit(); bus_unregister_notifier(&serio_bus, &i8042_kbd_bind_notifier_block); panic_blink = NULL; } module_init(i8042_init); module_exit(i8042_exit); |
| 10 3676 1280 5 8 6 2 8 8 6 5 3 2 1 4 2 1 1 1296 1280 127 12 12 748 748 748 4344 3781 1 1360 4239 4237 6 1 4 1 1 2492 1280 127 2492 747 4264 4262 2492 1405 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 | // SPDX-License-Identifier: GPL-2.0 /* * Management Component Transport Protocol (MCTP) - device implementation. * * Copyright (c) 2021 Code Construct * Copyright (c) 2021 Google */ #include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/mctp.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <net/addrconf.h> #include <net/netlink.h> #include <net/mctp.h> #include <net/mctpdevice.h> #include <net/sock.h> struct mctp_dump_cb { unsigned long ifindex; size_t a_idx; }; /* unlocked: caller must hold rcu_read_lock. * Returned mctp_dev has its refcount incremented, or NULL if unset. */ struct mctp_dev *__mctp_dev_get(const struct net_device *dev) { struct mctp_dev *mdev = rcu_dereference(dev->mctp_ptr); /* RCU guarantees that any mdev is still live. * Zero refcount implies a pending free, return NULL. */ if (mdev) if (!refcount_inc_not_zero(&mdev->refs)) return NULL; return mdev; } /* Returned mctp_dev does not have refcount incremented. The returned pointer * remains live while rtnl_lock is held, as that prevents mctp_unregister() */ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->mctp_ptr); } static int mctp_addrinfo_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(1) // IFA_LOCAL + nla_total_size(1) // IFA_ADDRESS ; } /* flag should be NLM_F_MULTI for dump calls */ static int mctp_fill_addrinfo(struct sk_buff *skb, struct mctp_dev *mdev, mctp_eid_t eid, int msg_type, u32 portid, u32 seq, int flag) { struct ifaddrmsg *hdr; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, msg_type, sizeof(*hdr), flag); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifa_family = AF_MCTP; hdr->ifa_prefixlen = 0; hdr->ifa_flags = 0; hdr->ifa_scope = 0; hdr->ifa_index = mdev->dev->ifindex; if (nla_put_u8(skb, IFA_LOCAL, eid)) goto cancel; if (nla_put_u8(skb, IFA_ADDRESS, eid)) goto cancel; nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; u32 portid, seq; int rc = 0; portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) { rc = mctp_fill_addrinfo(skb, mdev, mdev->addrs[mcb->a_idx], RTM_NEWADDR, portid, seq, NLM_F_MULTI); if (rc < 0) break; } return rc; } static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct mctp_dump_cb *mcb = (void *)cb->ctx; struct net *net = sock_net(skb->sk); struct net_device *dev; struct ifaddrmsg *hdr; struct mctp_dev *mdev; int ifindex = 0, rc; /* Filter by ifindex if a header is provided */ hdr = nlmsg_payload(cb->nlh, sizeof(*hdr)); if (hdr) { ifindex = hdr->ifa_index; } else { if (cb->strict_check) { NL_SET_ERR_MSG(cb->extack, "mctp: Invalid header for addr dump request"); return -EINVAL; } } rcu_read_lock(); for_each_netdev_dump(net, dev, mcb->ifindex) { if (ifindex && ifindex != dev->ifindex) continue; mdev = __mctp_dev_get(dev); if (!mdev) continue; rc = mctp_dump_dev_addrinfo(mdev, skb, cb); mctp_dev_put(mdev); if (rc < 0) break; mcb->a_idx = 0; } rcu_read_unlock(); return skb->len; } static void mctp_addr_notify(struct mctp_dev *mdev, mctp_eid_t eid, int msg_type, struct sk_buff *req_skb, struct nlmsghdr *req_nlh) { u32 portid = NETLINK_CB(req_skb).portid; struct net *net = dev_net(mdev->dev); struct sk_buff *skb; int rc = -ENOBUFS; skb = nlmsg_new(mctp_addrinfo_size(), GFP_KERNEL); if (!skb) goto out; rc = mctp_fill_addrinfo(skb, mdev, eid, msg_type, portid, req_nlh->nlmsg_seq, 0); if (rc < 0) { WARN_ON_ONCE(rc == -EMSGSIZE); goto out; } rtnl_notify(skb, net, portid, RTNLGRP_MCTP_IFADDR, req_nlh, GFP_KERNEL); return; out: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_MCTP_IFADDR, rc); } static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = { [IFA_ADDRESS] = { .type = NLA_U8 }, [IFA_LOCAL] = { .type = NLA_U8 }, }; static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX + 1]; struct net_device *dev; struct mctp_addr *addr; struct mctp_dev *mdev; struct ifaddrmsg *ifm; unsigned long flags; u8 *tmp_addrs; int rc; rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, extack); if (rc < 0) return rc; ifm = nlmsg_data(nlh); if (tb[IFA_LOCAL]) addr = nla_data(tb[IFA_LOCAL]); else if (tb[IFA_ADDRESS]) addr = nla_data(tb[IFA_ADDRESS]); else return -EINVAL; /* find device */ dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; if (!mctp_address_unicast(addr->s_addr)) return -EINVAL; /* Prevent duplicates. Under RTNL so don't need to lock for reading */ if (memchr(mdev->addrs, addr->s_addr, mdev->num_addrs)) return -EEXIST; tmp_addrs = kmalloc(mdev->num_addrs + 1, GFP_KERNEL); if (!tmp_addrs) return -ENOMEM; memcpy(tmp_addrs, mdev->addrs, mdev->num_addrs); tmp_addrs[mdev->num_addrs] = addr->s_addr; /* Lock to write */ spin_lock_irqsave(&mdev->addrs_lock, flags); mdev->num_addrs++; swap(mdev->addrs, tmp_addrs); spin_unlock_irqrestore(&mdev->addrs_lock, flags); kfree(tmp_addrs); mctp_addr_notify(mdev, addr->s_addr, RTM_NEWADDR, skb, nlh); mctp_route_add_local(mdev, addr->s_addr); return 0; } static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX + 1]; struct net_device *dev; struct mctp_addr *addr; struct mctp_dev *mdev; struct ifaddrmsg *ifm; unsigned long flags; u8 *pos; int rc; rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy, extack); if (rc < 0) return rc; ifm = nlmsg_data(nlh); if (tb[IFA_LOCAL]) addr = nla_data(tb[IFA_LOCAL]); else if (tb[IFA_ADDRESS]) addr = nla_data(tb[IFA_ADDRESS]); else return -EINVAL; /* find device */ dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) return -ENODEV; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODEV; pos = memchr(mdev->addrs, addr->s_addr, mdev->num_addrs); if (!pos) return -ENOENT; rc = mctp_route_remove_local(mdev, addr->s_addr); // we can ignore -ENOENT in the case a route was already removed if (rc < 0 && rc != -ENOENT) return rc; spin_lock_irqsave(&mdev->addrs_lock, flags); memmove(pos, pos + 1, mdev->num_addrs - 1 - (pos - mdev->addrs)); mdev->num_addrs--; spin_unlock_irqrestore(&mdev->addrs_lock, flags); mctp_addr_notify(mdev, addr->s_addr, RTM_DELADDR, skb, nlh); return 0; } void mctp_dev_hold(struct mctp_dev *mdev) { refcount_inc(&mdev->refs); } void mctp_dev_put(struct mctp_dev *mdev) { if (mdev && refcount_dec_and_test(&mdev->refs)) { kfree(mdev->addrs); dev_put(mdev->dev); kfree_rcu(mdev, rcu); } } void mctp_dev_release_key(struct mctp_dev *dev, struct mctp_sk_key *key) __must_hold(&key->lock) { if (!dev) return; if (dev->ops && dev->ops->release_flow) dev->ops->release_flow(dev, key); key->dev = NULL; mctp_dev_put(dev); } void mctp_dev_set_key(struct mctp_dev *dev, struct mctp_sk_key *key) __must_hold(&key->lock) { mctp_dev_hold(dev); key->dev = dev; } static struct mctp_dev *mctp_add_dev(struct net_device *dev) { struct mctp_dev *mdev; ASSERT_RTNL(); mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(-ENOMEM); spin_lock_init(&mdev->addrs_lock); mdev->net = mctp_default_net(dev_net(dev)); /* associate to net_device */ refcount_set(&mdev->refs, 1); rcu_assign_pointer(dev->mctp_ptr, mdev); dev_hold(dev); mdev->dev = dev; return mdev; } static int mctp_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct mctp_dev *mdev; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return -ENODATA; if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net)) return -EMSGSIZE; if (nla_put_u8(skb, IFLA_MCTP_PHYS_BINDING, mdev->binding)) return -EMSGSIZE; return 0; } static size_t mctp_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct mctp_dev *mdev; unsigned int ret; /* caller holds RCU */ mdev = __mctp_dev_get(dev); if (!mdev) return 0; ret = nla_total_size(4); /* IFLA_MCTP_NET */ ret += nla_total_size(1); /* IFLA_MCTP_PHYS_BINDING */ mctp_dev_put(mdev); return ret; } static const struct nla_policy ifla_af_mctp_policy[IFLA_MCTP_MAX + 1] = { [IFLA_MCTP_NET] = { .type = NLA_U32 }, }; static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_MCTP_MAX + 1]; struct mctp_dev *mdev; int rc; rc = nla_parse_nested(tb, IFLA_MCTP_MAX, attr, ifla_af_mctp_policy, NULL); if (rc) return rc; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return 0; if (tb[IFLA_MCTP_NET]) WRITE_ONCE(mdev->net, nla_get_u32(tb[IFLA_MCTP_NET])); return 0; } /* Matches netdev types that should have MCTP handling */ static bool mctp_known(struct net_device *dev) { /* only register specific types (inc. NONE for TUN devices) */ return dev->type == ARPHRD_MCTP || dev->type == ARPHRD_LOOPBACK || dev->type == ARPHRD_NONE; } static void mctp_unregister(struct net_device *dev) { struct mctp_dev *mdev; mdev = mctp_dev_get_rtnl(dev); if (!mdev) return; RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL); mctp_route_remove_dev(mdev); mctp_neigh_remove_dev(mdev); mctp_dev_put(mdev); } static int mctp_register(struct net_device *dev) { struct mctp_dev *mdev; /* Already registered? */ if (rtnl_dereference(dev->mctp_ptr)) return 0; /* only register specific types */ if (!mctp_known(dev)) return 0; mdev = mctp_add_dev(dev); if (IS_ERR(mdev)) return PTR_ERR(mdev); return 0; } static int mctp_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); int rc; switch (event) { case NETDEV_REGISTER: rc = mctp_register(dev); if (rc) return notifier_from_errno(rc); break; case NETDEV_UNREGISTER: mctp_unregister(dev); break; } return NOTIFY_OK; } static int mctp_register_netdevice(struct net_device *dev, const struct mctp_netdev_ops *ops, enum mctp_phys_binding binding) { struct mctp_dev *mdev; mdev = mctp_add_dev(dev); if (IS_ERR(mdev)) return PTR_ERR(mdev); mdev->ops = ops; mdev->binding = binding; return register_netdevice(dev); } int mctp_register_netdev(struct net_device *dev, const struct mctp_netdev_ops *ops, enum mctp_phys_binding binding) { int rc; rtnl_lock(); rc = mctp_register_netdevice(dev, ops, binding); rtnl_unlock(); return rc; } EXPORT_SYMBOL_GPL(mctp_register_netdev); void mctp_unregister_netdev(struct net_device *dev) { unregister_netdev(dev); } EXPORT_SYMBOL_GPL(mctp_unregister_netdev); static struct rtnl_af_ops mctp_af_ops = { .family = AF_MCTP, .fill_link_af = mctp_fill_link_af, .get_link_af_size = mctp_get_link_af_size, .set_link_af = mctp_set_link_af, }; static struct notifier_block mctp_dev_nb = { .notifier_call = mctp_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY, }; static const struct rtnl_msg_handler mctp_device_rtnl_msg_handlers[] = { {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_NEWADDR, .doit = mctp_rtm_newaddr}, {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_DELADDR, .doit = mctp_rtm_deladdr}, {.owner = THIS_MODULE, .protocol = PF_MCTP, .msgtype = RTM_GETADDR, .dumpit = mctp_dump_addrinfo}, }; int __init mctp_device_init(void) { int err; register_netdevice_notifier(&mctp_dev_nb); err = rtnl_af_register(&mctp_af_ops); if (err) goto err_notifier; err = rtnl_register_many(mctp_device_rtnl_msg_handlers); if (err) goto err_af; return 0; err_af: rtnl_af_unregister(&mctp_af_ops); err_notifier: unregister_netdevice_notifier(&mctp_dev_nb); return err; } void __exit mctp_device_exit(void) { rtnl_unregister_many(mctp_device_rtnl_msg_handlers); rtnl_af_unregister(&mctp_af_ops); unregister_netdevice_notifier(&mctp_dev_nb); } |
| 12 107 161 2 2 2 5 5 5 23 1 24 1 1 263 11 24 11 109 59 55 8 4 137 21 113 12 298 296 297 10 6 6 296 291 42 297 8 8 2 8 157 5 146 37 8 113 101 120 109 12 10 5 12 121 97 146 5 12 4 90 11 293 110 132 12 294 124 5 94 93 25 71 73 1 7 272 26 24 137 137 137 133 6 31 43 5 7 6 6 3 9 3 2 6 2 5 17 3 7 2 6 1 20 111 21 1 39 50 63 32 78 20 58 51 22 58 14 39 34 70 3 71 2 67 6 65 7 68 5 70 3 70 3 67 5 61 12 2 71 78 112 1 73 38 123 122 1 88 71 88 1 4 86 88 80 5 12 8 9 16 88 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/sch_netem.c Network emulator * * Many of the algorithms and ideas for this came from * NIST Net which is not copyrighted. * * Authors: Stephen Hemminger <shemminger@osdl.org> * Catalin(ux aka Dino) BOIE <catab at umbrella dot ro> */ #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/prandom.h> #include <linux/rtnetlink.h> #include <linux/reciprocal_div.h> #include <linux/rbtree.h> #include <net/gso.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/inet_ecn.h> #define VERSION "1.3" /* Network Emulation Queuing algorithm. ==================================== Sources: [1] Mark Carson, Darrin Santay, "NIST Net - A Linux-based Network Emulation Tool [2] Luigi Rizzo, DummyNet for FreeBSD ---------------------------------------------------------------- This started out as a simple way to delay outgoing packets to test TCP but has grown to include most of the functionality of a full blown network emulator like NISTnet. It can delay packets and add random jitter (and correlation). The random distribution can be loaded from a table as well to provide normal, Pareto, or experimental curves. Packet loss, duplication, and reordering can also be emulated. This qdisc does not do classification that can be handled in layering other disciplines. It does not need to do bandwidth control either since that can be handled by using token bucket or other rate control. Correlated Loss Generator models Added generation of correlated loss according to the "Gilbert-Elliot" model, a 4-state markov model. References: [1] NetemCLG Home http://netgroup.uniroma2.it/NetemCLG [2] S. Salsano, F. Ludovici, A. Ordine, "Definition of a general and intuitive loss model for packet networks and its implementation in the Netem module in the Linux kernel", available in [1] Authors: Stefano Salsano <stefano.salsano at uniroma2.it Fabio Ludovici <fabio.ludovici at yahoo.it> */ struct disttable { u32 size; s16 table[] __counted_by(size); }; struct netem_sched_data { /* internal t(ime)fifo qdisc uses t_root and sch->limit */ struct rb_root t_root; /* a linear queue; reduces rbtree rebalancing when jitter is low */ struct sk_buff *t_head; struct sk_buff *t_tail; u32 t_len; /* optional qdisc for classful handling (NULL at netem init) */ struct Qdisc *qdisc; struct qdisc_watchdog watchdog; s64 latency; s64 jitter; u32 loss; u32 ecn; u32 limit; u32 counter; u32 gap; u32 duplicate; u32 reorder; u32 corrupt; u64 rate; s32 packet_overhead; u32 cell_size; struct reciprocal_value cell_size_reciprocal; s32 cell_overhead; struct crndstate { u32 last; u32 rho; } delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor; struct prng { u64 seed; struct rnd_state prng_state; } prng; struct disttable *delay_dist; enum { CLG_RANDOM, CLG_4_STATES, CLG_GILB_ELL, } loss_model; enum { TX_IN_GAP_PERIOD = 1, TX_IN_BURST_PERIOD, LOST_IN_GAP_PERIOD, LOST_IN_BURST_PERIOD, } _4_state_model; enum { GOOD_STATE = 1, BAD_STATE, } GE_state_model; /* Correlated Loss Generation models */ struct clgstate { /* state of the Markov chain */ u8 state; /* 4-states and Gilbert-Elliot models */ u32 a1; /* p13 for 4-states or p for GE */ u32 a2; /* p31 for 4-states or r for GE */ u32 a3; /* p32 for 4-states or h for GE */ u32 a4; /* p14 for 4-states or 1-k for GE */ u32 a5; /* p23 used only in 4-states */ } clg; struct tc_netem_slot slot_config; struct slotstate { u64 slot_next; s32 packets_left; s32 bytes_left; } slot; struct disttable *slot_dist; }; /* Time stamp put into socket buffer control block * Only valid when skbs are in our internal t(ime)fifo queue. * * As skb->rbnode uses same storage than skb->next, skb->prev and skb->tstamp, * and skb->next & skb->prev are scratch space for a qdisc, * we save skb->tstamp value in skb->cb[] before destroying it. */ struct netem_skb_cb { u64 time_to_send; }; static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { /* we assume we can use skb next/prev/tstamp as storage for rb_node */ qdisc_cb_private_validate(skb, sizeof(struct netem_skb_cb)); return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data; } /* init_crandom - initialize correlated random number generator * Use entropy source for initial seed. */ static void init_crandom(struct crndstate *state, unsigned long rho) { state->rho = rho; state->last = get_random_u32(); } /* get_crandom - correlated random number generator * Next number depends on last value. * rho is scaled to avoid floating point. */ static u32 get_crandom(struct crndstate *state, struct prng *p) { u64 value, rho; unsigned long answer; struct rnd_state *s = &p->prng_state; if (!state || state->rho == 0) /* no correlation */ return prandom_u32_state(s); value = prandom_u32_state(s); rho = (u64)state->rho + 1; answer = (value * ((1ull<<32) - rho) + state->last * rho) >> 32; state->last = answer; return answer; } /* loss_4state - 4-state model loss generator * Generates losses according to the 4-state Markov chain adopted in * the GI (General and Intuitive) loss model. */ static bool loss_4state(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; u32 rnd = prandom_u32_state(&q->prng.prng_state); /* * Makes a comparison between rnd and the transition * probabilities outgoing from the current state, then decides the * next state and if the next packet has to be transmitted or lost. * The four states correspond to: * TX_IN_GAP_PERIOD => successfully transmitted packets within a gap period * LOST_IN_GAP_PERIOD => isolated losses within a gap period * LOST_IN_BURST_PERIOD => lost packets within a burst period * TX_IN_BURST_PERIOD => successfully transmitted packets within a burst period */ switch (clg->state) { case TX_IN_GAP_PERIOD: if (rnd < clg->a4) { clg->state = LOST_IN_GAP_PERIOD; return true; } else if (clg->a4 < rnd && rnd < clg->a1 + clg->a4) { clg->state = LOST_IN_BURST_PERIOD; return true; } else if (clg->a1 + clg->a4 < rnd) { clg->state = TX_IN_GAP_PERIOD; } break; case TX_IN_BURST_PERIOD: if (rnd < clg->a5) { clg->state = LOST_IN_BURST_PERIOD; return true; } else { clg->state = TX_IN_BURST_PERIOD; } break; case LOST_IN_BURST_PERIOD: if (rnd < clg->a3) clg->state = TX_IN_BURST_PERIOD; else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { clg->state = TX_IN_GAP_PERIOD; } else if (clg->a2 + clg->a3 < rnd) { clg->state = LOST_IN_BURST_PERIOD; return true; } break; case LOST_IN_GAP_PERIOD: clg->state = TX_IN_GAP_PERIOD; break; } return false; } /* loss_gilb_ell - Gilbert-Elliot model loss generator * Generates losses according to the Gilbert-Elliot loss model or * its special cases (Gilbert or Simple Gilbert) * * Makes a comparison between random number and the transition * probabilities outgoing from the current state, then decides the * next state. A second random number is extracted and the comparison * with the loss probability of the current state decides if the next * packet will be transmitted or lost. */ static bool loss_gilb_ell(struct netem_sched_data *q) { struct clgstate *clg = &q->clg; struct rnd_state *s = &q->prng.prng_state; switch (clg->state) { case GOOD_STATE: if (prandom_u32_state(s) < clg->a1) clg->state = BAD_STATE; if (prandom_u32_state(s) < clg->a4) return true; break; case BAD_STATE: if (prandom_u32_state(s) < clg->a2) clg->state = GOOD_STATE; if (prandom_u32_state(s) > clg->a3) return true; } return false; } static bool loss_event(struct netem_sched_data *q) { switch (q->loss_model) { case CLG_RANDOM: /* Random packet drop 0 => none, ~0 => all */ return q->loss && q->loss >= get_crandom(&q->loss_cor, &q->prng); case CLG_4_STATES: /* 4state loss model algorithm (used also for GI model) * Extracts a value from the markov 4 state loss generator, * if it is 1 drops a packet and if needed writes the event in * the kernel logs */ return loss_4state(q); case CLG_GILB_ELL: /* Gilbert-Elliot loss model algorithm * Extracts a value from the Gilbert-Elliot loss generator, * if it is 1 drops a packet and if needed writes the event in * the kernel logs */ return loss_gilb_ell(q); } return false; /* not reached */ } /* tabledist - return a pseudo-randomly distributed value with mean mu and * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. */ static s64 tabledist(s64 mu, s32 sigma, struct crndstate *state, struct prng *prng, const struct disttable *dist) { s64 x; long t; u32 rnd; if (sigma == 0) return mu; rnd = get_crandom(state, prng); /* default uniform distribution */ if (dist == NULL) return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; if (x >= 0) x += NETEM_DIST_SCALE/2; else x -= NETEM_DIST_SCALE/2; return x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu; } static u64 packet_time_ns(u64 len, const struct netem_sched_data *q) { len += q->packet_overhead; if (q->cell_size) { u32 cells = reciprocal_divide(len, q->cell_size_reciprocal); if (len > cells * q->cell_size) /* extra cell needed for remainder */ cells++; len = cells * (q->cell_size + q->cell_overhead); } return div64_u64(len * NSEC_PER_SEC, q->rate); } static void tfifo_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct rb_node *p = rb_first(&q->t_root); while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase(&skb->rbnode, &q->t_root); rtnl_kfree_skbs(skb, skb); } rtnl_kfree_skbs(q->t_head, q->t_tail); q->t_head = NULL; q->t_tail = NULL; q->t_len = 0; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); u64 tnext = netem_skb_cb(nskb)->time_to_send; if (!q->t_tail || tnext >= netem_skb_cb(q->t_tail)->time_to_send) { if (q->t_tail) q->t_tail->next = nskb; else q->t_head = nskb; q->t_tail = nskb; } else { struct rb_node **p = &q->t_root.rb_node, *parent = NULL; while (*p) { struct sk_buff *skb; parent = *p; skb = rb_to_skb(parent); if (tnext >= netem_skb_cb(skb)->time_to_send) p = &parent->rb_right; else p = &parent->rb_left; } rb_link_node(&nskb->rbnode, parent, p); rb_insert_color(&nskb->rbnode, &q->t_root); } q->t_len++; sch->q.qlen++; } /* netem can't properly corrupt a megapacket (like we get from GSO), so instead * when we statistically choose to corrupt one, we instead segment it, returning * the first packet to be corrupted, and re-enqueue the remaining frames */ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct sk_buff *segs; netdev_features_t features = netif_skb_features(skb); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { qdisc_drop(skb, sch, to_free); return NULL; } consume_skb(skb); return segs; } /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. * NET_XMIT_DROP: queue length didn't change. * NET_XMIT_SUCCESS: one skb was queued. */ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor, &q->prng)) ++count; /* Drop packet? */ if (loss_event(q)) { if (q->ecn && INET_ECN_set_ce(skb)) qdisc_qstats_drop(sch); /* mark packet */ else --count; } if (count == 0) { qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; } /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) */ if (q->latency || q->jitter || q->rate) skb_orphan_partial(skb); /* * If we need to duplicate packet, then clone it before * original is modified. */ if (count > 1) skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. * Make copy if needed since we are modifying * If packet is going to be hardware checksummed, then * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor, &q->prng)) { if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) goto finish_segs; segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; } skb = skb_unshare(skb, GFP_ATOMIC); if (unlikely(!skb)) { qdisc_qstats_drop(sch); goto finish_segs; } if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); skb = NULL; goto finish_segs; } skb->data[get_random_u32_below(skb_headlen(skb))] ^= 1<<get_random_u32_below(8); } if (unlikely(q->t_len >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); if (skb2) __qdisc_drop(skb2, to_free); return NET_XMIT_DROP; } /* * If doing duplication then re-insert at top of the * qdisc tree, since parent queuer expects that only one * skb will be queued. */ if (skb2) { struct Qdisc *rootq = qdisc_root_bh(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ q->duplicate = 0; rootq->enqueue(skb2, rootq, to_free); q->duplicate = dupsave; skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); cb = netem_skb_cb(skb); if (q->gap == 0 || /* not doing reordering */ q->counter < q->gap - 1 || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor, &q->prng)) { u64 now; s64 delay; delay = tabledist(q->latency, q->jitter, &q->delay_cor, &q->prng, q->delay_dist); now = ktime_get_ns(); if (q->rate) { struct netem_skb_cb *last = NULL; if (sch->q.tail) last = netem_skb_cb(sch->q.tail); if (q->t_root.rb_node) { struct sk_buff *t_skb; struct netem_skb_cb *t_last; t_skb = skb_rb_last(&q->t_root); t_last = netem_skb_cb(t_skb); if (!last || t_last->time_to_send > last->time_to_send) last = t_last; } if (q->t_tail) { struct netem_skb_cb *t_last = netem_skb_cb(q->t_tail); if (!last || t_last->time_to_send > last->time_to_send) last = t_last; } if (last) { /* * Last packet in queue is reference point (now), * calculate this time bonus and subtract * from delay. */ delay -= last->time_to_send - now; delay = max_t(s64, 0, delay); now = last->time_to_send; } delay += packet_time_ns(qdisc_pkt_len(skb), q); } cb->time_to_send = now + delay; ++q->counter; tfifo_enqueue(skb, sch); } else { /* * Do re-ordering by putting one out of N packets at the front * of the queue. */ cb->time_to_send = ktime_get_ns(); q->counter = 0; __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } finish_segs: if (skb2) __qdisc_drop(skb2, to_free); if (segs) { unsigned int len, last_len; int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); if (rc != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(rc)) qdisc_qstats_drop(sch); } else { nb++; len += last_len; } segs = skb2; } /* Parent qdiscs accounted for 1 skb of size @prev_len */ qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); } else if (!skb) { return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } /* Delay the next round with a new future slot with a * correct number of bytes and packets. */ static void get_slot_next(struct netem_sched_data *q, u64 now) { s64 next_delay; if (!q->slot_dist) next_delay = q->slot_config.min_delay + (get_random_u32() * (q->slot_config.max_delay - q->slot_config.min_delay) >> 32); else next_delay = tabledist(q->slot_config.dist_delay, (s32)(q->slot_config.dist_jitter), NULL, &q->prng, q->slot_dist); q->slot.slot_next = now + next_delay; q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; } static struct sk_buff *netem_peek(struct netem_sched_data *q) { struct sk_buff *skb = skb_rb_first(&q->t_root); u64 t1, t2; if (!skb) return q->t_head; if (!q->t_head) return skb; t1 = netem_skb_cb(skb)->time_to_send; t2 = netem_skb_cb(q->t_head)->time_to_send; if (t1 < t2) return skb; return q->t_head; } static void netem_erase_head(struct netem_sched_data *q, struct sk_buff *skb) { if (skb == q->t_head) { q->t_head = skb->next; if (!q->t_head) q->t_tail = NULL; } else { rb_erase(&skb->rbnode, &q->t_root); } } static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); if (skb) { deliver: qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } skb = netem_peek(q); if (skb) { u64 time_to_send; u64 now = ktime_get_ns(); /* if more time remaining? */ time_to_send = netem_skb_cb(skb)->time_to_send; if (q->slot.slot_next && q->slot.slot_next < time_to_send) get_slot_next(q, now); if (time_to_send <= now && q->slot.slot_next <= now) { netem_erase_head(q, skb); q->t_len--; skb->next = NULL; skb->prev = NULL; /* skb->dev shares skb->rbnode area, * we need to restore its value. */ skb->dev = qdisc_dev(sch); if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); if (q->slot.packets_left <= 0 || q->slot.bytes_left <= 0) get_slot_next(q, now); } if (q->qdisc) { unsigned int pkt_len = qdisc_pkt_len(skb); struct sk_buff *to_free = NULL; int err; err = qdisc_enqueue(skb, q->qdisc, &to_free); kfree_skb_list(to_free); if (err != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); sch->qstats.backlog -= pkt_len; sch->q.qlen--; qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } sch->q.qlen--; goto deliver; } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) { sch->q.qlen--; goto deliver; } } qdisc_watchdog_schedule_ns(&q->watchdog, max(time_to_send, q->slot.slot_next)); } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) { sch->q.qlen--; goto deliver; } } return NULL; } static void netem_reset(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_reset_queue(sch); tfifo_reset(sch); if (q->qdisc) qdisc_reset(q->qdisc); qdisc_watchdog_cancel(&q->watchdog); } static void dist_free(struct disttable *d) { kvfree(d); } /* * Distribution data is a variable size payload containing * signed 16 bit values. */ static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); struct disttable *d; int i; if (!n || n > NETEM_DIST_MAX) return -EINVAL; d = kvmalloc(struct_size(d, table, n), GFP_KERNEL); if (!d) return -ENOMEM; d->size = n; for (i = 0; i < n; i++) d->table[i] = data[i]; *tbl = d; return 0; } static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_slot *c = nla_data(attr); q->slot_config = *c; if (q->slot_config.max_packets == 0) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; /* capping dist_jitter to the range acceptable by tabledist() */ q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | q->slot_config.dist_jitter) q->slot.slot_next = ktime_get_ns(); else q->slot.slot_next = 0; } static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corr *c = nla_data(attr); init_crandom(&q->delay_cor, c->delay_corr); init_crandom(&q->loss_cor, c->loss_corr); init_crandom(&q->dup_cor, c->dup_corr); } static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_reorder *r = nla_data(attr); q->reorder = r->probability; init_crandom(&q->reorder_cor, r->correlation); } static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_corrupt *r = nla_data(attr); q->corrupt = r->probability; init_crandom(&q->corrupt_cor, r->correlation); } static void get_rate(struct netem_sched_data *q, const struct nlattr *attr) { const struct tc_netem_rate *r = nla_data(attr); q->rate = r->rate; q->packet_overhead = r->packet_overhead; q->cell_size = r->cell_size; q->cell_overhead = r->cell_overhead; if (q->cell_size) q->cell_size_reciprocal = reciprocal_value(q->cell_size); else q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr) { const struct nlattr *la; int rem; nla_for_each_nested(la, attr, rem) { u16 type = nla_type(la); switch (type) { case NETEM_LOSS_GI: { const struct tc_netem_gimodel *gi = nla_data(la); if (nla_len(la) < sizeof(struct tc_netem_gimodel)) { pr_info("netem: incorrect gi model size\n"); return -EINVAL; } q->loss_model = CLG_4_STATES; q->clg.state = TX_IN_GAP_PERIOD; q->clg.a1 = gi->p13; q->clg.a2 = gi->p31; q->clg.a3 = gi->p32; q->clg.a4 = gi->p14; q->clg.a5 = gi->p23; break; } case NETEM_LOSS_GE: { const struct tc_netem_gemodel *ge = nla_data(la); if (nla_len(la) < sizeof(struct tc_netem_gemodel)) { pr_info("netem: incorrect ge model size\n"); return -EINVAL; } q->loss_model = CLG_GILB_ELL; q->clg.state = GOOD_STATE; q->clg.a1 = ge->p; q->clg.a2 = ge->r; q->clg.a3 = ge->h; q->clg.a4 = ge->k1; break; } default: pr_info("netem: unknown loss type %u\n", type); return -EINVAL; } } return 0; } static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_CORR] = { .len = sizeof(struct tc_netem_corr) }, [TCA_NETEM_REORDER] = { .len = sizeof(struct tc_netem_reorder) }, [TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) }, [TCA_NETEM_RATE] = { .len = sizeof(struct tc_netem_rate) }, [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, [TCA_NETEM_ECN] = { .type = NLA_U32 }, [TCA_NETEM_RATE64] = { .type = NLA_U64 }, [TCA_NETEM_LATENCY64] = { .type = NLA_S64 }, [TCA_NETEM_JITTER64] = { .type = NLA_S64 }, [TCA_NETEM_SLOT] = { .len = sizeof(struct tc_netem_slot) }, [TCA_NETEM_PRNG_SEED] = { .type = NLA_U64 }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, const struct nla_policy *policy, int len) { int nested_len = nla_len(nla) - NLA_ALIGN(len); if (nested_len < 0) { pr_info("netem: invalid attributes len %d\n", nested_len); return -EINVAL; } if (nested_len >= nla_attr_size(0)) return nla_parse_deprecated(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy, NULL); memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } /* Parse netlink message to set options */ static int netem_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; struct disttable *delay_dist = NULL; struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; int ret; qopt = nla_data(opt); ret = parse_attr(tb, TCA_NETEM_MAX, opt, netem_policy, sizeof(*qopt)); if (ret < 0) return ret; if (tb[TCA_NETEM_DELAY_DIST]) { ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); if (ret) goto table_free; } if (tb[TCA_NETEM_SLOT_DIST]) { ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); if (ret) goto table_free; } sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; if (tb[TCA_NETEM_LOSS]) { ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; q->clg = old_clg; goto unlock; } } else { q->loss_model = CLG_RANDOM; } if (delay_dist) swap(q->delay_dist, delay_dist); if (slot_dist) swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); q->jitter = PSCHED_TICKS2NS(qopt->jitter); q->limit = qopt->limit; q->gap = qopt->gap; q->counter = 0; q->loss = qopt->loss; q->duplicate = qopt->duplicate; /* for compatibility with earlier versions. * if gap is set, need to assume 100% probability */ if (q->gap) q->reorder = ~0; if (tb[TCA_NETEM_CORR]) get_correlation(q, tb[TCA_NETEM_CORR]); if (tb[TCA_NETEM_REORDER]) get_reorder(q, tb[TCA_NETEM_REORDER]); if (tb[TCA_NETEM_CORRUPT]) get_corrupt(q, tb[TCA_NETEM_CORRUPT]); if (tb[TCA_NETEM_RATE]) get_rate(q, tb[TCA_NETEM_RATE]); if (tb[TCA_NETEM_RATE64]) q->rate = max_t(u64, q->rate, nla_get_u64(tb[TCA_NETEM_RATE64])); if (tb[TCA_NETEM_LATENCY64]) q->latency = nla_get_s64(tb[TCA_NETEM_LATENCY64]); if (tb[TCA_NETEM_JITTER64]) q->jitter = nla_get_s64(tb[TCA_NETEM_JITTER64]); if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); /* capping jitter to the range acceptable by tabledist() */ q->jitter = min_t(s64, abs(q->jitter), INT_MAX); if (tb[TCA_NETEM_PRNG_SEED]) q->prng.seed = nla_get_u64(tb[TCA_NETEM_PRNG_SEED]); else q->prng.seed = get_random_u64(); prandom_seed_state(&q->prng.prng_state, q->prng.seed); unlock: sch_tree_unlock(sch); table_free: dist_free(delay_dist); dist_free(slot_dist); return ret; } static int netem_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); int ret; qdisc_watchdog_init(&q->watchdog, sch); if (!opt) return -EINVAL; q->loss_model = CLG_RANDOM; ret = netem_change(sch, opt, extack); if (ret) pr_info("netem: change failed\n"); return ret; } static void netem_destroy(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) qdisc_put(q->qdisc); dist_free(q->delay_dist); dist_free(q->slot_dist); } static int dump_loss_model(const struct netem_sched_data *q, struct sk_buff *skb) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_NETEM_LOSS); if (nest == NULL) goto nla_put_failure; switch (q->loss_model) { case CLG_RANDOM: /* legacy loss model */ nla_nest_cancel(skb, nest); return 0; /* no data */ case CLG_4_STATES: { struct tc_netem_gimodel gi = { .p13 = q->clg.a1, .p31 = q->clg.a2, .p32 = q->clg.a3, .p14 = q->clg.a4, .p23 = q->clg.a5, }; if (nla_put(skb, NETEM_LOSS_GI, sizeof(gi), &gi)) goto nla_put_failure; break; } case CLG_GILB_ELL: { struct tc_netem_gemodel ge = { .p = q->clg.a1, .r = q->clg.a2, .h = q->clg.a3, .k1 = q->clg.a4, }; if (nla_put(skb, NETEM_LOSS_GE, sizeof(ge), &ge)) goto nla_put_failure; break; } } nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) { const struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *nla = (struct nlattr *) skb_tail_pointer(skb); struct tc_netem_qopt qopt; struct tc_netem_corr cor; struct tc_netem_reorder reorder; struct tc_netem_corrupt corrupt; struct tc_netem_rate rate; struct tc_netem_slot slot; qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency), UINT_MAX); qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter), UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; qopt.gap = q->gap; qopt.duplicate = q->duplicate; if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt)) goto nla_put_failure; if (nla_put(skb, TCA_NETEM_LATENCY64, sizeof(q->latency), &q->latency)) goto nla_put_failure; if (nla_put(skb, TCA_NETEM_JITTER64, sizeof(q->jitter), &q->jitter)) goto nla_put_failure; cor.delay_corr = q->delay_cor.rho; cor.loss_corr = q->loss_cor.rho; cor.dup_corr = q->dup_cor.rho; if (nla_put(skb, TCA_NETEM_CORR, sizeof(cor), &cor)) goto nla_put_failure; reorder.probability = q->reorder; reorder.correlation = q->reorder_cor.rho; if (nla_put(skb, TCA_NETEM_REORDER, sizeof(reorder), &reorder)) goto nla_put_failure; corrupt.probability = q->corrupt; corrupt.correlation = q->corrupt_cor.rho; if (nla_put(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt)) goto nla_put_failure; if (q->rate >= (1ULL << 32)) { if (nla_put_u64_64bit(skb, TCA_NETEM_RATE64, q->rate, TCA_NETEM_PAD)) goto nla_put_failure; rate.rate = ~0U; } else { rate.rate = q->rate; } rate.packet_overhead = q->packet_overhead; rate.cell_size = q->cell_size; rate.cell_overhead = q->cell_overhead; if (nla_put(skb, TCA_NETEM_RATE, sizeof(rate), &rate)) goto nla_put_failure; if (q->ecn && nla_put_u32(skb, TCA_NETEM_ECN, q->ecn)) goto nla_put_failure; if (dump_loss_model(q, skb) != 0) goto nla_put_failure; if (q->slot_config.min_delay | q->slot_config.max_delay | q->slot_config.dist_jitter) { slot = q->slot_config; if (slot.max_packets == INT_MAX) slot.max_packets = 0; if (slot.max_bytes == INT_MAX) slot.max_bytes = 0; if (nla_put(skb, TCA_NETEM_SLOT, sizeof(slot), &slot)) goto nla_put_failure; } if (nla_put_u64_64bit(skb, TCA_NETEM_PRNG_SEED, q->prng.seed, TCA_NETEM_PAD)) goto nla_put_failure; return nla_nest_end(skb, nla); nla_put_failure: nlmsg_trim(skb, nla); return -1; } static int netem_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct netem_sched_data *q = qdisc_priv(sch); if (cl != 1 || !q->qdisc) /* only one class */ return -ENOENT; tcm->tcm_handle |= TC_H_MIN(1); tcm->tcm_info = q->qdisc->handle; return 0; } static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct netem_sched_data *q = qdisc_priv(sch); *old = qdisc_replace(sch, new, &q->qdisc); return 0; } static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg) { struct netem_sched_data *q = qdisc_priv(sch); return q->qdisc; } static unsigned long netem_find(struct Qdisc *sch, u32 classid) { return 1; } static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker) { if (!walker->stop) { if (!tc_qdisc_stats_dump(sch, 1, walker)) return; } } static const struct Qdisc_class_ops netem_class_ops = { .graft = netem_graft, .leaf = netem_leaf, .find = netem_find, .walk = netem_walk, .dump = netem_dump_class, }; static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .id = "netem", .cl_ops = &netem_class_ops, .priv_size = sizeof(struct netem_sched_data), .enqueue = netem_enqueue, .dequeue = netem_dequeue, .peek = qdisc_peek_dequeued, .init = netem_init, .reset = netem_reset, .destroy = netem_destroy, .change = netem_change, .dump = netem_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("netem"); static int __init netem_module_init(void) { pr_info("netem: version " VERSION "\n"); return register_qdisc(&netem_qdisc_ops); } static void __exit netem_module_exit(void) { unregister_qdisc(&netem_qdisc_ops); } module_init(netem_module_init) module_exit(netem_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Network characteristics emulator qdisc"); |
| 1 1 1 1 1 1 1 114 114 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/trace.c * * Copyright (C) 2006 Linus Torvalds * * Trace facility for suspend/resume problems, when none of the * devices may be working. */ #define pr_fmt(fmt) "PM: " fmt #include <linux/pm-trace.h> #include <linux/export.h> #include <linux/rtc.h> #include <linux/suspend.h> #include <linux/init.h> #include <linux/mc146818rtc.h> #include "power.h" /* * Horrid, horrid, horrid. * * It turns out that the _only_ piece of hardware that actually * keeps its value across a hard boot (and, more importantly, the * POST init sequence) is literally the realtime clock. * * Never mind that an RTC chip has 114 bytes (and often a whole * other bank of an additional 128 bytes) of nice SRAM that is * _designed_ to keep data - the POST will clear it. So we literally * can just use the few bytes of actual time data, which means that * we're really limited. * * It means, for example, that we can't use the seconds at all * (since the time between the hang and the boot might be more * than a minute), and we'd better not depend on the low bits of * the minutes either. * * There are the wday fields etc, but I wouldn't guarantee those * are dependable either. And if the date isn't valid, either the * hw or POST will do strange things. * * So we're left with: * - year: 0-99 * - month: 0-11 * - day-of-month: 1-28 * - hour: 0-23 * - min: (0-30)*2 * * Giving us a total range of 0-16128000 (0xf61800), ie less * than 24 bits of actual data we can save across reboots. * * And if your box can't boot in less than three minutes, * you're screwed. * * Now, almost 24 bits of data is pitifully small, so we need * to be pretty dense if we want to use it for anything nice. * What we do is that instead of saving off nice readable info, * we save off _hashes_ of information that we can hopefully * regenerate after the reboot. * * In particular, this means that we might be unlucky, and hit * a case where we have a hash collision, and we end up not * being able to tell for certain exactly which case happened. * But that's hopefully unlikely. * * What we do is to take the bits we can fit, and split them * into three parts (16*997*1009 = 16095568), and use the values * for: * - 0-15: user-settable * - 0-996: file + line number * - 0-1008: device */ #define USERHASH (16) #define FILEHASH (997) #define DEVHASH (1009) #define DEVSEED (7919) bool pm_trace_rtc_abused __read_mostly; EXPORT_SYMBOL_GPL(pm_trace_rtc_abused); static unsigned int dev_hash_value; static int set_magic_time(unsigned int user, unsigned int file, unsigned int device) { unsigned int n = user + USERHASH*(file + FILEHASH*device); // June 7th, 2006 static struct rtc_time time = { .tm_sec = 0, .tm_min = 0, .tm_hour = 0, .tm_mday = 7, .tm_mon = 5, // June - counting from zero .tm_year = 106, .tm_wday = 3, .tm_yday = 160, .tm_isdst = 1 }; time.tm_year = (n % 100); n /= 100; time.tm_mon = (n % 12); n /= 12; time.tm_mday = (n % 28) + 1; n /= 28; time.tm_hour = (n % 24); n /= 24; time.tm_min = (n % 20) * 3; n /= 20; mc146818_set_time(&time); pm_trace_rtc_abused = true; return n ? -1 : 0; } static unsigned int read_magic_time(void) { struct rtc_time time; unsigned int val; if (mc146818_get_time(&time, 1000) < 0) { pr_err("Unable to read current time from RTC\n"); return 0; } pr_info("RTC time: %ptRt, date: %ptRd\n", &time, &time); val = time.tm_year; /* 100 years */ if (val > 100) val -= 100; val += time.tm_mon * 100; /* 12 months */ val += (time.tm_mday-1) * 100 * 12; /* 28 month-days */ val += time.tm_hour * 100 * 12 * 28; /* 24 hours */ val += (time.tm_min / 3) * 100 * 12 * 28 * 24; /* 20 3-minute intervals */ return val; } /* * This is just the sdbm hash function with a user-supplied * seed and final size parameter. */ static unsigned int hash_string(unsigned int seed, const char *data, unsigned int mod) { unsigned char c; while ((c = *data++) != 0) { seed = (seed << 16) + (seed << 6) - seed + c; } return seed % mod; } void set_trace_device(struct device *dev) { dev_hash_value = hash_string(DEVSEED, dev_name(dev), DEVHASH); } EXPORT_SYMBOL(set_trace_device); /* * We could just take the "tracedata" index into the .tracedata * section instead. Generating a hash of the data gives us a * chance to work across kernel versions, and perhaps more * importantly it also gives us valid/invalid check (ie we will * likely not give totally bogus reports - if the hash matches, * it's not any guarantee, but it's a high _likelihood_ that * the match is valid). */ void generate_pm_trace(const void *tracedata, unsigned int user) { unsigned short lineno = *(unsigned short *)tracedata; const char *file = *(const char **)(tracedata + 2); unsigned int user_hash_value, file_hash_value; if (!x86_platform.legacy.rtc) return; user_hash_value = user % USERHASH; file_hash_value = hash_string(lineno, file, FILEHASH); set_magic_time(user_hash_value, file_hash_value, dev_hash_value); } EXPORT_SYMBOL(generate_pm_trace); extern char __tracedata_start[], __tracedata_end[]; static int show_file_hash(unsigned int value) { int match; char *tracedata; match = 0; for (tracedata = __tracedata_start ; tracedata < __tracedata_end ; tracedata += 2 + sizeof(unsigned long)) { unsigned short lineno = *(unsigned short *)tracedata; const char *file = *(const char **)(tracedata + 2); unsigned int hash = hash_string(lineno, file, FILEHASH); if (hash != value) continue; pr_info(" hash matches %s:%u\n", file, lineno); match++; } return match; } static int show_dev_hash(unsigned int value) { int match = 0; struct list_head *entry; device_pm_lock(); entry = dpm_list.prev; while (entry != &dpm_list) { struct device * dev = to_device(entry); unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH); if (hash == value) { dev_info(dev, "hash matches\n"); match++; } entry = entry->prev; } device_pm_unlock(); return match; } static unsigned int hash_value_early_read; int show_trace_dev_match(char *buf, size_t size) { unsigned int value = hash_value_early_read / (USERHASH * FILEHASH); int ret = 0; struct list_head *entry; /* * It's possible that multiple devices will match the hash and we can't * tell which is the culprit, so it's best to output them all. */ device_pm_lock(); entry = dpm_list.prev; while (size && entry != &dpm_list) { struct device *dev = to_device(entry); unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH); if (hash == value) { int len = snprintf(buf, size, "%s\n", dev_driver_string(dev)); if (len > size) len = size; buf += len; ret += len; size -= len; } entry = entry->prev; } device_pm_unlock(); return ret; } static int pm_trace_notify(struct notifier_block *nb, unsigned long mode, void *_unused) { switch (mode) { case PM_POST_HIBERNATION: case PM_POST_SUSPEND: if (pm_trace_rtc_abused) { pm_trace_rtc_abused = false; pr_warn("Possible incorrect RTC due to pm_trace, please use 'ntpdate' or 'rdate' to reset it.\n"); } break; default: break; } return 0; } static struct notifier_block pm_trace_nb = { .notifier_call = pm_trace_notify, }; static int __init early_resume_init(void) { if (!x86_platform.legacy.rtc) return 0; hash_value_early_read = read_magic_time(); register_pm_notifier(&pm_trace_nb); return 0; } static int __init late_resume_init(void) { unsigned int val = hash_value_early_read; unsigned int user, file, dev; if (!x86_platform.legacy.rtc) return 0; user = val % USERHASH; val = val / USERHASH; file = val % FILEHASH; val = val / FILEHASH; dev = val /* % DEVHASH */; pr_info(" Magic number: %d:%d:%d\n", user, file, dev); show_file_hash(file); show_dev_hash(dev); return 0; } core_initcall(early_resume_init); late_initcall(late_resume_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 | // SPDX-License-Identifier: GPL-2.0-only /* * Architecture specific (i386/x86_64) functions for kexec based crash dumps. * * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) * * Copyright (C) IBM Corporation, 2004. All rights reserved. * Copyright (C) Red Hat Inc., 2014. All rights reserved. * Authors: * Vivek Goyal <vgoyal@redhat.com> * */ #define pr_fmt(fmt) "kexec: " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/smp.h> #include <linux/reboot.h> #include <linux/kexec.h> #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/memblock.h> #include <asm/bootparam.h> #include <asm/processor.h> #include <asm/hardirq.h> #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/e820/types.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> #include <asm/sev.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { struct boot_params *params; /* Type of memory */ unsigned int type; }; #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { crash_save_cpu(regs, cpu); /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); kdump_sev_callback(); disable_local_APIC(); } void kdump_nmi_shootdown_cpus(void) { nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); } /* Override the weak function in kernel/panic.c */ void crash_smp_send_stop(void) { static int cpus_stopped; if (cpus_stopped) return; if (smp_ops.crash_stop_other_cpus) smp_ops.crash_stop_other_cpus(); else smp_send_stop(); cpus_stopped = 1; } #else void crash_smp_send_stop(void) { /* There are no cpus to shootdown */ } #endif void native_machine_crash_shutdown(struct pt_regs *regs) { /* This function is only called after the system * has panicked or is otherwise in a critical state. * The minimum amount of code to allow a kexec'd kernel * to run successfully needs to happen here. * * In practice this means shooting down the other cpus in * an SMP system. */ /* The kernel is broken so disable interrupts */ local_irq_disable(); crash_smp_send_stop(); cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); clear_IO_APIC(); #endif lapic_shutdown(); restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif /* * Non-crash kexec calls enc_kexec_begin() while scheduling is still * active. This allows the callback to wait until all in-flight * shared<->private conversions are complete. In a crash scenario, * enc_kexec_begin() gets called after all but one CPU have been shut * down and interrupts have been disabled. This allows the callback to * detect a race with the conversion and report it. */ x86_platform.guest.enc_kexec_begin(); x86_platform.guest.enc_kexec_finish(); crash_save_cpu(regs, smp_processor_id()); } #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG) static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; } /* Gather all the required information to prepare elf headers for ram regions */ static struct crash_mem *fill_up_crash_elf_data(void) { unsigned int nr_ranges = 0; struct crash_mem *cmem; walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); if (!nr_ranges) return NULL; /* * Exclusion of crash region and/or crashk_low_res may cause * another range split. So add extra two slots here. */ nr_ranges += 2; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return NULL; cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; return cmem; } /* * Look for any unwanted ranges between mstart, mend and remove them. This * might lead to split and split ranges are put in cmem->ranges[] array */ static int elf_header_exclude_ranges(struct crash_mem *cmem) { int ret = 0; /* Exclude the low 1M because it is always reserved */ ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); if (ret) return ret; /* Exclude crashkernel region */ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); return ret; } static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_mem *cmem = arg; cmem->ranges[cmem->nr_ranges].start = res->start; cmem->ranges[cmem->nr_ranges].end = res->end; cmem->nr_ranges++; return 0; } /* Prepare elf headers. Return addr and size */ static int prepare_elf_headers(void **addr, unsigned long *sz, unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; cmem = fill_up_crash_elf_data(); if (!cmem) return -ENOMEM; ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); if (ret) goto out; /* Exclude unwanted mem ranges */ ret = elf_header_exclude_ranges(cmem); if (ret) goto out; /* Return the computed number of memory ranges, for hotplug usage */ *nr_mem_ranges = cmem->nr_ranges; /* By default prepare 64bit headers */ ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); return ret; } #endif #ifdef CONFIG_KEXEC_FILE static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) { unsigned int nr_e820_entries; nr_e820_entries = params->e820_entries; if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE) return 1; memcpy(¶ms->e820_table[nr_e820_entries], entry, sizeof(struct e820_entry)); params->e820_entries++; return 0; } static int memmap_entry_callback(struct resource *res, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; struct e820_entry ei; ei.addr = res->start; ei.size = resource_size(res); ei.type = cmd->type; add_e820_entry(params, &ei); return 0; } static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, unsigned long long mstart, unsigned long long mend) { unsigned long start, end; int ret; cmem->ranges[0].start = mstart; cmem->ranges[0].end = mend; cmem->nr_ranges = 1; /* Exclude elf header region */ start = image->elf_load_addr; end = start + image->elf_headers_sz - 1; ret = crash_exclude_mem_range(cmem, start, end); if (ret) return ret; /* Exclude dm crypt keys region */ if (image->dm_crypt_keys_addr) { start = image->dm_crypt_keys_addr; end = start + image->dm_crypt_keys_sz - 1; return crash_exclude_mem_range(cmem, start, end); } return ret; } /* Prepare memory map for crash dump kernel */ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { unsigned int nr_ranges = 0; int i, ret = 0; unsigned long flags; struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; /* * Using random kexec_buf for passing dm crypt keys may cause a range * split. So use two slots here. */ nr_ranges = 2; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return -ENOMEM; cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; /* Add the low 1M */ cmd.type = E820_TYPE_RAM; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_NONE, flags, 0, (1<<20)-1, &cmd, memmap_entry_callback); /* Add ACPI tables */ cmd.type = E820_TYPE_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ cmd.type = E820_TYPE_NVS; walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); /* Add e820 reserved ranges */ cmd.type = E820_TYPE_RESERVED; flags = IORESOURCE_MEM; walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd, memmap_entry_callback); /* Add crashk_low_res region */ if (crashk_low_res.end) { ei.addr = crashk_low_res.start; ei.size = resource_size(&crashk_low_res); ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } /* Exclude some ranges from crashk_res and add rest to memmap */ ret = memmap_exclude_ranges(image, cmem, crashk_res.start, crashk_res.end); if (ret) goto out; for (i = 0; i < cmem->nr_ranges; i++) { ei.size = cmem->ranges[i].end - cmem->ranges[i].start + 1; /* If entry is less than a page, skip it */ if (ei.size < PAGE_SIZE) continue; ei.addr = cmem->ranges[i].start; ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } out: vfree(cmem); return ret; } int crash_load_segments(struct kimage *image) { int ret; unsigned long pnum = 0; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; image->elf_headers = kbuf.buffer; image->elf_headers_sz = kbuf.bufsz; kbuf.memsz = kbuf.bufsz; #ifdef CONFIG_CRASH_HOTPLUG /* * The elfcorehdr segment size accounts for VMCOREINFO, kernel_map, * maximum CPUs and maximum memory ranges. */ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) pnum = 2 + CONFIG_NR_CPUS_DEFAULT + CONFIG_CRASH_MAX_MEMORY_RANGES; else pnum += 2 + CONFIG_NR_CPUS_DEFAULT; if (pnum < (unsigned long)PN_XNUM) { kbuf.memsz = pnum * sizeof(Elf64_Phdr); kbuf.memsz += sizeof(Elf64_Ehdr); image->elfcorehdr_index = image->nr_segments; /* Mark as usable to crash kernel, else crash kernel fails on boot */ image->elf_headers_sz = kbuf.memsz; } else { pr_err("number of Phdrs %lu exceeds max\n", pnum); } #endif kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) return ret; image->elf_load_addr = kbuf.mem; kexec_dprintk("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_CRASH_HOTPLUG #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) { #ifdef CONFIG_KEXEC_FILE if (image->file_mode) return 1; #endif /* * Initially, crash hotplug support for kexec_load was added * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this * functionality was expanded to accommodate multiple kexec * segment updates, leading to the introduction of the * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently, * when the kexec tool sends either of these flags, it indicates * that the required kexec segment (elfcorehdr) is excluded from * the SHA calculation. */ return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR || kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT); } unsigned int arch_crash_get_elfcorehdr_size(void) { unsigned int sz; /* kernel_map, VMCOREINFO and maximum CPUs */ sz = 2 + CONFIG_NR_CPUS_DEFAULT; if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) sz += CONFIG_CRASH_MAX_MEMORY_RANGES; sz *= sizeof(Elf64_Phdr); return sz; } /** * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes * @image: a pointer to kexec_crash_image * @arg: struct memory_notify handler for memory hotplug case and * NULL for CPU hotplug case. * * Prepare the new elfcorehdr and replace the existing elfcorehdr. */ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { void *elfbuf = NULL, *old_elfcorehdr; unsigned long nr_mem_ranges; unsigned long mem, memsz; unsigned long elfsz = 0; /* * As crash_prepare_elf64_headers() has already described all * possible CPUs, there is no need to update the elfcorehdr * for additional CPU changes. */ if ((image->file_mode || image->elfcorehdr_updated) && ((image->hp_action == KEXEC_CRASH_HP_ADD_CPU) || (image->hp_action == KEXEC_CRASH_HP_REMOVE_CPU))) return; /* * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { pr_err("unable to create new elfcorehdr"); goto out; } /* * Obtain address and size of the elfcorehdr segment, and * check it against the new elfcorehdr buffer. */ mem = image->segment[image->elfcorehdr_index].mem; memsz = image->segment[image->elfcorehdr_index].memsz; if (elfsz > memsz) { pr_err("update elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz); goto out; } /* * Copy new elfcorehdr over the old elfcorehdr at destination. */ old_elfcorehdr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT)); if (!old_elfcorehdr) { pr_err("mapping elfcorehdr segment failed\n"); goto out; } /* * Temporarily invalidate the crash image while the * elfcorehdr is updated. */ xchg(&kexec_crash_image, NULL); memcpy_flushcache(old_elfcorehdr, elfbuf, elfsz); xchg(&kexec_crash_image, image); kunmap_local(old_elfcorehdr); pr_debug("updated elfcorehdr\n"); out: vfree(elfbuf); } #endif |
| 288 11 7 93 35 337 93 93 1 337 337 337 337 1 68 24 24 68 92 56 22 25 93 49 48 47 2 4 8 8 9 43 1 81 1 72 2 7 23 52 2 1 2 47 2 2 2 18 25 43 41 1 3 1 14 1 2 47 49 1 7 1 1 1 1 1 2 1 2 1 2 3 3 1 1 1 1 1 1 1 1 3 3 9 9 1 1 1 82 82 1 3 36 13 12 9 9 9 3 9 3 3 1 1 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * binfmt_misc.c * * Copyright (C) 1997 Richard Günther * * binfmt_misc detects binaries via a magic or filename extension and invokes * a specified wrapper. See Documentation/admin-guide/binfmt-misc.rst for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/magic.h> #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/string_helpers.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/uaccess.h> #include "internal.h" #ifdef DEBUG # define USE_DEBUG 1 #else # define USE_DEBUG 0 #endif enum { VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */ }; enum {Enabled, Magic}; #define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) #define MISC_FMT_OPEN_BINARY (1UL << 30) #define MISC_FMT_CREDENTIALS (1UL << 29) #define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; unsigned long flags; /* type, status, etc. */ int offset; /* offset of magic */ int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; refcount_t users; /* sync removal with load_misc_binary() */ } Node; static struct file_system_type bm_fs_type; /* * Max length of the register string. Determined by: * - 7 delimiters * - name: ~50 bytes * - type: 1 byte * - offset: 3 bytes (has to be smaller than BINPRM_BUF_SIZE) * - magic: 128 bytes (512 in escaped form) * - mask: 128 bytes (512 in escaped form) * - interp: ~50 bytes * - flags: 5 bytes * Round that up a bit, and then back off to hold the internal data * (like struct Node). */ #define MAX_REGISTER_LENGTH 1920 /** * search_binfmt_handler - search for a binary handler for @bprm * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Search for a binary type handler for @bprm in the list of registered binary * type handlers. * * Return: binary type list entry on success, NULL on failure */ static Node *search_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { char *p = strrchr(bprm->interp, '.'); Node *e; /* Walk all the registered handlers. */ list_for_each_entry(e, &misc->entries, list) { char *s; int j; /* Make sure this one is currently enabled. */ if (!test_bit(Enabled, &e->flags)) continue; /* Do matching based on extension if applicable. */ if (!test_bit(Magic, &e->flags)) { if (p && !strcmp(e->magic, p + 1)) return e; continue; } /* Do matching based on magic & mask. */ s = bprm->buf + e->offset; if (e->mask) { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j]) & e->mask[j]) break; } else { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j])) break; } if (j == e->size) return e; } return NULL; } /** * get_binfmt_handler - try to find a binary type handler * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Try to find a binfmt handler for the binary type. If one is found take a * reference to protect against removal via bm_{entry,status}_write(). * * Return: binary type list entry on success, NULL on failure */ static Node *get_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { Node *e; read_lock(&misc->entries_lock); e = search_binfmt_handler(misc, bprm); if (e) refcount_inc(&e->users); read_unlock(&misc->entries_lock); return e; } /** * put_binfmt_handler - put binary handler node * @e: node to put * * Free node syncing with load_misc_binary() and defer final free to * load_misc_binary() in case it is using the binary type handler we were * requested to remove. */ static void put_binfmt_handler(Node *e) { if (refcount_dec_and_test(&e->users)) { if (e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); kfree(e); } } /** * load_binfmt_misc - load the binfmt_misc of the caller's user namespace * * To be called in load_misc_binary() to load the relevant struct binfmt_misc. * If a user namespace doesn't have its own binfmt_misc mount it can make use * of its ancestor's binfmt_misc handlers. This mimicks the behavior of * pre-namespaced binfmt_misc where all registered binfmt_misc handlers where * available to all user and user namespaces on the system. * * Return: the binfmt_misc instance of the caller's user namespace */ static struct binfmt_misc *load_binfmt_misc(void) { const struct user_namespace *user_ns; struct binfmt_misc *misc; user_ns = current_user_ns(); while (user_ns) { /* Pairs with smp_store_release() in bm_fill_super(). */ misc = smp_load_acquire(&user_ns->binfmt_misc); if (misc) return misc; user_ns = user_ns->parent; } return &init_binfmt_misc; } /* * the loader itself */ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; int retval = -ENOEXEC; struct binfmt_misc *misc; misc = load_binfmt_misc(); if (!misc->enabled) return retval; fmt = get_binfmt_handler(misc, bprm); if (!fmt) return retval; /* Need to be able to load the file after exec */ retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) goto ret; if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) { bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0; } else { retval = remove_arg_zero(bprm); if (retval) goto ret; } if (fmt->flags & MISC_FMT_OPEN_BINARY) bprm->have_execfd = 1; /* make argv[1] be the path to the binary */ retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) goto ret; bprm->argc++; /* add the interp as argv[0] */ retval = copy_string_kernel(fmt->interpreter, bprm); if (retval < 0) goto ret; bprm->argc++; /* Update interp in case binfmt_script needs it. */ retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto ret; if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) goto ret; bprm->interpreter = interp_file; if (fmt->flags & MISC_FMT_CREDENTIALS) bprm->execfd_creds = 1; retval = 0; ret: /* * If we actually put the node here all concurrent calls to * load_misc_binary() will have finished. We also know * that for the refcount to be zero someone must have concurently * removed the binary type handler from the list and it's our job to * free it. */ put_binfmt_handler(fmt); return retval; } /* Command parsers */ /* * parses and copies one argument enclosed in del from *sp to *dp, * recognising the \x special. * returns pointer to the copied argument or NULL in case of an * error (and sets err) or null argument length. */ static char *scanarg(char *s, char del) { char c; while ((c = *s++) != del) { if (c == '\\' && *s == 'x') { s++; if (!isxdigit(*s++)) return NULL; if (!isxdigit(*s++)) return NULL; } } s[-1] ='\0'; return s; } static char *check_special_flags(char *sfs, Node *e) { char *p = sfs; int cont = 1; /* special flags */ while (cont) { switch (*p) { case 'P': pr_debug("register: flag: P (preserve argv0)\n"); p++; e->flags |= MISC_FMT_PRESERVE_ARGV0; break; case 'O': pr_debug("register: flag: O (open binary)\n"); p++; e->flags |= MISC_FMT_OPEN_BINARY; break; case 'C': pr_debug("register: flag: C (preserve creds)\n"); p++; /* this flags also implies the open-binary flag */ e->flags |= (MISC_FMT_CREDENTIALS | MISC_FMT_OPEN_BINARY); break; case 'F': pr_debug("register: flag: F: open interpreter file now\n"); p++; e->flags |= MISC_FMT_OPEN_FILE; break; default: cont = 0; } } return p; } /* * This registers a new binary format, it recognises the syntax * ':name:type:offset:magic:mask:interpreter:flags' * where the ':' is the IFS, that can be chosen with the first char */ static Node *create_entry(const char __user *buffer, size_t count) { Node *e; int memsize, err; char *buf, *p; char del; pr_debug("register: received %zu bytes\n", count); /* some sanity checks */ err = -EINVAL; if ((count < 11) || (count > MAX_REGISTER_LENGTH)) goto out; err = -ENOMEM; memsize = sizeof(Node) + count + 8; e = kmalloc(memsize, GFP_KERNEL_ACCOUNT); if (!e) goto out; p = buf = (char *)e + sizeof(Node); memset(e, 0, sizeof(Node)); if (copy_from_user(buf, buffer, count)) goto efault; del = *p++; /* delimeter */ pr_debug("register: delim: %#x {%c}\n", del, del); /* Pad the buffer with the delim to simplify parsing below. */ memset(buf + count, del, 8); /* Parse the 'name' field. */ e->name = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->name[0] || !strcmp(e->name, ".") || !strcmp(e->name, "..") || strchr(e->name, '/')) goto einval; pr_debug("register: name: {%s}\n", e->name); /* Parse the 'type' field. */ switch (*p++) { case 'E': pr_debug("register: type: E (extension)\n"); e->flags = 1 << Enabled; break; case 'M': pr_debug("register: type: M (magic)\n"); e->flags = (1 << Enabled) | (1 << Magic); break; default: goto einval; } if (*p++ != del) goto einval; if (test_bit(Magic, &e->flags)) { /* Handle the 'M' (magic) format. */ char *s; /* Parse the 'offset' field. */ s = strchr(p, del); if (!s) goto einval; *s = '\0'; if (p != s) { int r = kstrtoint(p, 10, &e->offset); if (r != 0 || e->offset < 0) goto einval; } p = s; if (*p++) goto einval; pr_debug("register: offset: %#x\n", e->offset); /* Parse the 'magic' field. */ e->magic = p; p = scanarg(p, del); if (!p) goto einval; if (!e->magic[0]) goto einval; if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[raw]: ", DUMP_PREFIX_NONE, e->magic, p - e->magic); /* Parse the 'mask' field. */ e->mask = p; p = scanarg(p, del); if (!p) goto einval; if (!e->mask[0]) { e->mask = NULL; pr_debug("register: mask[raw]: none\n"); } else if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[raw]: ", DUMP_PREFIX_NONE, e->mask, p - e->mask); /* * Decode the magic & mask fields. * Note: while we might have accepted embedded NUL bytes from * above, the unescape helpers here will stop at the first one * it encounters. */ e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX); if (e->mask && string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto einval; if (e->size > BINPRM_BUF_SIZE || BINPRM_BUF_SIZE - e->size < e->offset) goto einval; pr_debug("register: magic/mask length: %i\n", e->size); if (USE_DEBUG) { print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[decoded]: ", DUMP_PREFIX_NONE, e->magic, e->size); if (e->mask) { int i; char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT); print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[decoded]: ", DUMP_PREFIX_NONE, e->mask, e->size); if (masked) { for (i = 0; i < e->size; ++i) masked[i] = e->magic[i] & e->mask[i]; print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[masked]: ", DUMP_PREFIX_NONE, masked, e->size); kfree(masked); } } } } else { /* Handle the 'E' (extension) format. */ /* Skip the 'offset' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; /* Parse the 'magic' field. */ e->magic = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->magic[0] || strchr(e->magic, '/')) goto einval; pr_debug("register: extension: {%s}\n", e->magic); /* Skip the 'mask' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; } /* Parse the 'interpreter' field. */ e->interpreter = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->interpreter[0]) goto einval; pr_debug("register: interpreter: {%s}\n", e->interpreter); /* Parse the 'flags' field. */ p = check_special_flags(p, e); if (*p == '\n') p++; if (p != buf + count) goto einval; return e; out: return ERR_PTR(err); efault: kfree(e); return ERR_PTR(-EFAULT); einval: kfree(e); return ERR_PTR(-EINVAL); } /* * Set status of entry/binfmt_misc: * '1' enables, '0' disables and '-1' clears entry/binfmt_misc */ static int parse_command(const char __user *buffer, size_t count) { char s[4]; if (count > 3) return -EINVAL; if (copy_from_user(s, buffer, count)) return -EFAULT; if (!count) return 0; if (s[count - 1] == '\n') count--; if (count == 1 && s[0] == '0') return 1; if (count == 1 && s[0] == '1') return 2; if (count == 2 && s[0] == '-' && s[1] == '1') return 3; return -EINVAL; } /* generic stuff */ static void entry_status(Node *e, char *page) { char *dp = page; const char *status = "disabled"; if (test_bit(Enabled, &e->flags)) status = "enabled"; if (!VERBOSE_STATUS) { sprintf(page, "%s\n", status); return; } dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter); /* print the special flags */ dp += sprintf(dp, "flags: "); if (e->flags & MISC_FMT_PRESERVE_ARGV0) *dp++ = 'P'; if (e->flags & MISC_FMT_OPEN_BINARY) *dp++ = 'O'; if (e->flags & MISC_FMT_CREDENTIALS) *dp++ = 'C'; if (e->flags & MISC_FMT_OPEN_FILE) *dp++ = 'F'; *dp++ = '\n'; if (!test_bit(Magic, &e->flags)) { sprintf(dp, "extension .%s\n", e->magic); } else { dp += sprintf(dp, "offset %i\nmagic ", e->offset); dp = bin2hex(dp, e->magic, e->size); if (e->mask) { dp += sprintf(dp, "\nmask "); dp = bin2hex(dp, e->mask, e->size); } *dp++ = '\n'; *dp = '\0'; } } static struct inode *bm_get_inode(struct super_block *sb, int mode) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; simple_inode_init_ts(inode); } return inode; } /** * i_binfmt_misc - retrieve struct binfmt_misc from a binfmt_misc inode * @inode: inode of the relevant binfmt_misc instance * * This helper retrieves struct binfmt_misc from a binfmt_misc inode. This can * be done without any memory barriers because we are guaranteed that * user_ns->binfmt_misc is fully initialized. It was fully initialized when the * binfmt_misc mount was first created. * * Return: struct binfmt_misc of the relevant binfmt_misc instance */ static struct binfmt_misc *i_binfmt_misc(struct inode *inode) { return inode->i_sb->s_user_ns->binfmt_misc; } /** * bm_evict_inode - cleanup data associated with @inode * @inode: inode to which the data is attached * * Cleanup the binary type handler data associated with @inode if a binary type * entry is removed or the filesystem is unmounted and the super block is * shutdown. * * If the ->evict call was not caused by a super block shutdown but by a write * to remove the entry or all entries via bm_{entry,status}_write() the entry * will have already been removed from the list. We keep the list_empty() check * to make that explicit. */ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; clear_inode(inode); if (e) { struct binfmt_misc *misc; misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); if (!list_empty(&e->list)) list_del_init(&e->list); write_unlock(&misc->entries_lock); put_binfmt_handler(e); } } /** * unlink_binfmt_dentry - remove the dentry for the binary type handler * @dentry: dentry associated with the binary type handler * * Do the actual filesystem work to remove a dentry for a registered binary * type handler. Since binfmt_misc only allows simple files to be created * directly under the root dentry of the filesystem we ensure that we are * indeed passed a dentry directly beneath the root dentry, that the inode * associated with the root dentry is locked, and that it is a regular file we * are asked to remove. */ static void unlink_binfmt_dentry(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; struct inode *inode, *parent_inode; /* All entries are immediate descendants of the root dentry. */ if (WARN_ON_ONCE(dentry->d_sb->s_root != parent)) return; /* We only expect to be called on regular files. */ inode = d_inode(dentry); if (WARN_ON_ONCE(!S_ISREG(inode->i_mode))) return; /* The parent inode must be locked. */ parent_inode = d_inode(parent); if (WARN_ON_ONCE(!inode_is_locked(parent_inode))) return; if (simple_positive(dentry)) { dget(dentry); simple_unlink(parent_inode, dentry); d_delete(dentry); dput(dentry); } } /** * remove_binfmt_handler - remove a binary type handler * @misc: handle to binfmt_misc instance * @e: binary type handler to remove * * Remove a binary type handler from the list of binary type handlers and * remove its associated dentry. This is called from * binfmt_{entry,status}_write(). In the future, we might want to think about * adding a proper ->unlink() method to binfmt_misc instead of forcing caller's * to use writes to files in order to delete binary type handlers. But it has * worked for so long that it's not a pressing issue. */ static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e) { write_lock(&misc->entries_lock); list_del_init(&e->list); write_unlock(&misc->entries_lock); unlink_binfmt_dentry(e->dentry); } /* /<entry> */ static ssize_t bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { Node *e = file_inode(file)->i_private; ssize_t res; char *page; page = (char *) __get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; entry_status(e, page); res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page)); free_page((unsigned long) page); return res; } static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); Node *e = inode->i_private; int res = parse_command(buffer, count); switch (res) { case 1: /* Disable this handler. */ clear_bit(Enabled, &e->flags); break; case 2: /* Enable this handler. */ set_bit(Enabled, &e->flags); break; case 3: /* Delete this handler. */ inode = d_inode(inode->i_sb->s_root); inode_lock(inode); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ if (!list_empty(&e->list)) remove_binfmt_handler(i_binfmt_misc(inode), e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_entry_operations = { .read = bm_entry_read, .write = bm_entry_write, .llseek = default_llseek, }; /* /register */ static ssize_t bm_register_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { Node *e; struct inode *inode; struct super_block *sb = file_inode(file)->i_sb; struct dentry *root = sb->s_root, *dentry; struct binfmt_misc *misc; int err = 0; struct file *f = NULL; e = create_entry(buffer, count); if (IS_ERR(e)) return PTR_ERR(e); if (e->flags & MISC_FMT_OPEN_FILE) { const struct cred *old_cred; /* * Now that we support unprivileged binfmt_misc mounts make * sure we use the credentials that the register @file was * opened with to also open the interpreter. Before that this * didn't matter much as only a privileged process could open * the register file. */ old_cred = override_creds(file->f_cred); f = open_exec(e->interpreter); revert_creds(old_cred); if (IS_ERR(f)) { pr_notice("register: failed to install interpreter file %s\n", e->interpreter); kfree(e); return PTR_ERR(f); } e->interp_file = f; } inode_lock(d_inode(root)); dentry = lookup_noperm(&QSTR(e->name), root); err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out; err = -EEXIST; if (d_really_is_positive(dentry)) goto out2; inode = bm_get_inode(sb, S_IFREG | 0644); err = -ENOMEM; if (!inode) goto out2; refcount_set(&e->users, 1); e->dentry = dget(dentry); inode->i_private = e; inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); list_add(&e->list, &misc->entries); write_unlock(&misc->entries_lock); err = 0; out2: dput(dentry); out: inode_unlock(d_inode(root)); if (err) { if (f) filp_close(f, NULL); kfree(e); return err; } return count; } static const struct file_operations bm_register_operations = { .write = bm_register_write, .llseek = noop_llseek, }; /* /status */ static ssize_t bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { struct binfmt_misc *misc; char *s; misc = i_binfmt_misc(file_inode(file)); s = misc->enabled ? "enabled\n" : "disabled\n"; return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s)); } static ssize_t bm_status_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct binfmt_misc *misc; int res = parse_command(buffer, count); Node *e, *next; struct inode *inode; misc = i_binfmt_misc(file_inode(file)); switch (res) { case 1: /* Disable all handlers. */ misc->enabled = false; break; case 2: /* Enable all handlers. */ misc->enabled = true; break; case 3: /* Delete all handlers. */ inode = d_inode(file_inode(file)->i_sb->s_root); inode_lock(inode); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ list_for_each_entry_safe(e, next, &misc->entries, list) remove_binfmt_handler(misc, e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_status_operations = { .read = bm_status_read, .write = bm_status_write, .llseek = default_llseek, }; /* Superblock handling */ static void bm_put_super(struct super_block *sb) { struct user_namespace *user_ns = sb->s_fs_info; sb->s_fs_info = NULL; put_user_ns(user_ns); } static const struct super_operations s_ops = { .statfs = simple_statfs, .evict_inode = bm_evict_inode, .put_super = bm_put_super, }; static int bm_fill_super(struct super_block *sb, struct fs_context *fc) { int err; struct user_namespace *user_ns = sb->s_user_ns; struct binfmt_misc *misc; static const struct tree_descr bm_files[] = { [2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO}, [3] = {"register", &bm_register_operations, S_IWUSR}, /* last one */ {""} }; if (WARN_ON(user_ns != current_user_ns())) return -EINVAL; /* * Lazily allocate a new binfmt_misc instance for this namespace, i.e. * do it here during the first mount of binfmt_misc. We don't need to * waste memory for every user namespace allocation. It's likely much * more common to not mount a separate binfmt_misc instance than it is * to mount one. * * While multiple superblocks can exist they are keyed by userns in * s_fs_info for binfmt_misc. Hence, the vfs guarantees that * bm_fill_super() is called exactly once whenever a binfmt_misc * superblock for a userns is created. This in turn lets us conclude * that when a binfmt_misc superblock is created for the first time for * a userns there's no one racing us. Therefore we don't need any * barriers when we dereference binfmt_misc. */ misc = user_ns->binfmt_misc; if (!misc) { /* * If it turns out that most user namespaces actually want to * register their own binary type handler and therefore all * create their own separate binfmt_misc mounts we should * consider turning this into a kmem cache. */ misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); if (!misc) return -ENOMEM; INIT_LIST_HEAD(&misc->entries); rwlock_init(&misc->entries_lock); /* Pairs with smp_load_acquire() in load_binfmt_misc(). */ smp_store_release(&user_ns->binfmt_misc, misc); } /* * When the binfmt_misc superblock for this userns is shutdown * ->enabled might have been set to false and we don't reinitialize * ->enabled again in put_super() as someone might already be mounting * binfmt_misc again. It also would be pointless since by the time * ->put_super() is called we know that the binary type list for this * bintfmt_misc mount is empty making load_misc_binary() return * -ENOEXEC independent of whether ->enabled is true. Instead, if * someone mounts binfmt_misc for the first time or again we simply * reset ->enabled to true. */ misc->enabled = true; err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files); if (!err) sb->s_op = &s_ops; return err; } static void bm_free(struct fs_context *fc) { if (fc->s_fs_info) put_user_ns(fc->s_fs_info); } static int bm_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, bm_fill_super, get_user_ns(fc->user_ns)); } static const struct fs_context_operations bm_context_ops = { .free = bm_free, .get_tree = bm_get_tree, }; static int bm_init_fs_context(struct fs_context *fc) { fc->ops = &bm_context_ops; return 0; } static struct linux_binfmt misc_format = { .module = THIS_MODULE, .load_binary = load_misc_binary, }; static struct file_system_type bm_fs_type = { .owner = THIS_MODULE, .name = "binfmt_misc", .init_fs_context = bm_init_fs_context, .fs_flags = FS_USERNS_MOUNT, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("binfmt_misc"); static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); return err; } static void __exit exit_misc_binfmt(void) { unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } core_initcall(init_misc_binfmt); module_exit(exit_misc_binfmt); MODULE_DESCRIPTION("Kernel support for miscellaneous binaries"); MODULE_LICENSE("GPL"); |
| 97 18 20 97 20 97 22 97 27 116 117 117 117 97 18 77 11 78 79 11 8 8 199 325 20 274 228 36 20 116 116 116 117 97 97 8 8 20 20 326 325 20 20 20 13 7 324 325 20 8 108 111 67 67 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Asynchronous Cryptographic Hash operations. * * This is the implementation of the ahash (asynchronous hash) API. It differs * from shash (synchronous hash) in that ahash supports asynchronous operations, * and it hashes data from scatterlists instead of virtually addressed buffers. * * The ahash API provides access to both ahash and shash algorithms. The shash * API only provides access to shash algorithms. * * Copyright (c) 2008 Loc Ho <lho@amcc.com> */ #include <crypto/scatterwalk.h> #include <linux/cryptouser.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/string_choices.h> #include <net/netlink.h> #include "hash.h" #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e struct crypto_hash_walk { const char *data; unsigned int offset; unsigned int flags; struct page *pg; unsigned int entrylen; unsigned int total; struct scatterlist *sg; }; static int ahash_def_finup(struct ahash_request *req); static inline bool crypto_ahash_block_only(struct crypto_ahash *tfm) { return crypto_ahash_alg(tfm)->halg.base.cra_flags & CRYPTO_AHASH_ALG_BLOCK_ONLY; } static inline bool crypto_ahash_final_nonzero(struct crypto_ahash *tfm) { return crypto_ahash_alg(tfm)->halg.base.cra_flags & CRYPTO_AHASH_ALG_FINAL_NONZERO; } static inline bool crypto_ahash_need_fallback(struct crypto_ahash *tfm) { return crypto_ahash_alg(tfm)->halg.base.cra_flags & CRYPTO_ALG_NEED_FALLBACK; } static inline void ahash_op_done(void *data, int err, int (*finish)(struct ahash_request *, int)) { struct ahash_request *areq = data; crypto_completion_t compl; compl = areq->saved_complete; data = areq->saved_data; if (err == -EINPROGRESS) goto out; areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP; err = finish(areq, err); if (err == -EINPROGRESS || err == -EBUSY) return; out: compl(data, err); } static int hash_walk_next(struct crypto_hash_walk *walk) { unsigned int offset = walk->offset; unsigned int nbytes = min(walk->entrylen, ((unsigned int)(PAGE_SIZE)) - offset); walk->data = kmap_local_page(walk->pg); walk->data += offset; walk->entrylen -= nbytes; return nbytes; } static int hash_walk_new_entry(struct crypto_hash_walk *walk) { struct scatterlist *sg; sg = walk->sg; walk->offset = sg->offset; walk->pg = nth_page(sg_page(walk->sg), (walk->offset >> PAGE_SHIFT)); walk->offset = offset_in_page(walk->offset); walk->entrylen = sg->length; if (walk->entrylen > walk->total) walk->entrylen = walk->total; walk->total -= walk->entrylen; return hash_walk_next(walk); } static int crypto_hash_walk_first(struct ahash_request *req, struct crypto_hash_walk *walk) { walk->total = req->nbytes; walk->entrylen = 0; if (!walk->total) return 0; walk->flags = req->base.flags; if (ahash_request_isvirt(req)) { walk->data = req->svirt; walk->total = 0; return req->nbytes; } walk->sg = req->src; return hash_walk_new_entry(walk); } static int crypto_hash_walk_done(struct crypto_hash_walk *walk, int err) { if ((walk->flags & CRYPTO_AHASH_REQ_VIRT)) return err; walk->data -= walk->offset; kunmap_local(walk->data); crypto_yield(walk->flags); if (err) return err; if (walk->entrylen) { walk->offset = 0; walk->pg++; return hash_walk_next(walk); } if (!walk->total) return 0; walk->sg = sg_next(walk->sg); return hash_walk_new_entry(walk); } static inline int crypto_hash_walk_last(struct crypto_hash_walk *walk) { return !(walk->entrylen | walk->total); } /* * For an ahash tfm that is using an shash algorithm (instead of an ahash * algorithm), this returns the underlying shash tfm. */ static inline struct crypto_shash *ahash_to_shash(struct crypto_ahash *tfm) { return *(struct crypto_shash **)crypto_ahash_ctx(tfm); } static inline struct shash_desc *prepare_shash_desc(struct ahash_request *req, struct crypto_ahash *tfm) { struct shash_desc *desc = ahash_request_ctx(req); desc->tfm = ahash_to_shash(tfm); return desc; } int shash_ahash_update(struct ahash_request *req, struct shash_desc *desc) { struct crypto_hash_walk walk; int nbytes; for (nbytes = crypto_hash_walk_first(req, &walk); nbytes > 0; nbytes = crypto_hash_walk_done(&walk, nbytes)) nbytes = crypto_shash_update(desc, walk.data, nbytes); return nbytes; } EXPORT_SYMBOL_GPL(shash_ahash_update); int shash_ahash_finup(struct ahash_request *req, struct shash_desc *desc) { struct crypto_hash_walk walk; int nbytes; nbytes = crypto_hash_walk_first(req, &walk); if (!nbytes) return crypto_shash_final(desc, req->result); do { nbytes = crypto_hash_walk_last(&walk) ? crypto_shash_finup(desc, walk.data, nbytes, req->result) : crypto_shash_update(desc, walk.data, nbytes); nbytes = crypto_hash_walk_done(&walk, nbytes); } while (nbytes > 0); return nbytes; } EXPORT_SYMBOL_GPL(shash_ahash_finup); int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc) { unsigned int nbytes = req->nbytes; struct scatterlist *sg; unsigned int offset; struct page *page; const u8 *data; int err; data = req->svirt; if (!nbytes || ahash_request_isvirt(req)) return crypto_shash_digest(desc, data, nbytes, req->result); sg = req->src; if (nbytes > sg->length) return crypto_shash_init(desc) ?: shash_ahash_finup(req, desc); page = sg_page(sg); offset = sg->offset; data = lowmem_page_address(page) + offset; if (!IS_ENABLED(CONFIG_HIGHMEM)) return crypto_shash_digest(desc, data, nbytes, req->result); page = nth_page(page, offset >> PAGE_SHIFT); offset = offset_in_page(offset); if (nbytes > (unsigned int)PAGE_SIZE - offset) return crypto_shash_init(desc) ?: shash_ahash_finup(req, desc); data = kmap_local_page(page); err = crypto_shash_digest(desc, data + offset, nbytes, req->result); kunmap_local(data); return err; } EXPORT_SYMBOL_GPL(shash_ahash_digest); static void crypto_exit_ahash_using_shash(struct crypto_tfm *tfm) { struct crypto_shash **ctx = crypto_tfm_ctx(tfm); crypto_free_shash(*ctx); } static int crypto_init_ahash_using_shash(struct crypto_tfm *tfm) { struct crypto_alg *calg = tfm->__crt_alg; struct crypto_ahash *crt = __crypto_ahash_cast(tfm); struct crypto_shash **ctx = crypto_tfm_ctx(tfm); struct crypto_shash *shash; if (!crypto_mod_get(calg)) return -EAGAIN; shash = crypto_create_tfm(calg, &crypto_shash_type); if (IS_ERR(shash)) { crypto_mod_put(calg); return PTR_ERR(shash); } crt->using_shash = true; *ctx = shash; tfm->exit = crypto_exit_ahash_using_shash; crypto_ahash_set_flags(crt, crypto_shash_get_flags(shash) & CRYPTO_TFM_NEED_KEY); return 0; } static int ahash_nosetkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen) { return -ENOSYS; } static void ahash_set_needkey(struct crypto_ahash *tfm, struct ahash_alg *alg) { if (alg->setkey != ahash_nosetkey && !(alg->halg.base.cra_flags & CRYPTO_ALG_OPTIONAL_KEY)) crypto_ahash_set_flags(tfm, CRYPTO_TFM_NEED_KEY); } int crypto_ahash_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int keylen) { if (likely(tfm->using_shash)) { struct crypto_shash *shash = ahash_to_shash(tfm); int err; err = crypto_shash_setkey(shash, key, keylen); if (unlikely(err)) { crypto_ahash_set_flags(tfm, crypto_shash_get_flags(shash) & CRYPTO_TFM_NEED_KEY); return err; } } else { struct ahash_alg *alg = crypto_ahash_alg(tfm); int err; err = alg->setkey(tfm, key, keylen); if (!err && crypto_ahash_need_fallback(tfm)) err = crypto_ahash_setkey(crypto_ahash_fb(tfm), key, keylen); if (unlikely(err)) { ahash_set_needkey(tfm, alg); return err; } } crypto_ahash_clear_flags(tfm, CRYPTO_TFM_NEED_KEY); return 0; } EXPORT_SYMBOL_GPL(crypto_ahash_setkey); static int ahash_do_req_chain(struct ahash_request *req, int (*const *op)(struct ahash_request *req)) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); int err; if (crypto_ahash_req_virt(tfm) || !ahash_request_isvirt(req)) return (*op)(req); if (crypto_ahash_statesize(tfm) > HASH_MAX_STATESIZE) return -ENOSYS; { u8 state[HASH_MAX_STATESIZE]; if (op == &crypto_ahash_alg(tfm)->digest) { ahash_request_set_tfm(req, crypto_ahash_fb(tfm)); err = crypto_ahash_digest(req); goto out_no_state; } err = crypto_ahash_export(req, state); ahash_request_set_tfm(req, crypto_ahash_fb(tfm)); err = err ?: crypto_ahash_import(req, state); if (op == &crypto_ahash_alg(tfm)->finup) { err = err ?: crypto_ahash_finup(req); goto out_no_state; } err = err ?: crypto_ahash_update(req) ?: crypto_ahash_export(req, state); ahash_request_set_tfm(req, tfm); return err ?: crypto_ahash_import(req, state); out_no_state: ahash_request_set_tfm(req, tfm); return err; } } int crypto_ahash_init(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (likely(tfm->using_shash)) return crypto_shash_init(prepare_shash_desc(req, tfm)); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; if (ahash_req_on_stack(req) && ahash_is_async(tfm)) return -EAGAIN; if (crypto_ahash_block_only(tfm)) { u8 *buf = ahash_request_ctx(req); buf += crypto_ahash_reqsize(tfm) - 1; *buf = 0; } return crypto_ahash_alg(tfm)->init(req); } EXPORT_SYMBOL_GPL(crypto_ahash_init); static void ahash_save_req(struct ahash_request *req, crypto_completion_t cplt) { req->saved_complete = req->base.complete; req->saved_data = req->base.data; req->base.complete = cplt; req->base.data = req; } static void ahash_restore_req(struct ahash_request *req) { req->base.complete = req->saved_complete; req->base.data = req->saved_data; } static int ahash_update_finish(struct ahash_request *req, int err) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); bool nonzero = crypto_ahash_final_nonzero(tfm); int bs = crypto_ahash_blocksize(tfm); u8 *blenp = ahash_request_ctx(req); int blen; u8 *buf; blenp += crypto_ahash_reqsize(tfm) - 1; blen = *blenp; buf = blenp - bs; if (blen) { req->src = req->sg_head + 1; if (sg_is_chain(req->src)) req->src = sg_chain_ptr(req->src); } req->nbytes += nonzero - blen; blen = err < 0 ? 0 : err + nonzero; if (ahash_request_isvirt(req)) memcpy(buf, req->svirt + req->nbytes - blen, blen); else memcpy_from_sglist(buf, req->src, req->nbytes - blen, blen); *blenp = blen; ahash_restore_req(req); return err; } static void ahash_update_done(void *data, int err) { ahash_op_done(data, err, ahash_update_finish); } int crypto_ahash_update(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); bool nonzero = crypto_ahash_final_nonzero(tfm); int bs = crypto_ahash_blocksize(tfm); u8 *blenp = ahash_request_ctx(req); int blen, err; u8 *buf; if (likely(tfm->using_shash)) return shash_ahash_update(req, ahash_request_ctx(req)); if (ahash_req_on_stack(req) && ahash_is_async(tfm)) return -EAGAIN; if (!crypto_ahash_block_only(tfm)) return ahash_do_req_chain(req, &crypto_ahash_alg(tfm)->update); blenp += crypto_ahash_reqsize(tfm) - 1; blen = *blenp; buf = blenp - bs; if (blen + req->nbytes < bs + nonzero) { if (ahash_request_isvirt(req)) memcpy(buf + blen, req->svirt, req->nbytes); else memcpy_from_sglist(buf + blen, req->src, 0, req->nbytes); *blenp += req->nbytes; return 0; } if (blen) { memset(req->sg_head, 0, sizeof(req->sg_head[0])); sg_set_buf(req->sg_head, buf, blen); if (req->src != req->sg_head + 1) sg_chain(req->sg_head, 2, req->src); req->src = req->sg_head; req->nbytes += blen; } req->nbytes -= nonzero; ahash_save_req(req, ahash_update_done); err = ahash_do_req_chain(req, &crypto_ahash_alg(tfm)->update); if (err == -EINPROGRESS || err == -EBUSY) return err; return ahash_update_finish(req, err); } EXPORT_SYMBOL_GPL(crypto_ahash_update); static int ahash_finup_finish(struct ahash_request *req, int err) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); u8 *blenp = ahash_request_ctx(req); int blen; blenp += crypto_ahash_reqsize(tfm) - 1; blen = *blenp; if (blen) { if (sg_is_last(req->src)) req->src = NULL; else { req->src = req->sg_head + 1; if (sg_is_chain(req->src)) req->src = sg_chain_ptr(req->src); } req->nbytes -= blen; } ahash_restore_req(req); return err; } static void ahash_finup_done(void *data, int err) { ahash_op_done(data, err, ahash_finup_finish); } int crypto_ahash_finup(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); int bs = crypto_ahash_blocksize(tfm); u8 *blenp = ahash_request_ctx(req); int blen, err; u8 *buf; if (likely(tfm->using_shash)) return shash_ahash_finup(req, ahash_request_ctx(req)); if (ahash_req_on_stack(req) && ahash_is_async(tfm)) return -EAGAIN; if (!crypto_ahash_alg(tfm)->finup) return ahash_def_finup(req); if (!crypto_ahash_block_only(tfm)) return ahash_do_req_chain(req, &crypto_ahash_alg(tfm)->finup); blenp += crypto_ahash_reqsize(tfm) - 1; blen = *blenp; buf = blenp - bs; if (blen) { memset(req->sg_head, 0, sizeof(req->sg_head[0])); sg_set_buf(req->sg_head, buf, blen); if (!req->src) sg_mark_end(req->sg_head); else if (req->src != req->sg_head + 1) sg_chain(req->sg_head, 2, req->src); req->src = req->sg_head; req->nbytes += blen; } ahash_save_req(req, ahash_finup_done); err = ahash_do_req_chain(req, &crypto_ahash_alg(tfm)->finup); if (err == -EINPROGRESS || err == -EBUSY) return err; return ahash_finup_finish(req, err); } EXPORT_SYMBOL_GPL(crypto_ahash_finup); int crypto_ahash_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (likely(tfm->using_shash)) return shash_ahash_digest(req, prepare_shash_desc(req, tfm)); if (ahash_req_on_stack(req) && ahash_is_async(tfm)) return -EAGAIN; if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return ahash_do_req_chain(req, &crypto_ahash_alg(tfm)->digest); } EXPORT_SYMBOL_GPL(crypto_ahash_digest); static void ahash_def_finup_done2(void *data, int err) { struct ahash_request *areq = data; if (err == -EINPROGRESS) return; ahash_restore_req(areq); ahash_request_complete(areq, err); } static int ahash_def_finup_finish1(struct ahash_request *req, int err) { if (err) goto out; req->base.complete = ahash_def_finup_done2; err = crypto_ahash_final(req); if (err == -EINPROGRESS || err == -EBUSY) return err; out: ahash_restore_req(req); return err; } static void ahash_def_finup_done1(void *data, int err) { ahash_op_done(data, err, ahash_def_finup_finish1); } static int ahash_def_finup(struct ahash_request *req) { int err; ahash_save_req(req, ahash_def_finup_done1); err = crypto_ahash_update(req); if (err == -EINPROGRESS || err == -EBUSY) return err; return ahash_def_finup_finish1(req, err); } int crypto_ahash_export_core(struct ahash_request *req, void *out) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (likely(tfm->using_shash)) return crypto_shash_export_core(ahash_request_ctx(req), out); return crypto_ahash_alg(tfm)->export_core(req, out); } EXPORT_SYMBOL_GPL(crypto_ahash_export_core); int crypto_ahash_export(struct ahash_request *req, void *out) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (likely(tfm->using_shash)) return crypto_shash_export(ahash_request_ctx(req), out); if (crypto_ahash_block_only(tfm)) { unsigned int plen = crypto_ahash_blocksize(tfm) + 1; unsigned int reqsize = crypto_ahash_reqsize(tfm); unsigned int ss = crypto_ahash_statesize(tfm); u8 *buf = ahash_request_ctx(req); memcpy(out + ss - plen, buf + reqsize - plen, plen); } return crypto_ahash_alg(tfm)->export(req, out); } EXPORT_SYMBOL_GPL(crypto_ahash_export); int crypto_ahash_import_core(struct ahash_request *req, const void *in) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (likely(tfm->using_shash)) return crypto_shash_import_core(prepare_shash_desc(req, tfm), in); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; return crypto_ahash_alg(tfm)->import_core(req, in); } EXPORT_SYMBOL_GPL(crypto_ahash_import_core); int crypto_ahash_import(struct ahash_request *req, const void *in) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); if (likely(tfm->using_shash)) return crypto_shash_import(prepare_shash_desc(req, tfm), in); if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY) return -ENOKEY; if (crypto_ahash_block_only(tfm)) { unsigned int reqsize = crypto_ahash_reqsize(tfm); u8 *buf = ahash_request_ctx(req); buf[reqsize - 1] = 0; } return crypto_ahash_alg(tfm)->import(req, in); } EXPORT_SYMBOL_GPL(crypto_ahash_import); static void crypto_ahash_exit_tfm(struct crypto_tfm *tfm) { struct crypto_ahash *hash = __crypto_ahash_cast(tfm); struct ahash_alg *alg = crypto_ahash_alg(hash); if (alg->exit_tfm) alg->exit_tfm(hash); else if (tfm->__crt_alg->cra_exit) tfm->__crt_alg->cra_exit(tfm); if (crypto_ahash_need_fallback(hash)) crypto_free_ahash(crypto_ahash_fb(hash)); } static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) { struct crypto_ahash *hash = __crypto_ahash_cast(tfm); struct ahash_alg *alg = crypto_ahash_alg(hash); struct crypto_ahash *fb = NULL; int err; crypto_ahash_set_statesize(hash, alg->halg.statesize); crypto_ahash_set_reqsize(hash, crypto_tfm_alg_reqsize(tfm)); if (tfm->__crt_alg->cra_type == &crypto_shash_type) return crypto_init_ahash_using_shash(tfm); if (crypto_ahash_need_fallback(hash)) { fb = crypto_alloc_ahash(crypto_ahash_alg_name(hash), CRYPTO_ALG_REQ_VIRT, CRYPTO_ALG_ASYNC | CRYPTO_ALG_REQ_VIRT | CRYPTO_AHASH_ALG_NO_EXPORT_CORE); if (IS_ERR(fb)) return PTR_ERR(fb); tfm->fb = crypto_ahash_tfm(fb); } ahash_set_needkey(hash, alg); tfm->exit = crypto_ahash_exit_tfm; if (alg->init_tfm) err = alg->init_tfm(hash); else if (tfm->__crt_alg->cra_init) err = tfm->__crt_alg->cra_init(tfm); else return 0; if (err) goto out_free_sync_hash; if (!ahash_is_async(hash) && crypto_ahash_reqsize(hash) > MAX_SYNC_HASH_REQSIZE) goto out_exit_tfm; BUILD_BUG_ON(HASH_MAX_DESCSIZE > MAX_SYNC_HASH_REQSIZE); if (crypto_ahash_reqsize(hash) < HASH_MAX_DESCSIZE) crypto_ahash_set_reqsize(hash, HASH_MAX_DESCSIZE); return 0; out_exit_tfm: if (alg->exit_tfm) alg->exit_tfm(hash); else if (tfm->__crt_alg->cra_exit) tfm->__crt_alg->cra_exit(tfm); err = -EINVAL; out_free_sync_hash: crypto_free_ahash(fb); return err; } static unsigned int crypto_ahash_extsize(struct crypto_alg *alg) { if (alg->cra_type == &crypto_shash_type) return sizeof(struct crypto_shash *); return crypto_alg_extsize(alg); } static void crypto_ahash_free_instance(struct crypto_instance *inst) { struct ahash_instance *ahash = ahash_instance(inst); ahash->free(ahash); } static int __maybe_unused crypto_ahash_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_hash rhash; memset(&rhash, 0, sizeof(rhash)); strscpy(rhash.type, "ahash", sizeof(rhash.type)); rhash.blocksize = alg->cra_blocksize; rhash.digestsize = __crypto_hash_alg_common(alg)->digestsize; return nla_put(skb, CRYPTOCFGA_REPORT_HASH, sizeof(rhash), &rhash); } static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg) __maybe_unused; static void crypto_ahash_show(struct seq_file *m, struct crypto_alg *alg) { seq_printf(m, "type : ahash\n"); seq_printf(m, "async : %s\n", str_yes_no(alg->cra_flags & CRYPTO_ALG_ASYNC)); seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); seq_printf(m, "digestsize : %u\n", __crypto_hash_alg_common(alg)->digestsize); } static const struct crypto_type crypto_ahash_type = { .extsize = crypto_ahash_extsize, .init_tfm = crypto_ahash_init_tfm, .free = crypto_ahash_free_instance, #ifdef CONFIG_PROC_FS .show = crypto_ahash_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_ahash_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_AHASH_MASK, .type = CRYPTO_ALG_TYPE_AHASH, .tfmsize = offsetof(struct crypto_ahash, base), .algsize = offsetof(struct ahash_alg, halg.base), }; int crypto_grab_ahash(struct crypto_ahash_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask) { spawn->base.frontend = &crypto_ahash_type; return crypto_grab_spawn(&spawn->base, inst, name, type, mask); } EXPORT_SYMBOL_GPL(crypto_grab_ahash); struct crypto_ahash *crypto_alloc_ahash(const char *alg_name, u32 type, u32 mask) { return crypto_alloc_tfm(alg_name, &crypto_ahash_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_alloc_ahash); int crypto_has_ahash(const char *alg_name, u32 type, u32 mask) { return crypto_type_has_alg(alg_name, &crypto_ahash_type, type, mask); } EXPORT_SYMBOL_GPL(crypto_has_ahash); bool crypto_hash_alg_has_setkey(struct hash_alg_common *halg) { struct crypto_alg *alg = &halg->base; if (alg->cra_type == &crypto_shash_type) return crypto_shash_alg_has_setkey(__crypto_shash_alg(alg)); return __crypto_ahash_alg(alg)->setkey != ahash_nosetkey; } EXPORT_SYMBOL_GPL(crypto_hash_alg_has_setkey); struct crypto_ahash *crypto_clone_ahash(struct crypto_ahash *hash) { struct hash_alg_common *halg = crypto_hash_alg_common(hash); struct crypto_tfm *tfm = crypto_ahash_tfm(hash); struct crypto_ahash *fb = NULL; struct crypto_ahash *nhash; struct ahash_alg *alg; int err; if (!crypto_hash_alg_has_setkey(halg)) { tfm = crypto_tfm_get(tfm); if (IS_ERR(tfm)) return ERR_CAST(tfm); return hash; } nhash = crypto_clone_tfm(&crypto_ahash_type, tfm); if (IS_ERR(nhash)) return nhash; nhash->reqsize = hash->reqsize; nhash->statesize = hash->statesize; if (likely(hash->using_shash)) { struct crypto_shash **nctx = crypto_ahash_ctx(nhash); struct crypto_shash *shash; shash = crypto_clone_shash(ahash_to_shash(hash)); if (IS_ERR(shash)) { err = PTR_ERR(shash); goto out_free_nhash; } crypto_ahash_tfm(nhash)->exit = crypto_exit_ahash_using_shash; nhash->using_shash = true; *nctx = shash; return nhash; } if (crypto_ahash_need_fallback(hash)) { fb = crypto_clone_ahash(crypto_ahash_fb(hash)); err = PTR_ERR(fb); if (IS_ERR(fb)) goto out_free_nhash; crypto_ahash_tfm(nhash)->fb = crypto_ahash_tfm(fb); } err = -ENOSYS; alg = crypto_ahash_alg(hash); if (!alg->clone_tfm) goto out_free_fb; err = alg->clone_tfm(nhash, hash); if (err) goto out_free_fb; crypto_ahash_tfm(nhash)->exit = crypto_ahash_exit_tfm; return nhash; out_free_fb: crypto_free_ahash(fb); out_free_nhash: crypto_free_ahash(nhash); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(crypto_clone_ahash); static int ahash_default_export_core(struct ahash_request *req, void *out) { return -ENOSYS; } static int ahash_default_import_core(struct ahash_request *req, const void *in) { return -ENOSYS; } static int ahash_prepare_alg(struct ahash_alg *alg) { struct crypto_alg *base = &alg->halg.base; int err; if (alg->halg.statesize == 0) return -EINVAL; if (base->cra_reqsize && base->cra_reqsize < alg->halg.statesize) return -EINVAL; if (!(base->cra_flags & CRYPTO_ALG_ASYNC) && base->cra_reqsize > MAX_SYNC_HASH_REQSIZE) return -EINVAL; err = hash_prepare_alg(&alg->halg); if (err) return err; base->cra_type = &crypto_ahash_type; base->cra_flags |= CRYPTO_ALG_TYPE_AHASH; if ((base->cra_flags ^ CRYPTO_ALG_REQ_VIRT) & (CRYPTO_ALG_ASYNC | CRYPTO_ALG_REQ_VIRT)) base->cra_flags |= CRYPTO_ALG_NEED_FALLBACK; if (!alg->setkey) alg->setkey = ahash_nosetkey; if (base->cra_flags & CRYPTO_AHASH_ALG_BLOCK_ONLY) { BUILD_BUG_ON(MAX_ALGAPI_BLOCKSIZE >= 256); if (!alg->finup) return -EINVAL; base->cra_reqsize += base->cra_blocksize + 1; alg->halg.statesize += base->cra_blocksize + 1; alg->export_core = alg->export; alg->import_core = alg->import; } else if (!alg->export_core || !alg->import_core) { alg->export_core = ahash_default_export_core; alg->import_core = ahash_default_import_core; base->cra_flags |= CRYPTO_AHASH_ALG_NO_EXPORT_CORE; } return 0; } int crypto_register_ahash(struct ahash_alg *alg) { struct crypto_alg *base = &alg->halg.base; int err; err = ahash_prepare_alg(alg); if (err) return err; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_ahash); void crypto_unregister_ahash(struct ahash_alg *alg) { crypto_unregister_alg(&alg->halg.base); } EXPORT_SYMBOL_GPL(crypto_unregister_ahash); int crypto_register_ahashes(struct ahash_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_ahash(&algs[i]); if (ret) goto err; } return 0; err: for (--i; i >= 0; --i) crypto_unregister_ahash(&algs[i]); return ret; } EXPORT_SYMBOL_GPL(crypto_register_ahashes); void crypto_unregister_ahashes(struct ahash_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_ahash(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_ahashes); int ahash_register_instance(struct crypto_template *tmpl, struct ahash_instance *inst) { int err; if (WARN_ON(!inst->free)) return -EINVAL; err = ahash_prepare_alg(&inst->alg); if (err) return err; return crypto_register_instance(tmpl, ahash_crypto_instance(inst)); } EXPORT_SYMBOL_GPL(ahash_register_instance); void ahash_request_free(struct ahash_request *req) { if (unlikely(!req)) return; if (!ahash_req_on_stack(req)) { kfree(req); return; } ahash_request_zero(req); } EXPORT_SYMBOL_GPL(ahash_request_free); int crypto_hash_digest(struct crypto_ahash *tfm, const u8 *data, unsigned int len, u8 *out) { HASH_REQUEST_ON_STACK(req, crypto_ahash_fb(tfm)); int err; ahash_request_set_callback(req, 0, NULL, NULL); ahash_request_set_virt(req, data, out, len); err = crypto_ahash_digest(req); ahash_request_zero(req); return err; } EXPORT_SYMBOL_GPL(crypto_hash_digest); void ahash_free_singlespawn_instance(struct ahash_instance *inst) { crypto_drop_spawn(ahash_instance_ctx(inst)); kfree(inst); } EXPORT_SYMBOL_GPL(ahash_free_singlespawn_instance); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Asynchronous cryptographic hash type"); |
| 128 127 2 4 68 4 28 3 1 1 2 28 8 7 28 28 72 7 4 65 9 7 9 9 8 9 28 28 28 7 24 12 1 11 1 1 1 1 1 14 2 3 3 22 6 16 1 17 25 25 33 7 2 3 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 | // SPDX-License-Identifier: GPL-2.0 /* * To speed up listener socket lookup, create an array to store all sockets * listening on the same port. This allows a decision to be made after finding * the first socket. An optional BPF program can also be configured for * selecting the socket index from the array of available sockets. */ #include <net/ip.h> #include <net/sock_reuseport.h> #include <linux/bpf.h> #include <linux/idr.h> #include <linux/filter.h> #include <linux/rcupdate.h> #define INIT_SOCKS 128 DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); void reuseport_has_conns_set(struct sock *sk) { struct sock_reuseport *reuse; if (!rcu_access_pointer(sk->sk_reuseport_cb)) return; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (likely(reuse)) reuse->has_conns = 1; spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_has_conns_set); static void __reuseport_get_incoming_cpu(struct sock_reuseport *reuse) { /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu + 1); } static void __reuseport_put_incoming_cpu(struct sock_reuseport *reuse) { /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu - 1); } static void reuseport_get_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) { if (sk->sk_incoming_cpu >= 0) __reuseport_get_incoming_cpu(reuse); } static void reuseport_put_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) { if (sk->sk_incoming_cpu >= 0) __reuseport_put_incoming_cpu(reuse); } void reuseport_update_incoming_cpu(struct sock *sk, int val) { struct sock_reuseport *reuse; int old_sk_incoming_cpu; if (unlikely(!rcu_access_pointer(sk->sk_reuseport_cb))) { /* Paired with REAE_ONCE() in sk_incoming_cpu_update() * and compute_score(). */ WRITE_ONCE(sk->sk_incoming_cpu, val); return; } spin_lock_bh(&reuseport_lock); /* This must be done under reuseport_lock to avoid a race with * reuseport_grow(), which accesses sk->sk_incoming_cpu without * lock_sock() when detaching a shutdown()ed sk. * * Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ old_sk_incoming_cpu = sk->sk_incoming_cpu; WRITE_ONCE(sk->sk_incoming_cpu, val); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk. */ if (!reuse) goto out; if (old_sk_incoming_cpu < 0 && val >= 0) __reuseport_get_incoming_cpu(reuse); else if (old_sk_incoming_cpu >= 0 && val < 0) __reuseport_put_incoming_cpu(reuse); out: spin_unlock_bh(&reuseport_lock); } static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) { int left, right; if (!closed) { left = 0; right = reuse->num_socks; } else { left = reuse->max_socks - reuse->num_closed_socks; right = reuse->max_socks; } for (; left < right; left++) if (reuse->socks[left] == sk) return left; return -1; } static void __reuseport_add_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->num_socks] = sk; /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ smp_wmb(); reuse->num_socks++; reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, false); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; reuseport_put_incoming_cpu(sk, reuse); return true; } static void __reuseport_add_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, true); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); reuseport_put_incoming_cpu(sk, reuse); return true; } static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { struct sock_reuseport *reuse; reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC); if (!reuse) return NULL; reuse->max_socks = max_socks; RCU_INIT_POINTER(reuse->prog, NULL); return reuse; } int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; int id, ret = 0; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); /* Allocation attempts can occur concurrently via the setsockopt path * and the bind/hash path. Nothing to do when we lose the race. */ reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { if (reuse->num_closed_socks) { /* sk was shutdown()ed before */ ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); goto out; } /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. */ if (bind_inany) reuse->bind_inany = bind_inany; goto out; } reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { ret = -ENOMEM; goto out; } id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); ret = id; goto out; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; reuseport_get_incoming_cpu(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: spin_unlock_bh(&reuseport_lock); return ret; } EXPORT_SYMBOL(reuseport_alloc); static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) { struct sock_reuseport *more_reuse; u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; if (more_socks_size > U16_MAX) { if (reuse->num_closed_socks) { /* Make room by removing a closed sk. * The child has already been migrated. * Only reqsk left at this point. */ struct sock *sk; sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); __reuseport_detach_closed_sock(sk, reuse); return reuse; } return NULL; } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; more_reuse->incoming_cpu = reuse->incoming_cpu; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); memcpy(more_reuse->socks + (more_reuse->max_socks - more_reuse->num_closed_socks), reuse->socks + (reuse->max_socks - reuse->num_closed_socks), reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); /* Note: we use kfree_rcu here instead of reuseport_free_rcu so * that reuse and more_reuse can temporarily share a reference * to prog. */ kfree_rcu(reuse, rcu); return more_reuse; } static void reuseport_free_rcu(struct rcu_head *head) { struct sock_reuseport *reuse; reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); ida_free(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. * @sk2: Socket belonging to the existing reuseport group. * @bind_inany: Whether or not the group is bound to a local INANY address. * * May return ENOMEM and not add socket to group under memory pressure. */ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) { struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2, bind_inany); if (err) return err; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (old_reuse && old_reuse->num_closed_socks) { /* sk was shutdown()ed before */ int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); spin_unlock_bh(&reuseport_lock); return err; } if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); return -ENOMEM; } } __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); if (old_reuse) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } EXPORT_SYMBOL(reuseport_add_sock); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany) { if (old_reuse == reuse) { /* If sk was in the same reuseport group, just pop sk out of * the closed section and push sk into the listening section. */ __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, old_reuse); return 0; } if (!reuse) { /* In bind()/listen() path, we cannot carry over the eBPF prog * for the shutdown()ed socket. In setsockopt() path, we should * not change the eBPF prog of listening sockets by attaching a * prog to the shutdown()ed socket. Thus, we will allocate a new * reuseport group and detach sk from the old group. */ int id; reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) return -ENOMEM; id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); return id; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; } else { /* Move sk from the old group to the new one if * - all the other listeners in the old group were close()d or * shutdown()ed, and then sk2 has listen()ed on the same port * OR * - sk listen()ed without bind() (or with autobind), was * shutdown()ed, and then listen()s on another port which * sk2 listen()s on. */ if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) return -ENOMEM; } } __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk */ if (!reuse) goto out; /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * * Other bpf map types that work with reuseport, like sockmap, * don't need an explicit callback from here. They override sk * unhash/close ops to remove the sk from the map before we * get to this point. */ bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); if (!__reuseport_detach_closed_sock(sk, reuse)) __reuseport_detach_sock(sk, reuse); if (reuse->num_socks + reuse->num_closed_socks == 0) call_rcu(&reuse->rcu, reuseport_free_rcu); out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); void reuseport_stop_listen_sock(struct sock *sk) { if (sk->sk_protocol == IPPROTO_TCP) { struct sock_reuseport *reuse; struct bpf_prog *prog; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) || (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. */ bpf_sk_reuseport_detach(sk); __reuseport_detach_sock(sk, reuse); __reuseport_add_closed_sock(sk, reuse); spin_unlock_bh(&reuseport_lock); return; } spin_unlock_bh(&reuseport_lock); } /* Not capable to do migration, detach immediately */ reuseport_detach_sock(sk); } EXPORT_SYMBOL(reuseport_stop_listen_sock); static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) { struct sk_buff *nskb = NULL; u32 index; if (skb_shared(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return NULL; skb = nskb; } /* temporarily advance data past protocol header */ if (!pskb_pull(skb, hdr_len)) { kfree_skb(nskb); return NULL; } index = bpf_prog_run_save_cb(prog, skb); __skb_push(skb, hdr_len); consume_skb(nskb); if (index >= socks) return NULL; return reuse->socks[index]; } static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, u32 hash, u16 num_socks) { struct sock *first_valid_sk = NULL; int i, j; i = j = reciprocal_scale(hash, num_socks); do { struct sock *sk = reuse->socks[i]; if (sk->sk_state != TCP_ESTABLISHED) { /* Paired with WRITE_ONCE() in __reuseport_(get|put)_incoming_cpu(). */ if (!READ_ONCE(reuse->incoming_cpu)) return sk; /* Paired with WRITE_ONCE() in reuseport_update_incoming_cpu(). */ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) return sk; if (!first_valid_sk) first_valid_sk = sk; } i++; if (i >= num_socks) i = 0; } while (i != j); return first_valid_sk; } /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. * @hash: When no BPF filter is available, use this hash to select. * @skb: skb to run through BPF filter. * @hdr_len: BPF filter expects skb data pointer at payload data. If * the skb does not yet point at the payload, this parameter represents * how far the pointer needs to advance to reach the payload. * Returns a socket that should receive the packet (or NULL on error). */ struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len) { struct sock_reuseport *reuse; struct bpf_prog *prog; struct sock *sk2 = NULL; u16 socks; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); /* if memory allocation failed or add call is not yet complete */ if (!reuse) goto out; prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ if (!sk2) sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: rcu_read_unlock(); return sk2; } EXPORT_SYMBOL(reuseport_select_sock); /** * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. * @sk: close()ed or shutdown()ed socket in the group. * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or * NEW_SYN_RECV request socket during 3WHS. * @skb: skb to run through BPF filter. * Returns a socket (with sk_refcnt +1) that should accept the child socket * (or NULL on error). */ struct sock *reuseport_migrate_sock(struct sock *sk, struct sock *migrating_sk, struct sk_buff *skb) { struct sock_reuseport *reuse; struct sock *nsk = NULL; bool allocated = false; struct bpf_prog *prog; u16 socks; u32 hash; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (!reuse) goto out; socks = READ_ONCE(reuse->num_socks); if (unlikely(!socks)) goto failure; /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); hash = migrating_sk->sk_hash; prog = rcu_dereference(reuse->prog); if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req)) goto select_by_hash; goto failure; } if (!skb) { skb = alloc_skb(0, GFP_ATOMIC); if (!skb) goto failure; allocated = true; } nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); if (allocated) kfree_skb(skb); select_by_hash: if (!nsk) nsk = reuseport_select_sock_by_hash(reuse, hash, socks); if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) { nsk = NULL; goto failure; } out: rcu_read_unlock(); return nsk; failure: __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); goto out; } EXPORT_SYMBOL(reuseport_migrate_sock); int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; if (sk_unhashed(sk)) { int err; if (!sk->sk_reuseport) return -EINVAL; err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { /* The socket wasn't bound with SO_REUSEPORT */ return -EINVAL; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); rcu_assign_pointer(reuse->prog, prog); spin_unlock_bh(&reuseport_lock); sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_attach_prog); int reuseport_detach_prog(struct sock *sk) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuse must be checked after acquiring the reuseport_lock * because reuseport_grow() can detach a closed sk. */ if (!reuse) { spin_unlock_bh(&reuseport_lock); return sk->sk_reuseport ? -ENOENT : -EINVAL; } if (sk_unhashed(sk) && reuse->num_closed_socks) { spin_unlock_bh(&reuseport_lock); return -ENOENT; } old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); if (!old_prog) return -ENOENT; sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_detach_prog); |
| 2037 98 78 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Flexible mmap layout support * * Based on code by Ingo Molnar and Andi Kleen, copyrighted * as follows: * * Copyright 2003-2009 Red Hat Inc. * All Rights Reserved. * Copyright 2005 Andi Kleen, SUSE Labs. * Copyright 2007 Jiri Kosina, SUSE Labs. */ #include <linux/personality.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/limits.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/compat.h> #include <linux/elf-randomize.h> #include <asm/elf.h> #include <asm/io.h> #include "physaddr.h" struct va_alignment __read_mostly va_align = { .flags = -1, }; unsigned long task_size_32bit(void) { return IA32_PAGE_OFFSET; } unsigned long task_size_64bit(int full_addr_space) { return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW; } static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; if (current->flags & PF_RANDOMIZE) { max = (-1UL) & __STACK_RND_MASK(task_size == task_size_32bit()); max <<= PAGE_SHIFT; } return max; } #ifdef CONFIG_COMPAT # define mmap32_rnd_bits mmap_rnd_compat_bits # define mmap64_rnd_bits mmap_rnd_bits #else # define mmap32_rnd_bits mmap_rnd_bits # define mmap64_rnd_bits mmap_rnd_bits #endif #define SIZE_128M (128 * 1024 * 1024UL) static int mmap_is_legacy(void) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; return sysctl_legacy_va_layout; } static unsigned long arch_rnd(unsigned int rndbits) { if (!(current->flags & PF_RANDOMIZE)) return 0; return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; } unsigned long arch_mmap_rnd(void) { return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits); } static unsigned long mmap_base(unsigned long rnd, unsigned long task_size, struct rlimit *rlim_stack) { unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap; /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; /* * Top of mmap area (just below the process stack). * Leave an at least ~128 MB hole with possible stack randomization. */ gap = clamp(gap, SIZE_128M, (task_size / 6) * 5); return PAGE_ALIGN(task_size - gap - rnd); } static unsigned long mmap_legacy_base(unsigned long rnd, unsigned long task_size) { return __TASK_UNMAPPED_BASE(task_size) + rnd; } /* * This function, called very early during the creation of a new * process VM image, sets up which VM layout function to use: */ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base, unsigned long random_factor, unsigned long task_size, struct rlimit *rlim_stack) { *legacy_base = mmap_legacy_base(random_factor, task_size); if (mmap_is_legacy()) *base = *legacy_base; else *base = mmap_base(random_factor, task_size, rlim_stack); } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { if (mmap_is_legacy()) clear_bit(MMF_TOPDOWN, &mm->flags); else set_bit(MMF_TOPDOWN, &mm->flags); arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base, arch_rnd(mmap64_rnd_bits), task_size_64bit(0), rlim_stack); #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* * The mmap syscall mapping base decision depends solely on the * syscall type (64-bit or compat). This applies for 64bit * applications and 32bit applications. The 64bit syscall uses * mmap_base, the compat syscall uses mmap_compat_base. */ arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base, arch_rnd(mmap32_rnd_bits), task_size_32bit(), rlim_stack); #endif } unsigned long get_mmap_base(int is_legacy) { struct mm_struct *mm = current->mm; #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES if (in_32bit_syscall()) { return is_legacy ? mm->mmap_compat_legacy_base : mm->mmap_compat_base; } #endif return is_legacy ? mm->mmap_legacy_base : mm->mmap_base; } /** * mmap_address_hint_valid - Validate the address hint of mmap * @addr: Address hint * @len: Mapping length * * Check whether @addr and @addr + @len result in a valid mapping. * * On 32bit this only checks whether @addr + @len is <= TASK_SIZE. * * On 64bit with 5-level page tables another sanity check is required * because mappings requested by mmap(@addr, 0) which cross the 47-bit * virtual address boundary can cause the following theoretical issue: * * An application calls mmap(addr, 0), i.e. without MAP_FIXED, where @addr * is below the border of the 47-bit address space and @addr + @len is * above the border. * * With 4-level paging this request succeeds, but the resulting mapping * address will always be within the 47-bit virtual address space, because * the hint address does not result in a valid mapping and is * ignored. Hence applications which are not prepared to handle virtual * addresses above 47-bit work correctly. * * With 5-level paging this request would be granted and result in a * mapping which crosses the border of the 47-bit virtual address * space. If the application cannot handle addresses above 47-bit this * will lead to misbehaviour and hard to diagnose failures. * * Therefore ignore address hints which would result in a mapping crossing * the 47-bit virtual address boundary. * * Note, that in the same scenario with MAP_FIXED the behaviour is * different. The request with @addr < 47-bit and @addr + @len > 47-bit * fails on a 4-level paging machine but succeeds on a 5-level paging * machine. It is reasonable to expect that an application does not rely on * the failure of such a fixed mapping request, so the restriction is not * applied. */ bool mmap_address_hint_valid(unsigned long addr, unsigned long len) { if (TASK_SIZE - len < addr) return false; return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW); } /* Can we access it for direct reading/writing? Must be RAM: */ int valid_phys_addr_range(phys_addr_t addr, size_t count) { return addr + count - 1 <= __pa(high_memory - 1); } /* Can we access it through mmap? Must be a valid physical address: */ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count) { phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT; return phys_addr_valid(addr + count - 1); } /* * Only allow root to set high MMIO mappings to PROT_NONE. * This prevents an unpriv. user to set them to PROT_NONE and invert * them, then pointing to valid memory for L1TF speculation. * * Note: for locked down kernels may want to disable the root override. */ bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { if (!boot_cpu_has_bug(X86_BUG_L1TF)) return true; if (!__pte_needs_invert(pgprot_val(prot))) return true; /* If it's real memory always allow */ if (pfn_valid(pfn)) return true; if (pfn >= l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN)) return false; return true; } |
| 43 43 61 61 4 289 18 2 262 3 5 2 169 5 96 3 212 4 4 50 54 263 2 23 3 10 1 22 72 204 119 35 200 216 3 15 7 199 1 219 2 2 2 66 66 65 65 65 2 63 65 65 34 64 93 93 93 55 1 54 1 11 51 2 2 5 2 6 39 13 1 13 13 12 1 13 42 34 72 1 1 73 73 73 52 53 53 53 53 51 53 53 53 51 2 52 1 53 31 22 32 22 22 22 51 2 53 53 22 1 40 16 68 68 6 2 61 6 35 21 18 2 1 32 3 2 1 1 1 26 26 21 21 32 52 1 1 1 1 98 80 83 29 1 53 1 4 294 286 8 55 56 35 31 31 272 98 18 170 21 250 21 23 2 3 4 1 5 3 2 5 1 4 147 146 161 161 1 160 3 155 155 153 149 103 2 2 17 1 1 15 12 12 3 3 104 1 2 6 100 96 3 2 5 47 78 8 12 167 3 164 162 6 157 154 19 260 260 561 1 1 25 25 1 25 1 26 26 9 1 25 489 6 489 489 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * TCP over IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on: * linux/net/ipv4/tcp.c * linux/net/ipv4/tcp_input.c * linux/net/ipv4/tcp_output.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. * YOSHIFUJI Hideaki @USAGI: convert /proc/net/tcp6 to seq_file. */ #include <linux/bottom_half.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/jiffies.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/init.h> #include <linux/jhash.h> #include <linux/ipsec.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/random.h> #include <linux/indirect_call_wrapper.h> #include <net/tcp.h> #include <net/ndisc.h> #include <net/inet6_hashtables.h> #include <net/inet6_connection_sock.h> #include <net/ipv6.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/inet_ecn.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/snmp.h> #include <net/dsfield.h> #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> #include <net/hotdata.h> #include <net/busy_poll.h> #include <net/rstreason.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason); static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; const struct inet_connection_sock_af_ops ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #endif /* Helper returning the inet6 address from a given tcp socket. * It can be used in TCP stack instead of inet6_sk(sk). * This avoids a dereference and allow compiler optimizations. * It is a specialized version of inet6_sk_generic(). */ #define tcp_inet6_sk(sk) (&container_of_const(tcp_sk(sk), \ struct tcp6_sock, tcp)->inet6) static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); sk->sk_rx_dst_ifindex = skb->skb_iif; sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst)); } } static u32 tcp_v6_init_seq(const struct sk_buff *skb) { return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v6_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_connection_sock *icsk = inet_csk(sk); struct in6_addr *saddr = NULL, *final_p, final; struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct ipv6_txoptions *opt; struct dst_entry *dst; struct flowi6 fl6; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; memset(&fl6, 0, sizeof(fl6)); if (inet6_test_bit(SNDFLOW, sk)) { fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; IP6_ECN_flow_init(fl6.flowlabel); if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; fl6_sock_release(flowlabel); } } /* * connect() to INADDR_ANY means loopback (BSD'ism). */ if (ipv6_addr_any(&usin->sin6_addr)) { if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -ENETUNREACH; if (addr_type&IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { /* If interface is set while binding, indices * must coincide. */ if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) return -EINVAL; sk->sk_bound_dev_if = usin->sin6_scope_id; } /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) return -EINVAL; } if (tp->rx_opt.ts_recent_stamp && !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* * TCP over IPv4 */ if (addr_type & IPV6_ADDR_MAPPED) { u32 exthdrlen = icsk->icsk_ext_hdr_len; struct sockaddr_in sin; if (ipv6_only_sock(sk)) return -ENETUNREACH; sin.sin_family = AF_INET; sin.sin_port = usin->sin6_port; sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_mapped); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, true); sk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ WRITE_ONCE(icsk->icsk_af_ops, &ipv6_specific); if (sk_is_mptcp(sk)) mptcpv6_handle_mapped(sk, false); sk->sk_backlog_rcv = tcp_v6_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tp->af_specific = &tcp_sock_ipv6_specific; #endif goto failure; } np->saddr = sk->sk_v6_rcv_saddr; return err; } if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) saddr = &sk->sk_v6_rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; if (IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) && !fl6.fl6_sport) fl6.flowi6_flags = FLOWI_FLAG_ANY_SPORT; fl6.flowi6_uid = sk->sk_uid; opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); dst = ip6_dst_lookup_flow(net, sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; } tp->tcp_usec_ts = dst_tcp_usec_ts(dst); tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { saddr = &fl6.saddr; err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); if (err) goto failure; } /* set the source address */ np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (opt) icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; sk_set_txhash(sk); if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcpv6_seq(np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); } if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto late_failure; err = tcp_connect(sk); if (err) goto late_failure; return 0; late_failure: tcp_set_state(sk, TCP_CLOSE); inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); /* Drop requests trying to increase our current mss. * Check done in __ip6_rt_update_pmtu() is too late. */ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) return; dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { tcp_sync_mss(sk, dst_mtu(dst)); tcp_simple_retransmit(sk); } } static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct net *net = dev_net_rcu(skb->dev); struct request_sock *fastopen; struct ipv6_pinfo *np; struct tcp_sock *tp; __u32 seq, snd_una; struct sock *sk; bool fatal; int err; sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &hdr->daddr, th->dest, &hdr->saddr, ntohs(th->source), skb->dev->ifindex, inet6_sdif(skb)); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { /* To increase the counter of ignored icmps for TCP-AO */ tcp_ao_ignore_icmp(sk, AF_INET6, type, code); inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); fatal = icmpv6_err_convert(type, code, &err); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, fatal); return 0; } if (tcp_ao_ignore_icmp(sk, AF_INET6, type, code)) { sock_put(sk); return 0; } bh_lock_sock(sk); if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == TCP_CLOSE) goto out; if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (ipv6_hdr(skb)->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } } tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } np = tcp_inet6_sk(sk); if (type == NDISC_REDIRECT) { if (!sock_owned_by_user(sk)) { struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) dst->ops->redirect(dst, sk, skb); } goto out; } if (type == ICMPV6_PKT_TOOBIG) { u32 mtu = ntohl(info); /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; if (!ip6_sk_accept_pmtu(sk)) goto out; if (mtu < IPV6_MIN_MTU) goto out; WRITE_ONCE(tp->mtu_info, mtu); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); goto out; } /* Might be for an request_sock */ switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); if (!sock_owned_by_user(sk)) tcp_done_with_error(sk, err); else WRITE_ONCE(sk->sk_err_soft, err); goto out; case TCP_LISTEN: break; default: /* check if this ICMP message allows revert of backoff. * (see RFC 6069) */ if (!fastopen && type == ICMPV6_DEST_UNREACH && code == ICMPV6_NOROUTE) tcp_ld_RTO_revert(sk, seq); } if (!sock_owned_by_user(sk) && inet6_test_bit(RECVERR6, sk)) { WRITE_ONCE(sk->sk_err, err); sk_error_report(sk); } else { WRITE_ONCE(sk->sk_err_soft, err); } out: bh_unlock_sock(sk); sock_put(sk); return 0; } static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct flowi6 *fl6 = &fl->u.ip6; struct sk_buff *skb; int err = -ENOMEM; u8 tclass; /* First, grab a route. */ if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, IPPROTO_TCP)) == NULL) goto done; skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb); if (skb) { __tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr, &ireq->ir_v6_rmt_addr); fl6->daddr = ireq->ir_v6_rmt_addr; if (inet6_test_bit(REPFLOW, sk) && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && tcp_bpf_ca_needs_ecn((struct sock *)req)) tclass |= INET_ECN_ECT_0; rcu_read_lock(); opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); err = ip6_xmit(sk, skb, fl6, skb->mark ? : READ_ONCE(sk->sk_mark), opt, tclass, READ_ONCE(sk->sk_priority)); rcu_read_unlock(); err = net_xmit_eval(err); } done: return err; } static void tcp_v6_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->ipv6_opt); consume_skb(inet_rsk(req)->pktopts); } #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr, int l3index) { return tcp_md5_do_lookup(sk, l3index, (union tcp_md5_addr *)addr, AF_INET6); } static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { int l3index; l3index = l3mdev_master_ifindex_by_index(sock_net(sk), addr_sk->sk_bound_dev_if); return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr, l3index); } static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, sockptr_t optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; union tcp_ao_addr *addr; int l3index = 0; u8 prefixlen; bool l3flag; u8 flags; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_sockptr(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin6->sin6_family != AF_INET6) return -EINVAL; flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; l3flag = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 128 || (ipv6_addr_v4mapped(&sin6->sin6_addr) && prefixlen > 32)) return -EINVAL; } else { prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128; } if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex && cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); if (dev && netif_is_l3_master(dev)) l3index = dev->ifindex; rcu_read_unlock(); /* ok to reference set/not set outside of rcu; * right now device MUST be an L3 master */ if (!dev || !l3index) return -EINVAL; } if (!cmd.tcpm_keylen) { if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags); return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { addr = (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3]; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } addr = (union tcp_md5_addr *)&sin6->sin6_addr; /* Don't allow keys for peers that have a matching TCP-AO key. * See the comment in tcp_ao_add_cmd() */ if (tcp_ao_required(sk, addr, AF_INET6, l3flag ? l3index : -1, false)) return -EKEYREJECTED; return tcp_md5_do_add(sk, addr, AF_INET6, prefixlen, l3index, flags, cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v6_md5_hash_headers(struct tcp_sigpool *hp, const struct in6_addr *daddr, const struct in6_addr *saddr, const struct tcphdr *th, int nbytes) { struct tcp6_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; /* 1. TCP pseudo-header (RFC2460) */ bp->saddr = *saddr; bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->req); } static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, const struct in6_addr *daddr, struct in6_addr *saddr, const struct tcphdr *th) { struct tcp_sigpool hp; if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } static int tcp_v6_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); const struct in6_addr *saddr, *daddr; struct tcp_sigpool hp; if (sk) { /* valid for establish/request sockets */ saddr = &sk->sk_v6_rcv_saddr; daddr = &sk->sk_v6_daddr; } else { const struct ipv6hdr *ip6h = ipv6_hdr(skb); saddr = &ip6h->saddr; daddr = &ip6h->daddr; } if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) goto clear_hash_nostart; if (crypto_ahash_init(hp.req)) goto clear_hash; if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(&hp, key)) goto clear_hash; ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); if (crypto_ahash_final(hp.req)) goto clear_hash; tcp_sigpool_end(&hp); return 0; clear_hash: tcp_sigpool_end(&hp); clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } #endif static void tcp_v6_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb, u32 tw_isn) { bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); struct inet_request_sock *ireq = inet_rsk(req); const struct ipv6_pinfo *np = tcp_inet6_sk(sk_listener); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ir_rmt_addr = LOOPBACK4_IPV6; ireq->ir_loc_addr = LOOPBACK4_IPV6; /* So that link locals have meaning */ if ((!sk_listener->sk_bound_dev_if || l3_slave) && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); if (!tw_isn && (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || inet6_test_bit(REPFLOW, sk_listener))) { refcount_inc(&skb->users); ireq->pktopts = skb; } } static struct dst_entry *tcp_v6_route_req(const struct sock *sk, struct sk_buff *skb, struct flowi *fl, struct request_sock *req, u32 tw_isn) { tcp_v6_init_req(req, sk, skb, tw_isn); if (security_inet_conn_request(sk, skb, req)) return NULL; return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup_rsk, .ao_calc_key = tcp_v6_ao_calc_key_rsk, .ao_synack_hash = tcp_v6_ao_synack_hash, #endif #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, .init_seq = tcp_v6_init_seq, .init_ts_off = tcp_v6_init_ts_off, .send_synack = tcp_v6_send_synack, }; static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, int rst, u8 tclass, __be32 label, u32 priority, u32 txhash, struct tcp_key *key) { struct net *net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); unsigned int tot_len = sizeof(struct tcphdr); struct sock *ctl_sk = net->ipv6.tcp_sk; const struct tcphdr *th = tcp_hdr(skb); __be32 mrst = 0, *topt; struct dst_entry *dst; struct sk_buff *buff; struct tcphdr *t1; struct flowi6 fl6; u32 mark = 0; if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; if (tcp_key_is_md5(key)) tot_len += TCPOLEN_MD5SIG_ALIGNED; if (tcp_key_is_ao(key)) tot_len += tcp_ao_len_aligned(key->ao_key); #ifdef CONFIG_MPTCP if (rst && !tcp_key_is_md5(key)) { mrst = mptcp_reset_option(skb); if (mrst) tot_len += sizeof(__be32); } #endif buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (!buff) return; skb_reserve(buff, MAX_TCP_HEADER); t1 = skb_push(buff, tot_len); skb_reset_transport_header(buff); /* Swap the send and the receive. */ memset(t1, 0, sizeof(*t1)); t1->dest = th->source; t1->source = th->dest; t1->doff = tot_len / 4; t1->seq = htonl(seq); t1->ack_seq = htonl(ack); t1->ack = !rst || !th->ack; t1->rst = rst; t1->window = htons(win); topt = (__be32 *)(t1 + 1); if (tsecr) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); *topt++ = htonl(tsval); *topt++ = htonl(tsecr); } if (mrst) *topt++ = mrst; #ifdef CONFIG_TCP_MD5SIG if (tcp_key_is_md5(key)) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); tcp_v6_md5_hash_hdr((__u8 *)topt, key->md5_key, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, t1); } #endif #ifdef CONFIG_TCP_AO if (tcp_key_is_ao(key)) { *topt++ = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | (key->rcv_next)); tcp_ao_hash_hdr(AF_INET6, (char *)topt, key->ao_key, key->traffic_key, (union tcp_ao_addr *)&ipv6_hdr(skb)->saddr, (union tcp_ao_addr *)&ipv6_hdr(skb)->daddr, t1, key->sne); } #endif memset(&fl6, 0, sizeof(fl6)); fl6.daddr = ipv6_hdr(skb)->saddr; fl6.saddr = ipv6_hdr(skb)->daddr; fl6.flowlabel = label; buff->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr); fl6.flowi6_proto = IPPROTO_TCP; if (rt6_need_strict(&fl6.daddr) && !oif) fl6.flowi6_oif = tcp_v6_iif(skb); else { if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; fl6.flowi6_oif = oif; } if (sk) { /* unconstify the socket only to attach it to buff with care. */ skb_set_owner_edemux(buff, (struct sock *)sk); if (sk->sk_state == TCP_TIME_WAIT) mark = inet_twsk(sk)->tw_mark; else mark = READ_ONCE(sk->sk_mark); skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC); } if (txhash) { /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ skb_set_hash(buff, txhash, PKT_HASH_TYPE_L4); } fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); /* Pass a socket to ip6_dst_lookup either it is for RST * Underlying function will use this to retrieve the network * namespace */ if (sk && sk->sk_state != TCP_TIME_WAIT) dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); /*sk's xfrm_policy can be referred*/ else dst = ip6_dst_lookup_flow(net, ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass, priority); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); return; } kfree_skb(buff); } static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, enum sk_rst_reason reason) { const struct tcphdr *th = tcp_hdr(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); const __u8 *md5_hash_location = NULL; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) bool allocated_traffic_key = false; #endif const struct tcp_ao_hdr *aoh; struct tcp_key key = {}; u32 seq = 0, ack_seq = 0; __be32 label = 0; u32 priority = 0; struct net *net; u32 txhash = 0; int oif = 0; #ifdef CONFIG_TCP_MD5SIG unsigned char newhash[16]; int genhash; struct sock *sk1 = NULL; #endif if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && !ipv6_unicast_destination(skb)) return; net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev); /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(th, &md5_hash_location, &aoh)) return; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_lock(); #endif #ifdef CONFIG_TCP_MD5SIG if (sk && sk_fullsock(sk)) { int l3index; /* sdif set, means packet ingressed via a device * in an L3 domain and inet_iif is set to it. */ l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key.md5_key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr, l3index); if (key.md5_key) key.type = TCP_KEY_MD5; } else if (md5_hash_location) { int dif = tcp_v6_iif_l3_slave(skb); int sdif = tcp_v6_sdif(skb); int l3index; /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, ntohs(th->source), dif, sdif); if (!sk1) goto out; /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to it. */ l3index = tcp_v6_sdif(skb) ? dif : 0; key.md5_key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr, l3index); if (!key.md5_key) goto out; key.type = TCP_KEY_MD5; genhash = tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) goto out; } #endif if (th->ack) seq = ntohl(th->ack_seq); else ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); #ifdef CONFIG_TCP_AO if (aoh) { int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; if (tcp_ao_prepare_reset(sk, skb, aoh, l3index, seq, &key.ao_key, &key.traffic_key, &allocated_traffic_key, &key.rcv_next, &key.sne)) goto out; key.type = TCP_KEY_AO; } #endif if (sk) { oif = sk->sk_bound_dev_if; if (sk_fullsock(sk)) { if (inet6_test_bit(REPFLOW, sk)) label = ip6_flowlabel(ipv6h); priority = READ_ONCE(sk->sk_priority); txhash = sk->sk_txhash; } if (sk->sk_state == TCP_TIME_WAIT) { label = cpu_to_be32(inet_twsk(sk)->tw_flowlabel); priority = inet_twsk(sk)->tw_priority; txhash = inet_twsk(sk)->tw_txhash; } } else { if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET) label = ip6_flowlabel(ipv6h); } trace_tcp_send_reset(sk, skb, reason); tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1, ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK, label, priority, txhash, &key); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) out: if (allocated_traffic_key) kfree(key.traffic_key); rcu_read_unlock(); #endif } static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_key *key, u8 tclass, __be32 label, u32 priority, u32 txhash) { tcp_v6_send_response(sk, skb, seq, ack, win, tsval, tsecr, oif, 0, tclass, label, priority, txhash, key); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb, enum tcp_tw_status tw_status) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); u8 tclass = tw->tw_tclass; struct tcp_key key = {}; if (tw_status == TCP_TW_ACK_OOW) tclass &= ~INET_ECN_MASK; #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao_info; if (static_branch_unlikely(&tcp_ao_needed.key)) { /* FIXME: the segment to-be-acked is not verified yet */ ao_info = rcu_dereference(tcptw->ao_info); if (ao_info) { const struct tcp_ao_hdr *aoh; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto out; if (aoh) key.ao_key = tcp_ao_established_key(sk, ao_info, aoh->rnext_keyid, -1); } } if (key.ao_key) { struct tcp_ao_key *rnext_key; key.traffic_key = snd_other_key(key.ao_key); /* rcv_next switches to our rcv_next */ rnext_key = READ_ONCE(ao_info->rnext_key); key.rcv_next = rnext_key->rcvid; key.sne = READ_ONCE(ao_info->snd_sne); key.type = TCP_KEY_AO; #else if (0) { #endif #ifdef CONFIG_TCP_MD5SIG } else if (static_branch_unlikely(&tcp_md5_needed.key)) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, tw->tw_txhash); #ifdef CONFIG_TCP_AO out: #endif inet_twsk_put(tw); } static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_key key = {}; #ifdef CONFIG_TCP_AO if (static_branch_unlikely(&tcp_ao_needed.key) && tcp_rsk_used_ao(req)) { const struct in6_addr *addr = &ipv6_hdr(skb)->saddr; const struct tcp_ao_hdr *aoh; int l3index; l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; /* Invalid TCP option size or twice included auth */ if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) return; if (!aoh) return; key.ao_key = tcp_ao_do_lookup(sk, l3index, (union tcp_ao_addr *)addr, AF_INET6, aoh->rnext_keyid, -1); if (unlikely(!key.ao_key)) { /* Send ACK with any matching MKT for the peer */ key.ao_key = tcp_ao_do_lookup(sk, l3index, (union tcp_ao_addr *)addr, AF_INET6, -1, -1); /* Matching key disappeared (user removed the key?) * let the handshake timeout. */ if (!key.ao_key) { net_info_ratelimited("TCP-AO key for (%pI6, %d)->(%pI6, %d) suddenly disappeared, won't ACK new connection\n", addr, ntohs(tcp_hdr(skb)->source), &ipv6_hdr(skb)->daddr, ntohs(tcp_hdr(skb)->dest)); return; } } key.traffic_key = kmalloc(tcp_ao_digest_size(key.ao_key), GFP_ATOMIC); if (!key.traffic_key) return; key.type = TCP_KEY_AO; key.rcv_next = aoh->keyid; tcp_v6_ao_calc_key_rsk(key.ao_key, key.traffic_key, req); #else if (0) { #endif #ifdef CONFIG_TCP_MD5SIG } else if (static_branch_unlikely(&tcp_md5_needed.key)) { int l3index = tcp_v6_sdif(skb) ? tcp_v6_iif_l3_slave(skb) : 0; key.md5_key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), req->ts_recent, sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK, 0, READ_ONCE(sk->sk_priority), READ_ONCE(tcp_rsk(req)->txhash)); if (tcp_key_is_ao(&key)) kfree(key.traffic_key); } static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v6_check(sk, skb); #endif return sk; } u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, th); if (mss) { *cookie = __cookie_v6_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_conn_request(sk, skb); if (!ipv6_unicast_destination(skb)) goto drop; if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); return 0; } return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); drop: tcp_listendrop(sk); return 0; /* don't send reset */ } static void tcp_v6_restore_cb(struct sk_buff *skb) { /* We need to move header back to the beginning if xfrm6_policy_check() * and tcp_v6_fill_cb() are going to be called again. * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there. */ memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6, sizeof(struct inet6_skb_parm)); } static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; struct ipv6_pinfo *newnp; const struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct ipv6_txoptions *opt; struct inet_sock *newinet; bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; int l3index; #endif struct flowi6 fl6; if (skb->protocol == htons(ETH_P_IP)) { /* * v6 mapped */ newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst, req_unhash, own_req); if (!newsk) return NULL; inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); newnp = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newnp->saddr = newsk->sk_v6_rcv_saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; if (sk_is_mptcp(newsk)) mptcpv6_handle_mapped(newsk, true); newsk->sk_backlog_rcv = tcp_v4_do_rcv; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) newtp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet_iif(skb); newnp->mcast_hops = ip_hdr(skb)->ttl; newnp->rcv_flowinfo = 0; if (inet6_test_bit(REPFLOW, sk)) newnp->flow_label = 0; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count * here, tcp_create_openreq_child now does this for us, see the comment in * that function for the gory details. -acme */ /* It is tricky place. Until this moment IPv4 tcp worked with IPv6 icsk.icsk_af_ops. Sync it now. */ tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); return newsk; } ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) goto out_overflow; if (!dst) { dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) goto out; } newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks * count here, tcp_create_openreq_child now does this for us, see the * comment in that function for the gory details. -acme */ newsk->sk_gso_type = SKB_GSO_TCPV6; inet6_sk_rx_dst_set(newsk, skb); inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); newnp = tcp_inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); ip6_dst_store(newsk, dst, NULL, NULL); newnp->saddr = ireq->ir_v6_loc_addr; /* Now IPv6 options... First: no IPv4 options. */ newinet->inet_opt = NULL; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; newnp->ipv6_fl_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = tcp_v6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb)); if (inet6_test_bit(REPFLOW, sk)) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; /* Clone native IPv6 options from listening socket (if any) Yes, keeping reference count would be much more clever, but we make one more one thing there: reattach optmem to newsk. */ opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); RCU_INIT_POINTER(newnp->opt, opt); } inet_csk(newsk)->icsk_ext_hdr_len = 0; if (opt) inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen + opt->opt_flen; tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); if (!tcp_rsk_used_ao(req)) { /* Copy over the MD5 key from the original socket */ key = tcp_v6_md5_do_lookup(sk, &newsk->sk_v6_daddr, l3index); if (key) { const union tcp_md5_addr *addr; addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr; if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) { inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto out; } } } #endif #ifdef CONFIG_TCP_AO /* Copy over tcp_ao_info if any */ if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET6)) goto out; /* OOM */ #endif if (__inet_inherit_port(sk, newsk) < 0) { inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto out; } *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); } } else { if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; out_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); out_nonewsk: dst_release(dst); out: tcp_listendrop(sk); return NULL; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, u32)); /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ INDIRECT_CALLABLE_SCOPE int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct sk_buff *opt_skb = NULL; enum skb_drop_reason reason; struct tcp_sock *tp; /* Imagine: socket is IPv6. IPv4 packet arrives, goes to IPv4 receive handler and backlogged. From backlog it always goes here. Kerboom... Fortunately, tcp_rcv_established and rcv_established handle them correctly, but it is not case with tcp_v6_hnd_req and tcp_v6_send_reset(). --ANK */ if (skb->protocol == htons(ETH_P_IP)) return tcp_v4_do_rcv(sk, skb); /* * socket locking is here for SMP purposes as backlog rcv * is currently called with bh processing disabled. */ /* Do Stevens' IPV6_PKTOPTIONS. Yes, guys, it is the only place in our code, where we may make it not affecting IPv4. The rest of code is protocol independent, and I do not like idea to uglify IPv4. Actually, all the idea behind IPV6_PKTOPTIONS looks not very well thought. For now we latch options, received in the last packet, enqueued by tcp. Feel free to propose better solution. --ANK (980728) */ if (np->rxopt.all && sk->sk_state != TCP_LISTEN) opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, dst, sk->sk_rx_dst_cookie) == NULL) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); if (opt_skb) goto ipv6_pktoptions; return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v6_cookie_check(sk, skb); if (nsk != sk) { if (nsk) { reason = tcp_child_process(sk, nsk, skb); if (reason) goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); reason = tcp_rcv_state_process(sk, skb); if (reason) goto reset; if (opt_skb) goto ipv6_pktoptions; return 0; reset: tcp_v6_send_reset(sk, skb, sk_rst_convert_drop_reason(reason)); discard: if (opt_skb) __kfree_skb(opt_skb); sk_skb_reason_drop(sk, skb, reason); return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; ipv6_pktoptions: /* Do you ask, what is it? 1. skb was enqueued by tcp. 2. skb is added to tail of read queue, rather than out of order. 3. socket is not in passive state. 4. Finally, it really contains options, which user wants to receive. */ tp = tcp_sk(sk); if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { if (np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo) WRITE_ONCE(np->mcast_oif, tcp_v6_iif(opt_skb)); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) WRITE_ONCE(np->mcast_hops, ipv6_hdr(opt_skb)->hop_limit); if (np->rxopt.bits.rxflow || np->rxopt.bits.rxtclass) np->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(opt_skb)); if (inet6_test_bit(REPFLOW, sk)) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { __kfree_skb(opt_skb); opt_skb = xchg(&np->pktoptions, NULL); } } consume_skb(opt_skb); return 0; } static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, const struct tcphdr *th) { /* This is tricky: we move IP6CB at its correct location into * TCP_SKB_CB(). It must be done after xfrm6_policy_check(), because * _decode_session6() uses IP6CB(). * barrier() makes sure compiler won't play aliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h6, IP6CB(skb), sizeof(struct inet6_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff*4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th); TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); enum skb_drop_reason drop_reason; enum tcp_tw_status tw_status; int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; struct sock *sk = NULL; bool refcounted; int ret; u32 isn; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* * Count it even if it's bad. */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; } if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); lookup: sk = __inet6_lookup_skb(net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, inet6_iif(skb), sdif, &refcounted); if (!sk) goto no_tcp_socket; if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) drop_reason = SKB_DROP_REASON_XFRM_POLICY; else drop_reason = tcp_inbound_hash(sk, req, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); if (!nsk) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } sk = nsk; /* reuseport_migrate_sock() has already held one sk_refcnt * before returning. */ } else { sock_hold(sk); } refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); } else { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v6_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); } else { drop_reason = tcp_child_process(sk, nsk, skb); if (drop_reason) { enum sk_rst_reason rst_reason; rst_reason = sk_rst_convert_drop_reason(drop_reason); tcp_v6_send_reset(nsk, skb, rst_reason); goto discard_and_relse; } sock_put(sk); return 0; } } process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); drop_reason = SKB_DROP_REASON_TCP_MINTTL; goto discard_and_relse; } } if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; } drop_reason = tcp_inbound_hash(sk, NULL, skb, &hdr->saddr, &hdr->daddr, AF_INET6, dif, sdif); if (drop_reason) goto discard_and_relse; nf_reset_ct(skb); if (tcp_filter(sk, skb)) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v6_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { ret = tcp_v6_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); put_and_return: if (refcounted) sock_put(sk); return ret ? -1 : 0; no_tcp_socket: drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { csum_error: drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v6_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason)); } discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v6_fill_cb(skb, hdr, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn, &drop_reason); switch (tw_status) { case TCP_TW_SYN: { struct sock *sk2; sk2 = inet6_lookup_listener(net, net->ipv4.tcp_death_row.hashinfo, skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); inet_twsk_deschedule_put(tw); sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; __this_cpu_write(tcp_tw_isn, isn); goto process; } } /* to ACK */ fallthrough; case TCP_TW_ACK: case TCP_TW_ACK_OOW: tcp_v6_timewait_ack(sk, skb, tw_status); break; case TCP_TW_RST: tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS: ; } goto discard_it; } void tcp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net_rcu(skb->dev); const struct ipv6hdr *hdr; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return; hdr = ipv6_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return; /* Note : We use inet6_iif() here, not tcp_v6_iif() */ sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &hdr->saddr, th->source, &hdr->daddr, ntohs(th->dest), inet6_iif(skb), inet6_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } } static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp6_timewait_sock), .twsk_destructor = tcp_twsk_destructor, }; INDIRECT_CALLABLE_SCOPE void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { __tcp_v6_send_check(skb, &sk->sk_v6_rcv_saddr, &sk->sk_v6_daddr); } const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, .sk_rx_dst_set = inet6_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .mtu_reduced = tcp_v6_mtu_reduced, }; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup, .calc_ao_hash = tcp_v6_ao_hash_skb, .ao_parse = tcp_v6_parse_ao, .ao_calc_key_sk = tcp_v6_ao_calc_key_sk, #endif }; #endif /* * TCP over IPv4 via INET6 API */ static const struct inet_connection_sock_af_ops ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .mtu_reduced = tcp_v4_mtu_reduced, }; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { #ifdef CONFIG_TCP_MD5SIG .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v6_parse_md5_keys, #endif #ifdef CONFIG_TCP_AO .ao_lookup = tcp_v6_ao_lookup, .calc_ao_hash = tcp_v4_ao_hash_skb, .ao_parse = tcp_v6_parse_ao, .ao_calc_key_sk = tcp_v4_ao_calc_key_sk, #endif }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v6_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv6_specific; #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) tcp_sk(sk)->af_specific = &tcp_sock_ipv6_specific; #endif return 0; } #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, const struct request_sock *req, int i) { long ttd = req->rsk_timer.expires - jiffies; const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr; const struct in6_addr *dest = &inet_rsk(req)->ir_v6_rmt_addr; if (ttd < 0) ttd = 0; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], inet_rsk(req)->ir_num, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], ntohs(inet_rsk(req)->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_to_clock_t(ttd), req->num_timeout, from_kuid_munged(seq_user_ns(seq), sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) { const struct in6_addr *dest, *src; __u16 destp, srcp; int timer_active; unsigned long timer_expires; const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; u8 icsk_pending; int rx_queue; int state; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); icsk_pending = smp_load_acquire(&icsk->icsk_pending); if (icsk_pending == ICSK_TIME_RETRANS || icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk_timeout(icsk); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk_timeout(icsk); } else if (timer_pending(&sp->sk_timer)) { timer_active = 2; timer_expires = sp->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sp); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sp->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)), icsk->icsk_probes_out, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp), tcp_snd_cwnd(tp), state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } static void get_timewait6_sock(struct seq_file *seq, struct inet_timewait_sock *tw, int i) { long delta = tw->tw_timer.expires - jiffies; const struct in6_addr *dest, *src; __u16 destp, srcp; dest = &tw->tw_v6_daddr; src = &tw->tw_v6_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } static int tcp6_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl " "local_address " "remote_address " "st tx_queue rx_queue tr tm->when retrnsmt" " uid timeout inode\n"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait6_sock(seq, v, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq6(seq, v, st->num); else get_tcp6_sock(seq, v, st->num); out: return 0; } static const struct seq_operations tcp6_seq_ops = { .show = tcp6_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp6_seq_afinfo = { .family = AF_INET6, }; int __net_init tcp6_proc_init(struct net *net) { if (!proc_create_net_data("tcp6", 0444, net->proc_net, &tcp6_seq_ops, sizeof(struct tcp_iter_state), &tcp6_seq_afinfo)) return -ENOMEM; return 0; } void tcp6_proc_exit(struct net *net) { remove_proc_entry("tcp6", net->proc_net); } #endif struct proto tcpv6_prot = { .name = "TCPv6", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v6_pre_connect, .connect = tcp_v6_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .bpf_bypass_getsockopt = tcp_bpf_bypass_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, .hash = inet6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .put_port = inet_put_port, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = tcp_bpf_update_proto, #endif .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), .ipv6_pinfo_offset = offsetof(struct tcp6_sock, inet6), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp6_timewait_sock_ops, .rsk_prot = &tcp6_request_sock_ops, .h.hashinfo = NULL, .no_autobind = true, .diag_destroy = tcp_abort, }; EXPORT_SYMBOL_GPL(tcpv6_prot); static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }; static int __net_init tcpv6_net_init(struct net *net) { int res; res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, SOCK_RAW, IPPROTO_TCP, net); if (!res) net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC; return res; } static void __net_exit tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); } static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, }; int __init tcpv6_init(void) { int ret; net_hotdata.tcpv6_protocol = (struct inet6_protocol) { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; /* register inet6 protocol */ ret = inet6_register_protosw(&tcpv6_protosw); if (ret) goto out_tcpv6_protocol; ret = register_pernet_subsys(&tcpv6_net_ops); if (ret) goto out_tcpv6_protosw; ret = mptcpv6_init(); if (ret) goto out_tcpv6_pernet_subsys; out: return ret; out_tcpv6_pernet_subsys: unregister_pernet_subsys(&tcpv6_net_ops); out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } |
| 11 11 43 43 10 7 4 1 3 2 2 3 4 81 81 81 96 97 97 10 6 4 1 4 3 3 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 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "originator.h" #include "main.h" #include <linux/atomic.h> #include <linux/container_of.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> #include "bat_algo.h" #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "multicast.h" #include "netlink.h" #include "network-coding.h" #include "routing.h" #include "translation-table.h" /* hash class keys */ static struct lock_class_key batadv_orig_hash_lock_class_key; /** * batadv_orig_hash_find() - Find and return originator from orig_hash * @bat_priv: the bat priv with all the mesh interface information * @data: mac address of the originator * * Return: orig_node (with increased refcnt), NULL on errors */ struct batadv_orig_node * batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; struct batadv_orig_node *orig_node, *orig_node_tmp = NULL; int index; if (!hash) return NULL; index = batadv_choose_orig(data, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { if (!batadv_compare_eth(orig_node, data)) continue; if (!kref_get_unless_zero(&orig_node->refcount)) continue; orig_node_tmp = orig_node; break; } rcu_read_unlock(); return orig_node_tmp; } static void batadv_purge_orig(struct work_struct *work); /** * batadv_compare_orig() - comparing function used in the originator hash table * @node: node in the local table * @data2: second object to compare the node to * * Return: true if they are the same originator */ bool batadv_compare_orig(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_orig_node, hash_entry); return batadv_compare_eth(data1, data2); } /** * batadv_orig_node_vlan_get() - get an orig_node_vlan object * @orig_node: the originator serving the VLAN * @vid: the VLAN identifier * * Return: the vlan object identified by vid and belonging to orig_node or NULL * if it does not exist. */ struct batadv_orig_node_vlan * batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_orig_node_vlan *vlan = NULL, *tmp; rcu_read_lock(); hlist_for_each_entry_rcu(tmp, &orig_node->vlan_list, list) { if (tmp->vid != vid) continue; if (!kref_get_unless_zero(&tmp->refcount)) continue; vlan = tmp; break; } rcu_read_unlock(); return vlan; } /** * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding * @vid: the VLAN identifier * * Return: true when either no vlan is set or if VLAN is in correct range, * false otherwise */ static bool batadv_vlan_id_valid(unsigned short vid) { unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK); if (vid == 0) return true; if (!(vid & BATADV_VLAN_HAS_TAG)) return false; if (non_vlan) return false; return true; } /** * batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan * object * @orig_node: the originator serving the VLAN * @vid: the VLAN identifier * * Return: NULL in case of failure or the vlan object identified by vid and * belonging to orig_node otherwise. The object is created and added to the list * if it does not exist. * * The object is returned with refcounter increased by 1. */ struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_orig_node_vlan *vlan; if (!batadv_vlan_id_valid(vid)) return NULL; spin_lock_bh(&orig_node->vlan_list_lock); /* first look if an object for this vid already exists */ vlan = batadv_orig_node_vlan_get(orig_node, vid); if (vlan) goto out; vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC); if (!vlan) goto out; kref_init(&vlan->refcount); vlan->vid = vid; kref_get(&vlan->refcount); hlist_add_head_rcu(&vlan->list, &orig_node->vlan_list); out: spin_unlock_bh(&orig_node->vlan_list_lock); return vlan; } /** * batadv_orig_node_vlan_release() - release originator-vlan object from lists * and queue for free after rcu grace period * @ref: kref pointer of the originator-vlan object */ void batadv_orig_node_vlan_release(struct kref *ref) { struct batadv_orig_node_vlan *orig_vlan; orig_vlan = container_of(ref, struct batadv_orig_node_vlan, refcount); kfree_rcu(orig_vlan, rcu); } /** * batadv_originator_init() - Initialize all originator structures * @bat_priv: the bat priv with all the mesh interface information * * Return: 0 on success or negative error number in case of failure */ int batadv_originator_init(struct batadv_priv *bat_priv) { if (bat_priv->orig_hash) return 0; bat_priv->orig_hash = batadv_hash_new(1024); if (!bat_priv->orig_hash) goto err; batadv_hash_set_lock_class(bat_priv->orig_hash, &batadv_orig_hash_lock_class_key); INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); queue_delayed_work(batadv_event_workqueue, &bat_priv->orig_work, msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); return 0; err: return -ENOMEM; } /** * batadv_neigh_ifinfo_release() - release neigh_ifinfo from lists and queue for * free after rcu grace period * @ref: kref pointer of the neigh_ifinfo */ void batadv_neigh_ifinfo_release(struct kref *ref) { struct batadv_neigh_ifinfo *neigh_ifinfo; neigh_ifinfo = container_of(ref, struct batadv_neigh_ifinfo, refcount); if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_put(neigh_ifinfo->if_outgoing); kfree_rcu(neigh_ifinfo, rcu); } /** * batadv_hardif_neigh_release() - release hardif neigh node from lists and * queue for free after rcu grace period * @ref: kref pointer of the neigh_node */ void batadv_hardif_neigh_release(struct kref *ref) { struct batadv_hardif_neigh_node *hardif_neigh; hardif_neigh = container_of(ref, struct batadv_hardif_neigh_node, refcount); spin_lock_bh(&hardif_neigh->if_incoming->neigh_list_lock); hlist_del_init_rcu(&hardif_neigh->list); spin_unlock_bh(&hardif_neigh->if_incoming->neigh_list_lock); batadv_hardif_put(hardif_neigh->if_incoming); kfree_rcu(hardif_neigh, rcu); } /** * batadv_neigh_node_release() - release neigh_node from lists and queue for * free after rcu grace period * @ref: kref pointer of the neigh_node */ void batadv_neigh_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; neigh_node = container_of(ref, struct batadv_neigh_node, refcount); hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh_node->ifinfo_list, list) { batadv_neigh_ifinfo_put(neigh_ifinfo); } batadv_hardif_neigh_put(neigh_node->hardif_neigh); batadv_hardif_put(neigh_node->if_incoming); kfree_rcu(neigh_node, rcu); } /** * batadv_orig_router_get() - router to the originator depending on iface * @orig_node: the orig node for the router * @if_outgoing: the interface where the payload packet has been received or * the OGM should be sent to * * Return: the neighbor which should be the router for this orig_node/iface. * * The object is returned with refcounter increased by 1. */ struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(orig_ifinfo, &orig_node->ifinfo_list, list) { if (orig_ifinfo->if_outgoing != if_outgoing) continue; router = rcu_dereference(orig_ifinfo->router); break; } if (router && !kref_get_unless_zero(&router->refcount)) router = NULL; rcu_read_unlock(); return router; } /** * batadv_orig_to_router() - get next hop neighbor to an orig address * @bat_priv: the bat priv with all the mesh interface information * @orig_addr: the originator MAC address to search the best next hop router for * @if_outgoing: the interface where the payload packet has been received or * the OGM should be sent to * * Return: A neighbor node which is the best router towards the given originator * address. */ struct batadv_neigh_node * batadv_orig_to_router(struct batadv_priv *bat_priv, u8 *orig_addr, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; orig_node = batadv_orig_hash_find(bat_priv, orig_addr); if (!orig_node) return NULL; neigh_node = batadv_find_router(bat_priv, orig_node, if_outgoing); batadv_orig_node_put(orig_node); return neigh_node; } /** * batadv_orig_ifinfo_get() - find the ifinfo from an orig_node * @orig_node: the orig node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * Return: the requested orig_ifinfo or NULL if not found. * * The object is returned with refcounter increased by 1. */ struct batadv_orig_ifinfo * batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *tmp, *orig_ifinfo = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp, &orig_node->ifinfo_list, list) { if (tmp->if_outgoing != if_outgoing) continue; if (!kref_get_unless_zero(&tmp->refcount)) continue; orig_ifinfo = tmp; break; } rcu_read_unlock(); return orig_ifinfo; } /** * batadv_orig_ifinfo_new() - search and possibly create an orig_ifinfo object * @orig_node: the orig node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * Return: NULL in case of failure or the orig_ifinfo object for the if_outgoing * interface otherwise. The object is created and added to the list * if it does not exist. * * The object is returned with refcounter increased by 1. */ struct batadv_orig_ifinfo * batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_orig_ifinfo *orig_ifinfo; unsigned long reset_time; spin_lock_bh(&orig_node->neigh_list_lock); orig_ifinfo = batadv_orig_ifinfo_get(orig_node, if_outgoing); if (orig_ifinfo) goto out; orig_ifinfo = kzalloc(sizeof(*orig_ifinfo), GFP_ATOMIC); if (!orig_ifinfo) goto out; if (if_outgoing != BATADV_IF_DEFAULT) kref_get(&if_outgoing->refcount); reset_time = jiffies - 1; reset_time -= msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_ifinfo->batman_seqno_reset = reset_time; orig_ifinfo->if_outgoing = if_outgoing; INIT_HLIST_NODE(&orig_ifinfo->list); kref_init(&orig_ifinfo->refcount); kref_get(&orig_ifinfo->refcount); hlist_add_head_rcu(&orig_ifinfo->list, &orig_node->ifinfo_list); out: spin_unlock_bh(&orig_node->neigh_list_lock); return orig_ifinfo; } /** * batadv_neigh_ifinfo_get() - find the ifinfo from an neigh_node * @neigh: the neigh node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * The object is returned with refcounter increased by 1. * * Return: the requested neigh_ifinfo or NULL if not found */ struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_ifinfo *neigh_ifinfo = NULL, *tmp_neigh_ifinfo; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_ifinfo, &neigh->ifinfo_list, list) { if (tmp_neigh_ifinfo->if_outgoing != if_outgoing) continue; if (!kref_get_unless_zero(&tmp_neigh_ifinfo->refcount)) continue; neigh_ifinfo = tmp_neigh_ifinfo; break; } rcu_read_unlock(); return neigh_ifinfo; } /** * batadv_neigh_ifinfo_new() - search and possibly create an neigh_ifinfo object * @neigh: the neigh node to be queried * @if_outgoing: the interface for which the ifinfo should be acquired * * Return: NULL in case of failure or the neigh_ifinfo object for the * if_outgoing interface otherwise. The object is created and added to the list * if it does not exist. * * The object is returned with refcounter increased by 1. */ struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_ifinfo *neigh_ifinfo; spin_lock_bh(&neigh->ifinfo_lock); neigh_ifinfo = batadv_neigh_ifinfo_get(neigh, if_outgoing); if (neigh_ifinfo) goto out; neigh_ifinfo = kzalloc(sizeof(*neigh_ifinfo), GFP_ATOMIC); if (!neigh_ifinfo) goto out; if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&neigh_ifinfo->list); kref_init(&neigh_ifinfo->refcount); neigh_ifinfo->if_outgoing = if_outgoing; kref_get(&neigh_ifinfo->refcount); hlist_add_head_rcu(&neigh_ifinfo->list, &neigh->ifinfo_list); out: spin_unlock_bh(&neigh->ifinfo_lock); return neigh_ifinfo; } /** * batadv_neigh_node_get() - retrieve a neighbour from the list * @orig_node: originator which the neighbour belongs to * @hard_iface: the interface where this neighbour is connected to * @addr: the address of the neighbour * * Looks for and possibly returns a neighbour belonging to this originator list * which is connected through the provided hard interface. * * Return: neighbor when found. Otherwise NULL */ static struct batadv_neigh_node * batadv_neigh_node_get(const struct batadv_orig_node *orig_node, const struct batadv_hard_iface *hard_iface, const u8 *addr) { struct batadv_neigh_node *tmp_neigh_node, *res = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { if (!batadv_compare_eth(tmp_neigh_node->addr, addr)) continue; if (tmp_neigh_node->if_incoming != hard_iface) continue; if (!kref_get_unless_zero(&tmp_neigh_node->refcount)) continue; res = tmp_neigh_node; break; } rcu_read_unlock(); return res; } /** * batadv_hardif_neigh_create() - create a hardif neighbour node * @hard_iface: the interface this neighbour is connected to * @neigh_addr: the interface address of the neighbour to retrieve * @orig_node: originator object representing the neighbour * * Return: the hardif neighbour node if found or created or NULL otherwise. */ static struct batadv_hardif_neigh_node * batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, struct batadv_orig_node *orig_node) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); struct batadv_hardif_neigh_node *hardif_neigh; spin_lock_bh(&hard_iface->neigh_list_lock); /* check if neighbor hasn't been added in the meantime */ hardif_neigh = batadv_hardif_neigh_get(hard_iface, neigh_addr); if (hardif_neigh) goto out; hardif_neigh = kzalloc(sizeof(*hardif_neigh), GFP_ATOMIC); if (!hardif_neigh) goto out; kref_get(&hard_iface->refcount); INIT_HLIST_NODE(&hardif_neigh->list); ether_addr_copy(hardif_neigh->addr, neigh_addr); ether_addr_copy(hardif_neigh->orig, orig_node->orig); hardif_neigh->if_incoming = hard_iface; hardif_neigh->last_seen = jiffies; kref_init(&hardif_neigh->refcount); if (bat_priv->algo_ops->neigh.hardif_init) bat_priv->algo_ops->neigh.hardif_init(hardif_neigh); hlist_add_head_rcu(&hardif_neigh->list, &hard_iface->neigh_list); out: spin_unlock_bh(&hard_iface->neigh_list_lock); return hardif_neigh; } /** * batadv_hardif_neigh_get_or_create() - retrieve or create a hardif neighbour * node * @hard_iface: the interface this neighbour is connected to * @neigh_addr: the interface address of the neighbour to retrieve * @orig_node: originator object representing the neighbour * * Return: the hardif neighbour node if found or created or NULL otherwise. */ static struct batadv_hardif_neigh_node * batadv_hardif_neigh_get_or_create(struct batadv_hard_iface *hard_iface, const u8 *neigh_addr, struct batadv_orig_node *orig_node) { struct batadv_hardif_neigh_node *hardif_neigh; /* first check without locking to avoid the overhead */ hardif_neigh = batadv_hardif_neigh_get(hard_iface, neigh_addr); if (hardif_neigh) return hardif_neigh; return batadv_hardif_neigh_create(hard_iface, neigh_addr, orig_node); } /** * batadv_hardif_neigh_get() - retrieve a hardif neighbour from the list * @hard_iface: the interface where this neighbour is connected to * @neigh_addr: the address of the neighbour * * Looks for and possibly returns a neighbour belonging to this hard interface. * * Return: neighbor when found. Otherwise NULL */ struct batadv_hardif_neigh_node * batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, const u8 *neigh_addr) { struct batadv_hardif_neigh_node *tmp_hardif_neigh, *hardif_neigh = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tmp_hardif_neigh, &hard_iface->neigh_list, list) { if (!batadv_compare_eth(tmp_hardif_neigh->addr, neigh_addr)) continue; if (!kref_get_unless_zero(&tmp_hardif_neigh->refcount)) continue; hardif_neigh = tmp_hardif_neigh; break; } rcu_read_unlock(); return hardif_neigh; } /** * batadv_neigh_node_create() - create a neigh node object * @orig_node: originator object representing the neighbour * @hard_iface: the interface where the neighbour is connected to * @neigh_addr: the mac address of the neighbour interface * * Allocates a new neigh_node object and initialises all the generic fields. * * Return: the neighbour node if found or created or NULL otherwise. */ static struct batadv_neigh_node * batadv_neigh_node_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr) { struct batadv_neigh_node *neigh_node; struct batadv_hardif_neigh_node *hardif_neigh = NULL; spin_lock_bh(&orig_node->neigh_list_lock); neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); if (neigh_node) goto out; hardif_neigh = batadv_hardif_neigh_get_or_create(hard_iface, neigh_addr, orig_node); if (!hardif_neigh) goto out; neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); if (!neigh_node) goto out; INIT_HLIST_NODE(&neigh_node->list); INIT_HLIST_HEAD(&neigh_node->ifinfo_list); spin_lock_init(&neigh_node->ifinfo_lock); kref_get(&hard_iface->refcount); ether_addr_copy(neigh_node->addr, neigh_addr); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; neigh_node->last_seen = jiffies; /* increment unique neighbor refcount */ kref_get(&hardif_neigh->refcount); neigh_node->hardif_neigh = hardif_neigh; /* extra reference for return */ kref_init(&neigh_node->refcount); kref_get(&neigh_node->refcount); hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", neigh_addr, orig_node->orig, hard_iface->net_dev->name); out: spin_unlock_bh(&orig_node->neigh_list_lock); batadv_hardif_neigh_put(hardif_neigh); return neigh_node; } /** * batadv_neigh_node_get_or_create() - retrieve or create a neigh node object * @orig_node: originator object representing the neighbour * @hard_iface: the interface where the neighbour is connected to * @neigh_addr: the mac address of the neighbour interface * * Return: the neighbour node if found or created or NULL otherwise. */ struct batadv_neigh_node * batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr) { struct batadv_neigh_node *neigh_node; /* first check without locking to avoid the overhead */ neigh_node = batadv_neigh_node_get(orig_node, hard_iface, neigh_addr); if (neigh_node) return neigh_node; return batadv_neigh_node_create(orig_node, hard_iface, neigh_addr); } /** * batadv_hardif_neigh_dump() - Dump to netlink the neighbor infos for a * specific outgoing interface * @msg: message to dump into * @cb: parameters for the dump * * Return: 0 or error value */ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if, *hard_iface; struct net_device *mesh_iface; struct batadv_priv *bat_priv; int ret; mesh_iface = batadv_netlink_get_meshif(cb); if (IS_ERR(mesh_iface)) return PTR_ERR(mesh_iface); bat_priv = netdev_priv(mesh_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out_put_mesh_iface; } hard_iface = batadv_netlink_get_hardif(bat_priv, cb); if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { ret = PTR_ERR(hard_iface); goto out_put_primary_if; } else if (IS_ERR(hard_iface)) { /* => PTR_ERR(hard_iface) == -ENONET * => no hard-iface given, ok */ hard_iface = BATADV_IF_DEFAULT; } if (!bat_priv->algo_ops->neigh.dump) { ret = -EOPNOTSUPP; goto out_put_hard_iface; } bat_priv->algo_ops->neigh.dump(msg, cb, bat_priv, hard_iface); ret = msg->len; out_put_hard_iface: batadv_hardif_put(hard_iface); out_put_primary_if: batadv_hardif_put(primary_if); out_put_mesh_iface: dev_put(mesh_iface); return ret; } /** * batadv_orig_ifinfo_release() - release orig_ifinfo from lists and queue for * free after rcu grace period * @ref: kref pointer of the orig_ifinfo */ void batadv_orig_ifinfo_release(struct kref *ref) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; orig_ifinfo = container_of(ref, struct batadv_orig_ifinfo, refcount); if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) batadv_hardif_put(orig_ifinfo->if_outgoing); /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); batadv_neigh_node_put(router); kfree_rcu(orig_ifinfo, rcu); } /** * batadv_orig_node_free_rcu() - free the orig_node * @rcu: rcu pointer of the orig_node */ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { struct batadv_orig_node *orig_node; orig_node = container_of(rcu, struct batadv_orig_node, rcu); batadv_mcast_purge_orig(orig_node); batadv_frag_purge_orig(orig_node, NULL); kfree(orig_node->tt_buff); kfree(orig_node); } /** * batadv_orig_node_release() - release orig_node from lists and queue for * free after rcu grace period * @ref: kref pointer of the orig_node */ void batadv_orig_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_orig_node_vlan *vlan; struct batadv_orig_ifinfo *last_candidate; orig_node = container_of(ref, struct batadv_orig_node, refcount); spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); batadv_neigh_node_put(neigh_node); } hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_put(orig_ifinfo); } last_candidate = orig_node->last_bonding_candidate; orig_node->last_bonding_candidate = NULL; spin_unlock_bh(&orig_node->neigh_list_lock); batadv_orig_ifinfo_put(last_candidate); spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry_safe(vlan, node_tmp, &orig_node->vlan_list, list) { hlist_del_rcu(&vlan->list); batadv_orig_node_vlan_put(vlan); } spin_unlock_bh(&orig_node->vlan_list_lock); /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } /** * batadv_originator_free() - Free all originator structures * @bat_priv: the bat priv with all the mesh interface information */ void batadv_originator_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; u32 i; if (!hash) return; cancel_delayed_work_sync(&bat_priv->orig_work); bat_priv->orig_hash = NULL; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { hlist_del_rcu(&orig_node->hash_entry); batadv_orig_node_put(orig_node); } spin_unlock_bh(list_lock); } batadv_hash_destroy(hash); } /** * batadv_orig_node_new() - creates a new orig_node * @bat_priv: the bat priv with all the mesh interface information * @addr: the mac address of the originator * * Creates a new originator object and initialises all the generic fields. * The new object is not added to the originator list. * * Return: the newly created object or NULL on failure. */ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr) { struct batadv_orig_node *orig_node; struct batadv_orig_node_vlan *vlan; unsigned long reset_time; int i; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Creating new originator: %pM\n", addr); orig_node = kzalloc(sizeof(*orig_node), GFP_ATOMIC); if (!orig_node) return NULL; INIT_HLIST_HEAD(&orig_node->neigh_list); INIT_HLIST_HEAD(&orig_node->vlan_list); INIT_HLIST_HEAD(&orig_node->ifinfo_list); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); spin_lock_init(&orig_node->tt_buff_lock); spin_lock_init(&orig_node->tt_lock); spin_lock_init(&orig_node->vlan_list_lock); batadv_nc_init_orig(orig_node); /* extra reference for return */ kref_init(&orig_node->refcount); orig_node->bat_priv = bat_priv; ether_addr_copy(orig_node->orig, addr); batadv_dat_init_orig_node_addr(orig_node); atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; orig_node->tt_buff_len = 0; orig_node->last_seen = jiffies; reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS); orig_node->bcast_seqno_reset = reset_time; #ifdef CONFIG_BATMAN_ADV_MCAST orig_node->mcast_flags = BATADV_MCAST_WANT_NO_RTR4; orig_node->mcast_flags |= BATADV_MCAST_WANT_NO_RTR6; orig_node->mcast_flags |= BATADV_MCAST_HAVE_MC_PTYPE_CAPA; INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node); INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node); spin_lock_init(&orig_node->mcast_handler_lock); #endif /* create a vlan object for the "untagged" LAN */ vlan = batadv_orig_node_vlan_new(orig_node, BATADV_NO_FLAGS); if (!vlan) goto free_orig_node; /* batadv_orig_node_vlan_new() increases the refcounter. * Immediately release vlan since it is not needed anymore in this * context */ batadv_orig_node_vlan_put(vlan); for (i = 0; i < BATADV_FRAG_BUFFER_COUNT; i++) { INIT_HLIST_HEAD(&orig_node->fragments[i].fragment_list); spin_lock_init(&orig_node->fragments[i].lock); orig_node->fragments[i].size = 0; } return orig_node; free_orig_node: kfree(orig_node); return NULL; } /** * batadv_purge_neigh_ifinfo() - purge obsolete ifinfo entries from neighbor * @bat_priv: the bat priv with all the mesh interface information * @neigh: orig node which is to be checked */ static void batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh) { struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_hard_iface *if_outgoing; struct hlist_node *node_tmp; spin_lock_bh(&neigh->ifinfo_lock); /* for all ifinfo objects for this neighinator */ hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh->ifinfo_list, list) { if_outgoing = neigh_ifinfo->if_outgoing; /* always keep the default interface */ if (if_outgoing == BATADV_IF_DEFAULT) continue; /* don't purge if the interface is not (going) down */ if (if_outgoing->if_status != BATADV_IF_INACTIVE && if_outgoing->if_status != BATADV_IF_NOT_IN_USE && if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor/ifinfo purge: neighbor %pM, iface: %s\n", neigh->addr, if_outgoing->net_dev->name); hlist_del_rcu(&neigh_ifinfo->list); batadv_neigh_ifinfo_put(neigh_ifinfo); } spin_unlock_bh(&neigh->ifinfo_lock); } /** * batadv_purge_orig_ifinfo() - purge obsolete ifinfo entries from originator * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig node which is to be checked * * Return: true if any ifinfo entry was purged, false otherwise. */ static bool batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_hard_iface *if_outgoing; struct hlist_node *node_tmp; bool ifinfo_purged = false; spin_lock_bh(&orig_node->neigh_list_lock); /* for all ifinfo objects for this originator */ hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { if_outgoing = orig_ifinfo->if_outgoing; /* always keep the default interface */ if (if_outgoing == BATADV_IF_DEFAULT) continue; /* don't purge if the interface is not (going) down */ if (if_outgoing->if_status != BATADV_IF_INACTIVE && if_outgoing->if_status != BATADV_IF_NOT_IN_USE && if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "router/ifinfo purge: originator %pM, iface: %s\n", orig_node->orig, if_outgoing->net_dev->name); ifinfo_purged = true; hlist_del_rcu(&orig_ifinfo->list); batadv_orig_ifinfo_put(orig_ifinfo); if (orig_node->last_bonding_candidate == orig_ifinfo) { orig_node->last_bonding_candidate = NULL; batadv_orig_ifinfo_put(orig_ifinfo); } } spin_unlock_bh(&orig_node->neigh_list_lock); return ifinfo_purged; } /** * batadv_purge_orig_neighbors() - purges neighbors from originator * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig node which is to be checked * * Return: true if any neighbor was purged, false otherwise */ static bool batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; struct batadv_hard_iface *if_incoming; spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) || if_incoming->if_status == BATADV_IF_INACTIVE || if_incoming->if_status == BATADV_IF_NOT_IN_USE || if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) { if (if_incoming->if_status == BATADV_IF_INACTIVE || if_incoming->if_status == BATADV_IF_NOT_IN_USE || if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", orig_node->orig, neigh_node->addr, if_incoming->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor timeout: originator %pM, neighbor: %pM, last_seen: %u\n", orig_node->orig, neigh_node->addr, jiffies_to_msecs(last_seen)); neigh_purged = true; hlist_del_rcu(&neigh_node->list); batadv_neigh_node_put(neigh_node); } else { /* only necessary if not the whole neighbor is to be * deleted, but some interface has been removed. */ batadv_purge_neigh_ifinfo(bat_priv, neigh_node); } } spin_unlock_bh(&orig_node->neigh_list_lock); return neigh_purged; } /** * batadv_find_best_neighbor() - finds the best neighbor after purging * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig node which is to be checked * @if_outgoing: the interface for which the metric should be compared * * Return: the current best neighbor, with refcount increased. */ static struct batadv_neigh_node * batadv_find_best_neighbor(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing) { struct batadv_neigh_node *best = NULL, *neigh; struct batadv_algo_ops *bao = bat_priv->algo_ops; rcu_read_lock(); hlist_for_each_entry_rcu(neigh, &orig_node->neigh_list, list) { if (best && (bao->neigh.cmp(neigh, if_outgoing, best, if_outgoing) <= 0)) continue; if (!kref_get_unless_zero(&neigh->refcount)) continue; batadv_neigh_node_put(best); best = neigh; } rcu_read_unlock(); return best; } /** * batadv_purge_orig_node() - purges obsolete information from an orig_node * @bat_priv: the bat priv with all the mesh interface information * @orig_node: orig node which is to be checked * * This function checks if the orig_node or substructures of it have become * obsolete, and purges this information if that's the case. * * Return: true if the orig_node is to be removed, false otherwise. */ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node) { struct batadv_neigh_node *best_neigh_node; struct batadv_hard_iface *hard_iface; bool changed_ifinfo, changed_neigh; if (batadv_has_timed_out(orig_node->last_seen, 2 * BATADV_PURGE_TIMEOUT)) { batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "Originator timeout: originator %pM, last_seen %u\n", orig_node->orig, jiffies_to_msecs(orig_node->last_seen)); return true; } changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node); changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node); if (!changed_ifinfo && !changed_neigh) return false; /* first for NULL ... */ best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node, BATADV_IF_DEFAULT); batadv_update_route(bat_priv, orig_node, BATADV_IF_DEFAULT, best_neigh_node); batadv_neigh_node_put(best_neigh_node); /* ... then for all other interfaces. */ rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; if (hard_iface->mesh_iface != bat_priv->mesh_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; best_neigh_node = batadv_find_best_neighbor(bat_priv, orig_node, hard_iface); batadv_update_route(bat_priv, orig_node, hard_iface, best_neigh_node); batadv_neigh_node_put(best_neigh_node); batadv_hardif_put(hard_iface); } rcu_read_unlock(); return false; } /** * batadv_purge_orig_ref() - Purge all outdated originators * @bat_priv: the bat priv with all the mesh interface information */ void batadv_purge_orig_ref(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; u32 i; if (!hash) return; /* for all origins... */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; if (hlist_empty(head)) continue; list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { if (batadv_purge_orig_node(bat_priv, orig_node)) { batadv_gw_node_delete(bat_priv, orig_node); hlist_del_rcu(&orig_node->hash_entry); batadv_tt_global_del_orig(orig_node->bat_priv, orig_node, -1, "originator timed out"); batadv_orig_node_put(orig_node); continue; } batadv_frag_purge_orig(orig_node, batadv_frag_check_entry); } spin_unlock_bh(list_lock); } batadv_gw_election(bat_priv); } static void batadv_purge_orig(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv *bat_priv; delayed_work = to_delayed_work(work); bat_priv = container_of(delayed_work, struct batadv_priv, orig_work); batadv_purge_orig_ref(bat_priv); queue_delayed_work(batadv_event_workqueue, &bat_priv->orig_work, msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); } /** * batadv_orig_dump() - Dump to netlink the originator infos for a specific * outgoing interface * @msg: message to dump into * @cb: parameters for the dump * * Return: 0 or error value */ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if, *hard_iface; struct net_device *mesh_iface; struct batadv_priv *bat_priv; int ret; mesh_iface = batadv_netlink_get_meshif(cb); if (IS_ERR(mesh_iface)) return PTR_ERR(mesh_iface); bat_priv = netdev_priv(mesh_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out_put_mesh_iface; } hard_iface = batadv_netlink_get_hardif(bat_priv, cb); if (IS_ERR(hard_iface) && PTR_ERR(hard_iface) != -ENONET) { ret = PTR_ERR(hard_iface); goto out_put_primary_if; } else if (IS_ERR(hard_iface)) { /* => PTR_ERR(hard_iface) == -ENONET * => no hard-iface given, ok */ hard_iface = BATADV_IF_DEFAULT; } if (!bat_priv->algo_ops->orig.dump) { ret = -EOPNOTSUPP; goto out_put_hard_iface; } bat_priv->algo_ops->orig.dump(msg, cb, bat_priv, hard_iface); ret = msg->len; out_put_hard_iface: batadv_hardif_put(hard_iface); out_put_primary_if: batadv_hardif_put(primary_if); out_put_mesh_iface: dev_put(mesh_iface); return 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FPU_XCR_H #define _ASM_X86_FPU_XCR_H #define XCR_XFEATURE_ENABLED_MASK 0x00000000 #define XCR_XFEATURE_IN_USE_MASK 0x00000001 static __always_inline u64 xgetbv(u32 index) { u32 eax, edx; asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); return eax + ((u64)edx << 32); } static inline void xsetbv(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } /* * Return a mask of xfeatures which are currently being tracked * by the processor as being in the initial configuration. * * Callers should check X86_FEATURE_XGETBV1. */ static __always_inline u64 xfeatures_in_use(void) { return xgetbv(XCR_XFEATURE_IN_USE_MASK); } #endif /* _ASM_X86_FPU_XCR_H */ |
| 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #ifndef _SIW_MEM_H #define _SIW_MEM_H struct siw_umem *siw_umem_get(struct ib_device *base_dave, u64 start, u64 len, int rights); void siw_umem_release(struct siw_umem *umem); struct siw_pbl *siw_pbl_alloc(u32 num_buf); dma_addr_t siw_pbl_get_buffer(struct siw_pbl *pbl, u64 off, int *len, int *idx); struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index); int siw_invalidate_stag(struct ib_pd *pd, u32 stag); int siw_check_mem(struct ib_pd *pd, struct siw_mem *mem, u64 addr, enum ib_access_flags perms, int len); int siw_check_sge(struct ib_pd *pd, struct siw_sge *sge, struct siw_mem *mem[], enum ib_access_flags perms, u32 off, int len); void siw_wqe_put_mem(struct siw_wqe *wqe, enum siw_opcode op); int siw_mr_add_mem(struct siw_mr *mr, struct ib_pd *pd, void *mem_obj, u64 start, u64 len, int rights); void siw_mr_drop_mem(struct siw_mr *mr); void siw_free_mem(struct kref *ref); static inline void siw_mem_put(struct siw_mem *mem) { kref_put(&mem->ref, siw_free_mem); } static inline void siw_unref_mem_sgl(struct siw_mem **mem, unsigned int num_sge) { while (num_sge) { if (*mem == NULL) break; siw_mem_put(*mem); *mem = NULL; mem++; num_sge--; } } #define CHUNK_SHIFT 9 /* sets number of pages per chunk */ #define PAGES_PER_CHUNK (_AC(1, UL) << CHUNK_SHIFT) #define CHUNK_MASK (~(PAGES_PER_CHUNK - 1)) #define PAGE_CHUNK_SIZE (PAGES_PER_CHUNK * sizeof(struct page *)) /* * siw_get_upage() * * Get page pointer for address on given umem. * * @umem: two dimensional list of page pointers * @addr: user virtual address */ static inline struct page *siw_get_upage(struct siw_umem *umem, u64 addr) { unsigned int page_idx = (addr - umem->fp_addr) >> PAGE_SHIFT, chunk_idx = page_idx >> CHUNK_SHIFT, page_in_chunk = page_idx & ~CHUNK_MASK; if (likely(page_idx < umem->num_pages)) return umem->page_chunk[chunk_idx].plist[page_in_chunk]; return NULL; } #endif |
| 34 34 34 30 30 1 30 1 30 34 30 30 30 30 1 30 30 30 34 34 30 30 30 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 | // SPDX-License-Identifier: GPL-2.0-or-later /* * The Serio abstraction module * * Copyright (c) 1999-2004 Vojtech Pavlik * Copyright (c) 2004 Dmitry Torokhov * Copyright (c) 2003 Daniele Bellucci */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/stddef.h> #include <linux/module.h> #include <linux/serio.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/mutex.h> MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>"); MODULE_DESCRIPTION("Serio abstraction core"); MODULE_LICENSE("GPL"); /* * serio_mutex protects entire serio subsystem and is taken every time * serio port or driver registered or unregistered. */ static DEFINE_MUTEX(serio_mutex); static LIST_HEAD(serio_list); static void serio_add_port(struct serio *serio); static int serio_reconnect_port(struct serio *serio); static void serio_disconnect_port(struct serio *serio); static void serio_reconnect_subtree(struct serio *serio); static void serio_attach_driver(struct serio_driver *drv); static int serio_connect_driver(struct serio *serio, struct serio_driver *drv) { guard(mutex)(&serio->drv_mutex); return drv->connect(serio, drv); } static int serio_reconnect_driver(struct serio *serio) { guard(mutex)(&serio->drv_mutex); if (serio->drv && serio->drv->reconnect) return serio->drv->reconnect(serio); return -1; } static void serio_disconnect_driver(struct serio *serio) { guard(mutex)(&serio->drv_mutex); if (serio->drv) serio->drv->disconnect(serio); } static int serio_match_port(const struct serio_device_id *ids, struct serio *serio) { while (ids->type || ids->proto) { if ((ids->type == SERIO_ANY || ids->type == serio->id.type) && (ids->proto == SERIO_ANY || ids->proto == serio->id.proto) && (ids->extra == SERIO_ANY || ids->extra == serio->id.extra) && (ids->id == SERIO_ANY || ids->id == serio->id.id)) return 1; ids++; } return 0; } /* * Basic serio -> driver core mappings */ static int serio_bind_driver(struct serio *serio, struct serio_driver *drv) { int error; if (serio_match_port(drv->id_table, serio)) { serio->dev.driver = &drv->driver; if (serio_connect_driver(serio, drv)) { serio->dev.driver = NULL; return -ENODEV; } error = device_bind_driver(&serio->dev); if (error) { dev_warn(&serio->dev, "device_bind_driver() failed for %s (%s) and %s, error: %d\n", serio->phys, serio->name, drv->description, error); serio_disconnect_driver(serio); serio->dev.driver = NULL; return error; } } return 0; } static void serio_find_driver(struct serio *serio) { int error; error = device_attach(&serio->dev); if (error < 0 && error != -EPROBE_DEFER) dev_warn(&serio->dev, "device_attach() failed for %s (%s), error: %d\n", serio->phys, serio->name, error); } /* * Serio event processing. */ enum serio_event_type { SERIO_RESCAN_PORT, SERIO_RECONNECT_PORT, SERIO_RECONNECT_SUBTREE, SERIO_REGISTER_PORT, SERIO_ATTACH_DRIVER, }; struct serio_event { enum serio_event_type type; void *object; struct module *owner; struct list_head node; }; static DEFINE_SPINLOCK(serio_event_lock); /* protects serio_event_list */ static LIST_HEAD(serio_event_list); static struct serio_event *serio_get_event(void) { struct serio_event *event = NULL; guard(spinlock_irqsave)(&serio_event_lock); if (!list_empty(&serio_event_list)) { event = list_first_entry(&serio_event_list, struct serio_event, node); list_del_init(&event->node); } return event; } static void serio_free_event(struct serio_event *event) { module_put(event->owner); kfree(event); } static void serio_remove_duplicate_events(void *object, enum serio_event_type type) { struct serio_event *e, *next; guard(spinlock_irqsave)(&serio_event_lock); list_for_each_entry_safe(e, next, &serio_event_list, node) { if (object == e->object) { /* * If this event is of different type we should not * look further - we only suppress duplicate events * that were sent back-to-back. */ if (type != e->type) break; list_del_init(&e->node); serio_free_event(e); } } } static void serio_handle_event(struct work_struct *work) { struct serio_event *event; guard(mutex)(&serio_mutex); while ((event = serio_get_event())) { switch (event->type) { case SERIO_REGISTER_PORT: serio_add_port(event->object); break; case SERIO_RECONNECT_PORT: serio_reconnect_port(event->object); break; case SERIO_RESCAN_PORT: serio_disconnect_port(event->object); serio_find_driver(event->object); break; case SERIO_RECONNECT_SUBTREE: serio_reconnect_subtree(event->object); break; case SERIO_ATTACH_DRIVER: serio_attach_driver(event->object); break; } serio_remove_duplicate_events(event->object, event->type); serio_free_event(event); } } static DECLARE_WORK(serio_event_work, serio_handle_event); static int serio_queue_event(void *object, struct module *owner, enum serio_event_type event_type) { struct serio_event *event; guard(spinlock_irqsave)(&serio_event_lock); /* * Scan event list for the other events for the same serio port, * starting with the most recent one. If event is the same we * do not need add new one. If event is of different type we * need to add this event and should not look further because * we need to preseve sequence of distinct events. */ list_for_each_entry_reverse(event, &serio_event_list, node) { if (event->object == object) { if (event->type == event_type) return 0; break; } } event = kmalloc(sizeof(*event), GFP_ATOMIC); if (!event) { pr_err("Not enough memory to queue event %d\n", event_type); return -ENOMEM; } if (!try_module_get(owner)) { pr_warn("Can't get module reference, dropping event %d\n", event_type); kfree(event); return -EINVAL; } event->type = event_type; event->object = object; event->owner = owner; list_add_tail(&event->node, &serio_event_list); queue_work(system_long_wq, &serio_event_work); return 0; } /* * Remove all events that have been submitted for a given * object, be it serio port or driver. */ static void serio_remove_pending_events(void *object) { struct serio_event *event, *next; guard(spinlock_irqsave)(&serio_event_lock); list_for_each_entry_safe(event, next, &serio_event_list, node) { if (event->object == object) { list_del_init(&event->node); serio_free_event(event); } } } /* * Locate child serio port (if any) that has not been fully registered yet. * * Children are registered by driver's connect() handler so there can't be a * grandchild pending registration together with a child. */ static struct serio *serio_get_pending_child(struct serio *parent) { struct serio_event *event; struct serio *serio; guard(spinlock_irqsave)(&serio_event_lock); list_for_each_entry(event, &serio_event_list, node) { if (event->type == SERIO_REGISTER_PORT) { serio = event->object; if (serio->parent == parent) return serio; } } return NULL; } /* * Serio port operations */ static ssize_t serio_show_description(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%s\n", serio->name); } static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "serio:ty%02Xpr%02Xid%02Xex%02X\n", serio->id.type, serio->id.proto, serio->id.id, serio->id.extra); } static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%02x\n", serio->id.type); } static ssize_t proto_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%02x\n", serio->id.proto); } static ssize_t id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%02x\n", serio->id.id); } static ssize_t extra_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%02x\n", serio->id.extra); } static ssize_t drvctl_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct serio *serio = to_serio_port(dev); struct device_driver *drv; int error; scoped_cond_guard(mutex_intr, return -EINTR, &serio_mutex) { if (!strncmp(buf, "none", count)) { serio_disconnect_port(serio); } else if (!strncmp(buf, "reconnect", count)) { serio_reconnect_subtree(serio); } else if (!strncmp(buf, "rescan", count)) { serio_disconnect_port(serio); serio_find_driver(serio); serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT); } else if ((drv = driver_find(buf, &serio_bus)) != NULL) { serio_disconnect_port(serio); error = serio_bind_driver(serio, to_serio_driver(drv)); serio_remove_duplicate_events(serio, SERIO_RESCAN_PORT); if (error) return error; } else { return -EINVAL; } } return count; } static ssize_t serio_show_bind_mode(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%s\n", serio->manual_bind ? "manual" : "auto"); } static ssize_t serio_set_bind_mode(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct serio *serio = to_serio_port(dev); int retval; retval = count; if (!strncmp(buf, "manual", count)) { serio->manual_bind = true; } else if (!strncmp(buf, "auto", count)) { serio->manual_bind = false; } else { retval = -EINVAL; } return retval; } static ssize_t firmware_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serio *serio = to_serio_port(dev); return sprintf(buf, "%s\n", serio->firmware_id); } static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(proto); static DEVICE_ATTR_RO(id); static DEVICE_ATTR_RO(extra); static struct attribute *serio_device_id_attrs[] = { &dev_attr_type.attr, &dev_attr_proto.attr, &dev_attr_id.attr, &dev_attr_extra.attr, NULL }; static const struct attribute_group serio_id_attr_group = { .name = "id", .attrs = serio_device_id_attrs, }; static DEVICE_ATTR_RO(modalias); static DEVICE_ATTR_WO(drvctl); static DEVICE_ATTR(description, S_IRUGO, serio_show_description, NULL); static DEVICE_ATTR(bind_mode, S_IWUSR | S_IRUGO, serio_show_bind_mode, serio_set_bind_mode); static DEVICE_ATTR_RO(firmware_id); static struct attribute *serio_device_attrs[] = { &dev_attr_modalias.attr, &dev_attr_description.attr, &dev_attr_drvctl.attr, &dev_attr_bind_mode.attr, &dev_attr_firmware_id.attr, NULL }; static const struct attribute_group serio_device_attr_group = { .attrs = serio_device_attrs, }; static const struct attribute_group *serio_device_attr_groups[] = { &serio_id_attr_group, &serio_device_attr_group, NULL }; static void serio_release_port(struct device *dev) { struct serio *serio = to_serio_port(dev); kfree(serio); module_put(THIS_MODULE); } /* * Prepare serio port for registration. */ static void serio_init_port(struct serio *serio) { static atomic_t serio_no = ATOMIC_INIT(-1); __module_get(THIS_MODULE); INIT_LIST_HEAD(&serio->node); INIT_LIST_HEAD(&serio->child_node); INIT_LIST_HEAD(&serio->children); spin_lock_init(&serio->lock); mutex_init(&serio->drv_mutex); device_initialize(&serio->dev); dev_set_name(&serio->dev, "serio%lu", (unsigned long)atomic_inc_return(&serio_no)); serio->dev.bus = &serio_bus; serio->dev.release = serio_release_port; serio->dev.groups = serio_device_attr_groups; if (serio->parent) { serio->dev.parent = &serio->parent->dev; serio->depth = serio->parent->depth + 1; } else serio->depth = 0; lockdep_set_subclass(&serio->lock, serio->depth); } /* * Complete serio port registration. * Driver core will attempt to find appropriate driver for the port. */ static void serio_add_port(struct serio *serio) { struct serio *parent = serio->parent; int error; if (parent) { guard(serio_pause_rx)(parent); list_add_tail(&serio->child_node, &parent->children); } list_add_tail(&serio->node, &serio_list); if (serio->start) serio->start(serio); error = device_add(&serio->dev); if (error) dev_err(&serio->dev, "device_add() failed for %s (%s), error: %d\n", serio->phys, serio->name, error); } /* * serio_destroy_port() completes unregistration process and removes * port from the system */ static void serio_destroy_port(struct serio *serio) { struct serio *child; while ((child = serio_get_pending_child(serio)) != NULL) { serio_remove_pending_events(child); put_device(&child->dev); } if (serio->stop) serio->stop(serio); if (serio->parent) { guard(serio_pause_rx)(serio->parent); list_del_init(&serio->child_node); serio->parent = NULL; } if (device_is_registered(&serio->dev)) device_del(&serio->dev); list_del_init(&serio->node); serio_remove_pending_events(serio); put_device(&serio->dev); } /* * Reconnect serio port (re-initialize attached device). * If reconnect fails (old device is no longer attached or * there was no device to begin with) we do full rescan in * hope of finding a driver for the port. */ static int serio_reconnect_port(struct serio *serio) { int error = serio_reconnect_driver(serio); if (error) { serio_disconnect_port(serio); serio_find_driver(serio); } return error; } /* * Reconnect serio port and all its children (re-initialize attached * devices). */ static void serio_reconnect_subtree(struct serio *root) { struct serio *s = root; int error; do { error = serio_reconnect_port(s); if (!error) { /* * Reconnect was successful, move on to do the * first child. */ if (!list_empty(&s->children)) { s = list_first_entry(&s->children, struct serio, child_node); continue; } } /* * Either it was a leaf node or reconnect failed and it * became a leaf node. Continue reconnecting starting with * the next sibling of the parent node. */ while (s != root) { struct serio *parent = s->parent; if (!list_is_last(&s->child_node, &parent->children)) { s = list_entry(s->child_node.next, struct serio, child_node); break; } s = parent; } } while (s != root); } /* * serio_disconnect_port() unbinds a port from its driver. As a side effect * all children ports are unbound and destroyed. */ static void serio_disconnect_port(struct serio *serio) { struct serio *s = serio; /* * Children ports should be disconnected and destroyed * first; we travel the tree in depth-first order. */ while (!list_empty(&serio->children)) { /* Locate a leaf */ while (!list_empty(&s->children)) s = list_first_entry(&s->children, struct serio, child_node); /* * Prune this leaf node unless it is the one we * started with. */ if (s != serio) { struct serio *parent = s->parent; device_release_driver(&s->dev); serio_destroy_port(s); s = parent; } } /* * OK, no children left, now disconnect this port. */ device_release_driver(&serio->dev); } void serio_rescan(struct serio *serio) { serio_queue_event(serio, NULL, SERIO_RESCAN_PORT); } EXPORT_SYMBOL(serio_rescan); void serio_reconnect(struct serio *serio) { serio_queue_event(serio, NULL, SERIO_RECONNECT_SUBTREE); } EXPORT_SYMBOL(serio_reconnect); /* * Submits register request to kseriod for subsequent execution. * Note that port registration is always asynchronous. */ void __serio_register_port(struct serio *serio, struct module *owner) { serio_init_port(serio); serio_queue_event(serio, owner, SERIO_REGISTER_PORT); } EXPORT_SYMBOL(__serio_register_port); /* * Synchronously unregisters serio port. */ void serio_unregister_port(struct serio *serio) { guard(mutex)(&serio_mutex); serio_disconnect_port(serio); serio_destroy_port(serio); } EXPORT_SYMBOL(serio_unregister_port); /* * Safely unregisters children ports if they are present. */ void serio_unregister_child_port(struct serio *serio) { struct serio *s, *next; guard(mutex)(&serio_mutex); list_for_each_entry_safe(s, next, &serio->children, child_node) { serio_disconnect_port(s); serio_destroy_port(s); } } EXPORT_SYMBOL(serio_unregister_child_port); /* * Serio driver operations */ static ssize_t description_show(struct device_driver *drv, char *buf) { struct serio_driver *driver = to_serio_driver(drv); return sprintf(buf, "%s\n", driver->description ? driver->description : "(none)"); } static DRIVER_ATTR_RO(description); static ssize_t bind_mode_show(struct device_driver *drv, char *buf) { struct serio_driver *serio_drv = to_serio_driver(drv); return sprintf(buf, "%s\n", serio_drv->manual_bind ? "manual" : "auto"); } static ssize_t bind_mode_store(struct device_driver *drv, const char *buf, size_t count) { struct serio_driver *serio_drv = to_serio_driver(drv); int retval; retval = count; if (!strncmp(buf, "manual", count)) { serio_drv->manual_bind = true; } else if (!strncmp(buf, "auto", count)) { serio_drv->manual_bind = false; } else { retval = -EINVAL; } return retval; } static DRIVER_ATTR_RW(bind_mode); static struct attribute *serio_driver_attrs[] = { &driver_attr_description.attr, &driver_attr_bind_mode.attr, NULL, }; ATTRIBUTE_GROUPS(serio_driver); static int serio_driver_probe(struct device *dev) { struct serio *serio = to_serio_port(dev); struct serio_driver *drv = to_serio_driver(dev->driver); return serio_connect_driver(serio, drv); } static void serio_driver_remove(struct device *dev) { struct serio *serio = to_serio_port(dev); serio_disconnect_driver(serio); } static void serio_cleanup(struct serio *serio) { guard(mutex)(&serio->drv_mutex); if (serio->drv && serio->drv->cleanup) serio->drv->cleanup(serio); } static void serio_shutdown(struct device *dev) { struct serio *serio = to_serio_port(dev); serio_cleanup(serio); } static void serio_attach_driver(struct serio_driver *drv) { int error; error = driver_attach(&drv->driver); if (error) pr_warn("driver_attach() failed for %s with error %d\n", drv->driver.name, error); } int __serio_register_driver(struct serio_driver *drv, struct module *owner, const char *mod_name) { bool manual_bind = drv->manual_bind; int error; drv->driver.bus = &serio_bus; drv->driver.owner = owner; drv->driver.mod_name = mod_name; /* * Temporarily disable automatic binding because probing * takes long time and we are better off doing it in kseriod */ drv->manual_bind = true; error = driver_register(&drv->driver); if (error) { pr_err("driver_register() failed for %s, error: %d\n", drv->driver.name, error); return error; } /* * Restore original bind mode and let kseriod bind the * driver to free ports */ if (!manual_bind) { drv->manual_bind = false; error = serio_queue_event(drv, NULL, SERIO_ATTACH_DRIVER); if (error) { driver_unregister(&drv->driver); return error; } } return 0; } EXPORT_SYMBOL(__serio_register_driver); void serio_unregister_driver(struct serio_driver *drv) { struct serio *serio; guard(mutex)(&serio_mutex); drv->manual_bind = true; /* so serio_find_driver ignores it */ serio_remove_pending_events(drv); start_over: list_for_each_entry(serio, &serio_list, node) { if (serio->drv == drv) { serio_disconnect_port(serio); serio_find_driver(serio); /* we could've deleted some ports, restart */ goto start_over; } } driver_unregister(&drv->driver); } EXPORT_SYMBOL(serio_unregister_driver); static void serio_set_drv(struct serio *serio, struct serio_driver *drv) { guard(serio_pause_rx)(serio); serio->drv = drv; } static int serio_bus_match(struct device *dev, const struct device_driver *drv) { struct serio *serio = to_serio_port(dev); const struct serio_driver *serio_drv = to_serio_driver(drv); if (serio->manual_bind || serio_drv->manual_bind) return 0; return serio_match_port(serio_drv->id_table, serio); } #define SERIO_ADD_UEVENT_VAR(fmt, val...) \ do { \ int err = add_uevent_var(env, fmt, val); \ if (err) \ return err; \ } while (0) static int serio_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct serio *serio; if (!dev) return -ENODEV; serio = to_serio_port(dev); SERIO_ADD_UEVENT_VAR("SERIO_TYPE=%02x", serio->id.type); SERIO_ADD_UEVENT_VAR("SERIO_PROTO=%02x", serio->id.proto); SERIO_ADD_UEVENT_VAR("SERIO_ID=%02x", serio->id.id); SERIO_ADD_UEVENT_VAR("SERIO_EXTRA=%02x", serio->id.extra); SERIO_ADD_UEVENT_VAR("MODALIAS=serio:ty%02Xpr%02Xid%02Xex%02X", serio->id.type, serio->id.proto, serio->id.id, serio->id.extra); if (serio->firmware_id[0]) SERIO_ADD_UEVENT_VAR("SERIO_FIRMWARE_ID=%s", serio->firmware_id); return 0; } #undef SERIO_ADD_UEVENT_VAR #ifdef CONFIG_PM static int serio_suspend(struct device *dev) { struct serio *serio = to_serio_port(dev); serio_cleanup(serio); return 0; } static int serio_resume(struct device *dev) { struct serio *serio = to_serio_port(dev); int error = -ENOENT; scoped_guard(mutex, &serio->drv_mutex) { if (serio->drv && serio->drv->fast_reconnect) { error = serio->drv->fast_reconnect(serio); if (error && error != -ENOENT) dev_warn(dev, "fast reconnect failed with error %d\n", error); } } if (error) { /* * Driver reconnect can take a while, so better let * kseriod deal with it. */ serio_queue_event(serio, NULL, SERIO_RECONNECT_PORT); } return 0; } static const struct dev_pm_ops serio_pm_ops = { .suspend = serio_suspend, .resume = serio_resume, .poweroff = serio_suspend, .restore = serio_resume, }; #endif /* CONFIG_PM */ /* called from serio_driver->connect/disconnect methods under serio_mutex */ int serio_open(struct serio *serio, struct serio_driver *drv) { serio_set_drv(serio, drv); if (serio->open && serio->open(serio)) { serio_set_drv(serio, NULL); return -1; } return 0; } EXPORT_SYMBOL(serio_open); /* called from serio_driver->connect/disconnect methods under serio_mutex */ void serio_close(struct serio *serio) { if (serio->close) serio->close(serio); serio_set_drv(serio, NULL); } EXPORT_SYMBOL(serio_close); irqreturn_t serio_interrupt(struct serio *serio, unsigned char data, unsigned int dfl) { guard(spinlock_irqsave)(&serio->lock); if (likely(serio->drv)) return serio->drv->interrupt(serio, data, dfl); if (!dfl && device_is_registered(&serio->dev)) { serio_rescan(serio); return IRQ_HANDLED; } return IRQ_NONE; } EXPORT_SYMBOL(serio_interrupt); const struct bus_type serio_bus = { .name = "serio", .drv_groups = serio_driver_groups, .match = serio_bus_match, .uevent = serio_uevent, .probe = serio_driver_probe, .remove = serio_driver_remove, .shutdown = serio_shutdown, #ifdef CONFIG_PM .pm = &serio_pm_ops, #endif }; EXPORT_SYMBOL(serio_bus); static int __init serio_init(void) { int error; error = bus_register(&serio_bus); if (error) { pr_err("Failed to register serio bus, error: %d\n", error); return error; } return 0; } static void __exit serio_exit(void) { bus_unregister(&serio_bus); /* * There should not be any outstanding events but work may * still be scheduled so simply cancel it. */ cancel_work_sync(&serio_event_work); } subsys_initcall(serio_init); module_exit(serio_exit); |
| 6050 6128 6131 6122 6057 4462 4463 4 1 1 4 9 4 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 | #include <linux/bpf.h> #include <linux/vmalloc.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/namei.h> #include <linux/user_namespace.h> #include <linux/security.h> static bool bpf_ns_capable(struct user_namespace *ns, int cap) { return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); } bool bpf_token_capable(const struct bpf_token *token, int cap) { struct user_namespace *userns; /* BPF token allows ns_capable() level of capabilities */ userns = token ? token->userns : &init_user_ns; if (!bpf_ns_capable(userns, cap)) return false; if (token && security_bpf_token_capable(token, cap) < 0) return false; return true; } void bpf_token_inc(struct bpf_token *token) { atomic64_inc(&token->refcnt); } static void bpf_token_free(struct bpf_token *token) { security_bpf_token_free(token); put_user_ns(token->userns); kfree(token); } static void bpf_token_put_deferred(struct work_struct *work) { struct bpf_token *token = container_of(work, struct bpf_token, work); bpf_token_free(token); } void bpf_token_put(struct bpf_token *token) { if (!token) return; if (!atomic64_dec_and_test(&token->refcnt)) return; INIT_WORK(&token->work, bpf_token_put_deferred); schedule_work(&token->work); } static int bpf_token_release(struct inode *inode, struct file *filp) { struct bpf_token *token = filp->private_data; bpf_token_put(token); return 0; } static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_token *token = filp->private_data; u64 mask; BUILD_BUG_ON(__MAX_BPF_CMD >= 64); mask = BIT_ULL(__MAX_BPF_CMD) - 1; if ((token->allowed_cmds & mask) == mask) seq_printf(m, "allowed_cmds:\tany\n"); else seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; if ((token->allowed_maps & mask) == mask) seq_printf(m, "allowed_maps:\tany\n"); else seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; if ((token->allowed_progs & mask) == mask) seq_printf(m, "allowed_progs:\tany\n"); else seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; if ((token->allowed_attachs & mask) == mask) seq_printf(m, "allowed_attachs:\tany\n"); else seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); } #define BPF_TOKEN_INODE_NAME "bpf-token" static const struct inode_operations bpf_token_iops = { }; static const struct file_operations bpf_token_fops = { .release = bpf_token_release, .show_fdinfo = bpf_token_show_fdinfo, }; int bpf_token_create(union bpf_attr *attr) { struct bpf_mount_opts *mnt_opts; struct bpf_token *token = NULL; struct user_namespace *userns; struct inode *inode; struct file *file; CLASS(fd, f)(attr->token_create.bpffs_fd); struct path path; struct super_block *sb; umode_t mode; int err, fd; if (fd_empty(f)) return -EBADF; path = fd_file(f)->f_path; sb = path.dentry->d_sb; if (path.dentry != sb->s_root) return -EINVAL; if (sb->s_op != &bpf_super_ops) return -EINVAL; err = path_permission(&path, MAY_ACCESS); if (err) return err; userns = sb->s_user_ns; /* * Enforce that creators of BPF tokens are in the same user * namespace as the BPF FS instance. This makes reasoning about * permissions a lot easier and we can always relax this later. */ if (current_user_ns() != userns) return -EPERM; if (!ns_capable(userns, CAP_BPF)) return -EPERM; /* Creating BPF token in init_user_ns doesn't make much sense. */ if (current_user_ns() == &init_user_ns) return -EOPNOTSUPP; mnt_opts = sb->s_fs_info; if (mnt_opts->delegate_cmds == 0 && mnt_opts->delegate_maps == 0 && mnt_opts->delegate_progs == 0 && mnt_opts->delegate_attachs == 0) return -ENOENT; /* no BPF token delegation is set up */ mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); inode = bpf_get_inode(sb, NULL, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &bpf_token_iops; inode->i_fop = &bpf_token_fops; clear_nlink(inode); /* make sure it is unlinked */ file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); if (IS_ERR(file)) { iput(inode); return PTR_ERR(file); } token = kzalloc(sizeof(*token), GFP_USER); if (!token) { err = -ENOMEM; goto out_file; } atomic64_set(&token->refcnt, 1); /* remember bpffs owning userns for future ns_capable() checks */ token->userns = get_user_ns(userns); token->allowed_cmds = mnt_opts->delegate_cmds; token->allowed_maps = mnt_opts->delegate_maps; token->allowed_progs = mnt_opts->delegate_progs; token->allowed_attachs = mnt_opts->delegate_attachs; err = security_bpf_token_create(token, attr, &path); if (err) goto out_token; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; goto out_token; } file->private_data = token; fd_install(fd, file); return fd; out_token: bpf_token_free(token); out_file: fput(file); return err; } struct bpf_token *bpf_token_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_token *token; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_token_fops) return ERR_PTR(-EINVAL); token = fd_file(f)->private_data; bpf_token_inc(token); return token; } bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { if (!token) return false; if (!(token->allowed_cmds & BIT_ULL(cmd))) return false; return security_bpf_token_cmd(token, cmd) == 0; } bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) { if (!token || type >= __MAX_BPF_MAP_TYPE) return false; return token->allowed_maps & BIT_ULL(type); } bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type) { if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) return false; return (token->allowed_progs & BIT_ULL(prog_type)) && (token->allowed_attachs & BIT_ULL(attach_type)); } |
| 2502 2368 866 56 1062 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H #include <linux/const.h> #include <asm/pgtable_64_types.h> #ifndef __ASSEMBLER__ /* * This file contains the functions and defines necessary to modify and use * the x86-64 page table tree. */ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> #include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %p(%016lx)\n", \ __FILE__, __LINE__, &(e), p4d_val(e)) #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; #define mm_p4d_folded mm_p4d_folded static inline bool mm_p4d_folded(struct mm_struct *mm) { return !pgtable_l5_enabled(); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); static inline void native_set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); } static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) { native_set_pmd(pmd, native_make_pmd(0)); } static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP return native_make_pte(xchg(&xp->pte, 0)); #else /* native_local_ptep_get_and_clear, but duplicated because of cyclic dependency */ pte_t ret = *xp; native_pte_clear(NULL, 0, xp); return ret; #endif } static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { #ifdef CONFIG_SMP return native_make_pmd(xchg(&xp->pmd, 0)); #else /* native_local_pmdp_get_and_clear, but duplicated because of cyclic dependency */ pmd_t ret = *xp; native_pmd_clear(xp); return ret; #endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) { WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) { native_set_pud(pud, native_make_pud(0)); } static inline pud_t native_pudp_get_and_clear(pud_t *xp) { #ifdef CONFIG_SMP return native_make_pud(xchg(&xp->pud, 0)); #else /* native_local_pudp_get_and_clear, * but duplicated because of cyclic dependency */ pud_t ret = *xp; native_pud_clear(xp); return ret; #endif } static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) { native_set_pgd(pgd, native_make_pgd(0)); } /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ /* PGD - Level 4 access */ /* PUD - Level 3 access */ /* PMD - Level 2 access */ /* PTE - Level 1 access */ /* * Encode and de-code a swap entry * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| E|F|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above * there. We also need to avoid using A and D because of an * erratum where they can be incorrectly set by hardware on * non-present PTEs. * * SD Bits 1-4 are not used in non-present format and available for * special use described below: * * SD (1) in swp entry is used to store soft dirty bit, which helps us * remember soft dirty over page migration * * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * * E (3) in swp entry is used to remember PG_anon_exclusive. * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define SWP_TYPE_BITS 5 #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) /* Extract the high bits for type */ #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) /* Shift up (to get rid of type), then down to get value */ #define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) /* * Shift the offset up "too far" by TYPE bits, then down again * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define __swp_entry(type, offset) ((swp_entry_t) { \ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) (__pte((x).val)) #define __swp_entry_to_pmd(x) (__pmd((x).val)) extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 /* fs/proc/kcore.c */ #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME #define vmemmap ((struct page *)VMEMMAP_START) extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; } #include <asm/pgtable-invert.h> #else /* __ASSEMBLER__ */ #define l4_index(x) (((x) >> 39) & 511) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) L4_START_KERNEL = l4_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ i = 0 ; \ .rept (COUNT) ; \ .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ i = i + 1 ; \ .endr #endif /* __ASSEMBLER__ */ #endif /* _ASM_X86_PGTABLE_64_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 | // SPDX-License-Identifier: GPL-2.0-or-later /* A network driver using virtio. * * Copyright 2007 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation */ //#define DEBUG #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/module.h> #include <linux/virtio.h> #include <linux/virtio_net.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/scatterlist.h> #include <linux/if_vlan.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/average.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/dim.h> #include <net/route.h> #include <net/xdp.h> #include <net/net_failover.h> #include <net/netdev_rx_queue.h> #include <net/netdev_queues.h> #include <net/xdp_sock_drv.h> static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); static bool csum = true, gso = true, napi_tx = true; module_param(csum, bool, 0444); module_param(gso, bool, 0444); module_param(napi_tx, bool, 0644); /* FIXME: MTU in config. */ #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) #define GOOD_COPY_LEN 128 #define VIRTNET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* Separating two types of XDP xmit */ #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- * term, transient changes in packet size. */ DECLARE_EWMA(pkt_len, 0, 64) #define VIRTNET_DRIVER_VERSION "1.0.0" static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GUEST_USO4, VIRTIO_NET_F_GUEST_USO6, VIRTIO_NET_F_GUEST_HDRLEN }; #define GUEST_OFFLOAD_GRO_HW_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ (1ULL << VIRTIO_NET_F_GUEST_UFO) | \ (1ULL << VIRTIO_NET_F_GUEST_USO4) | \ (1ULL << VIRTIO_NET_F_GUEST_USO6)) struct virtnet_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; size_t qstat_offset; }; struct virtnet_sq_free_stats { u64 packets; u64 bytes; u64 napi_packets; u64 napi_bytes; u64 xsk; }; struct virtnet_sq_stats { struct u64_stats_sync syncp; u64_stats_t packets; u64_stats_t bytes; u64_stats_t xdp_tx; u64_stats_t xdp_tx_drops; u64_stats_t kicks; u64_stats_t tx_timeouts; u64_stats_t stop; u64_stats_t wake; }; struct virtnet_rq_stats { struct u64_stats_sync syncp; u64_stats_t packets; u64_stats_t bytes; u64_stats_t drops; u64_stats_t xdp_packets; u64_stats_t xdp_tx; u64_stats_t xdp_redirects; u64_stats_t xdp_drops; u64_stats_t kicks; }; #define VIRTNET_SQ_STAT(name, m) {name, offsetof(struct virtnet_sq_stats, m), -1} #define VIRTNET_RQ_STAT(name, m) {name, offsetof(struct virtnet_rq_stats, m), -1} #define VIRTNET_SQ_STAT_QSTAT(name, m) \ { \ name, \ offsetof(struct virtnet_sq_stats, m), \ offsetof(struct netdev_queue_stats_tx, m), \ } #define VIRTNET_RQ_STAT_QSTAT(name, m) \ { \ name, \ offsetof(struct virtnet_rq_stats, m), \ offsetof(struct netdev_queue_stats_rx, m), \ } static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = { VIRTNET_SQ_STAT("xdp_tx", xdp_tx), VIRTNET_SQ_STAT("xdp_tx_drops", xdp_tx_drops), VIRTNET_SQ_STAT("kicks", kicks), VIRTNET_SQ_STAT("tx_timeouts", tx_timeouts), }; static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = { VIRTNET_RQ_STAT("drops", drops), VIRTNET_RQ_STAT("xdp_packets", xdp_packets), VIRTNET_RQ_STAT("xdp_tx", xdp_tx), VIRTNET_RQ_STAT("xdp_redirects", xdp_redirects), VIRTNET_RQ_STAT("xdp_drops", xdp_drops), VIRTNET_RQ_STAT("kicks", kicks), }; static const struct virtnet_stat_desc virtnet_sq_stats_desc_qstat[] = { VIRTNET_SQ_STAT_QSTAT("packets", packets), VIRTNET_SQ_STAT_QSTAT("bytes", bytes), VIRTNET_SQ_STAT_QSTAT("stop", stop), VIRTNET_SQ_STAT_QSTAT("wake", wake), }; static const struct virtnet_stat_desc virtnet_rq_stats_desc_qstat[] = { VIRTNET_RQ_STAT_QSTAT("packets", packets), VIRTNET_RQ_STAT_QSTAT("bytes", bytes), }; #define VIRTNET_STATS_DESC_CQ(name) \ {#name, offsetof(struct virtio_net_stats_cvq, name), -1} #define VIRTNET_STATS_DESC_RX(class, name) \ {#name, offsetof(struct virtio_net_stats_rx_ ## class, rx_ ## name), -1} #define VIRTNET_STATS_DESC_TX(class, name) \ {#name, offsetof(struct virtio_net_stats_tx_ ## class, tx_ ## name), -1} static const struct virtnet_stat_desc virtnet_stats_cvq_desc[] = { VIRTNET_STATS_DESC_CQ(command_num), VIRTNET_STATS_DESC_CQ(ok_num), }; static const struct virtnet_stat_desc virtnet_stats_rx_basic_desc[] = { VIRTNET_STATS_DESC_RX(basic, packets), VIRTNET_STATS_DESC_RX(basic, bytes), VIRTNET_STATS_DESC_RX(basic, notifications), VIRTNET_STATS_DESC_RX(basic, interrupts), }; static const struct virtnet_stat_desc virtnet_stats_tx_basic_desc[] = { VIRTNET_STATS_DESC_TX(basic, packets), VIRTNET_STATS_DESC_TX(basic, bytes), VIRTNET_STATS_DESC_TX(basic, notifications), VIRTNET_STATS_DESC_TX(basic, interrupts), }; static const struct virtnet_stat_desc virtnet_stats_rx_csum_desc[] = { VIRTNET_STATS_DESC_RX(csum, needs_csum), }; static const struct virtnet_stat_desc virtnet_stats_tx_gso_desc[] = { VIRTNET_STATS_DESC_TX(gso, gso_packets_noseg), VIRTNET_STATS_DESC_TX(gso, gso_bytes_noseg), }; static const struct virtnet_stat_desc virtnet_stats_rx_speed_desc[] = { VIRTNET_STATS_DESC_RX(speed, ratelimit_bytes), }; static const struct virtnet_stat_desc virtnet_stats_tx_speed_desc[] = { VIRTNET_STATS_DESC_TX(speed, ratelimit_bytes), }; #define VIRTNET_STATS_DESC_RX_QSTAT(class, name, qstat_field) \ { \ #name, \ offsetof(struct virtio_net_stats_rx_ ## class, rx_ ## name), \ offsetof(struct netdev_queue_stats_rx, qstat_field), \ } #define VIRTNET_STATS_DESC_TX_QSTAT(class, name, qstat_field) \ { \ #name, \ offsetof(struct virtio_net_stats_tx_ ## class, tx_ ## name), \ offsetof(struct netdev_queue_stats_tx, qstat_field), \ } static const struct virtnet_stat_desc virtnet_stats_rx_basic_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(basic, drops, hw_drops), VIRTNET_STATS_DESC_RX_QSTAT(basic, drop_overruns, hw_drop_overruns), }; static const struct virtnet_stat_desc virtnet_stats_tx_basic_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(basic, drops, hw_drops), VIRTNET_STATS_DESC_TX_QSTAT(basic, drop_malformed, hw_drop_errors), }; static const struct virtnet_stat_desc virtnet_stats_rx_csum_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(csum, csum_valid, csum_unnecessary), VIRTNET_STATS_DESC_RX_QSTAT(csum, csum_none, csum_none), VIRTNET_STATS_DESC_RX_QSTAT(csum, csum_bad, csum_bad), }; static const struct virtnet_stat_desc virtnet_stats_tx_csum_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(csum, csum_none, csum_none), VIRTNET_STATS_DESC_TX_QSTAT(csum, needs_csum, needs_csum), }; static const struct virtnet_stat_desc virtnet_stats_rx_gso_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_packets, hw_gro_packets), VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_bytes, hw_gro_bytes), VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_packets_coalesced, hw_gro_wire_packets), VIRTNET_STATS_DESC_RX_QSTAT(gso, gso_bytes_coalesced, hw_gro_wire_bytes), }; static const struct virtnet_stat_desc virtnet_stats_tx_gso_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_packets, hw_gso_packets), VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_bytes, hw_gso_bytes), VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_segments, hw_gso_wire_packets), VIRTNET_STATS_DESC_TX_QSTAT(gso, gso_segments_bytes, hw_gso_wire_bytes), }; static const struct virtnet_stat_desc virtnet_stats_rx_speed_desc_qstat[] = { VIRTNET_STATS_DESC_RX_QSTAT(speed, ratelimit_packets, hw_drop_ratelimits), }; static const struct virtnet_stat_desc virtnet_stats_tx_speed_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(speed, ratelimit_packets, hw_drop_ratelimits), }; #define VIRTNET_Q_TYPE_RX 0 #define VIRTNET_Q_TYPE_TX 1 #define VIRTNET_Q_TYPE_CQ 2 struct virtnet_interrupt_coalesce { u32 max_packets; u32 max_usecs; }; /* The dma information of pages allocated at a time. */ struct virtnet_rq_dma { dma_addr_t addr; u32 ref; u16 len; u16 need_sync; }; /* Internal representation of a send virtqueue */ struct send_queue { /* Virtqueue associated with this send _queue */ struct virtqueue *vq; /* TX: fragments + linear part + virtio header */ struct scatterlist sg[MAX_SKB_FRAGS + 2]; /* Name of the send queue: output.$index */ char name[16]; struct virtnet_sq_stats stats; struct virtnet_interrupt_coalesce intr_coal; struct napi_struct napi; /* Record whether sq is in reset state. */ bool reset; struct xsk_buff_pool *xsk_pool; dma_addr_t xsk_hdr_dma_addr; }; /* Internal representation of a receive virtqueue */ struct receive_queue { /* Virtqueue associated with this receive_queue */ struct virtqueue *vq; struct napi_struct napi; struct bpf_prog __rcu *xdp_prog; struct virtnet_rq_stats stats; /* The number of rx notifications */ u16 calls; /* Is dynamic interrupt moderation enabled? */ bool dim_enabled; /* Used to protect dim_enabled and inter_coal */ struct mutex dim_lock; /* Dynamic Interrupt Moderation */ struct dim dim; u32 packets_in_napi; struct virtnet_interrupt_coalesce intr_coal; /* Chain pages by the private ptr. */ struct page *pages; /* Average packet length for mergeable receive buffers. */ struct ewma_pkt_len mrg_avg_pkt_len; /* Page frag for packet buffer allocation. */ struct page_frag alloc_frag; /* RX: fragments + linear part + virtio header */ struct scatterlist sg[MAX_SKB_FRAGS + 2]; /* Min single buffer size for mergeable buffers case. */ unsigned int min_buf_len; /* Name of this receive queue: input.$index */ char name[16]; struct xdp_rxq_info xdp_rxq; /* Record the last dma info to free after new pages is allocated. */ struct virtnet_rq_dma *last_dma; struct xsk_buff_pool *xsk_pool; /* xdp rxq used by xsk */ struct xdp_rxq_info xsk_rxq_info; struct xdp_buff **xsk_buffs; }; #define VIRTIO_NET_RSS_MAX_KEY_SIZE 40 /* Control VQ buffers: protected by the rtnl lock */ struct control_buf { struct virtio_net_ctrl_hdr hdr; virtio_net_ctrl_ack status; }; struct virtnet_info { struct virtio_device *vdev; struct virtqueue *cvq; struct net_device *dev; struct send_queue *sq; struct receive_queue *rq; unsigned int status; /* Max # of queue pairs supported by the device */ u16 max_queue_pairs; /* # of queue pairs currently used by the driver */ u16 curr_queue_pairs; /* # of XDP queue pairs currently used by the driver */ u16 xdp_queue_pairs; /* xdp_queue_pairs may be 0, when xdp is already loaded. So add this. */ bool xdp_enabled; /* I like... big packets and I cannot lie! */ bool big_packets; /* number of sg entries allocated for big packets */ unsigned int big_packets_num_skbfrags; /* Host will merge rx buffers for big packets (shake it! shake it!) */ bool mergeable_rx_bufs; /* Host supports rss and/or hash report */ bool has_rss; bool has_rss_hash_report; u8 rss_key_size; u16 rss_indir_table_size; u32 rss_hash_types_supported; u32 rss_hash_types_saved; struct virtio_net_rss_config_hdr *rss_hdr; struct virtio_net_rss_config_trailer rss_trailer; u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE]; /* Has control virtqueue */ bool has_cvq; /* Lock to protect the control VQ */ struct mutex cvq_lock; /* Host can handle any s/g split between our header and packet data */ bool any_header_sg; /* Packet virtio header size */ u8 hdr_len; /* Work struct for delayed refilling if we run low on memory. */ struct delayed_work refill; /* Is delayed refill enabled? */ bool refill_enabled; /* The lock to synchronize the access to refill_enabled */ spinlock_t refill_lock; /* Work struct for config space updates */ struct work_struct config_work; /* Work struct for setting rx mode */ struct work_struct rx_mode_work; /* OK to queue work setting RX mode? */ bool rx_mode_work_enabled; /* Does the affinity hint is set for virtqueues? */ bool affinity_hint_set; /* CPU hotplug instances for online & dead */ struct hlist_node node; struct hlist_node node_dead; struct control_buf *ctrl; /* Ethtool settings */ u8 duplex; u32 speed; /* Is rx dynamic interrupt moderation enabled? */ bool rx_dim_enabled; /* Interrupt coalescing settings */ struct virtnet_interrupt_coalesce intr_coal_tx; struct virtnet_interrupt_coalesce intr_coal_rx; unsigned long guest_offloads; unsigned long guest_offloads_capable; /* failover when STANDBY feature enabled */ struct failover *failover; u64 device_stats_cap; }; struct padded_vnet_hdr { struct virtio_net_hdr_v1_hash hdr; /* * hdr is in a separate sg buffer, and data sg buffer shares same page * with this header sg. This padding makes next sg 16 byte aligned * after the header. */ char padding[12]; }; struct virtio_net_common_hdr { union { struct virtio_net_hdr hdr; struct virtio_net_hdr_mrg_rxbuf mrg_hdr; struct virtio_net_hdr_v1_hash hash_v1_hdr; }; }; static struct virtio_net_common_hdr xsk_hdr; static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq); static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp, struct net_device *dev, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats); static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq, struct sk_buff *skb, u8 flags); static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, struct sk_buff *curr_skb, struct page *page, void *buf, int len, int truesize); static void virtnet_xsk_completed(struct send_queue *sq, int num); enum virtnet_xmit_type { VIRTNET_XMIT_TYPE_SKB, VIRTNET_XMIT_TYPE_SKB_ORPHAN, VIRTNET_XMIT_TYPE_XDP, VIRTNET_XMIT_TYPE_XSK, }; static size_t virtnet_rss_hdr_size(const struct virtnet_info *vi) { u16 indir_table_size = vi->has_rss ? vi->rss_indir_table_size : 1; return struct_size(vi->rss_hdr, indirection_table, indir_table_size); } static size_t virtnet_rss_trailer_size(const struct virtnet_info *vi) { return struct_size(&vi->rss_trailer, hash_key_data, vi->rss_key_size); } /* We use the last two bits of the pointer to distinguish the xmit type. */ #define VIRTNET_XMIT_TYPE_MASK (BIT(0) | BIT(1)) #define VIRTIO_XSK_FLAG_OFFSET 2 static enum virtnet_xmit_type virtnet_xmit_ptr_unpack(void **ptr) { unsigned long p = (unsigned long)*ptr; *ptr = (void *)(p & ~VIRTNET_XMIT_TYPE_MASK); return p & VIRTNET_XMIT_TYPE_MASK; } static void *virtnet_xmit_ptr_pack(void *ptr, enum virtnet_xmit_type type) { return (void *)((unsigned long)ptr | type); } static int virtnet_add_outbuf(struct send_queue *sq, int num, void *data, enum virtnet_xmit_type type) { return virtqueue_add_outbuf(sq->vq, sq->sg, num, virtnet_xmit_ptr_pack(data, type), GFP_ATOMIC); } static u32 virtnet_ptr_to_xsk_buff_len(void *ptr) { return ((unsigned long)ptr) >> VIRTIO_XSK_FLAG_OFFSET; } static void sg_fill_dma(struct scatterlist *sg, dma_addr_t addr, u32 len) { sg_dma_address(sg) = addr; sg_dma_len(sg) = len; } static void __free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, bool in_napi, struct virtnet_sq_free_stats *stats) { struct xdp_frame *frame; struct sk_buff *skb; unsigned int len; void *ptr; while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { switch (virtnet_xmit_ptr_unpack(&ptr)) { case VIRTNET_XMIT_TYPE_SKB: skb = ptr; pr_debug("Sent skb %p\n", skb); stats->napi_packets++; stats->napi_bytes += skb->len; napi_consume_skb(skb, in_napi); break; case VIRTNET_XMIT_TYPE_SKB_ORPHAN: skb = ptr; stats->packets++; stats->bytes += skb->len; napi_consume_skb(skb, in_napi); break; case VIRTNET_XMIT_TYPE_XDP: frame = ptr; stats->packets++; stats->bytes += xdp_get_frame_len(frame); xdp_return_frame(frame); break; case VIRTNET_XMIT_TYPE_XSK: stats->bytes += virtnet_ptr_to_xsk_buff_len(ptr); stats->xsk++; break; } } netdev_tx_completed_queue(txq, stats->napi_packets, stats->napi_bytes); } static void virtnet_free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, bool in_napi, struct virtnet_sq_free_stats *stats) { __free_old_xmit(sq, txq, in_napi, stats); if (stats->xsk) virtnet_xsk_completed(sq, stats->xsk); } /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ static int vq2txq(struct virtqueue *vq) { return (vq->index - 1) / 2; } static int txq2vq(int txq) { return txq * 2 + 1; } static int vq2rxq(struct virtqueue *vq) { return vq->index / 2; } static int rxq2vq(int rxq) { return rxq * 2; } static int vq_type(struct virtnet_info *vi, int qid) { if (qid == vi->max_queue_pairs * 2) return VIRTNET_Q_TYPE_CQ; if (qid % 2) return VIRTNET_Q_TYPE_TX; return VIRTNET_Q_TYPE_RX; } static inline struct virtio_net_common_hdr * skb_vnet_common_hdr(struct sk_buff *skb) { return (struct virtio_net_common_hdr *)skb->cb; } /* * private is used to chain pages for big packets, put the whole * most recent used list in the beginning for reuse */ static void give_pages(struct receive_queue *rq, struct page *page) { struct page *end; /* Find end of list, sew whole thing into vi->rq.pages. */ for (end = page; end->private; end = (struct page *)end->private); end->private = (unsigned long)rq->pages; rq->pages = page; } static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) { struct page *p = rq->pages; if (p) { rq->pages = (struct page *)p->private; /* clear private here, it is used to chain pages */ p->private = 0; } else p = alloc_page(gfp_mask); return p; } static void virtnet_rq_free_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf) { if (vi->mergeable_rx_bufs) put_page(virt_to_head_page(buf)); else if (vi->big_packets) give_pages(rq, buf); else put_page(virt_to_head_page(buf)); } static void enable_delayed_refill(struct virtnet_info *vi) { spin_lock_bh(&vi->refill_lock); vi->refill_enabled = true; spin_unlock_bh(&vi->refill_lock); } static void disable_delayed_refill(struct virtnet_info *vi) { spin_lock_bh(&vi->refill_lock); vi->refill_enabled = false; spin_unlock_bh(&vi->refill_lock); } static void enable_rx_mode_work(struct virtnet_info *vi) { rtnl_lock(); vi->rx_mode_work_enabled = true; rtnl_unlock(); } static void disable_rx_mode_work(struct virtnet_info *vi) { rtnl_lock(); vi->rx_mode_work_enabled = false; rtnl_unlock(); } static void virtqueue_napi_schedule(struct napi_struct *napi, struct virtqueue *vq) { if (napi_schedule_prep(napi)) { virtqueue_disable_cb(vq); __napi_schedule(napi); } } static bool virtqueue_napi_complete(struct napi_struct *napi, struct virtqueue *vq, int processed) { int opaque; opaque = virtqueue_enable_cb_prepare(vq); if (napi_complete_done(napi, processed)) { if (unlikely(virtqueue_poll(vq, opaque))) virtqueue_napi_schedule(napi, vq); else return true; } else { virtqueue_disable_cb(vq); } return false; } static void skb_xmit_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; /* Suppress further interrupts. */ virtqueue_disable_cb(vq); if (napi->weight) virtqueue_napi_schedule(napi, vq); else /* We were probably waiting for more output buffers. */ netif_wake_subqueue(vi->dev, vq2txq(vq)); } #define MRG_CTX_HEADER_SHIFT 22 static void *mergeable_len_to_ctx(unsigned int truesize, unsigned int headroom) { return (void *)(unsigned long)((headroom << MRG_CTX_HEADER_SHIFT) | truesize); } static unsigned int mergeable_ctx_to_headroom(void *mrg_ctx) { return (unsigned long)mrg_ctx >> MRG_CTX_HEADER_SHIFT; } static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx) { return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1); } static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen, unsigned int headroom, unsigned int len) { struct sk_buff *skb; skb = build_skb(buf, buflen); if (unlikely(!skb)) return NULL; skb_reserve(skb, headroom); skb_put(skb, len); return skb; } /* Called from bottom half context */ static struct sk_buff *page_to_skb(struct virtnet_info *vi, struct receive_queue *rq, struct page *page, unsigned int offset, unsigned int len, unsigned int truesize, unsigned int headroom) { struct sk_buff *skb; struct virtio_net_common_hdr *hdr; unsigned int copy, hdr_len, hdr_padded_len; struct page *page_to_free = NULL; int tailroom, shinfo_size; char *p, *hdr_p, *buf; p = page_address(page) + offset; hdr_p = p; hdr_len = vi->hdr_len; if (vi->mergeable_rx_bufs) hdr_padded_len = hdr_len; else hdr_padded_len = sizeof(struct padded_vnet_hdr); buf = p - headroom; len -= hdr_len; offset += hdr_padded_len; p += hdr_padded_len; tailroom = truesize - headroom - hdr_padded_len - len; shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (!NET_IP_ALIGN && len > GOOD_COPY_LEN && tailroom >= shinfo_size) { skb = virtnet_build_skb(buf, truesize, p - buf, len); if (unlikely(!skb)) return NULL; page = (struct page *)page->private; if (page) give_pages(rq, page); goto ok; } /* copy small packet so we can reuse these pages for small data */ skb = napi_alloc_skb(&rq->napi, GOOD_COPY_LEN); if (unlikely(!skb)) return NULL; /* Copy all frame if it fits skb->head, otherwise * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. */ if (len <= skb_tailroom(skb)) copy = len; else copy = ETH_HLEN; skb_put_data(skb, p, copy); len -= copy; offset += copy; if (vi->mergeable_rx_bufs) { if (len) skb_add_rx_frag(skb, 0, page, offset, len, truesize); else page_to_free = page; goto ok; } /* * Verify that we can indeed put this data into a skb. * This is here to handle cases when the device erroneously * tries to receive more than is possible. This is usually * the case of a broken device. */ if (unlikely(len > MAX_SKB_FRAGS * PAGE_SIZE)) { net_dbg_ratelimited("%s: too much data\n", skb->dev->name); dev_kfree_skb(skb); return NULL; } BUG_ON(offset >= PAGE_SIZE); while (len) { unsigned int frag_size = min((unsigned)PAGE_SIZE - offset, len); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, offset, frag_size, truesize); len -= frag_size; page = (struct page *)page->private; offset = 0; } if (page) give_pages(rq, page); ok: hdr = skb_vnet_common_hdr(skb); memcpy(hdr, hdr_p, hdr_len); if (page_to_free) put_page(page_to_free); return skb; } static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len) { struct virtnet_info *vi = rq->vq->vdev->priv; struct page *page = virt_to_head_page(buf); struct virtnet_rq_dma *dma; void *head; int offset; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(page); dma = head; --dma->ref; if (dma->need_sync && len) { offset = buf - (head + sizeof(*dma)); virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, offset, len, DMA_FROM_DEVICE); } if (dma->ref) return; virtqueue_dma_unmap_single_attrs(rq->vq, dma->addr, dma->len, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); put_page(page); } static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx) { struct virtnet_info *vi = rq->vq->vdev->priv; void *buf; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); buf = virtqueue_get_buf_ctx(rq->vq, len, ctx); if (buf) virtnet_rq_unmap(rq, buf, *len); return buf; } static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len) { struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_dma *dma; dma_addr_t addr; u32 offset; void *head; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(rq->alloc_frag.page); offset = buf - head; dma = head; addr = dma->addr - sizeof(*dma) + offset; sg_init_table(rq->sg, 1); sg_fill_dma(rq->sg, addr, len); } static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp) { struct page_frag *alloc_frag = &rq->alloc_frag; struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_dma *dma; void *buf, *head; dma_addr_t addr; BUG_ON(vi->big_packets && !vi->mergeable_rx_bufs); head = page_address(alloc_frag->page); dma = head; /* new pages */ if (!alloc_frag->offset) { if (rq->last_dma) { /* Now, the new page is allocated, the last dma * will not be used. So the dma can be unmapped * if the ref is 0. */ virtnet_rq_unmap(rq, rq->last_dma, 0); rq->last_dma = NULL; } dma->len = alloc_frag->size - sizeof(*dma); addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1, dma->len, DMA_FROM_DEVICE, 0); if (virtqueue_dma_mapping_error(rq->vq, addr)) return NULL; dma->addr = addr; dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr); /* Add a reference to dma to prevent the entire dma from * being released during error handling. This reference * will be freed after the pages are no longer used. */ get_page(alloc_frag->page); dma->ref = 1; alloc_frag->offset = sizeof(*dma); rq->last_dma = dma; } ++dma->ref; buf = head + alloc_frag->offset; get_page(alloc_frag->page); alloc_frag->offset += size; return buf; } static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf) { struct virtnet_info *vi = vq->vdev->priv; struct receive_queue *rq; int i = vq2rxq(vq); rq = &vi->rq[i]; if (rq->xsk_pool) { xsk_buff_free((struct xdp_buff *)buf); return; } if (!vi->big_packets || vi->mergeable_rx_bufs) virtnet_rq_unmap(rq, buf, 0); virtnet_rq_free_buf(vi, rq, buf); } static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq, bool in_napi) { struct virtnet_sq_free_stats stats = {0}; virtnet_free_old_xmit(sq, txq, in_napi, &stats); /* Avoid overhead when no packets have been processed * happens when called speculatively from start_xmit. */ if (!stats.packets && !stats.napi_packets) return; u64_stats_update_begin(&sq->stats.syncp); u64_stats_add(&sq->stats.bytes, stats.bytes + stats.napi_bytes); u64_stats_add(&sq->stats.packets, stats.packets + stats.napi_packets); u64_stats_update_end(&sq->stats.syncp); } static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) { if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) return false; else if (q < vi->curr_queue_pairs) return true; else return false; } static bool tx_may_stop(struct virtnet_info *vi, struct net_device *dev, struct send_queue *sq) { int qnum; qnum = sq - vi->sq; /* If running out of space, stop queue to avoid getting packets that we * are then unable to transmit. * An alternative would be to force queuing layer to requeue the skb by * returning NETDEV_TX_BUSY. However, NETDEV_TX_BUSY should not be * returned in a normal path of operation: it means that driver is not * maintaining the TX queue stop/start state properly, and causes * the stack to do a non-trivial amount of useless work. * Since most packets only take 1 or 2 ring slots, stopping the queue * early means 16 slots are typically wasted. */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); netif_tx_stop_queue(txq); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.stop); u64_stats_update_end(&sq->stats.syncp); return true; } return false; } static void check_sq_full_and_disable(struct virtnet_info *vi, struct net_device *dev, struct send_queue *sq) { bool use_napi = sq->napi.weight; int qnum; qnum = sq - vi->sq; if (tx_may_stop(vi, dev, sq)) { struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); if (use_napi) { if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) virtqueue_napi_schedule(&sq->napi, sq->vq); } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ free_old_xmit(sq, txq, false); if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { netif_start_subqueue(dev, qnum); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); u64_stats_update_end(&sq->stats.syncp); virtqueue_disable_cb(sq->vq); } } } } static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi, struct receive_queue *rq, void *buf, u32 len) { struct xdp_buff *xdp; u32 bufsize; xdp = (struct xdp_buff *)buf; bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len; if (unlikely(len > bufsize)) { pr_debug("%s: rx error: len %u exceeds truesize %u\n", vi->dev->name, len, bufsize); DEV_STATS_INC(vi->dev, rx_length_errors); xsk_buff_free(xdp); return NULL; } xsk_buff_set_size(xdp, len); xsk_buff_dma_sync_for_cpu(xdp); return xdp; } static struct sk_buff *xsk_construct_skb(struct receive_queue *rq, struct xdp_buff *xdp) { unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; unsigned int size; size = xdp->data_end - xdp->data_hard_start; skb = napi_alloc_skb(&rq->napi, size); if (unlikely(!skb)) { xsk_buff_free(xdp); return NULL; } skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); size = xdp->data_end - xdp->data_meta; memcpy(__skb_put(skb, size), xdp->data_meta, size); if (metasize) { __skb_pull(skb, metasize); skb_metadata_set(skb, metasize); } xsk_buff_free(xdp); return skb; } static struct sk_buff *virtnet_receive_xsk_small(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct xdp_buff *xdp, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct bpf_prog *prog; u32 ret; ret = XDP_PASS; rcu_read_lock(); prog = rcu_dereference(rq->xdp_prog); if (prog) ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats); rcu_read_unlock(); switch (ret) { case XDP_PASS: return xsk_construct_skb(rq, xdp); case XDP_TX: case XDP_REDIRECT: return NULL; default: /* drop packet */ xsk_buff_free(xdp); u64_stats_inc(&stats->drops); return NULL; } } static void xsk_drop_follow_bufs(struct net_device *dev, struct receive_queue *rq, u32 num_buf, struct virtnet_rq_stats *stats) { struct xdp_buff *xdp; u32 len; while (num_buf-- > 1) { xdp = virtqueue_get_buf(rq->vq, &len); if (unlikely(!xdp)) { pr_debug("%s: rx error: %d buffers missing\n", dev->name, num_buf); DEV_STATS_INC(dev, rx_length_errors); break; } u64_stats_add(&stats->bytes, len); xsk_buff_free(xdp); } } static int xsk_append_merge_buffer(struct virtnet_info *vi, struct receive_queue *rq, struct sk_buff *head_skb, u32 num_buf, struct virtio_net_hdr_mrg_rxbuf *hdr, struct virtnet_rq_stats *stats) { struct sk_buff *curr_skb; struct xdp_buff *xdp; u32 len, truesize; struct page *page; void *buf; curr_skb = head_skb; while (--num_buf) { buf = virtqueue_get_buf(rq->vq, &len); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", vi->dev->name, num_buf, virtio16_to_cpu(vi->vdev, hdr->num_buffers)); DEV_STATS_INC(vi->dev, rx_length_errors); return -EINVAL; } u64_stats_add(&stats->bytes, len); xdp = buf_to_xdp(vi, rq, buf, len); if (!xdp) goto err; buf = napi_alloc_frag(len); if (!buf) { xsk_buff_free(xdp); goto err; } memcpy(buf, xdp->data - vi->hdr_len, len); xsk_buff_free(xdp); page = virt_to_page(buf); truesize = len; curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) { put_page(page); goto err; } } return 0; err: xsk_drop_follow_bufs(vi->dev, rq, num_buf, stats); return -EINVAL; } static struct sk_buff *virtnet_receive_xsk_merge(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct xdp_buff *xdp, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr; struct bpf_prog *prog; struct sk_buff *skb; u32 ret, num_buf; hdr = xdp->data - vi->hdr_len; num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); ret = XDP_PASS; rcu_read_lock(); prog = rcu_dereference(rq->xdp_prog); /* TODO: support multi buffer. */ if (prog && num_buf == 1) ret = virtnet_xdp_handler(prog, xdp, dev, xdp_xmit, stats); rcu_read_unlock(); switch (ret) { case XDP_PASS: skb = xsk_construct_skb(rq, xdp); if (!skb) goto drop_bufs; if (xsk_append_merge_buffer(vi, rq, skb, num_buf, hdr, stats)) { dev_kfree_skb(skb); goto drop; } return skb; case XDP_TX: case XDP_REDIRECT: return NULL; default: /* drop packet */ xsk_buff_free(xdp); } drop_bufs: xsk_drop_follow_bufs(dev, rq, num_buf, stats); drop: u64_stats_inc(&stats->drops); return NULL; } static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf, u32 len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct net_device *dev = vi->dev; struct sk_buff *skb = NULL; struct xdp_buff *xdp; u8 flags; len -= vi->hdr_len; u64_stats_add(&stats->bytes, len); xdp = buf_to_xdp(vi, rq, buf, len); if (!xdp) return; if (unlikely(len < ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); DEV_STATS_INC(dev, rx_length_errors); xsk_buff_free(xdp); return; } flags = ((struct virtio_net_common_hdr *)(xdp->data - vi->hdr_len))->hdr.flags; if (!vi->mergeable_rx_bufs) skb = virtnet_receive_xsk_small(dev, vi, rq, xdp, xdp_xmit, stats); else skb = virtnet_receive_xsk_merge(dev, vi, rq, xdp, xdp_xmit, stats); if (skb) virtnet_receive_done(vi, rq, skb, flags); } static int virtnet_add_recvbuf_xsk(struct virtnet_info *vi, struct receive_queue *rq, struct xsk_buff_pool *pool, gfp_t gfp) { struct xdp_buff **xsk_buffs; dma_addr_t addr; int err = 0; u32 len, i; int num; xsk_buffs = rq->xsk_buffs; num = xsk_buff_alloc_batch(pool, xsk_buffs, rq->vq->num_free); if (!num) return -ENOMEM; len = xsk_pool_get_rx_frame_size(pool) + vi->hdr_len; for (i = 0; i < num; ++i) { /* Use the part of XDP_PACKET_HEADROOM as the virtnet hdr space. * We assume XDP_PACKET_HEADROOM is larger than hdr->len. * (see function virtnet_xsk_pool_enable) */ addr = xsk_buff_xdp_get_dma(xsk_buffs[i]) - vi->hdr_len; sg_init_table(rq->sg, 1); sg_fill_dma(rq->sg, addr, len); err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, xsk_buffs[i], NULL, gfp); if (err) goto err; } return num; err: for (; i < num; ++i) xsk_buff_free(xsk_buffs[i]); return err; } static void *virtnet_xsk_to_ptr(u32 len) { unsigned long p; p = len << VIRTIO_XSK_FLAG_OFFSET; return virtnet_xmit_ptr_pack((void *)p, VIRTNET_XMIT_TYPE_XSK); } static int virtnet_xsk_xmit_one(struct send_queue *sq, struct xsk_buff_pool *pool, struct xdp_desc *desc) { struct virtnet_info *vi; dma_addr_t addr; vi = sq->vq->vdev->priv; addr = xsk_buff_raw_get_dma(pool, desc->addr); xsk_buff_raw_dma_sync_for_device(pool, addr, desc->len); sg_init_table(sq->sg, 2); sg_fill_dma(sq->sg, sq->xsk_hdr_dma_addr, vi->hdr_len); sg_fill_dma(sq->sg + 1, addr, desc->len); return virtqueue_add_outbuf_premapped(sq->vq, sq->sg, 2, virtnet_xsk_to_ptr(desc->len), GFP_ATOMIC); } static int virtnet_xsk_xmit_batch(struct send_queue *sq, struct xsk_buff_pool *pool, unsigned int budget, u64 *kicks) { struct xdp_desc *descs = pool->tx_descs; bool kick = false; u32 nb_pkts, i; int err; budget = min_t(u32, budget, sq->vq->num_free); nb_pkts = xsk_tx_peek_release_desc_batch(pool, budget); if (!nb_pkts) return 0; for (i = 0; i < nb_pkts; i++) { err = virtnet_xsk_xmit_one(sq, pool, &descs[i]); if (unlikely(err)) { xsk_tx_completed(sq->xsk_pool, nb_pkts - i); break; } kick = true; } if (kick && virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) (*kicks)++; return i; } static bool virtnet_xsk_xmit(struct send_queue *sq, struct xsk_buff_pool *pool, int budget) { struct virtnet_info *vi = sq->vq->vdev->priv; struct virtnet_sq_free_stats stats = {}; struct net_device *dev = vi->dev; u64 kicks = 0; int sent; /* Avoid to wakeup napi meanless, so call __free_old_xmit instead of * free_old_xmit(). */ __free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq), true, &stats); if (stats.xsk) xsk_tx_completed(sq->xsk_pool, stats.xsk); sent = virtnet_xsk_xmit_batch(sq, pool, budget, &kicks); if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq)) check_sq_full_and_disable(vi, vi->dev, sq); if (sent) { struct netdev_queue *txq; txq = netdev_get_tx_queue(vi->dev, sq - vi->sq); txq_trans_cond_update(txq); } u64_stats_update_begin(&sq->stats.syncp); u64_stats_add(&sq->stats.packets, stats.packets); u64_stats_add(&sq->stats.bytes, stats.bytes); u64_stats_add(&sq->stats.kicks, kicks); u64_stats_add(&sq->stats.xdp_tx, sent); u64_stats_update_end(&sq->stats.syncp); if (xsk_uses_need_wakeup(pool)) xsk_set_tx_need_wakeup(pool); return sent; } static void xsk_wakeup(struct send_queue *sq) { if (napi_if_scheduled_mark_missed(&sq->napi)) return; local_bh_disable(); virtqueue_napi_schedule(&sq->napi, sq->vq); local_bh_enable(); } static int virtnet_xsk_wakeup(struct net_device *dev, u32 qid, u32 flag) { struct virtnet_info *vi = netdev_priv(dev); struct send_queue *sq; if (!netif_running(dev)) return -ENETDOWN; if (qid >= vi->curr_queue_pairs) return -EINVAL; sq = &vi->sq[qid]; xsk_wakeup(sq); return 0; } static void virtnet_xsk_completed(struct send_queue *sq, int num) { xsk_tx_completed(sq->xsk_pool, num); /* If this is called by rx poll, start_xmit and xdp xmit we should * wakeup the tx napi to consume the xsk tx queue, because the tx * interrupt may not be triggered. */ xsk_wakeup(sq); } static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, struct send_queue *sq, struct xdp_frame *xdpf) { struct virtio_net_hdr_mrg_rxbuf *hdr; struct skb_shared_info *shinfo; u8 nr_frags = 0; int err, i; if (unlikely(xdpf->headroom < vi->hdr_len)) return -EOVERFLOW; if (unlikely(xdp_frame_has_frags(xdpf))) { shinfo = xdp_get_shared_info_from_frame(xdpf); nr_frags = shinfo->nr_frags; } /* In wrapping function virtnet_xdp_xmit(), we need to free * up the pending old buffers, where we need to calculate the * position of skb_shared_info in xdp_get_frame_len() and * xdp_return_frame(), which will involve to xdpf->data and * xdpf->headroom. Therefore, we need to update the value of * headroom synchronously here. */ xdpf->headroom -= vi->hdr_len; xdpf->data -= vi->hdr_len; /* Zero header and leave csum up to XDP layers */ hdr = xdpf->data; memset(hdr, 0, vi->hdr_len); xdpf->len += vi->hdr_len; sg_init_table(sq->sg, nr_frags + 1); sg_set_buf(sq->sg, xdpf->data, xdpf->len); for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = &shinfo->frags[i]; sg_set_page(&sq->sg[i + 1], skb_frag_page(frag), skb_frag_size(frag), skb_frag_off(frag)); } err = virtnet_add_outbuf(sq, nr_frags + 1, xdpf, VIRTNET_XMIT_TYPE_XDP); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ return 0; } /* when vi->curr_queue_pairs > nr_cpu_ids, the txq/sq is only used for xdp tx on * the current cpu, so it does not need to be locked. * * Here we use marco instead of inline functions because we have to deal with * three issues at the same time: 1. the choice of sq. 2. judge and execute the * lock/unlock of txq 3. make sparse happy. It is difficult for two inline * functions to perfectly solve these three problems at the same time. */ #define virtnet_xdp_get_sq(vi) ({ \ int cpu = smp_processor_id(); \ struct netdev_queue *txq; \ typeof(vi) v = (vi); \ unsigned int qp; \ \ if (v->curr_queue_pairs > nr_cpu_ids) { \ qp = v->curr_queue_pairs - v->xdp_queue_pairs; \ qp += cpu; \ txq = netdev_get_tx_queue(v->dev, qp); \ __netif_tx_acquire(txq); \ } else { \ qp = cpu % v->curr_queue_pairs; \ txq = netdev_get_tx_queue(v->dev, qp); \ __netif_tx_lock(txq, cpu); \ } \ v->sq + qp; \ }) #define virtnet_xdp_put_sq(vi, q) { \ struct netdev_queue *txq; \ typeof(vi) v = (vi); \ \ txq = netdev_get_tx_queue(v->dev, (q) - v->sq); \ if (v->curr_queue_pairs > nr_cpu_ids) \ __netif_tx_release(txq); \ else \ __netif_tx_unlock(txq); \ } static int virtnet_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { struct virtnet_info *vi = netdev_priv(dev); struct virtnet_sq_free_stats stats = {0}; struct receive_queue *rq = vi->rq; struct bpf_prog *xdp_prog; struct send_queue *sq; int nxmit = 0; int kicks = 0; int ret; int i; /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_access_pointer(rq->xdp_prog); if (!xdp_prog) return -ENXIO; sq = virtnet_xdp_get_sq(vi); if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { ret = -EINVAL; goto out; } /* Free up any pending old buffers before queueing new ones. */ virtnet_free_old_xmit(sq, netdev_get_tx_queue(dev, sq - vi->sq), false, &stats); for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; if (__virtnet_xdp_xmit_one(vi, sq, xdpf)) break; nxmit++; } ret = nxmit; if (!is_xdp_raw_buffer_queue(vi, sq - vi->sq)) check_sq_full_and_disable(vi, dev, sq); if (flags & XDP_XMIT_FLUSH) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) kicks = 1; } out: u64_stats_update_begin(&sq->stats.syncp); u64_stats_add(&sq->stats.bytes, stats.bytes); u64_stats_add(&sq->stats.packets, stats.packets); u64_stats_add(&sq->stats.xdp_tx, n); u64_stats_add(&sq->stats.xdp_tx_drops, n - nxmit); u64_stats_add(&sq->stats.kicks, kicks); u64_stats_update_end(&sq->stats.syncp); virtnet_xdp_put_sq(vi, sq); return ret; } static void put_xdp_frags(struct xdp_buff *xdp) { struct skb_shared_info *shinfo; struct page *xdp_page; int i; if (xdp_buff_has_frags(xdp)) { shinfo = xdp_get_shared_info_from_buff(xdp); for (i = 0; i < shinfo->nr_frags; i++) { xdp_page = skb_frag_page(&shinfo->frags[i]); put_page(xdp_page); } } } static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp, struct net_device *dev, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct xdp_frame *xdpf; int err; u32 act; act = bpf_prog_run_xdp(xdp_prog, xdp); u64_stats_inc(&stats->xdp_packets); switch (act) { case XDP_PASS: return act; case XDP_TX: u64_stats_inc(&stats->xdp_tx); xdpf = xdp_convert_buff_to_frame(xdp); if (unlikely(!xdpf)) { netdev_dbg(dev, "convert buff to frame failed for xdp\n"); return XDP_DROP; } err = virtnet_xdp_xmit(dev, 1, &xdpf, 0); if (unlikely(!err)) { xdp_return_frame_rx_napi(xdpf); } else if (unlikely(err < 0)) { trace_xdp_exception(dev, xdp_prog, act); return XDP_DROP; } *xdp_xmit |= VIRTIO_XDP_TX; return act; case XDP_REDIRECT: u64_stats_inc(&stats->xdp_redirects); err = xdp_do_redirect(dev, xdp, xdp_prog); if (err) return XDP_DROP; *xdp_xmit |= VIRTIO_XDP_REDIR; return act; default: bpf_warn_invalid_xdp_action(dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); fallthrough; case XDP_DROP: return XDP_DROP; } } static unsigned int virtnet_get_headroom(struct virtnet_info *vi) { return vi->xdp_enabled ? XDP_PACKET_HEADROOM : 0; } /* We copy the packet for XDP in the following cases: * * 1) Packet is scattered across multiple rx buffers. * 2) Headroom space is insufficient. * * This is inefficient but it's a temporary condition that * we hit right after XDP is enabled and until queue is refilled * with large buffers with sufficient headroom - so it should affect * at most queue size packets. * Afterwards, the conditions to enable * XDP should preclude the underlying device from sending packets * across multiple buffers (num_buf > 1), and we make sure buffers * have enough headroom. */ static struct page *xdp_linearize_page(struct receive_queue *rq, int *num_buf, struct page *p, int offset, int page_off, unsigned int *len) { int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); struct page *page; if (page_off + *len + tailroom > PAGE_SIZE) return NULL; page = alloc_page(GFP_ATOMIC); if (!page) return NULL; memcpy(page_address(page) + page_off, page_address(p) + offset, *len); page_off += *len; while (--*num_buf) { unsigned int buflen; void *buf; int off; buf = virtnet_rq_get_buf(rq, &buflen, NULL); if (unlikely(!buf)) goto err_buf; p = virt_to_head_page(buf); off = buf - page_address(p); /* guard against a misconfigured or uncooperative backend that * is sending packet larger than the MTU. */ if ((page_off + buflen + tailroom) > PAGE_SIZE) { put_page(p); goto err_buf; } memcpy(page_address(page) + page_off, page_address(p) + off, buflen); page_off += buflen; put_page(p); } /* Headroom does not contribute to packet length */ *len = page_off - XDP_PACKET_HEADROOM; return page; err_buf: __free_pages(page, 0); return NULL; } static struct sk_buff *receive_small_build_skb(struct virtnet_info *vi, unsigned int xdp_headroom, void *buf, unsigned int len) { unsigned int header_offset; unsigned int headroom; unsigned int buflen; struct sk_buff *skb; header_offset = VIRTNET_RX_PAD + xdp_headroom; headroom = vi->hdr_len + header_offset; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); skb = virtnet_build_skb(buf, buflen, headroom, len); if (unlikely(!skb)) return NULL; buf += header_offset; memcpy(skb_vnet_common_hdr(skb), buf, vi->hdr_len); return skb; } static struct sk_buff *receive_small_xdp(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct bpf_prog *xdp_prog, void *buf, unsigned int xdp_headroom, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int header_offset = VIRTNET_RX_PAD + xdp_headroom; unsigned int headroom = vi->hdr_len + header_offset; struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset; struct page *page = virt_to_head_page(buf); struct page *xdp_page; unsigned int buflen; struct xdp_buff xdp; struct sk_buff *skb; unsigned int metasize = 0; u32 act; if (unlikely(hdr->hdr.gso_type)) goto err_xdp; /* Partially checksummed packets must be dropped. */ if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) goto err_xdp; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (unlikely(xdp_headroom < virtnet_get_headroom(vi))) { int offset = buf - page_address(page) + header_offset; unsigned int tlen = len + vi->hdr_len; int num_buf = 1; xdp_headroom = virtnet_get_headroom(vi); header_offset = VIRTNET_RX_PAD + xdp_headroom; headroom = vi->hdr_len + header_offset; buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); xdp_page = xdp_linearize_page(rq, &num_buf, page, offset, header_offset, &tlen); if (!xdp_page) goto err_xdp; buf = page_address(xdp_page); put_page(page); page = xdp_page; } xdp_init_buff(&xdp, buflen, &rq->xdp_rxq); xdp_prepare_buff(&xdp, buf + VIRTNET_RX_PAD + vi->hdr_len, xdp_headroom, len, true); act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats); switch (act) { case XDP_PASS: /* Recalculate length in case bpf program changed it */ len = xdp.data_end - xdp.data; metasize = xdp.data - xdp.data_meta; break; case XDP_TX: case XDP_REDIRECT: goto xdp_xmit; default: goto err_xdp; } skb = virtnet_build_skb(buf, buflen, xdp.data - buf, len); if (unlikely(!skb)) goto err; if (metasize) skb_metadata_set(skb, metasize); return skb; err_xdp: u64_stats_inc(&stats->xdp_drops); err: u64_stats_inc(&stats->drops); put_page(page); xdp_xmit: return NULL; } static struct sk_buff *receive_small(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int xdp_headroom = (unsigned long)ctx; struct page *page = virt_to_head_page(buf); struct sk_buff *skb; /* We passed the address of virtnet header to virtio-core, * so truncate the padding. */ buf -= VIRTNET_RX_PAD + xdp_headroom; len -= vi->hdr_len; u64_stats_add(&stats->bytes, len); if (unlikely(len > GOOD_PACKET_LEN)) { pr_debug("%s: rx error: len %u exceeds max size %d\n", dev->name, len, GOOD_PACKET_LEN); DEV_STATS_INC(dev, rx_length_errors); goto err; } if (unlikely(vi->xdp_enabled)) { struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { skb = receive_small_xdp(dev, vi, rq, xdp_prog, buf, xdp_headroom, len, xdp_xmit, stats); rcu_read_unlock(); return skb; } rcu_read_unlock(); } skb = receive_small_build_skb(vi, xdp_headroom, buf, len); if (likely(skb)) return skb; err: u64_stats_inc(&stats->drops); put_page(page); return NULL; } static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, unsigned int len, struct virtnet_rq_stats *stats) { struct page *page = buf; struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE, 0); u64_stats_add(&stats->bytes, len - vi->hdr_len); if (unlikely(!skb)) goto err; return skb; err: u64_stats_inc(&stats->drops); give_pages(rq, page); return NULL; } static void mergeable_buf_free(struct receive_queue *rq, int num_buf, struct net_device *dev, struct virtnet_rq_stats *stats) { struct page *page; void *buf; int len; while (num_buf-- > 1) { buf = virtnet_rq_get_buf(rq, &len, NULL); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers missing\n", dev->name, num_buf); DEV_STATS_INC(dev, rx_length_errors); break; } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); put_page(page); } } /* Why not use xdp_build_skb_from_frame() ? * XDP core assumes that xdp frags are PAGE_SIZE in length, while in * virtio-net there are 2 points that do not match its requirements: * 1. The size of the prefilled buffer is not fixed before xdp is set. * 2. xdp_build_skb_from_frame() does more checks that we don't need, * like eth_type_trans() (which virtio-net does in receive_buf()). */ static struct sk_buff *build_skb_from_xdp_buff(struct net_device *dev, struct virtnet_info *vi, struct xdp_buff *xdp, unsigned int xdp_frags_truesz) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); unsigned int headroom, data_len; struct sk_buff *skb; int metasize; u8 nr_frags; if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { pr_debug("Error building skb as missing reserved tailroom for xdp"); return NULL; } if (unlikely(xdp_buff_has_frags(xdp))) nr_frags = sinfo->nr_frags; skb = build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; headroom = xdp->data - xdp->data_hard_start; data_len = xdp->data_end - xdp->data; skb_reserve(skb, headroom); __skb_put(skb, data_len); metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (metasize) skb_metadata_set(skb, metasize); if (unlikely(xdp_buff_has_frags(xdp))) xdp_update_skb_shared_info(skb, nr_frags, sinfo->xdp_frags_size, xdp_frags_truesz, xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } /* TODO: build xdp in big mode */ static int virtnet_build_xdp_buff_mrg(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct xdp_buff *xdp, void *buf, unsigned int len, unsigned int frame_sz, int *num_buf, unsigned int *xdp_frags_truesize, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; unsigned int headroom, tailroom, room; unsigned int truesize, cur_frag_size; struct skb_shared_info *shinfo; unsigned int xdp_frags_truesz = 0; struct page *page; skb_frag_t *frag; int offset; void *ctx; xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq); xdp_prepare_buff(xdp, buf - XDP_PACKET_HEADROOM, XDP_PACKET_HEADROOM + vi->hdr_len, len - vi->hdr_len, true); if (!*num_buf) return 0; if (*num_buf > 1) { /* If we want to build multi-buffer xdp, we need * to specify that the flags of xdp_buff have the * XDP_FLAGS_HAS_FRAG bit. */ if (!xdp_buff_has_frags(xdp)) xdp_buff_set_frags_flag(xdp); shinfo = xdp_get_shared_info_from_buff(xdp); shinfo->nr_frags = 0; shinfo->xdp_frags_size = 0; } if (*num_buf > MAX_SKB_FRAGS + 1) return -EINVAL; while (--*num_buf > 0) { buf = virtnet_rq_get_buf(rq, &len, &ctx); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", dev->name, *num_buf, virtio16_to_cpu(vi->vdev, hdr->num_buffers)); DEV_STATS_INC(dev, rx_length_errors); goto err; } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); offset = buf - page_address(page); truesize = mergeable_ctx_to_truesize(ctx); headroom = mergeable_ctx_to_headroom(ctx); tailroom = headroom ? sizeof(struct skb_shared_info) : 0; room = SKB_DATA_ALIGN(headroom + tailroom); cur_frag_size = truesize; xdp_frags_truesz += cur_frag_size; if (unlikely(len > truesize - room || cur_frag_size > PAGE_SIZE)) { put_page(page); pr_debug("%s: rx error: len %u exceeds truesize %lu\n", dev->name, len, (unsigned long)(truesize - room)); DEV_STATS_INC(dev, rx_length_errors); goto err; } frag = &shinfo->frags[shinfo->nr_frags++]; skb_frag_fill_page_desc(frag, page, offset, len); if (page_is_pfmemalloc(page)) xdp_buff_set_frag_pfmemalloc(xdp); shinfo->xdp_frags_size += len; } *xdp_frags_truesize = xdp_frags_truesz; return 0; err: put_xdp_frags(xdp); return -EINVAL; } static void *mergeable_xdp_get_buf(struct virtnet_info *vi, struct receive_queue *rq, struct bpf_prog *xdp_prog, void *ctx, unsigned int *frame_sz, int *num_buf, struct page **page, int offset, unsigned int *len, struct virtio_net_hdr_mrg_rxbuf *hdr) { unsigned int truesize = mergeable_ctx_to_truesize(ctx); unsigned int headroom = mergeable_ctx_to_headroom(ctx); struct page *xdp_page; unsigned int xdp_room; /* Transient failure which in theory could occur if * in-flight packets from before XDP was enabled reach * the receive path after XDP is loaded. */ if (unlikely(hdr->hdr.gso_type)) return NULL; /* Partially checksummed packets must be dropped. */ if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) return NULL; /* Now XDP core assumes frag size is PAGE_SIZE, but buffers * with headroom may add hole in truesize, which * make their length exceed PAGE_SIZE. So we disabled the * hole mechanism for xdp. See add_recvbuf_mergeable(). */ *frame_sz = truesize; if (likely(headroom >= virtnet_get_headroom(vi) && (*num_buf == 1 || xdp_prog->aux->xdp_has_frags))) { return page_address(*page) + offset; } /* This happens when headroom is not enough because * of the buffer was prefilled before XDP is set. * This should only happen for the first several packets. * In fact, vq reset can be used here to help us clean up * the prefilled buffers, but many existing devices do not * support it, and we don't want to bother users who are * using xdp normally. */ if (!xdp_prog->aux->xdp_has_frags) { /* linearize data for XDP */ xdp_page = xdp_linearize_page(rq, num_buf, *page, offset, XDP_PACKET_HEADROOM, len); if (!xdp_page) return NULL; } else { xdp_room = SKB_DATA_ALIGN(XDP_PACKET_HEADROOM + sizeof(struct skb_shared_info)); if (*len + xdp_room > PAGE_SIZE) return NULL; xdp_page = alloc_page(GFP_ATOMIC); if (!xdp_page) return NULL; memcpy(page_address(xdp_page) + XDP_PACKET_HEADROOM, page_address(*page) + offset, *len); } *frame_sz = PAGE_SIZE; put_page(*page); *page = xdp_page; return page_address(*page) + XDP_PACKET_HEADROOM; } static struct sk_buff *receive_mergeable_xdp(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, struct bpf_prog *xdp_prog, void *buf, void *ctx, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); struct page *page = virt_to_head_page(buf); int offset = buf - page_address(page); unsigned int xdp_frags_truesz = 0; struct sk_buff *head_skb; unsigned int frame_sz; struct xdp_buff xdp; void *data; u32 act; int err; data = mergeable_xdp_get_buf(vi, rq, xdp_prog, ctx, &frame_sz, &num_buf, &page, offset, &len, hdr); if (unlikely(!data)) goto err_xdp; err = virtnet_build_xdp_buff_mrg(dev, vi, rq, &xdp, data, len, frame_sz, &num_buf, &xdp_frags_truesz, stats); if (unlikely(err)) goto err_xdp; act = virtnet_xdp_handler(xdp_prog, &xdp, dev, xdp_xmit, stats); switch (act) { case XDP_PASS: head_skb = build_skb_from_xdp_buff(dev, vi, &xdp, xdp_frags_truesz); if (unlikely(!head_skb)) break; return head_skb; case XDP_TX: case XDP_REDIRECT: return NULL; default: break; } put_xdp_frags(&xdp); err_xdp: put_page(page); mergeable_buf_free(rq, num_buf, dev, stats); u64_stats_inc(&stats->xdp_drops); u64_stats_inc(&stats->drops); return NULL; } static struct sk_buff *virtnet_skb_append_frag(struct sk_buff *head_skb, struct sk_buff *curr_skb, struct page *page, void *buf, int len, int truesize) { int num_skb_frags; int offset; num_skb_frags = skb_shinfo(curr_skb)->nr_frags; if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) { struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC); if (unlikely(!nskb)) return NULL; if (curr_skb == head_skb) skb_shinfo(curr_skb)->frag_list = nskb; else curr_skb->next = nskb; curr_skb = nskb; head_skb->truesize += nskb->truesize; num_skb_frags = 0; } if (curr_skb != head_skb) { head_skb->data_len += len; head_skb->len += len; head_skb->truesize += truesize; } offset = buf - page_address(page); if (skb_can_coalesce(curr_skb, num_skb_frags, page, offset)) { put_page(page); skb_coalesce_rx_frag(curr_skb, num_skb_frags - 1, len, truesize); } else { skb_add_rx_frag(curr_skb, num_skb_frags, page, offset, len, truesize); } return curr_skb; } static struct sk_buff *receive_mergeable(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); struct page *page = virt_to_head_page(buf); int offset = buf - page_address(page); struct sk_buff *head_skb, *curr_skb; unsigned int truesize = mergeable_ctx_to_truesize(ctx); unsigned int headroom = mergeable_ctx_to_headroom(ctx); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); head_skb = NULL; u64_stats_add(&stats->bytes, len - vi->hdr_len); if (unlikely(len > truesize - room)) { pr_debug("%s: rx error: len %u exceeds truesize %lu\n", dev->name, len, (unsigned long)(truesize - room)); DEV_STATS_INC(dev, rx_length_errors); goto err_skb; } if (unlikely(vi->xdp_enabled)) { struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { head_skb = receive_mergeable_xdp(dev, vi, rq, xdp_prog, buf, ctx, len, xdp_xmit, stats); rcu_read_unlock(); return head_skb; } rcu_read_unlock(); } head_skb = page_to_skb(vi, rq, page, offset, len, truesize, headroom); curr_skb = head_skb; if (unlikely(!curr_skb)) goto err_skb; while (--num_buf) { buf = virtnet_rq_get_buf(rq, &len, &ctx); if (unlikely(!buf)) { pr_debug("%s: rx error: %d buffers out of %d missing\n", dev->name, num_buf, virtio16_to_cpu(vi->vdev, hdr->num_buffers)); DEV_STATS_INC(dev, rx_length_errors); goto err_buf; } u64_stats_add(&stats->bytes, len); page = virt_to_head_page(buf); truesize = mergeable_ctx_to_truesize(ctx); headroom = mergeable_ctx_to_headroom(ctx); tailroom = headroom ? sizeof(struct skb_shared_info) : 0; room = SKB_DATA_ALIGN(headroom + tailroom); if (unlikely(len > truesize - room)) { pr_debug("%s: rx error: len %u exceeds truesize %lu\n", dev->name, len, (unsigned long)(truesize - room)); DEV_STATS_INC(dev, rx_length_errors); goto err_skb; } curr_skb = virtnet_skb_append_frag(head_skb, curr_skb, page, buf, len, truesize); if (!curr_skb) goto err_skb; } ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len); return head_skb; err_skb: put_page(page); mergeable_buf_free(rq, num_buf, dev, stats); err_buf: u64_stats_inc(&stats->drops); dev_kfree_skb(head_skb); return NULL; } static void virtio_skb_set_hash(const struct virtio_net_hdr_v1_hash *hdr_hash, struct sk_buff *skb) { enum pkt_hash_types rss_hash_type; if (!hdr_hash || !skb) return; switch (__le16_to_cpu(hdr_hash->hash_report)) { case VIRTIO_NET_HASH_REPORT_TCPv4: case VIRTIO_NET_HASH_REPORT_UDPv4: case VIRTIO_NET_HASH_REPORT_TCPv6: case VIRTIO_NET_HASH_REPORT_UDPv6: case VIRTIO_NET_HASH_REPORT_TCPv6_EX: case VIRTIO_NET_HASH_REPORT_UDPv6_EX: rss_hash_type = PKT_HASH_TYPE_L4; break; case VIRTIO_NET_HASH_REPORT_IPv4: case VIRTIO_NET_HASH_REPORT_IPv6: case VIRTIO_NET_HASH_REPORT_IPv6_EX: rss_hash_type = PKT_HASH_TYPE_L3; break; case VIRTIO_NET_HASH_REPORT_NONE: default: rss_hash_type = PKT_HASH_TYPE_NONE; } skb_set_hash(skb, __le32_to_cpu(hdr_hash->hash_value), rss_hash_type); } static void virtnet_receive_done(struct virtnet_info *vi, struct receive_queue *rq, struct sk_buff *skb, u8 flags) { struct virtio_net_common_hdr *hdr; struct net_device *dev = vi->dev; hdr = skb_vnet_common_hdr(skb); if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) virtio_skb_set_hash(&hdr->hash_v1_hdr, skb); if (flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; if (virtio_net_hdr_to_skb(skb, &hdr->hdr, virtio_is_little_endian(vi->vdev))) { net_warn_ratelimited("%s: bad gso: type: %u, size: %u\n", dev->name, hdr->hdr.gso_type, hdr->hdr.gso_size); goto frame_err; } skb_record_rx_queue(skb, vq2rxq(rq->vq)); skb->protocol = eth_type_trans(skb, dev); pr_debug("Receiving skb proto 0x%04x len %i type %i\n", ntohs(skb->protocol), skb->len, skb->pkt_type); napi_gro_receive(&rq->napi, skb); return; frame_err: DEV_STATS_INC(dev, rx_frame_errors); dev_kfree_skb(skb); } static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, void *buf, unsigned int len, void **ctx, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { struct net_device *dev = vi->dev; struct sk_buff *skb; u8 flags; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); DEV_STATS_INC(dev, rx_length_errors); virtnet_rq_free_buf(vi, rq, buf); return; } /* 1. Save the flags early, as the XDP program might overwrite them. * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID * stay valid after XDP processing. * 2. XDP doesn't work with partially checksummed packets (refer to * virtnet_xdp_set()), so packets marked as * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. */ flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; if (vi->mergeable_rx_bufs) skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); else if (vi->big_packets) skb = receive_big(dev, vi, rq, buf, len, stats); else skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); if (unlikely(!skb)) return; virtnet_receive_done(vi, rq, skb, flags); } /* Unlike mergeable buffers, all buffers are allocated to the * same size, except for the headroom. For this reason we do * not need to use mergeable_len_to_ctx here - it is enough * to store the headroom as the context ignoring the truesize. */ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { char *buf; unsigned int xdp_headroom = virtnet_get_headroom(vi); void *ctx = (void *)(unsigned long)xdp_headroom; int len = vi->hdr_len + VIRTNET_RX_PAD + GOOD_PACKET_LEN + xdp_headroom; int err; len = SKB_DATA_ALIGN(len) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); if (unlikely(!skb_page_frag_refill(len, &rq->alloc_frag, gfp))) return -ENOMEM; buf = virtnet_rq_alloc(rq, len, gfp); if (unlikely(!buf)) return -ENOMEM; buf += VIRTNET_RX_PAD + xdp_headroom; virtnet_rq_init_one_sg(rq, buf, vi->hdr_len + GOOD_PACKET_LEN); err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) { virtnet_rq_unmap(rq, buf, 0); put_page(virt_to_head_page(buf)); } return err; } static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { struct page *first, *list = NULL; char *p; int i, err, offset; sg_init_table(rq->sg, vi->big_packets_num_skbfrags + 2); /* page in rq->sg[vi->big_packets_num_skbfrags + 1] is list tail */ for (i = vi->big_packets_num_skbfrags + 1; i > 1; --i) { first = get_a_page(rq, gfp); if (!first) { if (list) give_pages(rq, list); return -ENOMEM; } sg_set_buf(&rq->sg[i], page_address(first), PAGE_SIZE); /* chain new page in list head to match sg */ first->private = (unsigned long)list; list = first; } first = get_a_page(rq, gfp); if (!first) { give_pages(rq, list); return -ENOMEM; } p = page_address(first); /* rq->sg[0], rq->sg[1] share the same page */ /* a separated rq->sg[0] for header - required in case !any_header_sg */ sg_set_buf(&rq->sg[0], p, vi->hdr_len); /* rq->sg[1] for data packet, from offset */ offset = sizeof(struct padded_vnet_hdr); sg_set_buf(&rq->sg[1], p + offset, PAGE_SIZE - offset); /* chain first in list head */ first->private = (unsigned long)list; err = virtqueue_add_inbuf(rq->vq, rq->sg, vi->big_packets_num_skbfrags + 2, first, gfp); if (err < 0) give_pages(rq, first); return err; } static unsigned int get_mergeable_buf_len(struct receive_queue *rq, struct ewma_pkt_len *avg_pkt_len, unsigned int room) { struct virtnet_info *vi = rq->vq->vdev->priv; const size_t hdr_len = vi->hdr_len; unsigned int len; if (room) return PAGE_SIZE - room; len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len), rq->min_buf_len, PAGE_SIZE - hdr_len); return ALIGN(len, L1_CACHE_BYTES); } static int add_recvbuf_mergeable(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { struct page_frag *alloc_frag = &rq->alloc_frag; unsigned int headroom = virtnet_get_headroom(vi); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; unsigned int room = SKB_DATA_ALIGN(headroom + tailroom); unsigned int len, hole; void *ctx; char *buf; int err; /* Extra tailroom is needed to satisfy XDP's assumption. This * means rx frags coalescing won't work, but consider we've * disabled GSO for XDP, it won't be a big issue. */ len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room); if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp))) return -ENOMEM; if (!alloc_frag->offset && len + room + sizeof(struct virtnet_rq_dma) > alloc_frag->size) len -= sizeof(struct virtnet_rq_dma); buf = virtnet_rq_alloc(rq, len + room, gfp); if (unlikely(!buf)) return -ENOMEM; buf += headroom; /* advance address leaving hole at front of pkt */ hole = alloc_frag->size - alloc_frag->offset; if (hole < len + room) { /* To avoid internal fragmentation, if there is very likely not * enough space for another buffer, add the remaining space to * the current buffer. * XDP core assumes that frame_size of xdp_buff and the length * of the frag are PAGE_SIZE, so we disable the hole mechanism. */ if (!headroom) len += hole; alloc_frag->offset += hole; } virtnet_rq_init_one_sg(rq, buf, len); ctx = mergeable_len_to_ctx(len + room, headroom); err = virtqueue_add_inbuf_premapped(rq->vq, rq->sg, 1, buf, ctx, gfp); if (err < 0) { virtnet_rq_unmap(rq, buf, 0); put_page(virt_to_head_page(buf)); } return err; } /* * Returns false if we couldn't fill entirely (OOM). * * Normally run in the receive path, but can also be run from ndo_open * before we're receiving packets, or from refill_work which is * careful to disable receiving (using napi_disable). */ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, gfp_t gfp) { int err; if (rq->xsk_pool) { err = virtnet_add_recvbuf_xsk(vi, rq, rq->xsk_pool, gfp); goto kick; } do { if (vi->mergeable_rx_bufs) err = add_recvbuf_mergeable(vi, rq, gfp); else if (vi->big_packets) err = add_recvbuf_big(vi, rq, gfp); else err = add_recvbuf_small(vi, rq, gfp); if (err) break; } while (rq->vq->num_free); kick: if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { unsigned long flags; flags = u64_stats_update_begin_irqsave(&rq->stats.syncp); u64_stats_inc(&rq->stats.kicks); u64_stats_update_end_irqrestore(&rq->stats.syncp, flags); } return err != -ENOMEM; } static void skb_recv_done(struct virtqueue *rvq) { struct virtnet_info *vi = rvq->vdev->priv; struct receive_queue *rq = &vi->rq[vq2rxq(rvq)]; rq->calls++; virtqueue_napi_schedule(&rq->napi, rvq); } static void virtnet_napi_do_enable(struct virtqueue *vq, struct napi_struct *napi) { napi_enable(napi); /* If all buffers were filled by other side before we napi_enabled, we * won't get another interrupt, so process any outstanding packets now. * Call local_bh_enable after to trigger softIRQ processing. */ local_bh_disable(); virtqueue_napi_schedule(napi, vq); local_bh_enable(); } static void virtnet_napi_enable(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; int qidx = vq2rxq(rq->vq); virtnet_napi_do_enable(rq->vq, &rq->napi); netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, &rq->napi); } static void virtnet_napi_tx_enable(struct send_queue *sq) { struct virtnet_info *vi = sq->vq->vdev->priv; struct napi_struct *napi = &sq->napi; int qidx = vq2txq(sq->vq); if (!napi->weight) return; /* Tx napi touches cachelines on the cpu handling tx interrupts. Only * enable the feature if this is likely affine with the transmit path. */ if (!vi->affinity_hint_set) { napi->weight = 0; return; } virtnet_napi_do_enable(sq->vq, napi); netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, napi); } static void virtnet_napi_tx_disable(struct send_queue *sq) { struct virtnet_info *vi = sq->vq->vdev->priv; struct napi_struct *napi = &sq->napi; int qidx = vq2txq(sq->vq); if (napi->weight) { netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, NULL); napi_disable(napi); } } static void virtnet_napi_disable(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; struct napi_struct *napi = &rq->napi; int qidx = vq2rxq(rq->vq); netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, NULL); napi_disable(napi); } static void refill_work(struct work_struct *work) { struct virtnet_info *vi = container_of(work, struct virtnet_info, refill.work); bool still_empty; int i; for (i = 0; i < vi->curr_queue_pairs; i++) { struct receive_queue *rq = &vi->rq[i]; /* * When queue API support is added in the future and the call * below becomes napi_disable_locked, this driver will need to * be refactored. * * One possible solution would be to: * - cancel refill_work with cancel_delayed_work (note: * non-sync) * - cancel refill_work with cancel_delayed_work_sync in * virtnet_remove after the netdev is unregistered * - wrap all of the work in a lock (perhaps the netdev * instance lock) * - check netif_running() and return early to avoid a race */ napi_disable(&rq->napi); still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); virtnet_napi_do_enable(rq->vq, &rq->napi); /* In theory, this can happen: if we don't get any buffers in * we will *never* try to fill again. */ if (still_empty) schedule_delayed_work(&vi->refill, HZ/2); } } static int virtnet_receive_xsk_bufs(struct virtnet_info *vi, struct receive_queue *rq, int budget, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int len; int packets = 0; void *buf; while (packets < budget) { buf = virtqueue_get_buf(rq->vq, &len); if (!buf) break; virtnet_receive_xsk_buf(vi, rq, buf, len, xdp_xmit, stats); packets++; } return packets; } static int virtnet_receive_packets(struct virtnet_info *vi, struct receive_queue *rq, int budget, unsigned int *xdp_xmit, struct virtnet_rq_stats *stats) { unsigned int len; int packets = 0; void *buf; if (!vi->big_packets || vi->mergeable_rx_bufs) { void *ctx; while (packets < budget && (buf = virtnet_rq_get_buf(rq, &len, &ctx))) { receive_buf(vi, rq, buf, len, ctx, xdp_xmit, stats); packets++; } } else { while (packets < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { receive_buf(vi, rq, buf, len, NULL, xdp_xmit, stats); packets++; } } return packets; } static int virtnet_receive(struct receive_queue *rq, int budget, unsigned int *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; struct virtnet_rq_stats stats = {}; int i, packets; if (rq->xsk_pool) packets = virtnet_receive_xsk_bufs(vi, rq, budget, xdp_xmit, &stats); else packets = virtnet_receive_packets(vi, rq, budget, xdp_xmit, &stats); if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { if (!try_fill_recv(vi, rq, GFP_ATOMIC)) { spin_lock(&vi->refill_lock); if (vi->refill_enabled) schedule_delayed_work(&vi->refill, 0); spin_unlock(&vi->refill_lock); } } u64_stats_set(&stats.packets, packets); u64_stats_update_begin(&rq->stats.syncp); for (i = 0; i < ARRAY_SIZE(virtnet_rq_stats_desc); i++) { size_t offset = virtnet_rq_stats_desc[i].offset; u64_stats_t *item, *src; item = (u64_stats_t *)((u8 *)&rq->stats + offset); src = (u64_stats_t *)((u8 *)&stats + offset); u64_stats_add(item, u64_stats_read(src)); } u64_stats_add(&rq->stats.packets, u64_stats_read(&stats.packets)); u64_stats_add(&rq->stats.bytes, u64_stats_read(&stats.bytes)); u64_stats_update_end(&rq->stats.syncp); return packets; } static void virtnet_poll_cleantx(struct receive_queue *rq, int budget) { struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int index = vq2rxq(rq->vq); struct send_queue *sq = &vi->sq[index]; struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) return; if (__netif_tx_trylock(txq)) { if (sq->reset) { __netif_tx_unlock(txq); return; } do { virtqueue_disable_cb(sq->vq); free_old_xmit(sq, txq, !!budget); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { if (netif_tx_queue_stopped(txq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); u64_stats_update_end(&sq->stats.syncp); } netif_tx_wake_queue(txq); } __netif_tx_unlock(txq); } } static void virtnet_rx_dim_update(struct virtnet_info *vi, struct receive_queue *rq) { struct dim_sample cur_sample = {}; if (!rq->packets_in_napi) return; /* Don't need protection when fetching stats, since fetcher and * updater of the stats are in same context */ dim_update_sample(rq->calls, u64_stats_read(&rq->stats.packets), u64_stats_read(&rq->stats.bytes), &cur_sample); net_dim(&rq->dim, &cur_sample); rq->packets_in_napi = 0; } static int virtnet_poll(struct napi_struct *napi, int budget) { struct receive_queue *rq = container_of(napi, struct receive_queue, napi); struct virtnet_info *vi = rq->vq->vdev->priv; struct send_queue *sq; unsigned int received; unsigned int xdp_xmit = 0; bool napi_complete; virtnet_poll_cleantx(rq, budget); received = virtnet_receive(rq, budget, &xdp_xmit); rq->packets_in_napi += received; if (xdp_xmit & VIRTIO_XDP_REDIR) xdp_do_flush(); /* Out of packets? */ if (received < budget) { napi_complete = virtqueue_napi_complete(napi, rq->vq, received); /* Intentionally not taking dim_lock here. This may result in a * spurious net_dim call. But if that happens virtnet_rx_dim_work * will not act on the scheduled work. */ if (napi_complete && rq->dim_enabled) virtnet_rx_dim_update(vi, rq); } if (xdp_xmit & VIRTIO_XDP_TX) { sq = virtnet_xdp_get_sq(vi); if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.kicks); u64_stats_update_end(&sq->stats.syncp); } virtnet_xdp_put_sq(vi, sq); } return received; } static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) { virtnet_napi_tx_disable(&vi->sq[qp_index]); virtnet_napi_disable(&vi->rq[qp_index]); xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); } static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) { struct net_device *dev = vi->dev; int err; err = xdp_rxq_info_reg(&vi->rq[qp_index].xdp_rxq, dev, qp_index, vi->rq[qp_index].napi.napi_id); if (err < 0) return err; err = xdp_rxq_info_reg_mem_model(&vi->rq[qp_index].xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) goto err_xdp_reg_mem_model; virtnet_napi_enable(&vi->rq[qp_index]); virtnet_napi_tx_enable(&vi->sq[qp_index]); return 0; err_xdp_reg_mem_model: xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); return err; } static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim) { if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return; net_dim_work_cancel(dim); } static void virtnet_update_settings(struct virtnet_info *vi) { u32 speed; u8 duplex; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) return; virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); if (ethtool_validate_speed(speed)) vi->speed = speed; virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); if (ethtool_validate_duplex(duplex)) vi->duplex = duplex; } static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); int i, err; enable_delayed_refill(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) /* Make sure we have some buffers: if oom use wq. */ if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); err = virtnet_enable_queue_pair(vi, i); if (err < 0) goto err_enable_qp; } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { if (vi->status & VIRTIO_NET_S_LINK_UP) netif_carrier_on(vi->dev); virtio_config_driver_enable(vi->vdev); } else { vi->status = VIRTIO_NET_S_LINK_UP; netif_carrier_on(dev); } return 0; err_enable_qp: disable_delayed_refill(vi); cancel_delayed_work_sync(&vi->refill); for (i--; i >= 0; i--) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); } return err; } static int virtnet_poll_tx(struct napi_struct *napi, int budget) { struct send_queue *sq = container_of(napi, struct send_queue, napi); struct virtnet_info *vi = sq->vq->vdev->priv; unsigned int index = vq2txq(sq->vq); struct netdev_queue *txq; int opaque, xsk_done = 0; bool done; if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { /* We don't need to enable cb for XDP */ napi_complete_done(napi, 0); return 0; } txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); virtqueue_disable_cb(sq->vq); if (sq->xsk_pool) xsk_done = virtnet_xsk_xmit(sq, sq->xsk_pool, budget); else free_old_xmit(sq, txq, !!budget); if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) { if (netif_tx_queue_stopped(txq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.wake); u64_stats_update_end(&sq->stats.syncp); } netif_tx_wake_queue(txq); } if (xsk_done >= budget) { __netif_tx_unlock(txq); return budget; } opaque = virtqueue_enable_cb_prepare(sq->vq); done = napi_complete_done(napi, 0); if (!done) virtqueue_disable_cb(sq->vq); __netif_tx_unlock(txq); if (done) { if (unlikely(virtqueue_poll(sq->vq, opaque))) { if (napi_schedule_prep(napi)) { __netif_tx_lock(txq, raw_smp_processor_id()); virtqueue_disable_cb(sq->vq); __netif_tx_unlock(txq); __napi_schedule(napi); } } } return 0; } static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) { struct virtio_net_hdr_mrg_rxbuf *hdr; const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; struct virtnet_info *vi = sq->vq->vdev->priv; int num_sg; unsigned hdr_len = vi->hdr_len; bool can_push; pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); can_push = vi->any_header_sg && !((unsigned long)skb->data & (__alignof__(*hdr) - 1)) && !skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len; /* Even if we can, don't push here yet as this would skew * csum_start offset below. */ if (can_push) hdr = (struct virtio_net_hdr_mrg_rxbuf *)(skb->data - hdr_len); else hdr = &skb_vnet_common_hdr(skb)->mrg_hdr; if (virtio_net_hdr_from_skb(skb, &hdr->hdr, virtio_is_little_endian(vi->vdev), false, 0)) return -EPROTO; if (vi->mergeable_rx_bufs) hdr->num_buffers = 0; sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2)); if (can_push) { __skb_push(skb, hdr_len); num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len); if (unlikely(num_sg < 0)) return num_sg; /* Pull header back to avoid skew in tx bytes calculations. */ __skb_pull(skb, hdr_len); } else { sg_set_buf(sq->sg, hdr, hdr_len); num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len); if (unlikely(num_sg < 0)) return num_sg; num_sg++; } return virtnet_add_outbuf(sq, num_sg, skb, orphan ? VIRTNET_XMIT_TYPE_SKB_ORPHAN : VIRTNET_XMIT_TYPE_SKB); } static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); int qnum = skb_get_queue_mapping(skb); struct send_queue *sq = &vi->sq[qnum]; int err; struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); bool xmit_more = netdev_xmit_more(); bool use_napi = sq->napi.weight; bool kick; if (!use_napi) free_old_xmit(sq, txq, false); else virtqueue_disable_cb(sq->vq); /* timestamp packet in software */ skb_tx_timestamp(skb); /* Try to transmit */ err = xmit_skb(sq, skb, !use_napi); /* This should not happen! */ if (unlikely(err)) { DEV_STATS_INC(dev, tx_fifo_errors); if (net_ratelimit()) dev_warn(&dev->dev, "Unexpected TXQ (%d) queue failure: %d\n", qnum, err); DEV_STATS_INC(dev, tx_dropped); dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Don't wait up for transmitted skbs to be freed. */ if (!use_napi) { skb_orphan(skb); nf_reset_ct(skb); } if (use_napi) tx_may_stop(vi, dev, sq); else check_sq_full_and_disable(vi, dev,sq); kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) : !xmit_more || netif_xmit_stopped(txq); if (kick) { if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.kicks); u64_stats_update_end(&sq->stats.syncp); } } if (use_napi && kick && unlikely(!virtqueue_enable_cb_delayed(sq->vq))) virtqueue_napi_schedule(&sq->napi, sq->vq); return NETDEV_TX_OK; } static void __virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) { bool running = netif_running(vi->dev); if (running) { virtnet_napi_disable(rq); virtnet_cancel_dim(vi, &rq->dim); } } static void virtnet_rx_pause_all(struct virtnet_info *vi) { int i; /* * Make sure refill_work does not run concurrently to * avoid napi_disable race which leads to deadlock. */ disable_delayed_refill(vi); cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) __virtnet_rx_pause(vi, &vi->rq[i]); } static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) { /* * Make sure refill_work does not run concurrently to * avoid napi_disable race which leads to deadlock. */ disable_delayed_refill(vi); cancel_delayed_work_sync(&vi->refill); __virtnet_rx_pause(vi, rq); } static void __virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq, bool refill) { bool running = netif_running(vi->dev); bool schedule_refill = false; if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) schedule_refill = true; if (running) virtnet_napi_enable(rq); if (schedule_refill) schedule_delayed_work(&vi->refill, 0); } static void virtnet_rx_resume_all(struct virtnet_info *vi) { int i; enable_delayed_refill(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) __virtnet_rx_resume(vi, &vi->rq[i], true); else __virtnet_rx_resume(vi, &vi->rq[i], false); } } static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) { enable_delayed_refill(vi); __virtnet_rx_resume(vi, rq, true); } static int virtnet_rx_resize(struct virtnet_info *vi, struct receive_queue *rq, u32 ring_num) { int err, qindex; qindex = rq - vi->rq; virtnet_rx_pause(vi, rq); err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf, NULL); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); virtnet_rx_resume(vi, rq); return err; } static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq) { bool running = netif_running(vi->dev); struct netdev_queue *txq; int qindex; qindex = sq - vi->sq; if (running) virtnet_napi_tx_disable(sq); txq = netdev_get_tx_queue(vi->dev, qindex); /* 1. wait all ximt complete * 2. fix the race of netif_stop_subqueue() vs netif_start_subqueue() */ __netif_tx_lock_bh(txq); /* Prevent rx poll from accessing sq. */ sq->reset = true; /* Prevent the upper layer from trying to send packets. */ netif_stop_subqueue(vi->dev, qindex); __netif_tx_unlock_bh(txq); } static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq) { bool running = netif_running(vi->dev); struct netdev_queue *txq; int qindex; qindex = sq - vi->sq; txq = netdev_get_tx_queue(vi->dev, qindex); __netif_tx_lock_bh(txq); sq->reset = false; netif_tx_wake_queue(txq); __netif_tx_unlock_bh(txq); if (running) virtnet_napi_tx_enable(sq); } static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, u32 ring_num) { int qindex, err; qindex = sq - vi->sq; virtnet_tx_pause(vi, sq); err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf, virtnet_sq_free_unused_buf_done); if (err) netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err); virtnet_tx_resume(vi, sq); return err; } /* * Send command via the control virtqueue and check status. Commands * supported by the hypervisor, as indicated by feature bits, should * never fail unless improperly formatted. */ static bool virtnet_send_command_reply(struct virtnet_info *vi, u8 class, u8 cmd, struct scatterlist *out, struct scatterlist *in) { struct scatterlist *sgs[5], hdr, stat; u32 out_num = 0, tmp, in_num = 0; bool ok; int ret; /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); mutex_lock(&vi->cvq_lock); vi->ctrl->status = ~0; vi->ctrl->hdr.class = class; vi->ctrl->hdr.cmd = cmd; /* Add header */ sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr)); sgs[out_num++] = &hdr; if (out) sgs[out_num++] = out; /* Add return status. */ sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status)); sgs[out_num + in_num++] = &stat; if (in) sgs[out_num + in_num++] = in; BUG_ON(out_num + in_num > ARRAY_SIZE(sgs)); ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, in_num, vi, GFP_ATOMIC); if (ret < 0) { dev_warn(&vi->vdev->dev, "Failed to add sgs for command vq: %d\n.", ret); mutex_unlock(&vi->cvq_lock); return false; } if (unlikely(!virtqueue_kick(vi->cvq))) goto unlock; /* Spin for a response, the kick causes an ioport write, trapping * into the hypervisor, so the request should be handled immediately. */ while (!virtqueue_get_buf(vi->cvq, &tmp) && !virtqueue_is_broken(vi->cvq)) { cond_resched(); cpu_relax(); } unlock: ok = vi->ctrl->status == VIRTIO_NET_OK; mutex_unlock(&vi->cvq_lock); return ok; } static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, struct scatterlist *out) { return virtnet_send_command_reply(vi, class, cmd, out, NULL); } static int virtnet_set_mac_address(struct net_device *dev, void *p) { struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; int ret; struct sockaddr *addr; struct scatterlist sg; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY)) return -EOPNOTSUPP; addr = kmemdup(p, sizeof(*addr), GFP_KERNEL); if (!addr) return -ENOMEM; ret = eth_prepare_mac_addr_change(dev, addr); if (ret) goto out; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { sg_init_one(&sg, addr->sa_data, dev->addr_len); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { dev_warn(&vdev->dev, "Failed to set mac address by vq command.\n"); ret = -EINVAL; goto out; } } else if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && !virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) { unsigned int i; /* Naturally, this has an atomicity problem. */ for (i = 0; i < dev->addr_len; i++) virtio_cwrite8(vdev, offsetof(struct virtio_net_config, mac) + i, addr->sa_data[i]); } eth_commit_mac_addr_change(dev, p); ret = 0; out: kfree(addr); return ret; } static void virtnet_stats(struct net_device *dev, struct rtnl_link_stats64 *tot) { struct virtnet_info *vi = netdev_priv(dev); unsigned int start; int i; for (i = 0; i < vi->max_queue_pairs; i++) { u64 tpackets, tbytes, terrors, rpackets, rbytes, rdrops; struct receive_queue *rq = &vi->rq[i]; struct send_queue *sq = &vi->sq[i]; do { start = u64_stats_fetch_begin(&sq->stats.syncp); tpackets = u64_stats_read(&sq->stats.packets); tbytes = u64_stats_read(&sq->stats.bytes); terrors = u64_stats_read(&sq->stats.tx_timeouts); } while (u64_stats_fetch_retry(&sq->stats.syncp, start)); do { start = u64_stats_fetch_begin(&rq->stats.syncp); rpackets = u64_stats_read(&rq->stats.packets); rbytes = u64_stats_read(&rq->stats.bytes); rdrops = u64_stats_read(&rq->stats.drops); } while (u64_stats_fetch_retry(&rq->stats.syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; tot->rx_bytes += rbytes; tot->tx_bytes += tbytes; tot->rx_dropped += rdrops; tot->tx_errors += terrors; } tot->tx_dropped = DEV_STATS_READ(dev, tx_dropped); tot->tx_fifo_errors = DEV_STATS_READ(dev, tx_fifo_errors); tot->rx_length_errors = DEV_STATS_READ(dev, rx_length_errors); tot->rx_frame_errors = DEV_STATS_READ(dev, rx_frame_errors); } static void virtnet_ack_link_announce(struct virtnet_info *vi) { if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_ANNOUNCE, VIRTIO_NET_CTRL_ANNOUNCE_ACK, NULL)) dev_warn(&vi->dev->dev, "Failed to ack link announce.\n"); } static bool virtnet_commit_rss_command(struct virtnet_info *vi); static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pairs) { u32 indir_val = 0; int i = 0; for (; i < vi->rss_indir_table_size; ++i) { indir_val = ethtool_rxfh_indir_default(i, queue_pairs); vi->rss_hdr->indirection_table[i] = cpu_to_le16(indir_val); } vi->rss_trailer.max_tx_vq = cpu_to_le16(queue_pairs); } static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) { struct virtio_net_ctrl_mq *mq __free(kfree) = NULL; struct virtio_net_rss_config_hdr *old_rss_hdr; struct virtio_net_rss_config_trailer old_rss_trailer; struct net_device *dev = vi->dev; struct scatterlist sg; if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; /* Firstly check if we need update rss. Do updating if both (1) rss enabled and * (2) no user configuration. * * During rss command processing, device updates queue_pairs using rss.max_tx_vq. That is, * the device updates queue_pairs together with rss, so we can skip the sperate queue_pairs * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly. */ if (vi->has_rss && !netif_is_rxfh_configured(dev)) { old_rss_hdr = vi->rss_hdr; old_rss_trailer = vi->rss_trailer; vi->rss_hdr = devm_kzalloc(&dev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL); if (!vi->rss_hdr) { vi->rss_hdr = old_rss_hdr; return -ENOMEM; } *vi->rss_hdr = *old_rss_hdr; virtnet_rss_update_by_qpairs(vi, queue_pairs); if (!virtnet_commit_rss_command(vi)) { /* restore ctrl_rss if commit_rss_command failed */ devm_kfree(&dev->dev, vi->rss_hdr); vi->rss_hdr = old_rss_hdr; vi->rss_trailer = old_rss_trailer; dev_warn(&dev->dev, "Fail to set num of queue pairs to %d, because committing RSS failed\n", queue_pairs); return -EINVAL; } devm_kfree(&dev->dev, old_rss_hdr); goto succ; } mq = kzalloc(sizeof(*mq), GFP_KERNEL); if (!mq) return -ENOMEM; mq->virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); sg_init_one(&sg, mq, sizeof(*mq)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) { dev_warn(&dev->dev, "Fail to set num of queue pairs to %d\n", queue_pairs); return -EINVAL; } succ: vi->curr_queue_pairs = queue_pairs; /* virtnet_open() will refill when device is going to up. */ spin_lock_bh(&vi->refill_lock); if (dev->flags & IFF_UP && vi->refill_enabled) schedule_delayed_work(&vi->refill, 0); spin_unlock_bh(&vi->refill_lock); return 0; } static int virtnet_close(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); int i; /* Make sure NAPI doesn't schedule refill work */ disable_delayed_refill(vi); /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); /* Prevent the config change callback from changing carrier * after close */ virtio_config_driver_disable(vi->vdev); /* Stop getting status/speed updates: we don't care until next * open */ cancel_work_sync(&vi->config_work); for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); } netif_carrier_off(dev); return 0; } static void virtnet_rx_mode_work(struct work_struct *work) { struct virtnet_info *vi = container_of(work, struct virtnet_info, rx_mode_work); u8 *promisc_allmulti __free(kfree) = NULL; struct net_device *dev = vi->dev; struct scatterlist sg[2]; struct virtio_net_ctrl_mac *mac_data; struct netdev_hw_addr *ha; int uc_count; int mc_count; void *buf; int i; /* We can't dynamically set ndo_set_rx_mode, so return gracefully */ if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; promisc_allmulti = kzalloc(sizeof(*promisc_allmulti), GFP_KERNEL); if (!promisc_allmulti) { dev_warn(&dev->dev, "Failed to set RX mode, no memory.\n"); return; } rtnl_lock(); *promisc_allmulti = !!(dev->flags & IFF_PROMISC); sg_init_one(sg, promisc_allmulti, sizeof(*promisc_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_PROMISC, sg)) dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", *promisc_allmulti ? "en" : "dis"); *promisc_allmulti = !!(dev->flags & IFF_ALLMULTI); sg_init_one(sg, promisc_allmulti, sizeof(*promisc_allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_ALLMULTI, sg)) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", *promisc_allmulti ? "en" : "dis"); netif_addr_lock_bh(dev); uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); /* MAC filter - use one buffer for both lists */ buf = kzalloc(((uc_count + mc_count) * ETH_ALEN) + (2 * sizeof(mac_data->entries)), GFP_ATOMIC); mac_data = buf; if (!buf) { netif_addr_unlock_bh(dev); rtnl_unlock(); return; } sg_init_table(sg, 2); /* Store the unicast list and count in the front of the buffer */ mac_data->entries = cpu_to_virtio32(vi->vdev, uc_count); i = 0; netdev_for_each_uc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); sg_set_buf(&sg[0], mac_data, sizeof(mac_data->entries) + (uc_count * ETH_ALEN)); /* multicast list and count fill the end */ mac_data = (void *)&mac_data->macs[uc_count][0]; mac_data->entries = cpu_to_virtio32(vi->vdev, mc_count); i = 0; netdev_for_each_mc_addr(ha, dev) memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); netif_addr_unlock_bh(dev); sg_set_buf(&sg[1], mac_data, sizeof(mac_data->entries) + (mc_count * ETH_ALEN)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, VIRTIO_NET_CTRL_MAC_TABLE_SET, sg)) dev_warn(&dev->dev, "Failed to set MAC filter table.\n"); rtnl_unlock(); kfree(buf); } static void virtnet_set_rx_mode(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); if (vi->rx_mode_work_enabled) schedule_work(&vi->rx_mode_work); } static int virtnet_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct virtnet_info *vi = netdev_priv(dev); __virtio16 *_vid __free(kfree) = NULL; struct scatterlist sg; _vid = kzalloc(sizeof(*_vid), GFP_KERNEL); if (!_vid) return -ENOMEM; *_vid = cpu_to_virtio16(vi->vdev, vid); sg_init_one(&sg, _vid, sizeof(*_vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_ADD, &sg)) dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid); return 0; } static int virtnet_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct virtnet_info *vi = netdev_priv(dev); __virtio16 *_vid __free(kfree) = NULL; struct scatterlist sg; _vid = kzalloc(sizeof(*_vid), GFP_KERNEL); if (!_vid) return -ENOMEM; *_vid = cpu_to_virtio16(vi->vdev, vid); sg_init_one(&sg, _vid, sizeof(*_vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_DEL, &sg)) dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid); return 0; } static void virtnet_clean_affinity(struct virtnet_info *vi) { int i; if (vi->affinity_hint_set) { for (i = 0; i < vi->max_queue_pairs; i++) { virtqueue_set_affinity(vi->rq[i].vq, NULL); virtqueue_set_affinity(vi->sq[i].vq, NULL); } vi->affinity_hint_set = false; } } static void virtnet_set_affinity(struct virtnet_info *vi) { cpumask_var_t mask; int stragglers; int group_size; int i, start = 0, cpu; int num_cpu; int stride; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { virtnet_clean_affinity(vi); return; } num_cpu = num_online_cpus(); stride = max_t(int, num_cpu / vi->curr_queue_pairs, 1); stragglers = num_cpu >= vi->curr_queue_pairs ? num_cpu % vi->curr_queue_pairs : 0; for (i = 0; i < vi->curr_queue_pairs; i++) { group_size = stride + (i < stragglers ? 1 : 0); for_each_online_cpu_wrap(cpu, start) { if (!group_size--) { start = cpu; break; } cpumask_set_cpu(cpu, mask); } virtqueue_set_affinity(vi->rq[i].vq, mask); virtqueue_set_affinity(vi->sq[i].vq, mask); __netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, XPS_CPUS); cpumask_clear(mask); } vi->affinity_hint_set = true; free_cpumask_var(mask); } static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node) { struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, node); virtnet_set_affinity(vi); return 0; } static int virtnet_cpu_dead(unsigned int cpu, struct hlist_node *node) { struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, node_dead); virtnet_set_affinity(vi); return 0; } static int virtnet_cpu_down_prep(unsigned int cpu, struct hlist_node *node) { struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info, node); virtnet_clean_affinity(vi); return 0; } static enum cpuhp_state virtionet_online; static int virtnet_cpu_notif_add(struct virtnet_info *vi) { int ret; ret = cpuhp_state_add_instance_nocalls(virtionet_online, &vi->node); if (ret) return ret; ret = cpuhp_state_add_instance_nocalls(CPUHP_VIRT_NET_DEAD, &vi->node_dead); if (!ret) return ret; cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node); return ret; } static void virtnet_cpu_notif_remove(struct virtnet_info *vi) { cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node); cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_NET_DEAD, &vi->node_dead); } static int virtnet_send_ctrl_coal_vq_cmd(struct virtnet_info *vi, u16 vqn, u32 max_usecs, u32 max_packets) { struct virtio_net_ctrl_coal_vq *coal_vq __free(kfree) = NULL; struct scatterlist sgs; coal_vq = kzalloc(sizeof(*coal_vq), GFP_KERNEL); if (!coal_vq) return -ENOMEM; coal_vq->vqn = cpu_to_le16(vqn); coal_vq->coal.max_usecs = cpu_to_le32(max_usecs); coal_vq->coal.max_packets = cpu_to_le32(max_packets); sg_init_one(&sgs, coal_vq, sizeof(*coal_vq)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_VQ_SET, &sgs)) return -EINVAL; return 0; } static int virtnet_send_rx_ctrl_coal_vq_cmd(struct virtnet_info *vi, u16 queue, u32 max_usecs, u32 max_packets) { int err; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return -EOPNOTSUPP; err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue), max_usecs, max_packets); if (err) return err; vi->rq[queue].intr_coal.max_usecs = max_usecs; vi->rq[queue].intr_coal.max_packets = max_packets; return 0; } static int virtnet_send_tx_ctrl_coal_vq_cmd(struct virtnet_info *vi, u16 queue, u32 max_usecs, u32 max_packets) { int err; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return -EOPNOTSUPP; err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue), max_usecs, max_packets); if (err) return err; vi->sq[queue].intr_coal.max_usecs = max_usecs; vi->sq[queue].intr_coal.max_packets = max_packets; return 0; } static void virtnet_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); ring->rx_max_pending = vi->rq[0].vq->num_max; ring->tx_max_pending = vi->sq[0].vq->num_max; ring->rx_pending = virtqueue_get_vring_size(vi->rq[0].vq); ring->tx_pending = virtqueue_get_vring_size(vi->sq[0].vq); } static int virtnet_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); u32 rx_pending, tx_pending; struct receive_queue *rq; struct send_queue *sq; int i, err; if (ring->rx_mini_pending || ring->rx_jumbo_pending) return -EINVAL; rx_pending = virtqueue_get_vring_size(vi->rq[0].vq); tx_pending = virtqueue_get_vring_size(vi->sq[0].vq); if (ring->rx_pending == rx_pending && ring->tx_pending == tx_pending) return 0; if (ring->rx_pending > vi->rq[0].vq->num_max) return -EINVAL; if (ring->tx_pending > vi->sq[0].vq->num_max) return -EINVAL; for (i = 0; i < vi->max_queue_pairs; i++) { rq = vi->rq + i; sq = vi->sq + i; if (ring->tx_pending != tx_pending) { err = virtnet_tx_resize(vi, sq, ring->tx_pending); if (err) return err; /* Upon disabling and re-enabling a transmit virtqueue, the device must * set the coalescing parameters of the virtqueue to those configured * through the VIRTIO_NET_CTRL_NOTF_COAL_TX_SET command, or, if the driver * did not set any TX coalescing parameters, to 0. */ err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, i, vi->intr_coal_tx.max_usecs, vi->intr_coal_tx.max_packets); /* Don't break the tx resize action if the vq coalescing is not * supported. The same is true for rx resize below. */ if (err && err != -EOPNOTSUPP) return err; } if (ring->rx_pending != rx_pending) { err = virtnet_rx_resize(vi, rq, ring->rx_pending); if (err) return err; /* The reason is same as the transmit virtqueue reset */ mutex_lock(&vi->rq[i].dim_lock); err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, i, vi->intr_coal_rx.max_usecs, vi->intr_coal_rx.max_packets); mutex_unlock(&vi->rq[i].dim_lock); if (err && err != -EOPNOTSUPP) return err; } } return 0; } static bool virtnet_commit_rss_command(struct virtnet_info *vi) { struct net_device *dev = vi->dev; struct scatterlist sgs[2]; /* prepare sgs */ sg_init_table(sgs, 2); sg_set_buf(&sgs[0], vi->rss_hdr, virtnet_rss_hdr_size(vi)); sg_set_buf(&sgs[1], &vi->rss_trailer, virtnet_rss_trailer_size(vi)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG : VIRTIO_NET_CTRL_MQ_HASH_CONFIG, sgs)) goto err; return true; err: dev_warn(&dev->dev, "VIRTIONET issue with committing RSS sgs\n"); return false; } static void virtnet_init_default_rss(struct virtnet_info *vi) { vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_supported); vi->rss_hash_types_saved = vi->rss_hash_types_supported; vi->rss_hdr->indirection_table_mask = vi->rss_indir_table_size ? cpu_to_le16(vi->rss_indir_table_size - 1) : 0; vi->rss_hdr->unclassified_queue = 0; virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs); vi->rss_trailer.hash_key_length = vi->rss_key_size; netdev_rss_key_fill(vi->rss_hash_key_data, vi->rss_key_size); } static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info) { info->data = 0; switch (info->flow_type) { case TCP_V4_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv4) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case TCP_V6_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_TCPv6) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case UDP_V4_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv4) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case UDP_V6_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_UDPv6) { info->data = RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3; } else if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) { info->data = RXH_IP_SRC | RXH_IP_DST; } break; case IPV4_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv4) info->data = RXH_IP_SRC | RXH_IP_DST; break; case IPV6_FLOW: if (vi->rss_hash_types_saved & VIRTIO_NET_RSS_HASH_TYPE_IPv6) info->data = RXH_IP_SRC | RXH_IP_DST; break; default: info->data = 0; break; } } static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *info) { u32 new_hashtypes = vi->rss_hash_types_saved; bool is_disable = info->data & RXH_DISCARD; bool is_l4 = info->data == (RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3); /* supports only 'sd', 'sdfn' and 'r' */ if (!((info->data == (RXH_IP_SRC | RXH_IP_DST)) | is_l4 | is_disable)) return false; switch (info->flow_type) { case TCP_V4_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv4 : 0); break; case UDP_V4_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv4 | VIRTIO_NET_RSS_HASH_TYPE_UDPv4); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv4 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv4 : 0); break; case IPV4_FLOW: new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv4; if (!is_disable) new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv4; break; case TCP_V6_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_TCPv6); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_TCPv6 : 0); break; case UDP_V6_FLOW: new_hashtypes &= ~(VIRTIO_NET_RSS_HASH_TYPE_IPv6 | VIRTIO_NET_RSS_HASH_TYPE_UDPv6); if (!is_disable) new_hashtypes |= VIRTIO_NET_RSS_HASH_TYPE_IPv6 | (is_l4 ? VIRTIO_NET_RSS_HASH_TYPE_UDPv6 : 0); break; case IPV6_FLOW: new_hashtypes &= ~VIRTIO_NET_RSS_HASH_TYPE_IPv6; if (!is_disable) new_hashtypes = VIRTIO_NET_RSS_HASH_TYPE_IPv6; break; default: /* unsupported flow */ return false; } /* if unsupported hashtype was set */ if (new_hashtypes != (new_hashtypes & vi->rss_hash_types_supported)) return false; if (new_hashtypes != vi->rss_hash_types_saved) { vi->rss_hash_types_saved = new_hashtypes; vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_saved); if (vi->dev->features & NETIF_F_RXHASH) return virtnet_commit_rss_command(vi); } return true; } static void virtnet_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct virtnet_info *vi = netdev_priv(dev); struct virtio_device *vdev = vi->vdev; strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); strscpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version)); strscpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info)); } /* TODO: Eliminate OOO packets during switching */ static int virtnet_set_channels(struct net_device *dev, struct ethtool_channels *channels) { struct virtnet_info *vi = netdev_priv(dev); u16 queue_pairs = channels->combined_count; int err; /* We don't support separate rx/tx channels. * We don't allow setting 'other' channels. */ if (channels->rx_count || channels->tx_count || channels->other_count) return -EINVAL; if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0) return -EINVAL; /* For now we don't support modifying channels while XDP is loaded * also when XDP is loaded all RX queues have XDP programs so we only * need to check a single RX queue. */ if (vi->rq[0].xdp_prog) return -EINVAL; cpus_read_lock(); err = virtnet_set_queues(vi, queue_pairs); if (err) { cpus_read_unlock(); goto err; } virtnet_set_affinity(vi); cpus_read_unlock(); netif_set_real_num_tx_queues(dev, queue_pairs); netif_set_real_num_rx_queues(dev, queue_pairs); err: return err; } static void virtnet_stats_sprintf(u8 **p, const char *fmt, const char *noq_fmt, int num, int qid, const struct virtnet_stat_desc *desc) { int i; if (qid < 0) { for (i = 0; i < num; ++i) ethtool_sprintf(p, noq_fmt, desc[i].desc); } else { for (i = 0; i < num; ++i) ethtool_sprintf(p, fmt, qid, desc[i].desc); } } /* qid == -1: for rx/tx queue total field */ static void virtnet_get_stats_string(struct virtnet_info *vi, int type, int qid, u8 **data) { const struct virtnet_stat_desc *desc; const char *fmt, *noq_fmt; u8 *p = *data; u32 num; if (type == VIRTNET_Q_TYPE_CQ && qid >= 0) { noq_fmt = "cq_hw_%s"; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_CVQ) { desc = &virtnet_stats_cvq_desc[0]; num = ARRAY_SIZE(virtnet_stats_cvq_desc); virtnet_stats_sprintf(&p, NULL, noq_fmt, num, -1, desc); } } if (type == VIRTNET_Q_TYPE_RX) { fmt = "rx%u_%s"; noq_fmt = "rx_%s"; desc = &virtnet_rq_stats_desc[0]; num = ARRAY_SIZE(virtnet_rq_stats_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); fmt = "rx%u_hw_%s"; noq_fmt = "rx_hw_%s"; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { desc = &virtnet_stats_rx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_basic_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { desc = &virtnet_stats_rx_csum_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_csum_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { desc = &virtnet_stats_rx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_speed_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } } if (type == VIRTNET_Q_TYPE_TX) { fmt = "tx%u_%s"; noq_fmt = "tx_%s"; desc = &virtnet_sq_stats_desc[0]; num = ARRAY_SIZE(virtnet_sq_stats_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); fmt = "tx%u_hw_%s"; noq_fmt = "tx_hw_%s"; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { desc = &virtnet_stats_tx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_basic_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { desc = &virtnet_stats_tx_gso_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_gso_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { desc = &virtnet_stats_tx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_speed_desc); virtnet_stats_sprintf(&p, fmt, noq_fmt, num, qid, desc); } } *data = p; } struct virtnet_stats_ctx { /* The stats are write to qstats or ethtool -S */ bool to_qstat; /* Used to calculate the offset inside the output buffer. */ u32 desc_num[3]; /* The actual supported stat types. */ u64 bitmap[3]; /* Used to calculate the reply buffer size. */ u32 size[3]; /* Record the output buffer. */ u64 *data; }; static void virtnet_stats_ctx_init(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, u64 *data, bool to_qstat) { u32 queue_type; ctx->data = data; ctx->to_qstat = to_qstat; if (to_qstat) { ctx->desc_num[VIRTNET_Q_TYPE_RX] = ARRAY_SIZE(virtnet_rq_stats_desc_qstat); ctx->desc_num[VIRTNET_Q_TYPE_TX] = ARRAY_SIZE(virtnet_sq_stats_desc_qstat); queue_type = VIRTNET_Q_TYPE_RX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_basic_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_CSUM; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_csum_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_csum); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_GSO) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_GSO; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_gso_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_gso); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_speed_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_speed); } queue_type = VIRTNET_Q_TYPE_TX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_basic_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_CSUM) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_CSUM; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_csum_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_csum); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_GSO; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_gso_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_gso); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_speed_desc_qstat); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_speed); } return; } ctx->desc_num[VIRTNET_Q_TYPE_RX] = ARRAY_SIZE(virtnet_rq_stats_desc); ctx->desc_num[VIRTNET_Q_TYPE_TX] = ARRAY_SIZE(virtnet_sq_stats_desc); if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_CVQ) { queue_type = VIRTNET_Q_TYPE_CQ; ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_CVQ; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_cvq_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_cvq); } queue_type = VIRTNET_Q_TYPE_RX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_basic_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_CSUM; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_csum_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_csum); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_RX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_rx_speed_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_rx_speed); } queue_type = VIRTNET_Q_TYPE_TX; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_BASIC; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_basic_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_basic); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_GSO; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_gso_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_gso); } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { ctx->bitmap[queue_type] |= VIRTIO_NET_STATS_TYPE_TX_SPEED; ctx->desc_num[queue_type] += ARRAY_SIZE(virtnet_stats_tx_speed_desc); ctx->size[queue_type] += sizeof(struct virtio_net_stats_tx_speed); } } /* stats_sum_queue - Calculate the sum of the same fields in sq or rq. * @sum: the position to store the sum values * @num: field num * @q_value: the first queue fields * @q_num: number of the queues */ static void stats_sum_queue(u64 *sum, u32 num, u64 *q_value, u32 q_num) { u32 step = num; int i, j; u64 *p; for (i = 0; i < num; ++i) { p = sum + i; *p = 0; for (j = 0; j < q_num; ++j) *p += *(q_value + i + j * step); } } static void virtnet_fill_total_fields(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx) { u64 *data, *first_rx_q, *first_tx_q; u32 num_cq, num_rx, num_tx; num_cq = ctx->desc_num[VIRTNET_Q_TYPE_CQ]; num_rx = ctx->desc_num[VIRTNET_Q_TYPE_RX]; num_tx = ctx->desc_num[VIRTNET_Q_TYPE_TX]; first_rx_q = ctx->data + num_rx + num_tx + num_cq; first_tx_q = first_rx_q + vi->curr_queue_pairs * num_rx; data = ctx->data; stats_sum_queue(data, num_rx, first_rx_q, vi->curr_queue_pairs); data = ctx->data + num_rx; stats_sum_queue(data, num_tx, first_tx_q, vi->curr_queue_pairs); } static void virtnet_fill_stats_qstat(struct virtnet_info *vi, u32 qid, struct virtnet_stats_ctx *ctx, const u8 *base, bool drv_stats, u8 reply_type) { const struct virtnet_stat_desc *desc; const u64_stats_t *v_stat; u64 offset, bitmap; const __le64 *v; u32 queue_type; int i, num; queue_type = vq_type(vi, qid); bitmap = ctx->bitmap[queue_type]; if (drv_stats) { if (queue_type == VIRTNET_Q_TYPE_RX) { desc = &virtnet_rq_stats_desc_qstat[0]; num = ARRAY_SIZE(virtnet_rq_stats_desc_qstat); } else { desc = &virtnet_sq_stats_desc_qstat[0]; num = ARRAY_SIZE(virtnet_sq_stats_desc_qstat); } for (i = 0; i < num; ++i) { offset = desc[i].qstat_offset / sizeof(*ctx->data); v_stat = (const u64_stats_t *)(base + desc[i].offset); ctx->data[offset] = u64_stats_read(v_stat); } return; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { desc = &virtnet_stats_rx_basic_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_basic_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { desc = &virtnet_stats_rx_csum_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_csum_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_GSO) { desc = &virtnet_stats_rx_gso_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_gso_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_GSO) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { desc = &virtnet_stats_rx_speed_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_rx_speed_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { desc = &virtnet_stats_tx_basic_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_basic_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_CSUM) { desc = &virtnet_stats_tx_csum_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_csum_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_CSUM) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_GSO) { desc = &virtnet_stats_tx_gso_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_gso_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO) goto found; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { desc = &virtnet_stats_tx_speed_desc_qstat[0]; num = ARRAY_SIZE(virtnet_stats_tx_speed_desc_qstat); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED) goto found; } return; found: for (i = 0; i < num; ++i) { offset = desc[i].qstat_offset / sizeof(*ctx->data); v = (const __le64 *)(base + desc[i].offset); ctx->data[offset] = le64_to_cpu(*v); } } /* virtnet_fill_stats - copy the stats to qstats or ethtool -S * The stats source is the device or the driver. * * @vi: virtio net info * @qid: the vq id * @ctx: stats ctx (initiated by virtnet_stats_ctx_init()) * @base: pointer to the device reply or the driver stats structure. * @drv_stats: designate the base type (device reply, driver stats) * @type: the type of the device reply (if drv_stats is true, this must be zero) */ static void virtnet_fill_stats(struct virtnet_info *vi, u32 qid, struct virtnet_stats_ctx *ctx, const u8 *base, bool drv_stats, u8 reply_type) { u32 queue_type, num_rx, num_tx, num_cq; const struct virtnet_stat_desc *desc; const u64_stats_t *v_stat; u64 offset, bitmap; const __le64 *v; int i, num; if (ctx->to_qstat) return virtnet_fill_stats_qstat(vi, qid, ctx, base, drv_stats, reply_type); num_cq = ctx->desc_num[VIRTNET_Q_TYPE_CQ]; num_rx = ctx->desc_num[VIRTNET_Q_TYPE_RX]; num_tx = ctx->desc_num[VIRTNET_Q_TYPE_TX]; queue_type = vq_type(vi, qid); bitmap = ctx->bitmap[queue_type]; /* skip the total fields of pairs */ offset = num_rx + num_tx; if (queue_type == VIRTNET_Q_TYPE_TX) { offset += num_cq + num_rx * vi->curr_queue_pairs + num_tx * (qid / 2); num = ARRAY_SIZE(virtnet_sq_stats_desc); if (drv_stats) { desc = &virtnet_sq_stats_desc[0]; goto drv_stats; } offset += num; } else if (queue_type == VIRTNET_Q_TYPE_RX) { offset += num_cq + num_rx * (qid / 2); num = ARRAY_SIZE(virtnet_rq_stats_desc); if (drv_stats) { desc = &virtnet_rq_stats_desc[0]; goto drv_stats; } offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_CVQ) { desc = &virtnet_stats_cvq_desc[0]; num = ARRAY_SIZE(virtnet_stats_cvq_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_CVQ) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { desc = &virtnet_stats_rx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_basic_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_BASIC) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { desc = &virtnet_stats_rx_csum_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_csum_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_CSUM) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_RX_SPEED) { desc = &virtnet_stats_rx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_rx_speed_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_RX_SPEED) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { desc = &virtnet_stats_tx_basic_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_basic_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_BASIC) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_GSO) { desc = &virtnet_stats_tx_gso_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_gso_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_GSO) goto found; offset += num; } if (bitmap & VIRTIO_NET_STATS_TYPE_TX_SPEED) { desc = &virtnet_stats_tx_speed_desc[0]; num = ARRAY_SIZE(virtnet_stats_tx_speed_desc); if (reply_type == VIRTIO_NET_STATS_TYPE_REPLY_TX_SPEED) goto found; offset += num; } return; found: for (i = 0; i < num; ++i) { v = (const __le64 *)(base + desc[i].offset); ctx->data[offset + i] = le64_to_cpu(*v); } return; drv_stats: for (i = 0; i < num; ++i) { v_stat = (const u64_stats_t *)(base + desc[i].offset); ctx->data[offset + i] = u64_stats_read(v_stat); } } static int __virtnet_get_hw_stats(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, struct virtio_net_ctrl_queue_stats *req, int req_size, void *reply, int res_size) { struct virtio_net_stats_reply_hdr *hdr; struct scatterlist sgs_in, sgs_out; void *p; u32 qid; int ok; sg_init_one(&sgs_out, req, req_size); sg_init_one(&sgs_in, reply, res_size); ok = virtnet_send_command_reply(vi, VIRTIO_NET_CTRL_STATS, VIRTIO_NET_CTRL_STATS_GET, &sgs_out, &sgs_in); if (!ok) return ok; for (p = reply; p - reply < res_size; p += le16_to_cpu(hdr->size)) { hdr = p; qid = le16_to_cpu(hdr->vq_index); virtnet_fill_stats(vi, qid, ctx, p, false, hdr->type); } return 0; } static void virtnet_make_stat_req(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, struct virtio_net_ctrl_queue_stats *req, int qid, int *idx) { int qtype = vq_type(vi, qid); u64 bitmap = ctx->bitmap[qtype]; if (!bitmap) return; req->stats[*idx].vq_index = cpu_to_le16(qid); req->stats[*idx].types_bitmap[0] = cpu_to_le64(bitmap); *idx += 1; } /* qid: -1: get stats of all vq. * > 0: get the stats for the special vq. This must not be cvq. */ static int virtnet_get_hw_stats(struct virtnet_info *vi, struct virtnet_stats_ctx *ctx, int qid) { int qnum, i, j, res_size, qtype, last_vq, first_vq; struct virtio_net_ctrl_queue_stats *req; bool enable_cvq; void *reply; int ok; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_DEVICE_STATS)) return 0; if (qid == -1) { last_vq = vi->curr_queue_pairs * 2 - 1; first_vq = 0; enable_cvq = true; } else { last_vq = qid; first_vq = qid; enable_cvq = false; } qnum = 0; res_size = 0; for (i = first_vq; i <= last_vq ; ++i) { qtype = vq_type(vi, i); if (ctx->bitmap[qtype]) { ++qnum; res_size += ctx->size[qtype]; } } if (enable_cvq && ctx->bitmap[VIRTNET_Q_TYPE_CQ]) { res_size += ctx->size[VIRTNET_Q_TYPE_CQ]; qnum += 1; } req = kcalloc(qnum, sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; reply = kmalloc(res_size, GFP_KERNEL); if (!reply) { kfree(req); return -ENOMEM; } j = 0; for (i = first_vq; i <= last_vq ; ++i) virtnet_make_stat_req(vi, ctx, req, i, &j); if (enable_cvq) virtnet_make_stat_req(vi, ctx, req, vi->max_queue_pairs * 2, &j); ok = __virtnet_get_hw_stats(vi, ctx, req, sizeof(*req) * j, reply, res_size); kfree(req); kfree(reply); return ok; } static void virtnet_get_strings(struct net_device *dev, u32 stringset, u8 *data) { struct virtnet_info *vi = netdev_priv(dev); unsigned int i; u8 *p = data; switch (stringset) { case ETH_SS_STATS: /* Generate the total field names. */ virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_RX, -1, &p); virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_TX, -1, &p); virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_CQ, 0, &p); for (i = 0; i < vi->curr_queue_pairs; ++i) virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_RX, i, &p); for (i = 0; i < vi->curr_queue_pairs; ++i) virtnet_get_stats_string(vi, VIRTNET_Q_TYPE_TX, i, &p); break; } } static int virtnet_get_sset_count(struct net_device *dev, int sset) { struct virtnet_info *vi = netdev_priv(dev); struct virtnet_stats_ctx ctx = {0}; u32 pair_count; switch (sset) { case ETH_SS_STATS: virtnet_stats_ctx_init(vi, &ctx, NULL, false); pair_count = ctx.desc_num[VIRTNET_Q_TYPE_RX] + ctx.desc_num[VIRTNET_Q_TYPE_TX]; return pair_count + ctx.desc_num[VIRTNET_Q_TYPE_CQ] + vi->curr_queue_pairs * pair_count; default: return -EOPNOTSUPP; } } static void virtnet_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct virtnet_info *vi = netdev_priv(dev); struct virtnet_stats_ctx ctx = {0}; unsigned int start, i; const u8 *stats_base; virtnet_stats_ctx_init(vi, &ctx, data, false); if (virtnet_get_hw_stats(vi, &ctx, -1)) dev_warn(&vi->dev->dev, "Failed to get hw stats.\n"); for (i = 0; i < vi->curr_queue_pairs; i++) { struct receive_queue *rq = &vi->rq[i]; struct send_queue *sq = &vi->sq[i]; stats_base = (const u8 *)&rq->stats; do { start = u64_stats_fetch_begin(&rq->stats.syncp); virtnet_fill_stats(vi, i * 2, &ctx, stats_base, true, 0); } while (u64_stats_fetch_retry(&rq->stats.syncp, start)); stats_base = (const u8 *)&sq->stats; do { start = u64_stats_fetch_begin(&sq->stats.syncp); virtnet_fill_stats(vi, i * 2 + 1, &ctx, stats_base, true, 0); } while (u64_stats_fetch_retry(&sq->stats.syncp, start)); } virtnet_fill_total_fields(vi, &ctx); } static void virtnet_get_channels(struct net_device *dev, struct ethtool_channels *channels) { struct virtnet_info *vi = netdev_priv(dev); channels->combined_count = vi->curr_queue_pairs; channels->max_combined = vi->max_queue_pairs; channels->max_other = 0; channels->rx_count = 0; channels->tx_count = 0; channels->other_count = 0; } static int virtnet_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct virtnet_info *vi = netdev_priv(dev); return ethtool_virtdev_set_link_ksettings(dev, cmd, &vi->speed, &vi->duplex); } static int virtnet_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct virtnet_info *vi = netdev_priv(dev); cmd->base.speed = vi->speed; cmd->base.duplex = vi->duplex; cmd->base.port = PORT_OTHER; return 0; } static int virtnet_send_tx_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct virtio_net_ctrl_coal_tx *coal_tx __free(kfree) = NULL; struct scatterlist sgs_tx; int i; coal_tx = kzalloc(sizeof(*coal_tx), GFP_KERNEL); if (!coal_tx) return -ENOMEM; coal_tx->tx_usecs = cpu_to_le32(ec->tx_coalesce_usecs); coal_tx->tx_max_packets = cpu_to_le32(ec->tx_max_coalesced_frames); sg_init_one(&sgs_tx, coal_tx, sizeof(*coal_tx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_TX_SET, &sgs_tx)) return -EINVAL; vi->intr_coal_tx.max_usecs = ec->tx_coalesce_usecs; vi->intr_coal_tx.max_packets = ec->tx_max_coalesced_frames; for (i = 0; i < vi->max_queue_pairs; i++) { vi->sq[i].intr_coal.max_usecs = ec->tx_coalesce_usecs; vi->sq[i].intr_coal.max_packets = ec->tx_max_coalesced_frames; } return 0; } static int virtnet_send_rx_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { struct virtio_net_ctrl_coal_rx *coal_rx __free(kfree) = NULL; bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce; struct scatterlist sgs_rx; int i; if (rx_ctrl_dim_on && !virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return -EOPNOTSUPP; if (rx_ctrl_dim_on && (ec->rx_coalesce_usecs != vi->intr_coal_rx.max_usecs || ec->rx_max_coalesced_frames != vi->intr_coal_rx.max_packets)) return -EINVAL; if (rx_ctrl_dim_on && !vi->rx_dim_enabled) { vi->rx_dim_enabled = true; for (i = 0; i < vi->max_queue_pairs; i++) { mutex_lock(&vi->rq[i].dim_lock); vi->rq[i].dim_enabled = true; mutex_unlock(&vi->rq[i].dim_lock); } return 0; } coal_rx = kzalloc(sizeof(*coal_rx), GFP_KERNEL); if (!coal_rx) return -ENOMEM; if (!rx_ctrl_dim_on && vi->rx_dim_enabled) { vi->rx_dim_enabled = false; for (i = 0; i < vi->max_queue_pairs; i++) { mutex_lock(&vi->rq[i].dim_lock); vi->rq[i].dim_enabled = false; mutex_unlock(&vi->rq[i].dim_lock); } } /* Since the per-queue coalescing params can be set, * we need apply the global new params even if they * are not updated. */ coal_rx->rx_usecs = cpu_to_le32(ec->rx_coalesce_usecs); coal_rx->rx_max_packets = cpu_to_le32(ec->rx_max_coalesced_frames); sg_init_one(&sgs_rx, coal_rx, sizeof(*coal_rx)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_NOTF_COAL, VIRTIO_NET_CTRL_NOTF_COAL_RX_SET, &sgs_rx)) return -EINVAL; vi->intr_coal_rx.max_usecs = ec->rx_coalesce_usecs; vi->intr_coal_rx.max_packets = ec->rx_max_coalesced_frames; for (i = 0; i < vi->max_queue_pairs; i++) { mutex_lock(&vi->rq[i].dim_lock); vi->rq[i].intr_coal.max_usecs = ec->rx_coalesce_usecs; vi->rq[i].intr_coal.max_packets = ec->rx_max_coalesced_frames; mutex_unlock(&vi->rq[i].dim_lock); } return 0; } static int virtnet_send_notf_coal_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec) { int err; err = virtnet_send_tx_notf_coal_cmds(vi, ec); if (err) return err; err = virtnet_send_rx_notf_coal_cmds(vi, ec); if (err) return err; return 0; } static int virtnet_send_rx_notf_coal_vq_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec, u16 queue) { bool rx_ctrl_dim_on = !!ec->use_adaptive_rx_coalesce; u32 max_usecs, max_packets; bool cur_rx_dim; int err; mutex_lock(&vi->rq[queue].dim_lock); cur_rx_dim = vi->rq[queue].dim_enabled; max_usecs = vi->rq[queue].intr_coal.max_usecs; max_packets = vi->rq[queue].intr_coal.max_packets; if (rx_ctrl_dim_on && (ec->rx_coalesce_usecs != max_usecs || ec->rx_max_coalesced_frames != max_packets)) { mutex_unlock(&vi->rq[queue].dim_lock); return -EINVAL; } if (rx_ctrl_dim_on && !cur_rx_dim) { vi->rq[queue].dim_enabled = true; mutex_unlock(&vi->rq[queue].dim_lock); return 0; } if (!rx_ctrl_dim_on && cur_rx_dim) vi->rq[queue].dim_enabled = false; /* If no params are updated, userspace ethtool will * reject the modification. */ err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, queue, ec->rx_coalesce_usecs, ec->rx_max_coalesced_frames); mutex_unlock(&vi->rq[queue].dim_lock); return err; } static int virtnet_send_notf_coal_vq_cmds(struct virtnet_info *vi, struct ethtool_coalesce *ec, u16 queue) { int err; err = virtnet_send_rx_notf_coal_vq_cmds(vi, ec, queue); if (err) return err; err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, queue, ec->tx_coalesce_usecs, ec->tx_max_coalesced_frames); if (err) return err; return 0; } static void virtnet_rx_dim_work(struct work_struct *work) { struct dim *dim = container_of(work, struct dim, work); struct receive_queue *rq = container_of(dim, struct receive_queue, dim); struct virtnet_info *vi = rq->vq->vdev->priv; struct net_device *dev = vi->dev; struct dim_cq_moder update_moder; int qnum, err; qnum = rq - vi->rq; mutex_lock(&rq->dim_lock); if (!rq->dim_enabled) goto out; update_moder = net_dim_get_rx_irq_moder(dev, dim); if (update_moder.usec != rq->intr_coal.max_usecs || update_moder.pkts != rq->intr_coal.max_packets) { err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum, update_moder.usec, update_moder.pkts); if (err) pr_debug("%s: Failed to send dim parameters on rxq%d\n", dev->name, qnum); } out: dim->state = DIM_START_MEASURE; mutex_unlock(&rq->dim_lock); } static int virtnet_coal_params_supported(struct ethtool_coalesce *ec) { /* usecs coalescing is supported only if VIRTIO_NET_F_NOTF_COAL * or VIRTIO_NET_F_VQ_NOTF_COAL feature is negotiated. */ if (ec->rx_coalesce_usecs || ec->tx_coalesce_usecs) return -EOPNOTSUPP; if (ec->tx_max_coalesced_frames > 1 || ec->rx_max_coalesced_frames != 1) return -EINVAL; return 0; } static int virtnet_should_update_vq_weight(int dev_flags, int weight, int vq_weight, bool *should_update) { if (weight ^ vq_weight) { if (dev_flags & IFF_UP) return -EBUSY; *should_update = true; } return 0; } static int virtnet_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); int ret, queue_number, napi_weight, i; bool update_napi = false; /* Can't change NAPI weight if the link is up */ napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; for (queue_number = 0; queue_number < vi->max_queue_pairs; queue_number++) { ret = virtnet_should_update_vq_weight(dev->flags, napi_weight, vi->sq[queue_number].napi.weight, &update_napi); if (ret) return ret; if (update_napi) { /* All queues that belong to [queue_number, vi->max_queue_pairs] will be * updated for the sake of simplicity, which might not be necessary */ break; } } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) ret = virtnet_send_notf_coal_cmds(vi, ec); else ret = virtnet_coal_params_supported(ec); if (ret) return ret; if (update_napi) { /* xsk xmit depends on the tx napi. So if xsk is active, * prevent modifications to tx napi. */ for (i = queue_number; i < vi->max_queue_pairs; i++) { if (vi->sq[i].xsk_pool) return -EBUSY; } for (; queue_number < vi->max_queue_pairs; queue_number++) vi->sq[queue_number].napi.weight = napi_weight; } return ret; } static int virtnet_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { ec->rx_coalesce_usecs = vi->intr_coal_rx.max_usecs; ec->tx_coalesce_usecs = vi->intr_coal_tx.max_usecs; ec->tx_max_coalesced_frames = vi->intr_coal_tx.max_packets; ec->rx_max_coalesced_frames = vi->intr_coal_rx.max_packets; ec->use_adaptive_rx_coalesce = vi->rx_dim_enabled; } else { ec->rx_max_coalesced_frames = 1; if (vi->sq[0].napi.weight) ec->tx_max_coalesced_frames = 1; } return 0; } static int virtnet_set_per_queue_coalesce(struct net_device *dev, u32 queue, struct ethtool_coalesce *ec) { struct virtnet_info *vi = netdev_priv(dev); int ret, napi_weight; bool update_napi = false; if (queue >= vi->max_queue_pairs) return -EINVAL; /* Can't change NAPI weight if the link is up */ napi_weight = ec->tx_max_coalesced_frames ? NAPI_POLL_WEIGHT : 0; ret = virtnet_should_update_vq_weight(dev->flags, napi_weight, vi->sq[queue].napi.weight, &update_napi); if (ret) return ret; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) ret = virtnet_send_notf_coal_vq_cmds(vi, ec, queue); else ret = virtnet_coal_params_supported(ec); if (ret) return ret; if (update_napi) vi->sq[queue].napi.weight = napi_weight; return 0; } static int virtnet_get_per_queue_coalesce(struct net_device *dev, u32 queue, struct ethtool_coalesce *ec) { struct virtnet_info *vi = netdev_priv(dev); if (queue >= vi->max_queue_pairs) return -EINVAL; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) { mutex_lock(&vi->rq[queue].dim_lock); ec->rx_coalesce_usecs = vi->rq[queue].intr_coal.max_usecs; ec->tx_coalesce_usecs = vi->sq[queue].intr_coal.max_usecs; ec->tx_max_coalesced_frames = vi->sq[queue].intr_coal.max_packets; ec->rx_max_coalesced_frames = vi->rq[queue].intr_coal.max_packets; ec->use_adaptive_rx_coalesce = vi->rq[queue].dim_enabled; mutex_unlock(&vi->rq[queue].dim_lock); } else { ec->rx_max_coalesced_frames = 1; if (vi->sq[queue].napi.weight) ec->tx_max_coalesced_frames = 1; } return 0; } static void virtnet_init_settings(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); vi->speed = SPEED_UNKNOWN; vi->duplex = DUPLEX_UNKNOWN; } static u32 virtnet_get_rxfh_key_size(struct net_device *dev) { return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size; } static u32 virtnet_get_rxfh_indir_size(struct net_device *dev) { return ((struct virtnet_info *)netdev_priv(dev))->rss_indir_table_size; } static int virtnet_get_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh) { struct virtnet_info *vi = netdev_priv(dev); int i; if (rxfh->indir) { for (i = 0; i < vi->rss_indir_table_size; ++i) rxfh->indir[i] = le16_to_cpu(vi->rss_hdr->indirection_table[i]); } if (rxfh->key) memcpy(rxfh->key, vi->rss_hash_key_data, vi->rss_key_size); rxfh->hfunc = ETH_RSS_HASH_TOP; return 0; } static int virtnet_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); bool update = false; int i; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && rxfh->hfunc != ETH_RSS_HASH_TOP) return -EOPNOTSUPP; if (rxfh->indir) { if (!vi->has_rss) return -EOPNOTSUPP; for (i = 0; i < vi->rss_indir_table_size; ++i) vi->rss_hdr->indirection_table[i] = cpu_to_le16(rxfh->indir[i]); update = true; } if (rxfh->key) { /* If either _F_HASH_REPORT or _F_RSS are negotiated, the * device provides hash calculation capabilities, that is, * hash_key is configured. */ if (!vi->has_rss && !vi->has_rss_hash_report) return -EOPNOTSUPP; memcpy(vi->rss_hash_key_data, rxfh->key, vi->rss_key_size); update = true; } if (update) virtnet_commit_rss_command(vi); return 0; } static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct virtnet_info *vi = netdev_priv(dev); int rc = 0; switch (info->cmd) { case ETHTOOL_GRXRINGS: info->data = vi->curr_queue_pairs; break; case ETHTOOL_GRXFH: virtnet_get_hashflow(vi, info); break; default: rc = -EOPNOTSUPP; } return rc; } static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) { struct virtnet_info *vi = netdev_priv(dev); int rc = 0; switch (info->cmd) { case ETHTOOL_SRXFH: if (!virtnet_set_hashflow(vi, info)) rc = -EINVAL; break; default: rc = -EOPNOTSUPP; } return rc; } static const struct ethtool_ops virtnet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, .get_drvinfo = virtnet_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = virtnet_get_ringparam, .set_ringparam = virtnet_set_ringparam, .get_strings = virtnet_get_strings, .get_sset_count = virtnet_get_sset_count, .get_ethtool_stats = virtnet_get_ethtool_stats, .set_channels = virtnet_set_channels, .get_channels = virtnet_get_channels, .get_ts_info = ethtool_op_get_ts_info, .get_link_ksettings = virtnet_get_link_ksettings, .set_link_ksettings = virtnet_set_link_ksettings, .set_coalesce = virtnet_set_coalesce, .get_coalesce = virtnet_get_coalesce, .set_per_queue_coalesce = virtnet_set_per_queue_coalesce, .get_per_queue_coalesce = virtnet_get_per_queue_coalesce, .get_rxfh_key_size = virtnet_get_rxfh_key_size, .get_rxfh_indir_size = virtnet_get_rxfh_indir_size, .get_rxfh = virtnet_get_rxfh, .set_rxfh = virtnet_set_rxfh, .get_rxnfc = virtnet_get_rxnfc, .set_rxnfc = virtnet_set_rxnfc, }; static void virtnet_get_queue_stats_rx(struct net_device *dev, int i, struct netdev_queue_stats_rx *stats) { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = &vi->rq[i]; struct virtnet_stats_ctx ctx = {0}; virtnet_stats_ctx_init(vi, &ctx, (void *)stats, true); virtnet_get_hw_stats(vi, &ctx, i * 2); virtnet_fill_stats(vi, i * 2, &ctx, (void *)&rq->stats, true, 0); } static void virtnet_get_queue_stats_tx(struct net_device *dev, int i, struct netdev_queue_stats_tx *stats) { struct virtnet_info *vi = netdev_priv(dev); struct send_queue *sq = &vi->sq[i]; struct virtnet_stats_ctx ctx = {0}; virtnet_stats_ctx_init(vi, &ctx, (void *)stats, true); virtnet_get_hw_stats(vi, &ctx, i * 2 + 1); virtnet_fill_stats(vi, i * 2 + 1, &ctx, (void *)&sq->stats, true, 0); } static void virtnet_get_base_stats(struct net_device *dev, struct netdev_queue_stats_rx *rx, struct netdev_queue_stats_tx *tx) { struct virtnet_info *vi = netdev_priv(dev); /* The queue stats of the virtio-net will not be reset. So here we * return 0. */ rx->bytes = 0; rx->packets = 0; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_BASIC) { rx->hw_drops = 0; rx->hw_drop_overruns = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_CSUM) { rx->csum_unnecessary = 0; rx->csum_none = 0; rx->csum_bad = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_GSO) { rx->hw_gro_packets = 0; rx->hw_gro_bytes = 0; rx->hw_gro_wire_packets = 0; rx->hw_gro_wire_bytes = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_RX_SPEED) rx->hw_drop_ratelimits = 0; tx->bytes = 0; tx->packets = 0; tx->stop = 0; tx->wake = 0; if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_BASIC) { tx->hw_drops = 0; tx->hw_drop_errors = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_CSUM) { tx->csum_none = 0; tx->needs_csum = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_GSO) { tx->hw_gso_packets = 0; tx->hw_gso_bytes = 0; tx->hw_gso_wire_packets = 0; tx->hw_gso_wire_bytes = 0; } if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED) tx->hw_drop_ratelimits = 0; netdev_stat_queue_sum(dev, dev->real_num_rx_queues, vi->max_queue_pairs, rx, dev->real_num_tx_queues, vi->max_queue_pairs, tx); } static const struct netdev_stat_ops virtnet_stat_ops = { .get_queue_stats_rx = virtnet_get_queue_stats_rx, .get_queue_stats_tx = virtnet_get_queue_stats_tx, .get_base_stats = virtnet_get_base_stats, }; static void virtnet_freeze_down(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; /* Make sure no work handler is accessing the device */ flush_work(&vi->config_work); disable_rx_mode_work(vi); flush_work(&vi->rx_mode_work); netif_tx_lock_bh(vi->dev); netif_device_detach(vi->dev); netif_tx_unlock_bh(vi->dev); if (netif_running(vi->dev)) { rtnl_lock(); virtnet_close(vi->dev); rtnl_unlock(); } } static int init_vqs(struct virtnet_info *vi); static int virtnet_restore_up(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; int err; err = init_vqs(vi); if (err) return err; virtio_device_ready(vdev); enable_delayed_refill(vi); enable_rx_mode_work(vi); if (netif_running(vi->dev)) { rtnl_lock(); err = virtnet_open(vi->dev); rtnl_unlock(); if (err) return err; } netif_tx_lock_bh(vi->dev); netif_device_attach(vi->dev); netif_tx_unlock_bh(vi->dev); return err; } static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads) { __virtio64 *_offloads __free(kfree) = NULL; struct scatterlist sg; _offloads = kzalloc(sizeof(*_offloads), GFP_KERNEL); if (!_offloads) return -ENOMEM; *_offloads = cpu_to_virtio64(vi->vdev, offloads); sg_init_one(&sg, _offloads, sizeof(*_offloads)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS, VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) { dev_warn(&vi->dev->dev, "Fail to set guest offload.\n"); return -EINVAL; } return 0; } static int virtnet_clear_guest_offloads(struct virtnet_info *vi) { u64 offloads = 0; if (!vi->guest_offloads) return 0; return virtnet_set_guest_offloads(vi, offloads); } static int virtnet_restore_guest_offloads(struct virtnet_info *vi) { u64 offloads = vi->guest_offloads; if (!vi->guest_offloads) return 0; return virtnet_set_guest_offloads(vi, offloads); } static int virtnet_rq_bind_xsk_pool(struct virtnet_info *vi, struct receive_queue *rq, struct xsk_buff_pool *pool) { int err, qindex; qindex = rq - vi->rq; if (pool) { err = xdp_rxq_info_reg(&rq->xsk_rxq_info, vi->dev, qindex, rq->napi.napi_id); if (err < 0) return err; err = xdp_rxq_info_reg_mem_model(&rq->xsk_rxq_info, MEM_TYPE_XSK_BUFF_POOL, NULL); if (err < 0) goto unreg; xsk_pool_set_rxq_info(pool, &rq->xsk_rxq_info); } virtnet_rx_pause(vi, rq); err = virtqueue_reset(rq->vq, virtnet_rq_unmap_free_buf, NULL); if (err) { netdev_err(vi->dev, "reset rx fail: rx queue index: %d err: %d\n", qindex, err); pool = NULL; } rq->xsk_pool = pool; virtnet_rx_resume(vi, rq); if (pool) return 0; unreg: xdp_rxq_info_unreg(&rq->xsk_rxq_info); return err; } static int virtnet_sq_bind_xsk_pool(struct virtnet_info *vi, struct send_queue *sq, struct xsk_buff_pool *pool) { int err, qindex; qindex = sq - vi->sq; virtnet_tx_pause(vi, sq); err = virtqueue_reset(sq->vq, virtnet_sq_free_unused_buf, virtnet_sq_free_unused_buf_done); if (err) { netdev_err(vi->dev, "reset tx fail: tx queue index: %d err: %d\n", qindex, err); pool = NULL; } sq->xsk_pool = pool; virtnet_tx_resume(vi, sq); return err; } static int virtnet_xsk_pool_enable(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid) { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq; struct device *dma_dev; struct send_queue *sq; dma_addr_t hdr_dma; int err, size; if (vi->hdr_len > xsk_pool_get_headroom(pool)) return -EINVAL; /* In big_packets mode, xdp cannot work, so there is no need to * initialize xsk of rq. */ if (vi->big_packets && !vi->mergeable_rx_bufs) return -ENOENT; if (qid >= vi->curr_queue_pairs) return -EINVAL; sq = &vi->sq[qid]; rq = &vi->rq[qid]; /* xsk assumes that tx and rx must have the same dma device. The af-xdp * may use one buffer to receive from the rx and reuse this buffer to * send by the tx. So the dma dev of sq and rq must be the same one. * * But vq->dma_dev allows every vq has the respective dma dev. So I * check the dma dev of vq and sq is the same dev. */ if (virtqueue_dma_dev(rq->vq) != virtqueue_dma_dev(sq->vq)) return -EINVAL; dma_dev = virtqueue_dma_dev(rq->vq); if (!dma_dev) return -EINVAL; size = virtqueue_get_vring_size(rq->vq); rq->xsk_buffs = kvcalloc(size, sizeof(*rq->xsk_buffs), GFP_KERNEL); if (!rq->xsk_buffs) return -ENOMEM; hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len, DMA_TO_DEVICE, 0); if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) { err = -ENOMEM; goto err_free_buffs; } err = xsk_pool_dma_map(pool, dma_dev, 0); if (err) goto err_xsk_map; err = virtnet_rq_bind_xsk_pool(vi, rq, pool); if (err) goto err_rq; err = virtnet_sq_bind_xsk_pool(vi, sq, pool); if (err) goto err_sq; /* Now, we do not support tx offload(such as tx csum), so all the tx * virtnet hdr is zero. So all the tx packets can share a single hdr. */ sq->xsk_hdr_dma_addr = hdr_dma; return 0; err_sq: virtnet_rq_bind_xsk_pool(vi, rq, NULL); err_rq: xsk_pool_dma_unmap(pool, 0); err_xsk_map: virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len, DMA_TO_DEVICE, 0); err_free_buffs: kvfree(rq->xsk_buffs); return err; } static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid) { struct virtnet_info *vi = netdev_priv(dev); struct xsk_buff_pool *pool; struct receive_queue *rq; struct send_queue *sq; int err; if (qid >= vi->curr_queue_pairs) return -EINVAL; sq = &vi->sq[qid]; rq = &vi->rq[qid]; pool = rq->xsk_pool; err = virtnet_rq_bind_xsk_pool(vi, rq, NULL); err |= virtnet_sq_bind_xsk_pool(vi, sq, NULL); xsk_pool_dma_unmap(pool, 0); virtqueue_dma_unmap_single_attrs(sq->vq, sq->xsk_hdr_dma_addr, vi->hdr_len, DMA_TO_DEVICE, 0); kvfree(rq->xsk_buffs); return err; } static int virtnet_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp) { if (xdp->xsk.pool) return virtnet_xsk_pool_enable(dev, xdp->xsk.pool, xdp->xsk.queue_id); else return virtnet_xsk_pool_disable(dev, xdp->xsk.queue_id); } static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { unsigned int room = SKB_DATA_ALIGN(XDP_PACKET_HEADROOM + sizeof(struct skb_shared_info)); unsigned int max_sz = PAGE_SIZE - room - ETH_HLEN; struct virtnet_info *vi = netdev_priv(dev); struct bpf_prog *old_prog; u16 xdp_qp = 0, curr_qp; int i, err; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS) && (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_CSUM) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO6))) { NL_SET_ERR_MSG_MOD(extack, "Can't set XDP while host is implementing GRO_HW/CSUM, disable GRO_HW/CSUM first"); return -EOPNOTSUPP; } if (vi->mergeable_rx_bufs && !vi->any_header_sg) { NL_SET_ERR_MSG_MOD(extack, "XDP expects header/data in single page, any_header_sg required"); return -EINVAL; } if (prog && !prog->aux->xdp_has_frags && dev->mtu > max_sz) { NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP without frags"); netdev_warn(dev, "single-buffer XDP requires MTU less than %u\n", max_sz); return -EINVAL; } curr_qp = vi->curr_queue_pairs - vi->xdp_queue_pairs; if (prog) xdp_qp = nr_cpu_ids; /* XDP requires extra queues for XDP_TX */ if (curr_qp + xdp_qp > vi->max_queue_pairs) { netdev_warn_once(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n", curr_qp + xdp_qp, vi->max_queue_pairs); xdp_qp = 0; } old_prog = rtnl_dereference(vi->rq[0].xdp_prog); if (!prog && !old_prog) return 0; if (prog) bpf_prog_add(prog, vi->max_queue_pairs - 1); virtnet_rx_pause_all(vi); /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) virtnet_napi_tx_disable(&vi->sq[i]); } if (!prog) { for (i = 0; i < vi->max_queue_pairs; i++) { rcu_assign_pointer(vi->rq[i].xdp_prog, prog); if (i == 0) virtnet_restore_guest_offloads(vi); } synchronize_net(); } err = virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; if (prog) { vi->xdp_enabled = true; for (i = 0; i < vi->max_queue_pairs; i++) { rcu_assign_pointer(vi->rq[i].xdp_prog, prog); if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); } if (!old_prog) xdp_features_set_redirect_target(dev, true); } else { xdp_features_clear_redirect_target(dev); vi->xdp_enabled = false; } virtnet_rx_resume_all(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); if (netif_running(dev)) virtnet_napi_tx_enable(&vi->sq[i]); } return 0; err: if (!prog) { virtnet_clear_guest_offloads(vi); for (i = 0; i < vi->max_queue_pairs; i++) rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); } virtnet_rx_resume_all(vi); if (netif_running(dev)) { for (i = 0; i < vi->max_queue_pairs; i++) virtnet_napi_tx_enable(&vi->sq[i]); } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); return err; } static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return virtnet_xdp_set(dev, xdp->prog, xdp->extack); case XDP_SETUP_XSK_POOL: return virtnet_xsk_pool_setup(dev, xdp); default: return -EINVAL; } } static int virtnet_get_phys_port_name(struct net_device *dev, char *buf, size_t len) { struct virtnet_info *vi = netdev_priv(dev); int ret; if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_STANDBY)) return -EOPNOTSUPP; ret = snprintf(buf, len, "sby"); if (ret >= len) return -EOPNOTSUPP; return 0; } static int virtnet_set_features(struct net_device *dev, netdev_features_t features) { struct virtnet_info *vi = netdev_priv(dev); u64 offloads; int err; if ((dev->features ^ features) & NETIF_F_GRO_HW) { if (vi->xdp_enabled) return -EBUSY; if (features & NETIF_F_GRO_HW) offloads = vi->guest_offloads_capable; else offloads = vi->guest_offloads_capable & ~GUEST_OFFLOAD_GRO_HW_MASK; err = virtnet_set_guest_offloads(vi, offloads); if (err) return err; vi->guest_offloads = offloads; } if ((dev->features ^ features) & NETIF_F_RXHASH) { if (features & NETIF_F_RXHASH) vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_saved); else vi->rss_hdr->hash_types = cpu_to_le32(VIRTIO_NET_HASH_REPORT_NONE); if (!virtnet_commit_rss_command(vi)) return -EINVAL; } return 0; } static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct virtnet_info *priv = netdev_priv(dev); struct send_queue *sq = &priv->sq[txqueue]; struct netdev_queue *txq = netdev_get_tx_queue(dev, txqueue); u64_stats_update_begin(&sq->stats.syncp); u64_stats_inc(&sq->stats.tx_timeouts); u64_stats_update_end(&sq->stats.syncp); netdev_err(dev, "TX timeout on queue: %u, sq: %s, vq: 0x%x, name: %s, %u usecs ago\n", txqueue, sq->name, sq->vq->index, sq->vq->name, jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start))); } static int virtnet_init_irq_moder(struct virtnet_info *vi) { u8 profile_flags = 0, coal_flags = 0; int ret, i; profile_flags |= DIM_PROFILE_RX; coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS; ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags, DIM_CQ_PERIOD_MODE_START_FROM_EQE, 0, virtnet_rx_dim_work, NULL); if (ret) return ret; for (i = 0; i < vi->max_queue_pairs; i++) net_dim_setting(vi->dev, &vi->rq[i].dim, false); return 0; } static void virtnet_free_irq_moder(struct virtnet_info *vi) { if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) return; rtnl_lock(); net_dim_free_irq_moder(vi->dev); rtnl_unlock(); } static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, .ndo_start_xmit = start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = virtnet_set_mac_address, .ndo_set_rx_mode = virtnet_set_rx_mode, .ndo_get_stats64 = virtnet_stats, .ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid, .ndo_bpf = virtnet_xdp, .ndo_xdp_xmit = virtnet_xdp_xmit, .ndo_xsk_wakeup = virtnet_xsk_wakeup, .ndo_features_check = passthru_features_check, .ndo_get_phys_port_name = virtnet_get_phys_port_name, .ndo_set_features = virtnet_set_features, .ndo_tx_timeout = virtnet_tx_timeout, }; static void virtnet_config_changed_work(struct work_struct *work) { struct virtnet_info *vi = container_of(work, struct virtnet_info, config_work); u16 v; if (virtio_cread_feature(vi->vdev, VIRTIO_NET_F_STATUS, struct virtio_net_config, status, &v) < 0) return; if (v & VIRTIO_NET_S_ANNOUNCE) { netdev_notify_peers(vi->dev); virtnet_ack_link_announce(vi); } /* Ignore unknown (future) status bits */ v &= VIRTIO_NET_S_LINK_UP; if (vi->status == v) return; vi->status = v; if (vi->status & VIRTIO_NET_S_LINK_UP) { virtnet_update_settings(vi); netif_carrier_on(vi->dev); netif_tx_wake_all_queues(vi->dev); } else { netif_carrier_off(vi->dev); netif_tx_stop_all_queues(vi->dev); } } static void virtnet_config_changed(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; schedule_work(&vi->config_work); } static void virtnet_free_queues(struct virtnet_info *vi) { int i; for (i = 0; i < vi->max_queue_pairs; i++) { __netif_napi_del(&vi->rq[i].napi); __netif_napi_del(&vi->sq[i].napi); } /* We called __netif_napi_del(), * we need to respect an RCU grace period before freeing vi->rq */ synchronize_net(); kfree(vi->rq); kfree(vi->sq); kfree(vi->ctrl); } static void _free_receive_bufs(struct virtnet_info *vi) { struct bpf_prog *old_prog; int i; for (i = 0; i < vi->max_queue_pairs; i++) { while (vi->rq[i].pages) __free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0); old_prog = rtnl_dereference(vi->rq[i].xdp_prog); RCU_INIT_POINTER(vi->rq[i].xdp_prog, NULL); if (old_prog) bpf_prog_put(old_prog); } } static void free_receive_bufs(struct virtnet_info *vi) { rtnl_lock(); _free_receive_bufs(vi); rtnl_unlock(); } static void free_receive_page_frags(struct virtnet_info *vi) { int i; for (i = 0; i < vi->max_queue_pairs; i++) if (vi->rq[i].alloc_frag.page) { if (vi->rq[i].last_dma) virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0); put_page(vi->rq[i].alloc_frag.page); } } static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) { struct virtnet_info *vi = vq->vdev->priv; struct send_queue *sq; int i = vq2txq(vq); sq = &vi->sq[i]; switch (virtnet_xmit_ptr_unpack(&buf)) { case VIRTNET_XMIT_TYPE_SKB: case VIRTNET_XMIT_TYPE_SKB_ORPHAN: dev_kfree_skb(buf); break; case VIRTNET_XMIT_TYPE_XDP: xdp_return_frame(buf); break; case VIRTNET_XMIT_TYPE_XSK: xsk_tx_completed(sq->xsk_pool, 1); break; } } static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; int i = vq2txq(vq); netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); } static void free_unused_bufs(struct virtnet_info *vi) { void *buf; int i; for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_sq_free_unused_buf(vq, buf); cond_resched(); } for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->rq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) virtnet_rq_unmap_free_buf(vq, buf); cond_resched(); } } static void virtnet_del_vqs(struct virtnet_info *vi) { struct virtio_device *vdev = vi->vdev; virtnet_clean_affinity(vi); vdev->config->del_vqs(vdev); virtnet_free_queues(vi); } /* How large should a single buffer be so a queue full of these can fit at * least one full packet? * Logic below assumes the mergeable buffer header is used. */ static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq) { const unsigned int hdr_len = vi->hdr_len; unsigned int rq_size = virtqueue_get_vring_size(vq); unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu; unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len; unsigned int min_buf_len = DIV_ROUND_UP(buf_len, rq_size); return max(max(min_buf_len, hdr_len) - hdr_len, (unsigned int)GOOD_PACKET_LEN); } static int virtnet_find_vqs(struct virtnet_info *vi) { struct virtqueue_info *vqs_info; struct virtqueue **vqs; int ret = -ENOMEM; int total_vqs; bool *ctx; u16 i; /* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by * possible control vq. */ total_vqs = vi->max_queue_pairs * 2 + virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ); /* Allocate space for find_vqs parameters */ vqs = kcalloc(total_vqs, sizeof(*vqs), GFP_KERNEL); if (!vqs) goto err_vq; vqs_info = kcalloc(total_vqs, sizeof(*vqs_info), GFP_KERNEL); if (!vqs_info) goto err_vqs_info; if (!vi->big_packets || vi->mergeable_rx_bufs) { ctx = kcalloc(total_vqs, sizeof(*ctx), GFP_KERNEL); if (!ctx) goto err_ctx; } else { ctx = NULL; } /* Parameters for control virtqueue, if any */ if (vi->has_cvq) { vqs_info[total_vqs - 1].name = "control"; } /* Allocate/initialize parameters for send/receive virtqueues */ for (i = 0; i < vi->max_queue_pairs; i++) { vqs_info[rxq2vq(i)].callback = skb_recv_done; vqs_info[txq2vq(i)].callback = skb_xmit_done; sprintf(vi->rq[i].name, "input.%u", i); sprintf(vi->sq[i].name, "output.%u", i); vqs_info[rxq2vq(i)].name = vi->rq[i].name; vqs_info[txq2vq(i)].name = vi->sq[i].name; if (ctx) vqs_info[rxq2vq(i)].ctx = true; } ret = virtio_find_vqs(vi->vdev, total_vqs, vqs, vqs_info, NULL); if (ret) goto err_find; if (vi->has_cvq) { vi->cvq = vqs[total_vqs - 1]; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VLAN)) vi->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } for (i = 0; i < vi->max_queue_pairs; i++) { vi->rq[i].vq = vqs[rxq2vq(i)]; vi->rq[i].min_buf_len = mergeable_min_buf_len(vi, vi->rq[i].vq); vi->sq[i].vq = vqs[txq2vq(i)]; } /* run here: ret == 0. */ err_find: kfree(ctx); err_ctx: kfree(vqs_info); err_vqs_info: kfree(vqs); err_vq: return ret; } static int virtnet_alloc_queues(struct virtnet_info *vi) { int i; if (vi->has_cvq) { vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL); if (!vi->ctrl) goto err_ctrl; } else { vi->ctrl = NULL; } vi->sq = kcalloc(vi->max_queue_pairs, sizeof(*vi->sq), GFP_KERNEL); if (!vi->sq) goto err_sq; vi->rq = kcalloc(vi->max_queue_pairs, sizeof(*vi->rq), GFP_KERNEL); if (!vi->rq) goto err_rq; INIT_DELAYED_WORK(&vi->refill, refill_work); for (i = 0; i < vi->max_queue_pairs; i++) { vi->rq[i].pages = NULL; netif_napi_add_config(vi->dev, &vi->rq[i].napi, virtnet_poll, i); vi->rq[i].napi.weight = napi_weight; netif_napi_add_tx_weight(vi->dev, &vi->sq[i].napi, virtnet_poll_tx, napi_tx ? napi_weight : 0); sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg)); ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len); sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg)); u64_stats_init(&vi->rq[i].stats.syncp); u64_stats_init(&vi->sq[i].stats.syncp); mutex_init(&vi->rq[i].dim_lock); } return 0; err_rq: kfree(vi->sq); err_sq: kfree(vi->ctrl); err_ctrl: return -ENOMEM; } static int init_vqs(struct virtnet_info *vi) { int ret; /* Allocate send & receive queues */ ret = virtnet_alloc_queues(vi); if (ret) goto err; ret = virtnet_find_vqs(vi); if (ret) goto err_free; cpus_read_lock(); virtnet_set_affinity(vi); cpus_read_unlock(); return 0; err_free: virtnet_free_queues(vi); err: return ret; } #ifdef CONFIG_SYSFS static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue, char *buf) { struct virtnet_info *vi = netdev_priv(queue->dev); unsigned int queue_index = get_netdev_rx_queue_index(queue); unsigned int headroom = virtnet_get_headroom(vi); unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0; struct ewma_pkt_len *avg; BUG_ON(queue_index >= vi->max_queue_pairs); avg = &vi->rq[queue_index].mrg_avg_pkt_len; return sprintf(buf, "%u\n", get_mergeable_buf_len(&vi->rq[queue_index], avg, SKB_DATA_ALIGN(headroom + tailroom))); } static struct rx_queue_attribute mergeable_rx_buffer_size_attribute = __ATTR_RO(mergeable_rx_buffer_size); static struct attribute *virtio_net_mrg_rx_attrs[] = { &mergeable_rx_buffer_size_attribute.attr, NULL }; static const struct attribute_group virtio_net_mrg_rx_group = { .name = "virtio_net", .attrs = virtio_net_mrg_rx_attrs }; #endif static bool virtnet_fail_on_feature(struct virtio_device *vdev, unsigned int fbit, const char *fname, const char *dname) { if (!virtio_has_feature(vdev, fbit)) return false; dev_err(&vdev->dev, "device advertises feature %s but not %s", fname, dname); return true; } #define VIRTNET_FAIL_ON(vdev, fbit, dbit) \ virtnet_fail_on_feature(vdev, fbit, #fbit, dbit) static bool virtnet_validate_features(struct virtio_device *vdev) { if (!virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ) && (VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_RX, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_VLAN, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_GUEST_ANNOUNCE, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_MQ, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_CTRL_MAC_ADDR, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_RSS, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_HASH_REPORT, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_NOTF_COAL, "VIRTIO_NET_F_CTRL_VQ") || VIRTNET_FAIL_ON(vdev, VIRTIO_NET_F_VQ_NOTF_COAL, "VIRTIO_NET_F_CTRL_VQ"))) { return false; } return true; } #define MIN_MTU ETH_MIN_MTU #define MAX_MTU ETH_MAX_MTU static int virtnet_validate(struct virtio_device *vdev) { if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", __func__); return -EINVAL; } if (!virtnet_validate_features(vdev)) return -EINVAL; if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) { int mtu = virtio_cread16(vdev, offsetof(struct virtio_net_config, mtu)); if (mtu < MIN_MTU) __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU); } if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY) && !virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { dev_warn(&vdev->dev, "device advertises feature VIRTIO_NET_F_STANDBY but not VIRTIO_NET_F_MAC, disabling standby"); __virtio_clear_bit(vdev, VIRTIO_NET_F_STANDBY); } return 0; } static bool virtnet_check_guest_gso(const struct virtnet_info *vi) { return virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_UFO) || (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO4) && virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_USO6)); } static void virtnet_set_big_packets(struct virtnet_info *vi, const int mtu) { bool guest_gso = virtnet_check_guest_gso(vi); /* If device can receive ANY guest GSO packets, regardless of mtu, * allocate packets of maximum size, otherwise limit it to only * mtu size worth only. */ if (mtu > ETH_DATA_LEN || guest_gso) { vi->big_packets = true; vi->big_packets_num_skbfrags = guest_gso ? MAX_SKB_FRAGS : DIV_ROUND_UP(mtu, PAGE_SIZE); } } #define VIRTIO_NET_HASH_REPORT_MAX_TABLE 10 static enum xdp_rss_hash_type virtnet_xdp_rss_type[VIRTIO_NET_HASH_REPORT_MAX_TABLE] = { [VIRTIO_NET_HASH_REPORT_NONE] = XDP_RSS_TYPE_NONE, [VIRTIO_NET_HASH_REPORT_IPv4] = XDP_RSS_TYPE_L3_IPV4, [VIRTIO_NET_HASH_REPORT_TCPv4] = XDP_RSS_TYPE_L4_IPV4_TCP, [VIRTIO_NET_HASH_REPORT_UDPv4] = XDP_RSS_TYPE_L4_IPV4_UDP, [VIRTIO_NET_HASH_REPORT_IPv6] = XDP_RSS_TYPE_L3_IPV6, [VIRTIO_NET_HASH_REPORT_TCPv6] = XDP_RSS_TYPE_L4_IPV6_TCP, [VIRTIO_NET_HASH_REPORT_UDPv6] = XDP_RSS_TYPE_L4_IPV6_UDP, [VIRTIO_NET_HASH_REPORT_IPv6_EX] = XDP_RSS_TYPE_L3_IPV6_EX, [VIRTIO_NET_HASH_REPORT_TCPv6_EX] = XDP_RSS_TYPE_L4_IPV6_TCP_EX, [VIRTIO_NET_HASH_REPORT_UDPv6_EX] = XDP_RSS_TYPE_L4_IPV6_UDP_EX }; static int virtnet_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { const struct xdp_buff *xdp = (void *)_ctx; struct virtio_net_hdr_v1_hash *hdr_hash; struct virtnet_info *vi; u16 hash_report; if (!(xdp->rxq->dev->features & NETIF_F_RXHASH)) return -ENODATA; vi = netdev_priv(xdp->rxq->dev); hdr_hash = (struct virtio_net_hdr_v1_hash *)(xdp->data - vi->hdr_len); hash_report = __le16_to_cpu(hdr_hash->hash_report); if (hash_report >= VIRTIO_NET_HASH_REPORT_MAX_TABLE) hash_report = VIRTIO_NET_HASH_REPORT_NONE; *rss_type = virtnet_xdp_rss_type[hash_report]; *hash = __le32_to_cpu(hdr_hash->hash_value); return 0; } static const struct xdp_metadata_ops virtnet_xdp_metadata_ops = { .xmo_rx_hash = virtnet_xdp_rx_hash, }; static int virtnet_probe(struct virtio_device *vdev) { int i, err = -ENOMEM; struct net_device *dev; struct virtnet_info *vi; u16 max_queue_pairs; int mtu = 0; /* Find if host supports multiqueue/rss virtio_net device */ max_queue_pairs = 1; if (virtio_has_feature(vdev, VIRTIO_NET_F_MQ) || virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) max_queue_pairs = virtio_cread16(vdev, offsetof(struct virtio_net_config, max_virtqueue_pairs)); /* We need at least 2 queue's */ if (max_queue_pairs < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || max_queue_pairs > VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX || !virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) max_queue_pairs = 1; /* Allocate ourselves a network device with room for our info */ dev = alloc_etherdev_mq(sizeof(struct virtnet_info), max_queue_pairs); if (!dev) return -ENOMEM; /* Set up network device as normal. */ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE | IFF_TX_SKB_NO_LINEAR; dev->netdev_ops = &virtnet_netdev; dev->stat_ops = &virtnet_stat_ops; dev->features = NETIF_F_HIGHDMA; dev->ethtool_ops = &virtnet_ethtool_ops; SET_NETDEV_DEV(dev, &vdev->dev); /* Do we support "hardware" checksums? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) { /* This opens up the world of extra features. */ dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (csum) dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6; } /* Individual feature bits: what can host handle? */ if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO4)) dev->hw_features |= NETIF_F_TSO; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_TSO6)) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_USO)) dev->hw_features |= NETIF_F_GSO_UDP_L4; dev->features |= NETIF_F_GSO_ROBUST; if (gso) dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } /* 1. With VIRTIO_NET_F_GUEST_CSUM negotiation, the driver doesn't * need to calculate checksums for partially checksummed packets, * as they're considered valid by the upper layer. * 2. Without VIRTIO_NET_F_GUEST_CSUM negotiation, the driver only * receives fully checksummed packets. The device may assist in * validating these packets' checksums, so the driver won't have to. */ dev->features |= NETIF_F_RXCSUM; if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)) dev->features |= NETIF_F_GRO_HW; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS)) dev->hw_features |= NETIF_F_GRO_HW; dev->vlan_features = dev->features; dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY; /* MTU range: 68 - 65535 */ dev->min_mtu = MIN_MTU; dev->max_mtu = MAX_MTU; /* Configuration may specify what MAC to use. Otherwise random. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_MAC)) { u8 addr[ETH_ALEN]; virtio_cread_bytes(vdev, offsetof(struct virtio_net_config, mac), addr, ETH_ALEN); eth_hw_addr_set(dev, addr); } else { eth_hw_addr_random(dev); dev_info(&vdev->dev, "Assigned random MAC address %pM\n", dev->dev_addr); } /* Set up our device-specific information */ vi = netdev_priv(dev); vi->dev = dev; vi->vdev = vdev; vdev->priv = vi; INIT_WORK(&vi->config_work, virtnet_config_changed_work); INIT_WORK(&vi->rx_mode_work, virtnet_rx_mode_work); spin_lock_init(&vi->refill_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { vi->mergeable_rx_bufs = true; dev->xdp_features |= NETDEV_XDP_ACT_RX_SG; } if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT)) vi->has_rss_hash_report = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) { vi->has_rss = true; vi->rss_indir_table_size = virtio_cread16(vdev, offsetof(struct virtio_net_config, rss_max_indirection_table_length)); } vi->rss_hdr = devm_kzalloc(&vdev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL); if (!vi->rss_hdr) { err = -ENOMEM; goto free; } if (vi->has_rss || vi->has_rss_hash_report) { vi->rss_key_size = virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size)); if (vi->rss_key_size > VIRTIO_NET_RSS_MAX_KEY_SIZE) { dev_err(&vdev->dev, "rss_max_key_size=%u exceeds the limit %u.\n", vi->rss_key_size, VIRTIO_NET_RSS_MAX_KEY_SIZE); err = -EINVAL; goto free; } vi->rss_hash_types_supported = virtio_cread32(vdev, offsetof(struct virtio_net_config, supported_hash_types)); vi->rss_hash_types_supported &= ~(VIRTIO_NET_RSS_HASH_TYPE_IP_EX | VIRTIO_NET_RSS_HASH_TYPE_TCP_EX | VIRTIO_NET_RSS_HASH_TYPE_UDP_EX); dev->hw_features |= NETIF_F_RXHASH; dev->xdp_metadata_ops = &virtnet_xdp_metadata_ops; } if (vi->has_rss_hash_report) vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash); else if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF) || virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) vi->hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); else vi->hdr_len = sizeof(struct virtio_net_hdr); if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) || virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) vi->any_header_sg = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) vi->has_cvq = true; mutex_init(&vi->cvq_lock); if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) { mtu = virtio_cread16(vdev, offsetof(struct virtio_net_config, mtu)); if (mtu < dev->min_mtu) { /* Should never trigger: MTU was previously validated * in virtnet_validate. */ dev_err(&vdev->dev, "device MTU appears to have changed it is now %d < %d", mtu, dev->min_mtu); err = -EINVAL; goto free; } dev->mtu = mtu; dev->max_mtu = mtu; } virtnet_set_big_packets(vi, mtu); if (vi->any_header_sg) dev->needed_headroom = vi->hdr_len; /* Enable multiqueue by default */ if (num_online_cpus() >= max_queue_pairs) vi->curr_queue_pairs = max_queue_pairs; else vi->curr_queue_pairs = num_online_cpus(); vi->max_queue_pairs = max_queue_pairs; /* Allocate/initialize the rx/tx queues, and invoke find_vqs */ err = init_vqs(vi); if (err) goto free; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { vi->intr_coal_rx.max_usecs = 0; vi->intr_coal_tx.max_usecs = 0; vi->intr_coal_rx.max_packets = 0; /* Keep the default values of the coalescing parameters * aligned with the default napi_tx state. */ if (vi->sq[0].napi.weight) vi->intr_coal_tx.max_packets = 1; else vi->intr_coal_tx.max_packets = 0; } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) { /* The reason is the same as VIRTIO_NET_F_NOTF_COAL. */ for (i = 0; i < vi->max_queue_pairs; i++) if (vi->sq[i].napi.weight) vi->sq[i].intr_coal.max_packets = 1; err = virtnet_init_irq_moder(vi); if (err) goto free; } #ifdef CONFIG_SYSFS if (vi->mergeable_rx_bufs) dev->sysfs_rx_queue_group = &virtio_net_mrg_rx_group; #endif netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs); netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs); virtnet_init_settings(dev); if (virtio_has_feature(vdev, VIRTIO_NET_F_STANDBY)) { vi->failover = net_failover_create(vi->dev); if (IS_ERR(vi->failover)) { err = PTR_ERR(vi->failover); goto free_vqs; } } if (vi->has_rss || vi->has_rss_hash_report) virtnet_init_default_rss(vi); enable_rx_mode_work(vi); /* serialize netdev register + virtio_device_ready() with ndo_open() */ rtnl_lock(); err = register_netdevice(dev); if (err) { pr_debug("virtio_net: registering device failed\n"); rtnl_unlock(); goto free_failover; } /* Disable config change notification until ndo_open. */ virtio_config_driver_disable(vi->vdev); virtio_device_ready(vdev); if (vi->has_rss || vi->has_rss_hash_report) { if (!virtnet_commit_rss_command(vi)) { dev_warn(&vdev->dev, "RSS disabled because committing failed.\n"); dev->hw_features &= ~NETIF_F_RXHASH; vi->has_rss_hash_report = false; vi->has_rss = false; } } virtnet_set_queues(vi, vi->curr_queue_pairs); /* a random MAC address has been assigned, notify the device. * We don't fail probe if VIRTIO_NET_F_CTRL_MAC_ADDR is not there * because many devices work fine without getting MAC explicitly */ if (!virtio_has_feature(vdev, VIRTIO_NET_F_MAC) && virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_MAC_ADDR)) { struct scatterlist sg; sg_init_one(&sg, dev->dev_addr, dev->addr_len); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MAC, VIRTIO_NET_CTRL_MAC_ADDR_SET, &sg)) { pr_debug("virtio_net: setting MAC address failed\n"); rtnl_unlock(); err = -EINVAL; goto free_unregister_netdev; } } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_DEVICE_STATS)) { struct virtio_net_stats_capabilities *stats_cap __free(kfree) = NULL; struct scatterlist sg; __le64 v; stats_cap = kzalloc(sizeof(*stats_cap), GFP_KERNEL); if (!stats_cap) { rtnl_unlock(); err = -ENOMEM; goto free_unregister_netdev; } sg_init_one(&sg, stats_cap, sizeof(*stats_cap)); if (!virtnet_send_command_reply(vi, VIRTIO_NET_CTRL_STATS, VIRTIO_NET_CTRL_STATS_QUERY, NULL, &sg)) { pr_debug("virtio_net: fail to get stats capability\n"); rtnl_unlock(); err = -EINVAL; goto free_unregister_netdev; } v = stats_cap->supported_stats_types[0]; vi->device_stats_cap = le64_to_cpu(v); } /* Assume link up if device can't report link status, otherwise get link status from config. */ netif_carrier_off(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { virtnet_config_changed_work(&vi->config_work); } else { vi->status = VIRTIO_NET_S_LINK_UP; virtnet_update_settings(vi); netif_carrier_on(dev); } for (i = 0; i < ARRAY_SIZE(guest_offloads); i++) if (virtio_has_feature(vi->vdev, guest_offloads[i])) set_bit(guest_offloads[i], &vi->guest_offloads); vi->guest_offloads_capable = vi->guest_offloads; rtnl_unlock(); err = virtnet_cpu_notif_add(vi); if (err) { pr_debug("virtio_net: registering cpu notifier failed\n"); goto free_unregister_netdev; } pr_debug("virtnet: registered device %s with %d RX and TX vq's\n", dev->name, max_queue_pairs); return 0; free_unregister_netdev: unregister_netdev(dev); free_failover: net_failover_destroy(vi->failover); free_vqs: virtio_reset_device(vdev); cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); free: free_netdev(dev); return err; } static void remove_vq_common(struct virtnet_info *vi) { int i; virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); /* * Rule of thumb is netdev_tx_reset_queue() should follow any * skb freeing not followed by netdev_tx_completed_queue() */ for (i = 0; i < vi->max_queue_pairs; i++) netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); free_receive_bufs(vi); free_receive_page_frags(vi); virtnet_del_vqs(vi); } static void virtnet_remove(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; virtnet_cpu_notif_remove(vi); /* Make sure no work handler is accessing the device. */ flush_work(&vi->config_work); disable_rx_mode_work(vi); flush_work(&vi->rx_mode_work); virtnet_free_irq_moder(vi); unregister_netdev(vi->dev); net_failover_destroy(vi->failover); remove_vq_common(vi); free_netdev(vi->dev); } static __maybe_unused int virtnet_freeze(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; virtnet_cpu_notif_remove(vi); virtnet_freeze_down(vdev); remove_vq_common(vi); return 0; } static __maybe_unused int virtnet_restore(struct virtio_device *vdev) { struct virtnet_info *vi = vdev->priv; int err; err = virtnet_restore_up(vdev); if (err) return err; virtnet_set_queues(vi, vi->curr_queue_pairs); err = virtnet_cpu_notif_add(vi); if (err) { virtnet_freeze_down(vdev); remove_vq_common(vi); return err; } return 0; } static struct virtio_device_id id_table[] = { { VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID }, { 0 }, }; #define VIRTNET_FEATURES \ VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, \ VIRTIO_NET_F_MAC, \ VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, \ VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, \ VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, \ VIRTIO_NET_F_HOST_USO, VIRTIO_NET_F_GUEST_USO4, VIRTIO_NET_F_GUEST_USO6, \ VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, \ VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, \ VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, \ VIRTIO_NET_F_CTRL_MAC_ADDR, \ VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \ VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \ VIRTIO_NET_F_RSS, VIRTIO_NET_F_HASH_REPORT, VIRTIO_NET_F_NOTF_COAL, \ VIRTIO_NET_F_VQ_NOTF_COAL, \ VIRTIO_NET_F_GUEST_HDRLEN, VIRTIO_NET_F_DEVICE_STATS static unsigned int features[] = { VIRTNET_FEATURES, }; static unsigned int features_legacy[] = { VIRTNET_FEATURES, VIRTIO_NET_F_GSO, VIRTIO_F_ANY_LAYOUT, }; static struct virtio_driver virtio_net_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), .feature_table_legacy = features_legacy, .feature_table_size_legacy = ARRAY_SIZE(features_legacy), .driver.name = KBUILD_MODNAME, .id_table = id_table, .validate = virtnet_validate, .probe = virtnet_probe, .remove = virtnet_remove, .config_changed = virtnet_config_changed, #ifdef CONFIG_PM_SLEEP .freeze = virtnet_freeze, .restore = virtnet_restore, #endif }; static __init int virtio_net_driver_init(void) { int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "virtio/net:online", virtnet_cpu_online, virtnet_cpu_down_prep); if (ret < 0) goto out; virtionet_online = ret; ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "virtio/net:dead", NULL, virtnet_cpu_dead); if (ret) goto err_dead; ret = register_virtio_driver(&virtio_net_driver); if (ret) goto err_virtio; return 0; err_virtio: cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD); err_dead: cpuhp_remove_multi_state(virtionet_online); out: return ret; } module_init(virtio_net_driver_init); static __exit void virtio_net_driver_exit(void) { unregister_virtio_driver(&virtio_net_driver); cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD); cpuhp_remove_multi_state(virtionet_online); } module_exit(virtio_net_driver_exit); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio network driver"); MODULE_LICENSE("GPL"); |
| 1 4 1 1 1 1 1 1 1 1 1 12 2 14 1 1 1 6 5 3 2 3 2 2 2 2 2 12 12 12 8 8 3 5 2 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 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 | // SPDX-License-Identifier: GPL-2.0 /* net/sched/sch_etf.c Earliest TxTime First queueing discipline. * * Authors: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com> * Vinicius Costa Gomes <vinicius.gomes@intel.com> */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/rbtree.h> #include <linux/skbuff.h> #include <linux/posix-timers.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/sock.h> #define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON) #define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON) #define SKIP_SOCK_CHECK_IS_SET(x) ((x)->flags & TC_ETF_SKIP_SOCK_CHECK) struct etf_sched_data { bool offload; bool deadline_mode; bool skip_sock_check; int clockid; int queue; s32 delta; /* in ns */ ktime_t last; /* The txtime of the last skb sent to the netdevice. */ struct rb_root_cached head; struct qdisc_watchdog watchdog; ktime_t (*get_time)(void); }; static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = { [TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) }, }; static inline int validate_input_params(struct tc_etf_qopt *qopt, struct netlink_ext_ack *extack) { /* Check if params comply to the following rules: * * Clockid and delta must be valid. * * * Dynamic clockids are not supported. * * * Delta must be a positive integer. * * Also note that for the HW offload case, we must * expect that system clocks have been synchronized to PHC. */ if (qopt->clockid < 0) { NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported"); return -ENOTSUPP; } if (qopt->clockid != CLOCK_TAI) { NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used"); return -EINVAL; } if (qopt->delta < 0) { NL_SET_ERR_MSG(extack, "Delta must be positive"); return -EINVAL; } return 0; } static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb) { struct etf_sched_data *q = qdisc_priv(sch); ktime_t txtime = nskb->tstamp; struct sock *sk = nskb->sk; ktime_t now; if (q->skip_sock_check) goto skip; if (!sk || !sk_fullsock(sk)) return false; if (!sock_flag(sk, SOCK_TXTIME)) return false; /* We don't perform crosstimestamping. * Drop if packet's clockid differs from qdisc's. */ if (sk->sk_clockid != q->clockid) return false; if (sk->sk_txtime_deadline_mode != q->deadline_mode) return false; skip: now = q->get_time(); if (ktime_before(txtime, now) || ktime_before(txtime, q->last)) return false; return true; } static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct rb_node *p; p = rb_first_cached(&q->head); if (!p) return NULL; return rb_to_skb(p); } static void reset_watchdog(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = etf_peek_timesortedlist(sch); ktime_t next; if (!skb) { qdisc_watchdog_cancel(&q->watchdog); return; } next = ktime_sub_ns(skb->tstamp, q->delta); qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); } static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) { struct sock_exterr_skb *serr; struct sk_buff *clone; ktime_t txtime = skb->tstamp; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors)) return; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) return; serr = SKB_EXT_ERR(clone); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME; serr->ee.ee_type = 0; serr->ee.ee_code = code; serr->ee.ee_pad = 0; serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */ serr->ee.ee_info = txtime; /* low part of tstamp */ if (sock_queue_err_skb(sk, clone)) kfree_skb(clone); } static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, struct sk_buff **to_free) { struct etf_sched_data *q = qdisc_priv(sch); struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL; ktime_t txtime = nskb->tstamp; bool leftmost = true; if (!is_packet_valid(sch, nskb)) { report_sock_error(nskb, EINVAL, SO_EE_CODE_TXTIME_INVALID_PARAM); return qdisc_drop(nskb, sch, to_free); } while (*p) { struct sk_buff *skb; parent = *p; skb = rb_to_skb(parent); if (ktime_compare(txtime, skb->tstamp) >= 0) { p = &parent->rb_right; leftmost = false; } else { p = &parent->rb_left; } } rb_link_node(&nskb->rbnode, parent, p); rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost); qdisc_qstats_backlog_inc(sch, nskb); sch->q.qlen++; /* Now we may need to re-arm the qdisc watchdog for the next packet. */ reset_watchdog(sch); return NET_XMIT_SUCCESS; } static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb, ktime_t now) { struct etf_sched_data *q = qdisc_priv(sch); struct sk_buff *to_free = NULL; struct sk_buff *tmp = NULL; skb_rbtree_walk_from_safe(skb, tmp) { if (ktime_after(skb->tstamp, now)) break; rb_erase_cached(&skb->rbnode, &q->head); /* The rbnode field in the skb re-uses these fields, now that * we are done with the rbnode, reset them. */ skb->next = NULL; skb->prev = NULL; skb->dev = qdisc_dev(sch); report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED); qdisc_qstats_backlog_dec(sch, skb); qdisc_drop(skb, sch, &to_free); qdisc_qstats_overlimit(sch); sch->q.qlen--; } kfree_skb_list(to_free); } static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb) { struct etf_sched_data *q = qdisc_priv(sch); rb_erase_cached(&skb->rbnode, &q->head); /* The rbnode field in the skb re-uses these fields, now that * we are done with the rbnode, reset them. */ skb->next = NULL; skb->prev = NULL; skb->dev = qdisc_dev(sch); qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); q->last = skb->tstamp; sch->q.qlen--; } static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; ktime_t now, next; skb = etf_peek_timesortedlist(sch); if (!skb) return NULL; now = q->get_time(); /* Drop if packet has expired while in queue. */ if (ktime_before(skb->tstamp, now)) { timesortedlist_drop(sch, skb, now); skb = NULL; goto out; } /* When in deadline mode, dequeue as soon as possible and change the * txtime from deadline to (now + delta). */ if (q->deadline_mode) { timesortedlist_remove(sch, skb); skb->tstamp = now; goto out; } next = ktime_sub_ns(skb->tstamp, q->delta); /* Dequeue only if now is within the [txtime - delta, txtime] range. */ if (ktime_after(now, next)) timesortedlist_remove(sch, skb); else skb = NULL; out: /* Now we may need to re-arm the qdisc watchdog for the next packet. */ reset_watchdog(sch); return skb; } static void etf_disable_offload(struct net_device *dev, struct etf_sched_data *q) { struct tc_etf_qopt_offload etf = { }; const struct net_device_ops *ops; int err; if (!q->offload) return; ops = dev->netdev_ops; if (!ops->ndo_setup_tc) return; etf.queue = q->queue; etf.enable = 0; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); if (err < 0) pr_warn("Couldn't disable ETF offload for queue %d\n", etf.queue); } static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_etf_qopt_offload etf = { }; int err; if (!ops->ndo_setup_tc) { NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload"); return -EOPNOTSUPP; } etf.queue = q->queue; etf.enable = 1; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); if (err < 0) { NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload"); return err; } return 0; } static int etf_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct etf_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct nlattr *tb[TCA_ETF_MAX + 1]; struct tc_etf_qopt *qopt; int err; if (!opt) { NL_SET_ERR_MSG(extack, "Missing ETF qdisc options which are mandatory"); return -EINVAL; } err = nla_parse_nested_deprecated(tb, TCA_ETF_MAX, opt, etf_policy, extack); if (err < 0) return err; if (!tb[TCA_ETF_PARMS]) { NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters"); return -EINVAL; } qopt = nla_data(tb[TCA_ETF_PARMS]); pr_debug("delta %d clockid %d offload %s deadline %s\n", qopt->delta, qopt->clockid, OFFLOAD_IS_ON(qopt) ? "on" : "off", DEADLINE_MODE_IS_ON(qopt) ? "on" : "off"); err = validate_input_params(qopt, extack); if (err < 0) return err; q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); if (OFFLOAD_IS_ON(qopt)) { err = etf_enable_offload(dev, q, extack); if (err < 0) return err; } /* Everything went OK, save the parameters used. */ q->delta = qopt->delta; q->clockid = qopt->clockid; q->offload = OFFLOAD_IS_ON(qopt); q->deadline_mode = DEADLINE_MODE_IS_ON(qopt); q->skip_sock_check = SKIP_SOCK_CHECK_IS_SET(qopt); switch (q->clockid) { case CLOCK_REALTIME: q->get_time = ktime_get_real; break; case CLOCK_MONOTONIC: q->get_time = ktime_get; break; case CLOCK_BOOTTIME: q->get_time = ktime_get_boottime; break; case CLOCK_TAI: q->get_time = ktime_get_clocktai; break; default: NL_SET_ERR_MSG(extack, "Clockid is not supported"); return -ENOTSUPP; } qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid); return 0; } static void timesortedlist_clear(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct rb_node *p = rb_first_cached(&q->head); while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); rb_erase_cached(&skb->rbnode, &q->head); rtnl_kfree_skbs(skb, skb); sch->q.qlen--; } } static void etf_reset(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); /* Only cancel watchdog if it's been initialized. */ if (q->watchdog.qdisc == sch) qdisc_watchdog_cancel(&q->watchdog); /* No matter which mode we are on, it's safe to clear both lists. */ timesortedlist_clear(sch); __qdisc_reset_queue(&sch->q); q->last = 0; } static void etf_destroy(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); /* Only cancel watchdog if it's been initialized. */ if (q->watchdog.qdisc == sch) qdisc_watchdog_cancel(&q->watchdog); etf_disable_offload(dev, q); } static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) { struct etf_sched_data *q = qdisc_priv(sch); struct tc_etf_qopt opt = { }; struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto nla_put_failure; opt.delta = READ_ONCE(q->delta); opt.clockid = READ_ONCE(q->clockid); if (READ_ONCE(q->offload)) opt.flags |= TC_ETF_OFFLOAD_ON; if (READ_ONCE(q->deadline_mode)) opt.flags |= TC_ETF_DEADLINE_MODE_ON; if (READ_ONCE(q->skip_sock_check)) opt.flags |= TC_ETF_SKIP_SOCK_CHECK; if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static struct Qdisc_ops etf_qdisc_ops __read_mostly = { .id = "etf", .priv_size = sizeof(struct etf_sched_data), .enqueue = etf_enqueue_timesortedlist, .dequeue = etf_dequeue_timesortedlist, .peek = etf_peek_timesortedlist, .init = etf_init, .reset = etf_reset, .destroy = etf_destroy, .dump = etf_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("etf"); static int __init etf_module_init(void) { return register_qdisc(&etf_qdisc_ops); } static void __exit etf_module_exit(void) { unregister_qdisc(&etf_qdisc_ops); } module_init(etf_module_init) module_exit(etf_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Earliest TxTime First (ETF) qdisc"); |
| 7 203 2 35 110 49 7 56 3 7 49 56 3 1960 1918 50 11 1 652 646 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/gen_estimator.c Simple rate estimator. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Eric Dumazet <edumazet@google.com> * * Changes: * Jamal Hadi Salim - moved it to net/core and reshulfed * names to make it usable in general net subsystem. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seqlock.h> #include <net/sock.h> #include <net/gen_stats.h> /* This code is NOT intended to be used for statistics collection, * its purpose is to provide a base for statistical multiplexing * for controlled load service. * If you need only statistics, run a user level daemon which * periodically reads byte counters. */ struct net_rate_estimator { struct gnet_stats_basic_sync *bstats; spinlock_t *stats_lock; bool running; struct gnet_stats_basic_sync __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; u64 last_packets; u64 last_bytes; u64 avpps; u64 avbps; unsigned long next_jiffies; struct timer_list timer; struct rcu_head rcu; }; static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_sync *b) { gnet_stats_basic_sync_init(b); if (e->stats_lock) spin_lock(e->stats_lock); gnet_stats_add_basic(b, e->cpu_bstats, e->bstats, e->running); if (e->stats_lock) spin_unlock(e->stats_lock); } static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = timer_container_of(est, t, timer); struct gnet_stats_basic_sync b; u64 b_bytes, b_packets; u64 rate, brate; est_fetch_counters(est, &b); b_bytes = u64_stats_read(&b.bytes); b_packets = u64_stats_read(&b.packets); brate = (b_bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); rate = (b_packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); est->last_bytes = b_bytes; est->last_packets = b_packets; est->next_jiffies += ((HZ/4) << est->intvl_log); if (unlikely(time_after_eq(jiffies, est->next_jiffies))) { /* Ouch... timer was delayed. */ est->next_jiffies = jiffies + 1; } mod_timer(&est->timer, est->next_jiffies); } /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: true if @bstats represents a running qdisc, thus @bstats' * internal values might change during basic reads. Only used * if @bstats_cpu is NULL * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * */ int gen_new_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; struct gnet_stats_basic_sync b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) return -EINVAL; /* allowed timer periods are : * -2 : 250ms, -1 : 500ms, 0 : 1 sec * 1 : 2 sec, 2 : 4 sec, 3 : 8 sec */ if (parm->interval < -2 || parm->interval > 3) return -EINVAL; if (parm->ewma_log == 0 || parm->ewma_log >= 31) return -EINVAL; est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; est->stats_lock = lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; if (lock) local_bh_disable(); est_fetch_counters(est, &b); if (lock) local_bh_enable(); est->last_bytes = u64_stats_read(&b.bytes); est->last_packets = u64_stats_read(&b.packets); if (lock) spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { timer_delete_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } est->next_jiffies = jiffies + ((HZ/4) << intvl_log); timer_setup(&est->timer, est_timer, 0); mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); if (lock) spin_unlock_bh(lock); if (old) kfree_rcu(old, rcu); return 0; } EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @rate_est: rate estimator * * Removes the rate estimator. * */ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; est = unrcu_pointer(xchg(rate_est, NULL)); if (est) { timer_shutdown_sync(&est->timer); kfree_rcu(est, rcu); } } EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: true if @bstats represents a running qdisc, thus @bstats' * internal values might change during basic reads. Only used * if @cpu_bstats is NULL * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). * * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); /** * gen_estimator_active - test if estimator is currently in use * @rate_est: rate estimator * * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(struct net_rate_estimator __rcu **rate_est) { return !!rcu_access_pointer(*rate_est); } EXPORT_SYMBOL(gen_estimator_active); bool gen_estimator_read(struct net_rate_estimator __rcu **rate_est, struct gnet_stats_rate_est64 *sample) { struct net_rate_estimator *est; unsigned seq; rcu_read_lock(); est = rcu_dereference(*rate_est); if (!est) { rcu_read_unlock(); return false; } do { seq = read_seqcount_begin(&est->seq); sample->bps = est->avbps >> 8; sample->pps = est->avpps >> 8; } while (read_seqcount_retry(&est->seq, seq)); rcu_read_unlock(); return true; } EXPORT_SYMBOL(gen_estimator_read); |
| 7 3 3 2 1 2 1 1 1 1 1 1 1 1 1 1 1 473 473 467 6 3 2 3 1 1404 743 14 13 12 4264 4260 1405 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct nf_hook_ops *ops; struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (ops->pf != NFPROTO_NETDEV || ops->hooknum != NF_NETDEV_INGRESS) return false; dev = ops->dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct nf_hook_ops *ops; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (this_dev && this_dev != ops->dev) continue; err = nft_chain_offload_cmd(basechain, ops->dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (i-- <= 0) break; nft_chain_offload_cmd(basechain, ops->dev, FLOW_BLOCK_UNBIND); } } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->flags & NLM_F_REPLACE || !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (!nft_hook_find_ops(hook, dev)) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 3 775 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_RTNETLINK_H #define __NET_RTNETLINK_H #include <linux/rtnetlink.h> #include <linux/srcu.h> #include <net/netlink.h> typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { RTNL_FLAG_DOIT_UNLOCKED = BIT(0), #define RTNL_FLAG_DOIT_PERNET RTNL_FLAG_DOIT_UNLOCKED #define RTNL_FLAG_DOIT_PERNET_WIP RTNL_FLAG_DOIT_UNLOCKED RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), RTNL_FLAG_DUMP_UNLOCKED = BIT(2), RTNL_FLAG_DUMP_SPLIT_NLM_DONE = BIT(3), /* legacy behavior */ }; enum rtnl_kinds { RTNL_KIND_NEW, RTNL_KIND_DEL, RTNL_KIND_GET, RTNL_KIND_SET }; #define RTNL_KIND_MASK 0x3 static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) { return msgtype & RTNL_KIND_MASK; } /** * struct rtnl_msg_handler - rtnetlink message type and handlers * * @owner: NULL for built-in, THIS_MODULE for module * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions */ struct rtnl_msg_handler { struct module *owner; int protocol; int msgtype; rtnl_doit_func doit; rtnl_dumpit_func dumpit; int flags; }; void rtnl_unregister_all(int protocol); int __rtnl_register_many(const struct rtnl_msg_handler *handlers, int n); void __rtnl_unregister_many(const struct rtnl_msg_handler *handlers, int n); #define rtnl_register_many(handlers) \ __rtnl_register_many(handlers, ARRAY_SIZE(handlers)) #define rtnl_unregister_many(handlers) \ __rtnl_unregister_many(handlers, ARRAY_SIZE(handlers)) static inline int rtnl_msg_family(const struct nlmsghdr *nlh) { if (nlmsg_len(nlh) >= sizeof(struct rtgenmsg)) return ((struct rtgenmsg *) nlmsg_data(nlh))->rtgen_family; else return AF_UNSPEC; } /** * struct rtnl_newlink_params - parameters of rtnl_link_ops::newlink() * * @src_net: Source netns of rtnetlink socket * @link_net: Link netns by IFLA_LINK_NETNSID, NULL if not specified * @peer_net: Peer netns * @tb: IFLA_* attributes * @data: IFLA_INFO_DATA attributes */ struct rtnl_newlink_params { struct net *src_net; struct net *link_net; struct net *peer_net; struct nlattr **tb; struct nlattr **data; }; /* Get effective link netns from newlink params. Generally, this is link_net * and falls back to src_net. But for compatibility, a driver may * choose to * use dev_net(dev) instead. */ static inline struct net *rtnl_newlink_link_net(struct rtnl_newlink_params *p) { return p->link_net ? : p->src_net; } /* Get peer netns from newlink params. Fallback to link netns if peer netns is * not specified explicitly. */ static inline struct net *rtnl_newlink_peer_net(struct rtnl_newlink_params *p) { return p->peer_net ? : rtnl_newlink_link_net(p); } /** * struct rtnl_link_ops - rtnetlink link operations * * @list: Used internally, protected by link_ops_mutex and SRCU * @srcu: Used internally * @kind: Identifier * @netns_refund: Physical device, move to init_net on netns exit * @peer_type: Peer device specific netlink attribute number (e.g. VETH_INFO_PEER) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters * @alloc: netdev allocation function, can be %NULL and is then used * in place of alloc_netdev_mqs(), in this case @priv_size * and @setup are unused. Returns a netdev or ERR_PTR(). * @priv_size: sizeof net_device private space * @setup: net_device setup function * @newlink: Function for configuring and registering a new device * @changelink: Function for changing parameters of an existing device * @dellink: Function to remove a device * @get_size: Function to calculate required room for dumping device * specific netlink attributes * @fill_info: Function to dump device specific netlink attributes * @get_xstats_size: Function to calculate required room for dumping device * specific statistics * @fill_xstats: Function to dump device specific statistics * @get_num_tx_queues: Function to determine number of transmit queues * to create when creating a new device. * @get_num_rx_queues: Function to determine number of receive queues * to create when creating a new device. * @get_link_net: Function to get the i/o netns of the device * @get_linkxstats_size: Function to calculate the required room for * dumping device-specific extended link stats * @fill_linkxstats: Function to dump device-specific extended link stats */ struct rtnl_link_ops { struct list_head list; struct srcu_struct srcu; const char *kind; size_t priv_size; struct net_device *(*alloc)(struct nlattr *tb[], const char *ifname, unsigned char name_assign_type, unsigned int num_tx_queues, unsigned int num_rx_queues); void (*setup)(struct net_device *dev); bool netns_refund; const u16 peer_type; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); int (*newlink)(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); void (*dellink)(struct net_device *dev, struct list_head *head); size_t (*get_size)(const struct net_device *dev); int (*fill_info)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_xstats_size)(const struct net_device *dev); int (*fill_xstats)(struct sk_buff *skb, const struct net_device *dev); unsigned int (*get_num_tx_queues)(void); unsigned int (*get_num_rx_queues)(void); unsigned int slave_maxtype; const struct nla_policy *slave_policy; int (*slave_changelink)(struct net_device *dev, struct net_device *slave_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); size_t (*get_slave_size)(const struct net_device *dev, const struct net_device *slave_dev); int (*fill_slave_info)(struct sk_buff *skb, const struct net_device *dev, const struct net_device *slave_dev); struct net *(*get_link_net)(const struct net_device *dev); size_t (*get_linkxstats_size)(const struct net_device *dev, int attr); int (*fill_linkxstats)(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr); }; int rtnl_link_register(struct rtnl_link_ops *ops); void rtnl_link_unregister(struct rtnl_link_ops *ops); /** * struct rtnl_af_ops - rtnetlink address family operations * * @list: Used internally, protected by RTNL and SRCU * @srcu: Used internally * @family: Address family * @fill_link_af: Function to fill IFLA_AF_SPEC with address family * specific netlink attributes. * @get_link_af_size: Function to calculate size of address family specific * netlink attributes. * @validate_link_af: Validate a IFLA_AF_SPEC attribute, must check attr * for invalid configuration settings. * @set_link_af: Function to parse a IFLA_AF_SPEC attribute and modify * net_device accordingly. */ struct rtnl_af_ops { struct list_head list; struct srcu_struct srcu; int family; int (*fill_link_af)(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask); size_t (*get_link_af_size)(const struct net_device *dev, u32 ext_filter_mask); int (*validate_link_af)(const struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); int (*set_link_af)(struct net_device *dev, const struct nlattr *attr, struct netlink_ext_ack *extack); int (*fill_stats_af)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_stats_af_size)(const struct net_device *dev); }; int rtnl_af_register(struct rtnl_af_ops *ops); void rtnl_af_unregister(struct rtnl_af_ops *ops); struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, struct nlattr *tb[], struct netlink_ext_ack *extack); int rtnl_delete_link(struct net_device *dev, u32 portid, const struct nlmsghdr *nlh); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, u32 portid, const struct nlmsghdr *nlh); int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * Copyright (c) 2006 Intel Corporation. All rights reserved. */ #ifndef IB_SA_H #define IB_SA_H #include <linux/completion.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/netdevice.h> #include <rdma/ib_verbs.h> #include <rdma/ib_mad.h> #include <rdma/ib_addr.h> #include <rdma/opa_addr.h> enum { IB_SA_CLASS_VERSION = 2, /* IB spec version 1.1/1.2 */ IB_SA_METHOD_GET_TABLE = 0x12, IB_SA_METHOD_GET_TABLE_RESP = 0x92, IB_SA_METHOD_DELETE = 0x15, IB_SA_METHOD_DELETE_RESP = 0x95, IB_SA_METHOD_GET_MULTI = 0x14, IB_SA_METHOD_GET_MULTI_RESP = 0x94, IB_SA_METHOD_GET_TRACE_TBL = 0x13 }; #define OPA_SA_CLASS_VERSION 0x80 enum { IB_SA_ATTR_CLASS_PORTINFO = 0x01, IB_SA_ATTR_NOTICE = 0x02, IB_SA_ATTR_INFORM_INFO = 0x03, IB_SA_ATTR_NODE_REC = 0x11, IB_SA_ATTR_PORT_INFO_REC = 0x12, IB_SA_ATTR_SL2VL_REC = 0x13, IB_SA_ATTR_SWITCH_REC = 0x14, IB_SA_ATTR_LINEAR_FDB_REC = 0x15, IB_SA_ATTR_RANDOM_FDB_REC = 0x16, IB_SA_ATTR_MCAST_FDB_REC = 0x17, IB_SA_ATTR_SM_INFO_REC = 0x18, IB_SA_ATTR_LINK_REC = 0x20, IB_SA_ATTR_GUID_INFO_REC = 0x30, IB_SA_ATTR_SERVICE_REC = 0x31, IB_SA_ATTR_PARTITION_REC = 0x33, IB_SA_ATTR_PATH_REC = 0x35, IB_SA_ATTR_VL_ARB_REC = 0x36, IB_SA_ATTR_MC_MEMBER_REC = 0x38, IB_SA_ATTR_TRACE_REC = 0x39, IB_SA_ATTR_MULTI_PATH_REC = 0x3a, IB_SA_ATTR_SERVICE_ASSOC_REC = 0x3b, IB_SA_ATTR_INFORM_INFO_REC = 0xf3 }; enum ib_sa_selector { IB_SA_GT = 0, IB_SA_LT = 1, IB_SA_EQ = 2, /* * The meaning of "best" depends on the attribute: for * example, for MTU best will return the largest available * MTU, while for packet life time, best will return the * smallest available life time. */ IB_SA_BEST = 3 }; /* * There are 4 types of join states: * FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember. * The order corresponds to JoinState bits in MCMemberRecord. */ enum ib_sa_mc_join_states { FULLMEMBER_JOIN, NONMEMBER_JOIN, SENDONLY_NONMEBER_JOIN, SENDONLY_FULLMEMBER_JOIN, NUM_JOIN_MEMBERSHIP_TYPES, }; #define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT BIT(12) /* * Structures for SA records are named "struct ib_sa_xxx_rec." No * attempt is made to pack structures to match the physical layout of * SA records in SA MADs; all packing and unpacking is handled by the * SA query code. * * For a record with structure ib_sa_xxx_rec, the naming convention * for the component mask value for field yyy is IB_SA_XXX_REC_YYY (we * never use different abbreviations or otherwise change the spelling * of xxx/yyy between ib_sa_xxx_rec.yyy and IB_SA_XXX_REC_YYY). * * Reserved rows are indicated with comments to help maintainability. */ #define IB_SA_PATH_REC_SERVICE_ID (IB_SA_COMP_MASK( 0) |\ IB_SA_COMP_MASK( 1)) #define IB_SA_PATH_REC_DGID IB_SA_COMP_MASK( 2) #define IB_SA_PATH_REC_SGID IB_SA_COMP_MASK( 3) #define IB_SA_PATH_REC_DLID IB_SA_COMP_MASK( 4) #define IB_SA_PATH_REC_SLID IB_SA_COMP_MASK( 5) #define IB_SA_PATH_REC_RAW_TRAFFIC IB_SA_COMP_MASK( 6) /* reserved: 7 */ #define IB_SA_PATH_REC_FLOW_LABEL IB_SA_COMP_MASK( 8) #define IB_SA_PATH_REC_HOP_LIMIT IB_SA_COMP_MASK( 9) #define IB_SA_PATH_REC_TRAFFIC_CLASS IB_SA_COMP_MASK(10) #define IB_SA_PATH_REC_REVERSIBLE IB_SA_COMP_MASK(11) #define IB_SA_PATH_REC_NUMB_PATH IB_SA_COMP_MASK(12) #define IB_SA_PATH_REC_PKEY IB_SA_COMP_MASK(13) #define IB_SA_PATH_REC_QOS_CLASS IB_SA_COMP_MASK(14) #define IB_SA_PATH_REC_SL IB_SA_COMP_MASK(15) #define IB_SA_PATH_REC_MTU_SELECTOR IB_SA_COMP_MASK(16) #define IB_SA_PATH_REC_MTU IB_SA_COMP_MASK(17) #define IB_SA_PATH_REC_RATE_SELECTOR IB_SA_COMP_MASK(18) #define IB_SA_PATH_REC_RATE IB_SA_COMP_MASK(19) #define IB_SA_PATH_REC_PACKET_LIFE_TIME_SELECTOR IB_SA_COMP_MASK(20) #define IB_SA_PATH_REC_PACKET_LIFE_TIME IB_SA_COMP_MASK(21) #define IB_SA_PATH_REC_PREFERENCE IB_SA_COMP_MASK(22) enum sa_path_rec_type { SA_PATH_REC_TYPE_IB, SA_PATH_REC_TYPE_ROCE_V1, SA_PATH_REC_TYPE_ROCE_V2, SA_PATH_REC_TYPE_OPA }; struct sa_path_rec_ib { __be16 dlid; __be16 slid; u8 raw_traffic; }; /** * struct sa_path_rec_roce - RoCE specific portion of the path record entry * @route_resolved: When set, it indicates that this route is already * resolved for this path record entry. * @dmac: Destination mac address for the given DGID entry * of the path record entry. */ struct sa_path_rec_roce { bool route_resolved; u8 dmac[ETH_ALEN]; }; struct sa_path_rec_opa { __be32 dlid; __be32 slid; u8 raw_traffic; u8 l2_8B; u8 l2_10B; u8 l2_9B; u8 l2_16B; u8 qos_type; u8 qos_priority; }; struct sa_path_rec { union ib_gid dgid; union ib_gid sgid; __be64 service_id; /* reserved */ __be32 flow_label; u8 hop_limit; u8 traffic_class; u8 reversible; u8 numb_path; __be16 pkey; __be16 qos_class; u8 sl; u8 mtu_selector; u8 mtu; u8 rate_selector; u8 rate; u8 packet_life_time_selector; u8 packet_life_time; u8 preference; union { struct sa_path_rec_ib ib; struct sa_path_rec_roce roce; struct sa_path_rec_opa opa; }; enum sa_path_rec_type rec_type; u32 flags; }; static inline enum ib_gid_type sa_conv_pathrec_to_gid_type(struct sa_path_rec *rec) { switch (rec->rec_type) { case SA_PATH_REC_TYPE_ROCE_V1: return IB_GID_TYPE_ROCE; case SA_PATH_REC_TYPE_ROCE_V2: return IB_GID_TYPE_ROCE_UDP_ENCAP; default: return IB_GID_TYPE_IB; } } static inline enum sa_path_rec_type sa_conv_gid_to_pathrec_type(enum ib_gid_type type) { switch (type) { case IB_GID_TYPE_ROCE: return SA_PATH_REC_TYPE_ROCE_V1; case IB_GID_TYPE_ROCE_UDP_ENCAP: return SA_PATH_REC_TYPE_ROCE_V2; default: return SA_PATH_REC_TYPE_IB; } } static inline void path_conv_opa_to_ib(struct sa_path_rec *ib, struct sa_path_rec *opa) { if ((be32_to_cpu(opa->opa.dlid) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) || (be32_to_cpu(opa->opa.slid) >= be16_to_cpu(IB_MULTICAST_LID_BASE))) { /* Create OPA GID and zero out the LID */ ib->dgid.global.interface_id = OPA_MAKE_ID(be32_to_cpu(opa->opa.dlid)); ib->dgid.global.subnet_prefix = opa->dgid.global.subnet_prefix; ib->sgid.global.interface_id = OPA_MAKE_ID(be32_to_cpu(opa->opa.slid)); ib->dgid.global.subnet_prefix = opa->dgid.global.subnet_prefix; ib->ib.dlid = 0; ib->ib.slid = 0; } else { ib->ib.dlid = htons(ntohl(opa->opa.dlid)); ib->ib.slid = htons(ntohl(opa->opa.slid)); } ib->service_id = opa->service_id; ib->ib.raw_traffic = opa->opa.raw_traffic; } static inline void path_conv_ib_to_opa(struct sa_path_rec *opa, struct sa_path_rec *ib) { __be32 slid, dlid; if ((ib_is_opa_gid(&ib->sgid)) || (ib_is_opa_gid(&ib->dgid))) { slid = htonl(opa_get_lid_from_gid(&ib->sgid)); dlid = htonl(opa_get_lid_from_gid(&ib->dgid)); } else { slid = htonl(ntohs(ib->ib.slid)); dlid = htonl(ntohs(ib->ib.dlid)); } opa->opa.slid = slid; opa->opa.dlid = dlid; opa->service_id = ib->service_id; opa->opa.raw_traffic = ib->ib.raw_traffic; } /* Convert from OPA to IB path record */ static inline void sa_convert_path_opa_to_ib(struct sa_path_rec *dest, struct sa_path_rec *src) { if (src->rec_type != SA_PATH_REC_TYPE_OPA) return; *dest = *src; dest->rec_type = SA_PATH_REC_TYPE_IB; path_conv_opa_to_ib(dest, src); } /* Convert from IB to OPA path record */ static inline void sa_convert_path_ib_to_opa(struct sa_path_rec *dest, struct sa_path_rec *src) { if (src->rec_type != SA_PATH_REC_TYPE_IB) return; /* Do a structure copy and overwrite the relevant fields */ *dest = *src; dest->rec_type = SA_PATH_REC_TYPE_OPA; path_conv_ib_to_opa(dest, src); } #define IB_SA_MCMEMBER_REC_MGID IB_SA_COMP_MASK( 0) #define IB_SA_MCMEMBER_REC_PORT_GID IB_SA_COMP_MASK( 1) #define IB_SA_MCMEMBER_REC_QKEY IB_SA_COMP_MASK( 2) #define IB_SA_MCMEMBER_REC_MLID IB_SA_COMP_MASK( 3) #define IB_SA_MCMEMBER_REC_MTU_SELECTOR IB_SA_COMP_MASK( 4) #define IB_SA_MCMEMBER_REC_MTU IB_SA_COMP_MASK( 5) #define IB_SA_MCMEMBER_REC_TRAFFIC_CLASS IB_SA_COMP_MASK( 6) #define IB_SA_MCMEMBER_REC_PKEY IB_SA_COMP_MASK( 7) #define IB_SA_MCMEMBER_REC_RATE_SELECTOR IB_SA_COMP_MASK( 8) #define IB_SA_MCMEMBER_REC_RATE IB_SA_COMP_MASK( 9) #define IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME_SELECTOR IB_SA_COMP_MASK(10) #define IB_SA_MCMEMBER_REC_PACKET_LIFE_TIME IB_SA_COMP_MASK(11) #define IB_SA_MCMEMBER_REC_SL IB_SA_COMP_MASK(12) #define IB_SA_MCMEMBER_REC_FLOW_LABEL IB_SA_COMP_MASK(13) #define IB_SA_MCMEMBER_REC_HOP_LIMIT IB_SA_COMP_MASK(14) #define IB_SA_MCMEMBER_REC_SCOPE IB_SA_COMP_MASK(15) #define IB_SA_MCMEMBER_REC_JOIN_STATE IB_SA_COMP_MASK(16) #define IB_SA_MCMEMBER_REC_PROXY_JOIN IB_SA_COMP_MASK(17) struct ib_sa_mcmember_rec { union ib_gid mgid; union ib_gid port_gid; __be32 qkey; __be16 mlid; u8 mtu_selector; u8 mtu; u8 traffic_class; __be16 pkey; u8 rate_selector; u8 rate; u8 packet_life_time_selector; u8 packet_life_time; u8 sl; __be32 flow_label; u8 hop_limit; u8 scope; u8 join_state; u8 proxy_join; }; /* Service Record Component Mask Sec 15.2.5.14 Ver 1.1 */ #define IB_SA_SERVICE_REC_SERVICE_ID IB_SA_COMP_MASK( 0) #define IB_SA_SERVICE_REC_SERVICE_GID IB_SA_COMP_MASK( 1) #define IB_SA_SERVICE_REC_SERVICE_PKEY IB_SA_COMP_MASK( 2) /* reserved: 3 */ #define IB_SA_SERVICE_REC_SERVICE_LEASE IB_SA_COMP_MASK( 4) #define IB_SA_SERVICE_REC_SERVICE_KEY IB_SA_COMP_MASK( 5) #define IB_SA_SERVICE_REC_SERVICE_NAME IB_SA_COMP_MASK( 6) #define IB_SA_SERVICE_REC_SERVICE_DATA8_0 IB_SA_COMP_MASK( 7) #define IB_SA_SERVICE_REC_SERVICE_DATA8_1 IB_SA_COMP_MASK( 8) #define IB_SA_SERVICE_REC_SERVICE_DATA8_2 IB_SA_COMP_MASK( 9) #define IB_SA_SERVICE_REC_SERVICE_DATA8_3 IB_SA_COMP_MASK(10) #define IB_SA_SERVICE_REC_SERVICE_DATA8_4 IB_SA_COMP_MASK(11) #define IB_SA_SERVICE_REC_SERVICE_DATA8_5 IB_SA_COMP_MASK(12) #define IB_SA_SERVICE_REC_SERVICE_DATA8_6 IB_SA_COMP_MASK(13) #define IB_SA_SERVICE_REC_SERVICE_DATA8_7 IB_SA_COMP_MASK(14) #define IB_SA_SERVICE_REC_SERVICE_DATA8_8 IB_SA_COMP_MASK(15) #define IB_SA_SERVICE_REC_SERVICE_DATA8_9 IB_SA_COMP_MASK(16) #define IB_SA_SERVICE_REC_SERVICE_DATA8_10 IB_SA_COMP_MASK(17) #define IB_SA_SERVICE_REC_SERVICE_DATA8_11 IB_SA_COMP_MASK(18) #define IB_SA_SERVICE_REC_SERVICE_DATA8_12 IB_SA_COMP_MASK(19) #define IB_SA_SERVICE_REC_SERVICE_DATA8_13 IB_SA_COMP_MASK(20) #define IB_SA_SERVICE_REC_SERVICE_DATA8_14 IB_SA_COMP_MASK(21) #define IB_SA_SERVICE_REC_SERVICE_DATA8_15 IB_SA_COMP_MASK(22) #define IB_SA_SERVICE_REC_SERVICE_DATA16_0 IB_SA_COMP_MASK(23) #define IB_SA_SERVICE_REC_SERVICE_DATA16_1 IB_SA_COMP_MASK(24) #define IB_SA_SERVICE_REC_SERVICE_DATA16_2 IB_SA_COMP_MASK(25) #define IB_SA_SERVICE_REC_SERVICE_DATA16_3 IB_SA_COMP_MASK(26) #define IB_SA_SERVICE_REC_SERVICE_DATA16_4 IB_SA_COMP_MASK(27) #define IB_SA_SERVICE_REC_SERVICE_DATA16_5 IB_SA_COMP_MASK(28) #define IB_SA_SERVICE_REC_SERVICE_DATA16_6 IB_SA_COMP_MASK(29) #define IB_SA_SERVICE_REC_SERVICE_DATA16_7 IB_SA_COMP_MASK(30) #define IB_SA_SERVICE_REC_SERVICE_DATA32_0 IB_SA_COMP_MASK(31) #define IB_SA_SERVICE_REC_SERVICE_DATA32_1 IB_SA_COMP_MASK(32) #define IB_SA_SERVICE_REC_SERVICE_DATA32_2 IB_SA_COMP_MASK(33) #define IB_SA_SERVICE_REC_SERVICE_DATA32_3 IB_SA_COMP_MASK(34) #define IB_SA_SERVICE_REC_SERVICE_DATA64_0 IB_SA_COMP_MASK(35) #define IB_SA_SERVICE_REC_SERVICE_DATA64_1 IB_SA_COMP_MASK(36) #define IB_DEFAULT_SERVICE_LEASE 0xFFFFFFFF #define IB_SA_GUIDINFO_REC_LID IB_SA_COMP_MASK(0) #define IB_SA_GUIDINFO_REC_BLOCK_NUM IB_SA_COMP_MASK(1) #define IB_SA_GUIDINFO_REC_RES1 IB_SA_COMP_MASK(2) #define IB_SA_GUIDINFO_REC_RES2 IB_SA_COMP_MASK(3) #define IB_SA_GUIDINFO_REC_GID0 IB_SA_COMP_MASK(4) #define IB_SA_GUIDINFO_REC_GID1 IB_SA_COMP_MASK(5) #define IB_SA_GUIDINFO_REC_GID2 IB_SA_COMP_MASK(6) #define IB_SA_GUIDINFO_REC_GID3 IB_SA_COMP_MASK(7) #define IB_SA_GUIDINFO_REC_GID4 IB_SA_COMP_MASK(8) #define IB_SA_GUIDINFO_REC_GID5 IB_SA_COMP_MASK(9) #define IB_SA_GUIDINFO_REC_GID6 IB_SA_COMP_MASK(10) #define IB_SA_GUIDINFO_REC_GID7 IB_SA_COMP_MASK(11) struct ib_sa_guidinfo_rec { __be16 lid; u8 block_num; /* reserved */ u8 res1; __be32 res2; u8 guid_info_list[64]; }; struct ib_sa_client { atomic_t users; struct completion comp; }; /** * ib_sa_register_client - Register an SA client. */ void ib_sa_register_client(struct ib_sa_client *client); /** * ib_sa_unregister_client - Deregister an SA client. * @client: Client object to deregister. */ void ib_sa_unregister_client(struct ib_sa_client *client); struct ib_sa_query; void ib_sa_cancel_query(int id, struct ib_sa_query *query); int ib_sa_path_rec_get(struct ib_sa_client *client, struct ib_device *device, u32 port_num, struct sa_path_rec *rec, ib_sa_comp_mask comp_mask, unsigned long timeout_ms, gfp_t gfp_mask, void (*callback)(int status, struct sa_path_rec *resp, unsigned int num_prs, void *context), void *context, struct ib_sa_query **query); struct ib_sa_multicast { struct ib_sa_mcmember_rec rec; ib_sa_comp_mask comp_mask; int (*callback)(int status, struct ib_sa_multicast *multicast); void *context; }; /** * ib_sa_join_multicast - Initiates a join request to the specified multicast * group. * @client: SA client * @device: Device associated with the multicast group. * @port_num: Port on the specified device to associate with the multicast * group. * @rec: SA multicast member record specifying group attributes. * @comp_mask: Component mask indicating which group attributes of %rec are * valid. * @gfp_mask: GFP mask for memory allocations. * @callback: User callback invoked once the join operation completes. * @context: User specified context stored with the ib_sa_multicast structure. * * This call initiates a multicast join request with the SA for the specified * multicast group. If the join operation is started successfully, it returns * an ib_sa_multicast structure that is used to track the multicast operation. * Users must free this structure by calling ib_free_multicast, even if the * join operation later fails. (The callback status is non-zero.) * * If the join operation fails; status will be non-zero, with the following * failures possible: * -ETIMEDOUT: The request timed out. * -EIO: An error occurred sending the query. * -EINVAL: The MCMemberRecord values differed from the existing group's. * -ENETRESET: Indicates that an fatal error has occurred on the multicast * group, and the user must rejoin the group to continue using it. */ struct ib_sa_multicast *ib_sa_join_multicast(struct ib_sa_client *client, struct ib_device *device, u32 port_num, struct ib_sa_mcmember_rec *rec, ib_sa_comp_mask comp_mask, gfp_t gfp_mask, int (*callback)(int status, struct ib_sa_multicast *multicast), void *context); /** * ib_free_multicast - Frees the multicast tracking structure, and releases * any reference on the multicast group. * @multicast: Multicast tracking structure allocated by ib_join_multicast. * * This call blocks until the multicast identifier is destroyed. It may * not be called from within the multicast callback; however, returning a non- * zero value from the callback will result in destroying the multicast * tracking structure. */ void ib_sa_free_multicast(struct ib_sa_multicast *multicast); /** * ib_get_mcmember_rec - Looks up a multicast member record by its MGID and * returns it if found. * @device: Device associated with the multicast group. * @port_num: Port on the specified device to associate with the multicast * group. * @mgid: MGID of multicast group. * @rec: Location to copy SA multicast member record. */ int ib_sa_get_mcmember_rec(struct ib_device *device, u32 port_num, union ib_gid *mgid, struct ib_sa_mcmember_rec *rec); /** * ib_init_ah_from_mcmember - Initialize address handle attributes based on * an SA multicast member record. */ int ib_init_ah_from_mcmember(struct ib_device *device, u32 port_num, struct ib_sa_mcmember_rec *rec, struct net_device *ndev, enum ib_gid_type gid_type, struct rdma_ah_attr *ah_attr); int ib_init_ah_attr_from_path(struct ib_device *device, u32 port_num, struct sa_path_rec *rec, struct rdma_ah_attr *ah_attr, const struct ib_gid_attr *sgid_attr); /** * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec * to IB MAD wire format. */ void ib_sa_pack_path(struct sa_path_rec *rec, void *attribute); /** * ib_sa_unpack_path - Convert a path record from MAD format to struct * ib_sa_path_rec. */ void ib_sa_unpack_path(void *attribute, struct sa_path_rec *rec); /* Support GuidInfoRecord */ int ib_sa_guid_info_rec_query(struct ib_sa_client *client, struct ib_device *device, u32 port_num, struct ib_sa_guidinfo_rec *rec, ib_sa_comp_mask comp_mask, u8 method, unsigned long timeout_ms, gfp_t gfp_mask, void (*callback)(int status, struct ib_sa_guidinfo_rec *resp, void *context), void *context, struct ib_sa_query **sa_query); static inline bool sa_path_is_roce(struct sa_path_rec *rec) { return ((rec->rec_type == SA_PATH_REC_TYPE_ROCE_V1) || (rec->rec_type == SA_PATH_REC_TYPE_ROCE_V2)); } static inline bool sa_path_is_opa(struct sa_path_rec *rec) { return (rec->rec_type == SA_PATH_REC_TYPE_OPA); } static inline void sa_path_set_slid(struct sa_path_rec *rec, u32 slid) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) rec->ib.slid = cpu_to_be16(slid); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) rec->opa.slid = cpu_to_be32(slid); } static inline void sa_path_set_dlid(struct sa_path_rec *rec, u32 dlid) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) rec->ib.dlid = cpu_to_be16(dlid); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) rec->opa.dlid = cpu_to_be32(dlid); } static inline void sa_path_set_raw_traffic(struct sa_path_rec *rec, u8 raw_traffic) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) rec->ib.raw_traffic = raw_traffic; else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) rec->opa.raw_traffic = raw_traffic; } static inline __be32 sa_path_get_slid(struct sa_path_rec *rec) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) return htonl(ntohs(rec->ib.slid)); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) return rec->opa.slid; return 0; } static inline __be32 sa_path_get_dlid(struct sa_path_rec *rec) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) return htonl(ntohs(rec->ib.dlid)); else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) return rec->opa.dlid; return 0; } static inline u8 sa_path_get_raw_traffic(struct sa_path_rec *rec) { if (rec->rec_type == SA_PATH_REC_TYPE_IB) return rec->ib.raw_traffic; else if (rec->rec_type == SA_PATH_REC_TYPE_OPA) return rec->opa.raw_traffic; return 0; } static inline void sa_path_set_dmac(struct sa_path_rec *rec, u8 *dmac) { if (sa_path_is_roce(rec)) memcpy(rec->roce.dmac, dmac, ETH_ALEN); } static inline void sa_path_set_dmac_zero(struct sa_path_rec *rec) { if (sa_path_is_roce(rec)) eth_zero_addr(rec->roce.dmac); } static inline u8 *sa_path_get_dmac(struct sa_path_rec *rec) { if (sa_path_is_roce(rec)) return rec->roce.dmac; return NULL; } #endif /* IB_SA_H */ |
| 3207 84420 3577 3649 2203 2206 2200 2205 2203 44854 44869 44840 44849 3643 2754 995 3647 3645 3053 1433 3644 3643 3642 2757 995 429 1013 1438 430 577 978 1013 1013 1011 321 320 3142 3140 3142 3145 3144 3145 49950 84194 84279 49958 70380 3143 3139 3145 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/api.h> #include <asm/fpu/regset.h> #include <asm/fpu/sched.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/msr.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <uapi/asm/kvm.h> #include <linux/hardirq.h> #include <linux/pkeys.h> #include <linux/vmalloc.h> #include "context.h" #include "internal.h" #include "legacy.h" #include "xstate.h" #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> #ifdef CONFIG_X86_64 DEFINE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); DEFINE_PER_CPU(u64, xfd_state); #endif /* The FPU state configuration data for kernel and user space */ struct fpu_state_config fpu_kernel_cfg __ro_after_init; struct fpu_state_config fpu_user_cfg __ro_after_init; /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ struct fpstate init_fpstate __ro_after_init; /* * Track FPU initialization and kernel-mode usage. 'true' means the FPU is * initialized and is not currently being used by the kernel: */ DEFINE_PER_CPU(bool, kernel_fpu_allowed); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); #ifdef CONFIG_X86_DEBUG_FPU struct fpu *x86_task_fpu(struct task_struct *task) { if (WARN_ON_ONCE(task->flags & PF_KTHREAD)) return NULL; return (void *)task + sizeof(*task); } #endif /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? */ bool irq_fpu_usable(void) { if (WARN_ON_ONCE(in_nmi())) return false; /* * Return false in the following cases: * * - FPU is not yet initialized. This can happen only when the call is * coming from CPU onlining, for example for microcode checksumming. * - The kernel is already using the FPU, either because of explicit * nesting (which should never be done), or because of implicit * nesting when a hardirq interrupted a kernel-mode FPU section. * * The single boolean check below handles both cases: */ if (!this_cpu_read(kernel_fpu_allowed)) return false; /* * When not in NMI or hard interrupt context, FPU can be used in: * * - Task context except from within fpregs_lock()'ed critical * regions. * * - Soft interrupt processing context which cannot happen * while in a fpregs_lock()'ed critical region. */ if (!in_hardirq()) return true; /* * In hard interrupt context it's safe when soft interrupts * are enabled, which means the interrupt did not hit in * a fpregs_lock()'ed critical region. */ return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); /* * Track AVX512 state use because it is known to slow the max clock * speed of the core. */ static void update_avx_timestamp(struct fpu *fpu) { #define AVX512_TRACKING_MASK (XFEATURE_MASK_ZMM_Hi256 | XFEATURE_MASK_Hi16_ZMM) if (fpu->fpstate->regs.xsave.header.xfeatures & AVX512_TRACKING_MASK) fpu->avx512_timestamp = jiffies; } /* * Save the FPU register state in fpu->fpstate->regs. The register state is * preserved. * * Must be called with fpregs_lock() held. * * The legacy FNSAVE instruction clears all FPU state unconditionally, so * register state has to be reloaded. That might be a pointless exercise * when the FPU is going to be used by another task right after that. But * this only affects 20+ years old 32bit systems and avoids conditionals all * over the place. * * FXSAVE and all XSAVE variants preserve the FPU register state. */ void save_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { os_xsave(fpu->fpstate); update_avx_timestamp(fpu); return; } if (likely(use_fxsr())) { fxsave(&fpu->fpstate->regs.fxsave); return; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to reload them from the memory state. */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->fpstate->regs.fsave)); frstor(&fpu->fpstate->regs.fsave); } void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask) { /* * AMD K7/K8 and later CPUs up to Zen don't save/restore * FDP/FIP/FOP unless an exception is pending. Clear the x87 state * here by setting it to fixed values. "m" is a random variable * that should be in L1. */ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" "fildl %[addr]" /* set F?P to defined value */ : : [addr] "m" (*fpstate)); } if (use_xsave()) { /* * Dynamically enabled features are enabled in XCR0, but * usage requires also that the corresponding bits in XFD * are cleared. If the bits are set then using a related * instruction will raise #NM. This allows to do the * allocation of the larger FPU buffer lazy from #NM or if * the task has no permission to kill it which would happen * via #UD if the feature is disabled in XCR0. * * XFD state is following the same life time rules as * XSTATE and to restore state correctly XFD has to be * updated before XRSTORS otherwise the component would * stay in or go into init state even if the bits are set * in fpstate::regs::xsave::xfeatures. */ xfd_update_state(fpstate); /* * Restoring state always needs to modify all features * which are in @mask even if the current task cannot use * extended features. * * So fpstate->xfeatures cannot be used here, because then * a feature for which the task has no permission but was * used by the previous task would not go into init state. */ mask = fpu_kernel_cfg.max_features & mask; os_xrstor(fpstate, mask); } else { if (use_fxsr()) fxrstor(&fpstate->regs.fxsave); else frstor(&fpstate->regs.fsave); } } void fpu_reset_from_exception_fixup(void) { restore_fpregs_from_fpstate(&init_fpstate, XFEATURE_MASK_FPSTATE); } #if IS_ENABLED(CONFIG_KVM) static void __fpstate_reset(struct fpstate *fpstate, u64 xfd); static void fpu_lock_guest_permissions(void) { struct fpu_state_perm *fpuperm; u64 perm; if (!IS_ENABLED(CONFIG_X86_64)) return; spin_lock_irq(¤t->sighand->siglock); fpuperm = &x86_task_fpu(current->group_leader)->guest_perm; perm = fpuperm->__state_perm; /* First fpstate allocation locks down permissions. */ WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED); spin_unlock_irq(¤t->sighand->siglock); } bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) { struct fpstate *fpstate; unsigned int size; size = fpu_kernel_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64); fpstate = vzalloc(size); if (!fpstate) return false; /* Leave xfd to 0 (the reset value defined by spec) */ __fpstate_reset(fpstate, 0); fpstate_init_user(fpstate); fpstate->is_valloc = true; fpstate->is_guest = true; gfpu->fpstate = fpstate; gfpu->xfeatures = fpu_kernel_cfg.default_features; /* * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state * to userspace, even when XSAVE is unsupported, so that restoring FPU * state on a different CPU that does support XSAVE can cleanly load * the incoming state using its natural XSAVE. In other words, KVM's * uABI size may be larger than this host's default size. Conversely, * the default size should never be larger than KVM's base uABI size; * all features that can expand the uABI size must be opt-in. */ gfpu->uabi_size = sizeof(struct kvm_xsave); if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size)) gfpu->uabi_size = fpu_user_cfg.default_size; fpu_lock_guest_permissions(); return true; } EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate); void fpu_free_guest_fpstate(struct fpu_guest *gfpu) { struct fpstate *fpstate = gfpu->fpstate; if (!fpstate) return; if (WARN_ON_ONCE(!fpstate->is_valloc || !fpstate->is_guest || fpstate->in_use)) return; gfpu->fpstate = NULL; vfree(fpstate); } EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate); /* * fpu_enable_guest_xfd_features - Check xfeatures against guest perm and enable * @guest_fpu: Pointer to the guest FPU container * @xfeatures: Features requested by guest CPUID * * Enable all dynamic xfeatures according to guest perm and requested CPUID. * * Return: 0 on success, error code otherwise */ int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures) { lockdep_assert_preemption_enabled(); /* Nothing to do if all requested features are already enabled. */ xfeatures &= ~guest_fpu->xfeatures; if (!xfeatures) return 0; return __xfd_enable_feature(xfeatures, guest_fpu); } EXPORT_SYMBOL_GPL(fpu_enable_guest_xfd_features); #ifdef CONFIG_X86_64 void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { fpregs_lock(); guest_fpu->fpstate->xfd = xfd; if (guest_fpu->fpstate->in_use) xfd_update_state(guest_fpu->fpstate); fpregs_unlock(); } EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); /** * fpu_sync_guest_vmexit_xfd_state - Synchronize XFD MSR and software state * * Must be invoked from KVM after a VMEXIT before enabling interrupts when * XFD write emulation is disabled. This is required because the guest can * freely modify XFD and the state at VMEXIT is not guaranteed to be the * same as the state on VMENTER. So software state has to be updated before * any operation which depends on it can take place. * * Note: It can be invoked unconditionally even when write emulation is * enabled for the price of a then pointless MSR read. */ void fpu_sync_guest_vmexit_xfd_state(void) { struct fpstate *fpstate = x86_task_fpu(current)->fpstate; lockdep_assert_irqs_disabled(); if (fpu_state_size_dynamic()) { rdmsrq(MSR_IA32_XFD, fpstate->xfd); __this_cpu_write(xfd_state, fpstate->xfd); } } EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state); #endif /* CONFIG_X86_64 */ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) { struct fpstate *guest_fps = guest_fpu->fpstate; struct fpu *fpu = x86_task_fpu(current); struct fpstate *cur_fps = fpu->fpstate; fpregs_lock(); if (!cur_fps->is_confidential && !test_thread_flag(TIF_NEED_FPU_LOAD)) save_fpregs_to_fpstate(fpu); /* Swap fpstate */ if (enter_guest) { fpu->__task_fpstate = cur_fps; fpu->fpstate = guest_fps; guest_fps->in_use = true; } else { guest_fps->in_use = false; fpu->fpstate = fpu->__task_fpstate; fpu->__task_fpstate = NULL; } cur_fps = fpu->fpstate; if (!cur_fps->is_confidential) { /* Includes XFD update */ restore_fpregs_from_fpstate(cur_fps, XFEATURE_MASK_FPSTATE); } else { /* * XSTATE is restored by firmware from encrypted * memory. Make sure XFD state is correct while * running with guest fpstate */ xfd_update_state(cur_fps); } fpregs_mark_activate(); fpregs_unlock(); return 0; } EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate); void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u64 xfeatures, u32 pkru) { struct fpstate *kstate = gfpu->fpstate; union fpregs_state *ustate = buf; struct membuf mb = { .p = buf, .left = size }; if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru, XSTATE_COPY_XSAVE); } else { memcpy(&ustate->fxsave, &kstate->regs.fxsave, sizeof(ustate->fxsave)); /* Make it restorable on a XSAVE enabled host */ ustate->xsave.header.xfeatures = XFEATURE_MASK_FPSSE; } } EXPORT_SYMBOL_GPL(fpu_copy_guest_fpstate_to_uabi); int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru) { struct fpstate *kstate = gfpu->fpstate; const union fpregs_state *ustate = buf; if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) { if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE) return -EINVAL; if (ustate->fxsave.mxcsr & ~mxcsr_feature_mask) return -EINVAL; memcpy(&kstate->regs.fxsave, &ustate->fxsave, sizeof(ustate->fxsave)); return 0; } if (ustate->xsave.header.xfeatures & ~xcr0) return -EINVAL; /* * Nullify @vpkru to preserve its current value if PKRU's bit isn't set * in the header. KVM's odd ABI is to leave PKRU untouched in this * case (all other components are eventually re-initialized). */ if (!(ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU)) vpkru = NULL; return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); } EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate); #endif /* CONFIG_KVM */ void kernel_fpu_begin_mask(unsigned int kfpu_mask) { if (!irqs_disabled()) fpregs_lock(); WARN_ON_FPU(!irq_fpu_usable()); /* Toggle kernel_fpu_allowed to false: */ WARN_ON_FPU(!this_cpu_read(kernel_fpu_allowed)); this_cpu_write(kernel_fpu_allowed, false); if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); save_fpregs_to_fpstate(x86_task_fpu(current)); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { /* Toggle kernel_fpu_allowed back to true: */ WARN_ON_FPU(this_cpu_read(kernel_fpu_allowed)); this_cpu_write(kernel_fpu_allowed, true); if (!irqs_disabled()) fpregs_unlock(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Sync the FPU register state to current's memory register state when the * current task owns the FPU. The hardware register state is preserved. */ void fpu_sync_fpstate(struct fpu *fpu) { WARN_ON_FPU(fpu != x86_task_fpu(current)); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) save_fpregs_to_fpstate(fpu); trace_x86_fpu_after_save(fpu); fpregs_unlock(); } static inline unsigned int init_fpstate_copy_size(void) { if (!use_xsave()) return fpu_kernel_cfg.default_size; /* XSAVE(S) just needs the legacy and the xstate header part */ return sizeof(init_fpstate.regs.xsave); } static inline void fpstate_init_fxstate(struct fpstate *fpstate) { fpstate->regs.fxsave.cwd = 0x37f; fpstate->regs.fxsave.mxcsr = MXCSR_DEFAULT; } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fpstate *fpstate) { fpstate->regs.fsave.cwd = 0xffff037fu; fpstate->regs.fsave.swd = 0xffff0000u; fpstate->regs.fsave.twd = 0xffffffffu; fpstate->regs.fsave.fos = 0xffff0000u; } /* * Used in two places: * 1) Early boot to setup init_fpstate for non XSAVE systems * 2) fpu_alloc_guest_fpstate() which is invoked from KVM */ void fpstate_init_user(struct fpstate *fpstate) { if (!cpu_feature_enabled(X86_FEATURE_FPU)) { fpstate_init_soft(&fpstate->regs.soft); return; } xstate_init_xcomp_bv(&fpstate->regs.xsave, fpstate->xfeatures); if (cpu_feature_enabled(X86_FEATURE_FXSR)) fpstate_init_fxstate(fpstate); else fpstate_init_fstate(fpstate); } static void __fpstate_reset(struct fpstate *fpstate, u64 xfd) { /* Initialize sizes and feature masks */ fpstate->size = fpu_kernel_cfg.default_size; fpstate->user_size = fpu_user_cfg.default_size; fpstate->xfeatures = fpu_kernel_cfg.default_features; fpstate->user_xfeatures = fpu_user_cfg.default_features; fpstate->xfd = xfd; } void fpstate_reset(struct fpu *fpu) { /* Set the fpstate pointer to the default fpstate */ fpu->fpstate = &fpu->__fpstate; __fpstate_reset(fpu->fpstate, init_fpstate.xfd); /* Initialize the permission related info in fpu */ fpu->perm.__state_perm = fpu_kernel_cfg.default_features; fpu->perm.__state_size = fpu_kernel_cfg.default_size; fpu->perm.__user_state_size = fpu_user_cfg.default_size; /* Same defaults for guests */ fpu->guest_perm = fpu->perm; } static inline void fpu_inherit_perms(struct fpu *dst_fpu) { if (fpu_state_size_dynamic()) { struct fpu *src_fpu = x86_task_fpu(current->group_leader); spin_lock_irq(¤t->sighand->siglock); /* Fork also inherits the permissions of the parent */ dst_fpu->perm = src_fpu->perm; dst_fpu->guest_perm = src_fpu->guest_perm; spin_unlock_irq(¤t->sighand->siglock); } } /* A passed ssp of zero will not cause any update */ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp) { #ifdef CONFIG_X86_USER_SHADOW_STACK struct cet_user_state *xstate; /* If ssp update is not needed. */ if (!ssp) return 0; xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave, XFEATURE_CET_USER); /* * If there is a non-zero ssp, then 'dst' must be configured with a shadow * stack and the fpu state should be up to date since it was just copied * from the parent in fpu_clone(). So there must be a valid non-init CET * state location in the buffer. */ if (WARN_ON_ONCE(!xstate)) return 1; xstate->user_ssp = (u64)ssp; #endif return 0; } /* Clone current's FPU state on fork */ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal, unsigned long ssp) { /* * We allocate the new FPU structure right after the end of the task struct. * task allocation size already took this into account. * * This is safe because task_struct size is a multiple of cacheline size, * thus x86_task_fpu() will always be cacheline aligned as well. */ struct fpu *dst_fpu = (void *)dst + sizeof(*dst); BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0); /* The new task's FPU state cannot be valid in the hardware. */ dst_fpu->last_cpu = -1; fpstate_reset(dst_fpu); if (!cpu_feature_enabled(X86_FEATURE_FPU)) return 0; /* * Enforce reload for user space tasks and prevent kernel threads * from trying to save the FPU registers on context switch. */ set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); /* * No FPU state inheritance for kernel threads and IO * worker threads. */ if (minimal) { /* Clear out the minimal state */ memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size()); return 0; } /* * If a new feature is added, ensure all dynamic features are * caller-saved from here! */ BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA); /* * Save the default portion of the current FPU state into the * clone. Assume all dynamic features to be defined as caller- * saved, which enables skipping both the expansion of fpstate * and the copying of any dynamic state. * * Do not use memcpy() when TIF_NEED_FPU_LOAD is set because * copying is not valid when current uses non-default states. */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); save_fpregs_to_fpstate(dst_fpu); fpregs_unlock(); if (!(clone_flags & CLONE_THREAD)) fpu_inherit_perms(dst_fpu); /* * Children never inherit PASID state. * Force it to have its init value: */ if (use_xsave()) dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID; /* * Update shadow stack pointer, in case it changed during clone. */ if (update_fpu_shstk(dst, ssp)) return 1; trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * While struct fpu is no longer part of struct thread_struct, it is still * allocated after struct task_struct in the "task_struct" kmem cache. But * since FPU is expected to be part of struct thread_struct, we have to * adjust for it here. */ void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { /* The allocation follows struct task_struct. */ *offset = sizeof(struct task_struct) - offsetof(struct task_struct, thread); *offset += offsetof(struct fpu, __fpstate.regs); *size = fpu_kernel_cfg.default_size; } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct task_struct *tsk) { struct fpu *fpu; if (test_tsk_thread_flag(tsk, TIF_NEED_FPU_LOAD)) return; fpu = x86_task_fpu(tsk); preempt_disable(); if (fpu == x86_task_fpu(current)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void restore_fpregs_from_init_fpstate(u64 features_mask) { if (use_xsave()) os_xrstor(&init_fpstate, features_mask); else if (use_fxsr()) fxrstor(&init_fpstate.regs.fxsave); else frstor(&init_fpstate.regs.fsave); pkru_write_default(); } /* * Reset current->fpu memory state to the init values. */ static void fpu_reset_fpstate_regs(void) { struct fpu *fpu = x86_task_fpu(current); fpregs_lock(); __fpu_invalidate_fpregs_state(fpu); /* * This does not change the actual hardware registers. It just * resets the memory image and sets TIF_NEED_FPU_LOAD so a * subsequent return to usermode will reload the registers from the * task's memory image. * * Do not use fpstate_init() here. Just copy init_fpstate which has * the correct content already except for PKRU. * * PKRU handling does not rely on the xstate when restoring for * user space as PKRU is eagerly written in switch_to() and * flush_thread(). */ memcpy(&fpu->fpstate->regs, &init_fpstate.regs, init_fpstate_copy_size()); set_thread_flag(TIF_NEED_FPU_LOAD); fpregs_unlock(); } /* * Reset current's user FPU states to the init states. current's * supervisor states, if any, are not modified by this function. The * caller guarantees that the XSTATE header in memory is intact. */ void fpu__clear_user_states(struct fpu *fpu) { WARN_ON_FPU(fpu != x86_task_fpu(current)); fpregs_lock(); if (!cpu_feature_enabled(X86_FEATURE_FPU)) { fpu_reset_fpstate_regs(); fpregs_unlock(); return; } /* * Ensure that current's supervisor states are loaded into their * corresponding registers. */ if (xfeatures_mask_supervisor() && !fpregs_state_valid(fpu, smp_processor_id())) os_xrstor_supervisor(fpu->fpstate); /* Reset user states in registers. */ restore_fpregs_from_init_fpstate(XFEATURE_MASK_USER_RESTORE); /* * Now all FPU registers have their desired values. Inform the FPU * state machine that current's FPU registers are in the hardware * registers. The memory image does not need to be updated because * any operation relying on it has to save the registers first when * current's FPU is marked active. */ fpregs_mark_activate(); fpregs_unlock(); } void fpu_flush_thread(void) { fpstate_reset(x86_task_fpu(current)); fpu_reset_fpstate_regs(); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; fpregs_restore_userregs(); } EXPORT_SYMBOL_GPL(switch_fpu_return); void fpregs_lock_and_load(void) { /* * fpregs_lock() only disables preemption (mostly). So modifying state * in an interrupt could screw up some in progress fpregs operation. * Warn about it. */ WARN_ON_ONCE(!irq_fpu_usable()); WARN_ON_ONCE(current->flags & PF_KTHREAD); fpregs_lock(); fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); } #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = x86_task_fpu(current); if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = x86_task_fpu(current); fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->fpstate->regs.fxsave.cwd; swd = fpu->fpstate->regs.fxsave.swd; } else { cwd = (unsigned short)fpu->fpstate->regs.fsave.cwd; swd = (unsigned short)fpu->fpstate->regs.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->fpstate->regs.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; } /* * Initialize register state that may prevent from entering low-power idle. * This function will be invoked from the cpuidle driver only when needed. */ noinstr void fpu_idle_fpregs(void) { /* Note: AMX_TILE being enabled implies XGETBV1 support */ if (cpu_feature_enabled(X86_FEATURE_AMX_TILE) && (xfeatures_in_use() & XFEATURE_MASK_XTILE)) { tile_release(); __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } } |
| 2357 142 2254 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright(c) 2017 Intel Corporation. All rights reserved. * * This code is based in part on work published here: * * https://github.com/IAIK/KAISER * * The original work was written by and signed off by for the Linux * kernel by: * * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at> * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at> * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at> * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at> * * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com> * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and * Andy Lutomirsky <luto@amacapital.net> */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/types.h> #include <linux/bug.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/cpu.h> #include <asm/cpufeature.h> #include <asm/hypervisor.h> #include <asm/vsyscall.h> #include <asm/cmdline.h> #include <asm/pti.h> #include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/sections.h> #include <asm/set_memory.h> #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt /* Backporting helper */ #ifndef __GFP_NOTRACK #define __GFP_NOTRACK 0 #endif /* * Define the page-table levels we clone for user-space on 32 * and 64 bit. */ #ifdef CONFIG_X86_64 #define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PMD #else #define PTI_LEVEL_KERNEL_IMAGE PTI_CLONE_PTE #endif static void __init pti_print_if_insecure(const char *reason) { if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) pr_info("%s\n", reason); } static void __init pti_print_if_secure(const char *reason) { if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) pr_info("%s\n", reason); } /* Assume mode is auto unless overridden via cmdline below. */ static enum pti_mode { PTI_AUTO = 0, PTI_FORCE_OFF, PTI_FORCE_ON } pti_mode; void __init pti_check_boottime_disable(void) { if (hypervisor_is_type(X86_HYPER_XEN_PV)) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on XEN PV."); return; } if (cpu_mitigations_off()) pti_mode = PTI_FORCE_OFF; if (pti_mode == PTI_FORCE_OFF) { pti_print_if_insecure("disabled on command line."); return; } if (pti_mode == PTI_FORCE_ON) pti_print_if_secure("force enabled on command line."); if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return; setup_force_cpu_cap(X86_FEATURE_PTI); } static int __init pti_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) pti_mode = PTI_FORCE_OFF; else if (!strcmp(arg, "on")) pti_mode = PTI_FORCE_ON; else if (!strcmp(arg, "auto")) pti_mode = PTI_AUTO; else return -EINVAL; return 0; } early_param("pti", pti_parse_cmdline); static int __init pti_parse_cmdline_nopti(char *arg) { pti_mode = PTI_FORCE_OFF; return 0; } early_param("nopti", pti_parse_cmdline_nopti); pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { /* * Changes to the high (kernel) portion of the kernelmode page * tables are not automatically propagated to the usermode tables. * * Users should keep in mind that, unlike the kernelmode tables, * there is no vmalloc_fault equivalent for the usermode tables. * Top-level entries added to init_mm's usermode pgd after boot * will not be automatically propagated to other mms. */ if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW)) return pgd; /* * The user page tables get the full PGD, accessible from * userspace: */ kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd; /* * If this is normal user memory, make it NX in the kernel * pagetables so that, if we somehow screw up and return to * usermode with the kernel CR3 loaded, we'll get a page fault * instead of allowing user code to execute with the wrong CR3. * * As exceptions, we don't set NX if: * - _PAGE_USER is not set. This could be an executable * EFI runtime mapping or something similar, and the kernel * may execute from it * - we don't have NX support * - we're clearing the PGD (i.e. the new pgd is not present). */ if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) && (__supported_pte_mask & _PAGE_NX)) pgd.pgd |= _PAGE_NX; /* return the copy of the PGD we want the kernel to use: */ return pgd; } /* * Walk the user copy of the page tables (optionally) trying to allocate * page table pages on the way down. * * Returns a pointer to a P4D on success, or NULL on failure. */ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) { pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (address < PAGE_OFFSET) { WARN_ONCE(1, "attempt to walk user address\n"); return NULL; } if (pgd_none(*pgd)) { unsigned long new_p4d_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_p4d_page)) return NULL; set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); } BUILD_BUG_ON(pgd_leaf(*pgd)); return p4d_offset(pgd, address); } /* * Walk the user copy of the page tables (optionally) trying to allocate * page table pages on the way down. * * Returns a pointer to a PMD on success, or NULL on failure. */ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); p4d_t *p4d; pud_t *pud; p4d = pti_user_pagetable_walk_p4d(address); if (!p4d) return NULL; BUILD_BUG_ON(p4d_leaf(*p4d)); if (p4d_none(*p4d)) { unsigned long new_pud_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pud_page)) return NULL; set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); } pud = pud_offset(p4d, address); /* The user page tables do not use large mappings: */ if (pud_leaf(*pud)) { WARN_ON(1); return NULL; } if (pud_none(*pud)) { unsigned long new_pmd_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pmd_page)) return NULL; set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); } return pmd_offset(pud, address); } /* * Walk the shadow copy of the page tables (optionally) trying to allocate * page table pages on the way down. Does not support large pages. * * Note: this is only used when mapping *new* kernel data into the * user/shadow page tables. It is never used for userspace data. * * Returns a pointer to a PTE on success, or NULL on failure. */ static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; pte_t *pte; pmd = pti_user_pagetable_walk_pmd(address); if (!pmd) return NULL; /* Large PMD mapping found */ if (pmd_leaf(*pmd)) { /* Clear the PMD if we hit a large mapping from the first round */ if (late_text) { set_pmd(pmd, __pmd(0)); } else { WARN_ON_ONCE(1); return NULL; } } if (pmd_none(*pmd)) { unsigned long new_pte_page = __get_free_page(gfp); if (!new_pte_page) return NULL; set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); } pte = pte_offset_kernel(pmd, address); if (pte_flags(*pte) & _PAGE_USER) { WARN_ONCE(1, "attempt to walk to user pte\n"); return NULL; } return pte; } #ifdef CONFIG_X86_VSYSCALL_EMULATION static void __init pti_setup_vsyscall(void) { pte_t *pte, *target_pte; unsigned int level; pte = lookup_address(VSYSCALL_ADDR, &level); if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) return; target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false); if (WARN_ON(!target_pte)) return; *target_pte = *pte; set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir)); } #else static void __init pti_setup_vsyscall(void) { } #endif enum pti_clone_level { PTI_CLONE_PMD, PTI_CLONE_PTE, }; static void pti_clone_pgtable(unsigned long start, unsigned long end, enum pti_clone_level level, bool late_text) { unsigned long addr; /* * Clone the populated PMDs which cover start to end. These PMD areas * can have holes. */ for (addr = start; addr < end;) { pte_t *pte, *target_pte; pmd_t *pmd, *target_pmd; pgd_t *pgd; p4d_t *p4d; pud_t *pud; /* Overflow check */ if (addr < start) break; pgd = pgd_offset_k(addr); if (WARN_ON(pgd_none(*pgd))) return; p4d = p4d_offset(pgd, addr); if (WARN_ON(p4d_none(*p4d))) return; pud = pud_offset(p4d, addr); if (pud_none(*pud)) { WARN_ON_ONCE(addr & ~PUD_MASK); addr = round_up(addr + 1, PUD_SIZE); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { WARN_ON_ONCE(addr & ~PMD_MASK); addr = round_up(addr + 1, PMD_SIZE); continue; } if (pmd_leaf(*pmd) || level == PTI_CLONE_PMD) { target_pmd = pti_user_pagetable_walk_pmd(addr); if (WARN_ON(!target_pmd)) return; /* * Only clone present PMDs. This ensures only setting * _PAGE_GLOBAL on present PMDs. This should only be * called on well-known addresses anyway, so a non- * present PMD would be a surprise. */ if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT))) return; /* * Setting 'target_pmd' below creates a mapping in both * the user and kernel page tables. It is effectively * global, so set it as global in both copies. Note: * the X86_FEATURE_PGE check is not _required_ because * the CPU ignores _PAGE_GLOBAL when PGE is not * supported. The check keeps consistency with * code that only set this bit when supported. */ if (boot_cpu_has(X86_FEATURE_PGE)) *pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL); /* * Copy the PMD. That is, the kernelmode and usermode * tables will share the last-level page tables of this * address range */ *target_pmd = *pmd; addr = round_up(addr + 1, PMD_SIZE); } else if (level == PTI_CLONE_PTE) { /* Walk the page-table down to the pte level */ pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { addr = round_up(addr + 1, PAGE_SIZE); continue; } /* Only clone present PTEs */ if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT))) return; /* Allocate PTE in the user page-table */ target_pte = pti_user_pagetable_walk_pte(addr, late_text); if (WARN_ON(!target_pte)) return; /* Set GLOBAL bit in both PTEs */ if (boot_cpu_has(X86_FEATURE_PGE)) *pte = pte_set_flags(*pte, _PAGE_GLOBAL); /* Clone the PTE */ *target_pte = *pte; addr = round_up(addr + 1, PAGE_SIZE); } else { BUG(); } } } #ifdef CONFIG_X86_64 /* * Clone a single p4d (i.e. a top-level entry on 4-level systems and a * next-level entry on 5-level systems. */ static void __init pti_clone_p4d(unsigned long addr) { p4d_t *kernel_p4d, *user_p4d; pgd_t *kernel_pgd; user_p4d = pti_user_pagetable_walk_p4d(addr); if (!user_p4d) return; kernel_pgd = pgd_offset_k(addr); kernel_p4d = p4d_offset(kernel_pgd, addr); *user_p4d = *kernel_p4d; } /* * Clone the CPU_ENTRY_AREA and associated data into the user space visible * page table. */ static void __init pti_clone_user_shared(void) { unsigned int cpu; pti_clone_p4d(CPU_ENTRY_AREA_BASE); for_each_possible_cpu(cpu) { /* * The SYSCALL64 entry code needs one word of scratch space * in which to spill a register. It lives in the sp2 slot * of the CPU's TSS. * * This is done for all possible CPUs during boot to ensure * that it's propagated to all mms. */ unsigned long va = (unsigned long)&per_cpu(cpu_tss_rw, cpu); phys_addr_t pa = per_cpu_ptr_to_phys((void *)va); pte_t *target_pte; target_pte = pti_user_pagetable_walk_pte(va, false); if (WARN_ON(!target_pte)) return; *target_pte = pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL); } } #else /* CONFIG_X86_64 */ /* * On 32 bit PAE systems with 1GB of Kernel address space there is only * one pgd/p4d for the whole kernel. Cloning that would map the whole * address space into the user page-tables, making PTI useless. So clone * the page-table on the PMD level to prevent that. */ static void __init pti_clone_user_shared(void) { unsigned long start, end; start = CPU_ENTRY_AREA_BASE; end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES); pti_clone_pgtable(start, end, PTI_CLONE_PMD, false); } #endif /* CONFIG_X86_64 */ /* * Clone the ESPFIX P4D into the user space visible page table */ static void __init pti_setup_espfix64(void) { #ifdef CONFIG_X86_ESPFIX64 pti_clone_p4d(ESPFIX_BASE_ADDR); #endif } /* * Clone the populated PMDs of the entry text and force it RO. */ static void pti_clone_entry_text(bool late) { pti_clone_pgtable((unsigned long) __entry_text_start, (unsigned long) __entry_text_end, PTI_LEVEL_KERNEL_IMAGE, late); } /* * Global pages and PCIDs are both ways to make kernel TLB entries * live longer, reduce TLB misses and improve kernel performance. * But, leaving all kernel text Global makes it potentially accessible * to Meltdown-style attacks which make it trivial to find gadgets or * defeat KASLR. * * Only use global pages when it is really worth it. */ static inline bool pti_kernel_image_global_ok(void) { /* * Systems with PCIDs get little benefit from global * kernel text and are not worth the downsides. */ if (cpu_feature_enabled(X86_FEATURE_PCID)) return false; /* * Only do global kernel image for pti=auto. Do the most * secure thing (not global) if pti=on specified. */ if (pti_mode != PTI_AUTO) return false; /* * K8 may not tolerate the cleared _PAGE_RW on the userspace * global kernel image pages. Do the safe thing (disable * global kernel image). This is unlikely to ever be * noticed because PTI is disabled by default on AMD CPUs. */ if (boot_cpu_has(X86_FEATURE_K8)) return false; /* * RANDSTRUCT derives its hardening benefits from the * attacker's lack of knowledge about the layout of kernel * data structures. Keep the kernel image non-global in * cases where RANDSTRUCT is in use to help keep the layout a * secret. */ if (IS_ENABLED(CONFIG_RANDSTRUCT)) return false; return true; } /* * For some configurations, map all of kernel text into the user page * tables. This reduces TLB misses, especially on non-PCID systems. */ static void pti_clone_kernel_text(void) { /* * rodata is part of the kernel image and is normally * readable on the filesystem or on the web. But, do not * clone the areas past rodata, they might contain secrets. */ unsigned long start = PFN_ALIGN(_text); unsigned long end_clone = (unsigned long)__end_rodata_aligned; unsigned long end_global = PFN_ALIGN((unsigned long)_etext); if (!pti_kernel_image_global_ok()) return; pr_debug("mapping partial kernel image into user address space\n"); /* * Note that this will undo _some_ of the work that * pti_set_kernel_image_nonglobal() did to clear the * global bit. */ pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false); /* * pti_clone_pgtable() will set the global bit in any PMDs * that it clones, but we also need to get any PTEs in * the last level for areas that are not huge-page-aligned. */ /* Set the global bit for normal non-__init kernel text: */ set_memory_global(start, (end_global - start) >> PAGE_SHIFT); } static void pti_set_kernel_image_nonglobal(void) { /* * The identity map is created with PMDs, regardless of the * actual length of the kernel. We need to clear * _PAGE_GLOBAL up to a PMD boundary, not just to the end * of the image. */ unsigned long start = PFN_ALIGN(_text); unsigned long end = ALIGN((unsigned long)_end, PMD_SIZE); /* * This clears _PAGE_GLOBAL from the entire kernel image. * pti_clone_kernel_text() map put _PAGE_GLOBAL back for * areas that are mapped to userspace. */ set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT); } /* * Initialize kernel page table isolation */ void __init pti_init(void) { if (!boot_cpu_has(X86_FEATURE_PTI)) return; pr_info("enabled\n"); #ifdef CONFIG_X86_32 /* * We check for X86_FEATURE_PCID here. But the init-code will * clear the feature flag on 32 bit because the feature is not * supported on 32 bit anyway. To print the warning we need to * check with cpuid directly again. */ if (cpuid_ecx(0x1) & BIT(17)) { /* Use printk to work around pr_fmt() */ printk(KERN_WARNING "\n"); printk(KERN_WARNING "************************************************************\n"); printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); printk(KERN_WARNING "** **\n"); printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n"); printk(KERN_WARNING "** Your performance will increase dramatically if you **\n"); printk(KERN_WARNING "** switch to a 64-bit kernel! **\n"); printk(KERN_WARNING "** **\n"); printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! **\n"); printk(KERN_WARNING "************************************************************\n"); } #endif pti_clone_user_shared(); /* Undo all global bits from the init pagetables in head_64.S: */ pti_set_kernel_image_nonglobal(); /* Replace some of the global bits just for shared entry text: */ /* * This is very early in boot. Device and Late initcalls can do * modprobe before free_initmem() and mark_readonly(). This * pti_clone_entry_text() allows those user-mode-helpers to function, * but notably the text is still RW. */ pti_clone_entry_text(false); pti_setup_espfix64(); pti_setup_vsyscall(); } /* * Finalize the kernel mappings in the userspace page-table. Some of the * mappings for the kernel image might have changed since pti_init() * cloned them. This is because parts of the kernel image have been * mapped RO and/or NX. These changes need to be cloned again to the * userspace page-table. */ void pti_finalize(void) { if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* * This is after free_initmem() (all initcalls are done) and we've done * mark_readonly(). Text is now NX which might've split some PMDs * relative to the early clone. */ pti_clone_entry_text(true); pti_clone_kernel_text(); debug_checkwx_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/include/linux/sunrpc/addr.h * * Various routines for copying and comparing sockaddrs and for * converting them to and from presentation format. */ #ifndef _LINUX_SUNRPC_ADDR_H #define _LINUX_SUNRPC_ADDR_H #include <linux/socket.h> #include <linux/in.h> #include <linux/in6.h> #include <net/ipv6.h> size_t rpc_ntop(const struct sockaddr *, char *, const size_t); size_t rpc_pton(struct net *, const char *, const size_t, struct sockaddr *, const size_t); char * rpc_sockaddr2uaddr(const struct sockaddr *, gfp_t); size_t rpc_uaddr2sockaddr(struct net *, const char *, const size_t, struct sockaddr *, const size_t); static inline unsigned short rpc_get_port(const struct sockaddr *sap) { switch (sap->sa_family) { case AF_INET: return ntohs(((struct sockaddr_in *)sap)->sin_port); case AF_INET6: return ntohs(((struct sockaddr_in6 *)sap)->sin6_port); } return 0; } static inline void rpc_set_port(struct sockaddr *sap, const unsigned short port) { switch (sap->sa_family) { case AF_INET: ((struct sockaddr_in *)sap)->sin_port = htons(port); break; case AF_INET6: ((struct sockaddr_in6 *)sap)->sin6_port = htons(port); break; } } #define IPV6_SCOPE_DELIMITER '%' #define IPV6_SCOPE_ID_LEN sizeof("%nnnnnnnnnn") static inline bool rpc_cmp_addr4(const struct sockaddr *sap1, const struct sockaddr *sap2) { const struct sockaddr_in *sin1 = (const struct sockaddr_in *)sap1; const struct sockaddr_in *sin2 = (const struct sockaddr_in *)sap2; return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr; } static inline bool __rpc_copy_addr4(struct sockaddr *dst, const struct sockaddr *src) { const struct sockaddr_in *ssin = (struct sockaddr_in *) src; struct sockaddr_in *dsin = (struct sockaddr_in *) dst; dsin->sin_family = ssin->sin_family; dsin->sin_addr.s_addr = ssin->sin_addr.s_addr; return true; } #if IS_ENABLED(CONFIG_IPV6) static inline bool rpc_cmp_addr6(const struct sockaddr *sap1, const struct sockaddr *sap2) { const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1; const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2; if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) return false; else if (ipv6_addr_type(&sin1->sin6_addr) & IPV6_ADDR_LINKLOCAL) return sin1->sin6_scope_id == sin2->sin6_scope_id; return true; } static inline bool __rpc_copy_addr6(struct sockaddr *dst, const struct sockaddr *src) { const struct sockaddr_in6 *ssin6 = (const struct sockaddr_in6 *) src; struct sockaddr_in6 *dsin6 = (struct sockaddr_in6 *) dst; dsin6->sin6_family = ssin6->sin6_family; dsin6->sin6_addr = ssin6->sin6_addr; dsin6->sin6_scope_id = ssin6->sin6_scope_id; return true; } #else /* !(IS_ENABLED(CONFIG_IPV6) */ static inline bool rpc_cmp_addr6(const struct sockaddr *sap1, const struct sockaddr *sap2) { return false; } static inline bool __rpc_copy_addr6(struct sockaddr *dst, const struct sockaddr *src) { return false; } #endif /* !(IS_ENABLED(CONFIG_IPV6) */ /** * rpc_cmp_addr - compare the address portion of two sockaddrs. * @sap1: first sockaddr * @sap2: second sockaddr * * Just compares the family and address portion. Ignores port, but * compares the scope if it's a link-local address. * * Returns true if the addrs are equal, false if they aren't. */ static inline bool rpc_cmp_addr(const struct sockaddr *sap1, const struct sockaddr *sap2) { if (sap1->sa_family == sap2->sa_family) { switch (sap1->sa_family) { case AF_INET: return rpc_cmp_addr4(sap1, sap2); case AF_INET6: return rpc_cmp_addr6(sap1, sap2); } } return false; } /** * rpc_cmp_addr_port - compare the address and port number of two sockaddrs. * @sap1: first sockaddr * @sap2: second sockaddr */ static inline bool rpc_cmp_addr_port(const struct sockaddr *sap1, const struct sockaddr *sap2) { if (!rpc_cmp_addr(sap1, sap2)) return false; return rpc_get_port(sap1) == rpc_get_port(sap2); } /** * rpc_copy_addr - copy the address portion of one sockaddr to another * @dst: destination sockaddr * @src: source sockaddr * * Just copies the address portion and family. Ignores port, scope, etc. * Caller is responsible for making certain that dst is large enough to hold * the address in src. Returns true if address family is supported. Returns * false otherwise. */ static inline bool rpc_copy_addr(struct sockaddr *dst, const struct sockaddr *src) { switch (src->sa_family) { case AF_INET: return __rpc_copy_addr4(dst, src); case AF_INET6: return __rpc_copy_addr6(dst, src); } return false; } /** * rpc_get_scope_id - return scopeid for a given sockaddr * @sa: sockaddr to get scopeid from * * Returns the value of the sin6_scope_id for AF_INET6 addrs, or 0 if * not an AF_INET6 address. */ static inline u32 rpc_get_scope_id(const struct sockaddr *sa) { if (sa->sa_family != AF_INET6) return 0; return ((struct sockaddr_in6 *) sa)->sin6_scope_id; } #endif /* _LINUX_SUNRPC_ADDR_H */ |
| 8 2 6 8 4 3 2 2 122 122 5 27 7 137 42 42 1 9 28 5 1 1 1 9 8 7 5 1 1 13 13 1 1 5 169 1 65 108 162 127 28 6 154 144 17 162 20 1 1 1 1 4 5 1 1 1 1 1 1 1 4 1 1 1 1 10 10 11 11 2 8 2 1 1 1 40 40 14 27 14 27 40 40 41 1 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* AF_RXRPC implementation * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/poll.h> #include <linux/proc_fs.h> #include <linux/key-type.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/af_rxrpc.h> #define CREATE_TRACE_POINTS #include "ar-internal.h" MODULE_DESCRIPTION("RxRPC network protocol"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_RXRPC); unsigned int rxrpc_debug; // = RXRPC_DEBUG_KPROTO; module_param_named(debug, rxrpc_debug, uint, 0644); MODULE_PARM_DESC(debug, "RxRPC debugging mask"); static struct proto rxrpc_proto; static const struct proto_ops rxrpc_rpc_ops; /* current debugging ID */ atomic_t rxrpc_debug_id; EXPORT_SYMBOL(rxrpc_debug_id); /* count of skbs currently in use */ atomic_t rxrpc_n_rx_skbs; struct workqueue_struct *rxrpc_workqueue; static void rxrpc_sock_destructor(struct sock *); /* * see if an RxRPC socket is currently writable */ static inline int rxrpc_writable(struct sock *sk) { return refcount_read(&sk->sk_wmem_alloc) < (size_t) sk->sk_sndbuf; } /* * wait for write bufferage to become available */ static void rxrpc_write_space(struct sock *sk) { _enter("%p", sk); rcu_read_lock(); if (rxrpc_writable(sk)) { struct socket_wq *wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible(&wq->wait); sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); } /* * validate an RxRPC address */ static int rxrpc_validate_address(struct rxrpc_sock *rx, struct sockaddr_rxrpc *srx, int len) { unsigned int tail; if (len < sizeof(struct sockaddr_rxrpc)) return -EINVAL; if (srx->srx_family != AF_RXRPC) return -EAFNOSUPPORT; if (srx->transport_type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; len -= offsetof(struct sockaddr_rxrpc, transport); if (srx->transport_len < sizeof(sa_family_t) || srx->transport_len > len) return -EINVAL; switch (srx->transport.family) { case AF_INET: if (rx->family != AF_INET && rx->family != AF_INET6) return -EAFNOSUPPORT; if (srx->transport_len < sizeof(struct sockaddr_in)) return -EINVAL; tail = offsetof(struct sockaddr_rxrpc, transport.sin.__pad); break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: if (rx->family != AF_INET6) return -EAFNOSUPPORT; if (srx->transport_len < sizeof(struct sockaddr_in6)) return -EINVAL; tail = offsetof(struct sockaddr_rxrpc, transport) + sizeof(struct sockaddr_in6); break; #endif default: return -EAFNOSUPPORT; } if (tail < len) memset((void *)srx + tail, 0, len - tail); _debug("INET: %pISp", &srx->transport); return 0; } /* * bind a local address to an RxRPC socket */ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) { struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr; struct rxrpc_local *local; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); u16 service_id; int ret; _enter("%p,%p,%d", rx, saddr, len); ret = rxrpc_validate_address(rx, srx, len); if (ret < 0) goto error; service_id = srx->srx_service; lock_sock(&rx->sk); switch (rx->sk.sk_state) { case RXRPC_UNBOUND: rx->srx = *srx; local = rxrpc_lookup_local(sock_net(&rx->sk), &rx->srx); if (IS_ERR(local)) { ret = PTR_ERR(local); goto error_unlock; } if (service_id) { write_lock(&local->services_lock); if (local->service) goto service_in_use; rx->local = local; local->service = rx; write_unlock(&local->services_lock); rx->sk.sk_state = RXRPC_SERVER_BOUND; } else { rx->local = local; rx->sk.sk_state = RXRPC_CLIENT_BOUND; } break; case RXRPC_SERVER_BOUND: ret = -EINVAL; if (service_id == 0) goto error_unlock; ret = -EADDRINUSE; if (service_id == rx->srx.srx_service) goto error_unlock; ret = -EINVAL; srx->srx_service = rx->srx.srx_service; if (memcmp(srx, &rx->srx, sizeof(*srx)) != 0) goto error_unlock; rx->second_service = service_id; rx->sk.sk_state = RXRPC_SERVER_BOUND2; break; default: ret = -EINVAL; goto error_unlock; } release_sock(&rx->sk); _leave(" = 0"); return 0; service_in_use: write_unlock(&local->services_lock); rxrpc_unuse_local(local, rxrpc_local_unuse_bind); rxrpc_put_local(local, rxrpc_local_put_bind); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); error: _leave(" = %d", ret); return ret; } /* * set the number of pending calls permitted on a listening socket */ static int rxrpc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct rxrpc_sock *rx = rxrpc_sk(sk); unsigned int max, old; int ret; _enter("%p,%d", rx, backlog); lock_sock(&rx->sk); switch (rx->sk.sk_state) { case RXRPC_UNBOUND: ret = -EADDRNOTAVAIL; break; case RXRPC_SERVER_BOUND: case RXRPC_SERVER_BOUND2: ASSERT(rx->local != NULL); max = READ_ONCE(rxrpc_max_backlog); ret = -EINVAL; if (backlog == INT_MAX) backlog = max; else if (backlog < 0 || backlog > max) break; old = sk->sk_max_ack_backlog; sk->sk_max_ack_backlog = backlog; ret = rxrpc_service_prealloc(rx, GFP_KERNEL); if (ret == 0) rx->sk.sk_state = RXRPC_SERVER_LISTENING; else sk->sk_max_ack_backlog = old; break; case RXRPC_SERVER_LISTENING: if (backlog == 0) { rx->sk.sk_state = RXRPC_SERVER_LISTEN_DISABLED; sk->sk_max_ack_backlog = 0; rxrpc_discard_prealloc(rx); ret = 0; break; } fallthrough; default: ret = -EBUSY; break; } release_sock(&rx->sk); _leave(" = %d", ret); return ret; } /** * rxrpc_kernel_lookup_peer - Obtain remote transport endpoint for an address * @sock: The socket through which it will be accessed * @srx: The network address * @gfp: Allocation flags * * Lookup or create a remote transport endpoint record for the specified * address. * * Return: The peer record found with a reference, %NULL if no record is found * or a negative error code if the address is invalid or unsupported. */ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; ret = rxrpc_validate_address(rx, srx, sizeof(*srx)); if (ret < 0) return ERR_PTR(ret); return rxrpc_lookup_peer(rx->local, srx, gfp); } EXPORT_SYMBOL(rxrpc_kernel_lookup_peer); /** * rxrpc_kernel_get_peer - Get a reference on a peer * @peer: The peer to get a reference on (may be NULL). * * Get a reference for a remote peer record (if not NULL). * * Return: The @peer argument. */ struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer) { return peer ? rxrpc_get_peer(peer, rxrpc_peer_get_application) : NULL; } EXPORT_SYMBOL(rxrpc_kernel_get_peer); /** * rxrpc_kernel_put_peer - Allow a kernel app to drop a peer reference * @peer: The peer to drop a ref on * * Drop a reference on a peer record. */ void rxrpc_kernel_put_peer(struct rxrpc_peer *peer) { rxrpc_put_peer(peer, rxrpc_peer_put_application); } EXPORT_SYMBOL(rxrpc_kernel_put_peer); /** * rxrpc_kernel_begin_call - Allow a kernel service to begin a call * @sock: The socket on which to make the call * @peer: The peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use * @tx_total_len: Total length of data to transmit during the call (or -1) * @hard_timeout: The maximum lifespan of the call in sec * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue * @service_id: The ID of the service to contact * @upgrade: Request service upgrade for call * @interruptibility: The call is interruptible, or can be canceled. * @debug_id: The debug ID for tracing to be assigned to the call * * Allow a kernel service to begin a call on the nominated socket. This just * sets up all the internal tracking structures and allocates connection and * call IDs as appropriate. * * The default socket destination address and security may be overridden by * supplying @srx and @key. * * Return: The new call or an error code. */ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct rxrpc_peer *peer, struct key *key, unsigned long user_call_ID, s64 tx_total_len, u32 hard_timeout, gfp_t gfp, rxrpc_notify_rx_t notify_rx, u16 service_id, bool upgrade, enum rxrpc_interruptibility interruptibility, unsigned int debug_id) { struct rxrpc_conn_parameters cp; struct rxrpc_call_params p; struct rxrpc_call *call; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); _enter(",,%x,%lx", key_serial(key), user_call_ID); if (WARN_ON_ONCE(peer->local != rx->local)) return ERR_PTR(-EIO); lock_sock(&rx->sk); if (!key) key = rx->key; if (key && !key->payload.data[0]) key = NULL; /* a no-security key */ memset(&p, 0, sizeof(p)); p.user_call_ID = user_call_ID; p.tx_total_len = tx_total_len; p.interruptibility = interruptibility; p.kernel = true; p.timeouts.hard = hard_timeout; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; cp.peer = peer; cp.key = key; cp.security_level = rx->min_sec_level; cp.exclusive = false; cp.upgrade = upgrade; cp.service_id = service_id; call = rxrpc_new_client_call(rx, &cp, &p, gfp, debug_id); /* The socket has been unlocked. */ if (!IS_ERR(call)) { call->notify_rx = notify_rx; mutex_unlock(&call->user_mutex); } _leave(" = %p", call); return call; } EXPORT_SYMBOL(rxrpc_kernel_begin_call); /* * Dummy function used to stop the notifier talking to recvmsg(). */ static void rxrpc_dummy_notify_rx(struct sock *sk, struct rxrpc_call *rxcall, unsigned long call_user_ID) { } /** * rxrpc_kernel_shutdown_call - Allow a kernel service to shut down a call it was using * @sock: The socket the call is on * @call: The call to end * * Allow a kernel service to shut down a call it was using. The call must be * complete before this is called (the call should be aborted if necessary). */ void rxrpc_kernel_shutdown_call(struct socket *sock, struct rxrpc_call *call) { _enter("%d{%d}", call->debug_id, refcount_read(&call->ref)); mutex_lock(&call->user_mutex); if (!test_bit(RXRPC_CALL_RELEASED, &call->flags)) { rxrpc_release_call(rxrpc_sk(sock->sk), call); /* Make sure we're not going to call back into a kernel service */ if (call->notify_rx) { spin_lock_irq(&call->notify_lock); call->notify_rx = rxrpc_dummy_notify_rx; spin_unlock_irq(&call->notify_lock); } } mutex_unlock(&call->user_mutex); } EXPORT_SYMBOL(rxrpc_kernel_shutdown_call); /** * rxrpc_kernel_put_call - Release a reference to a call * @sock: The socket the call is on * @call: The call to put * * Drop the application's ref on an rxrpc call. */ void rxrpc_kernel_put_call(struct socket *sock, struct rxrpc_call *call) { rxrpc_put_call(call, rxrpc_call_put_kernel); } EXPORT_SYMBOL(rxrpc_kernel_put_call); /** * rxrpc_kernel_check_life - Check to see whether a call is still alive * @sock: The socket the call is on * @call: The call to check * * Allow a kernel service to find out whether a call is still alive - whether * it has completed successfully and all received data has been consumed. * * Return: %true if the call is still ongoing and %false if it has completed. */ bool rxrpc_kernel_check_life(const struct socket *sock, const struct rxrpc_call *call) { if (!rxrpc_call_is_complete(call)) return true; if (call->completion != RXRPC_CALL_SUCCEEDED) return false; return !skb_queue_empty(&call->recvmsg_queue); } EXPORT_SYMBOL(rxrpc_kernel_check_life); /** * rxrpc_kernel_set_notifications - Set table of callback operations * @sock: The socket to install table upon * @app_ops: Callback operation table to set * * Allow a kernel service to set a table of event notifications on a socket. */ void rxrpc_kernel_set_notifications(struct socket *sock, const struct rxrpc_kernel_ops *app_ops) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); rx->app_ops = app_ops; } EXPORT_SYMBOL(rxrpc_kernel_set_notifications); /* * connect an RxRPC socket * - this just targets it at a specific destination; no actual connection * negotiation takes place */ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)addr; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; _enter("%p,%p,%d,%d", rx, addr, addr_len, flags); ret = rxrpc_validate_address(rx, srx, addr_len); if (ret < 0) { _leave(" = %d [bad addr]", ret); return ret; } lock_sock(&rx->sk); ret = -EISCONN; if (test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) goto error; switch (rx->sk.sk_state) { case RXRPC_UNBOUND: rx->sk.sk_state = RXRPC_CLIENT_UNBOUND; break; case RXRPC_CLIENT_UNBOUND: case RXRPC_CLIENT_BOUND: break; default: ret = -EBUSY; goto error; } rx->connect_srx = *srx; set_bit(RXRPC_SOCK_CONNECTED, &rx->flags); ret = 0; error: release_sock(&rx->sk); return ret; } /* * send a message through an RxRPC socket * - in a client this does a number of things: * - finds/sets up a connection for the security specified (if any) * - initiates a call (ID in control data) * - ends the request phase of a call (if MSG_MORE is not set) * - sends a call data packet * - may send an abort (abort code in control data) */ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { struct rxrpc_local *local; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; _enter(",{%d},,%zu", rx->sk.sk_state, len); if (m->msg_flags & MSG_OOB) return -EOPNOTSUPP; if (m->msg_name) { ret = rxrpc_validate_address(rx, m->msg_name, m->msg_namelen); if (ret < 0) { _leave(" = %d [bad addr]", ret); return ret; } } lock_sock(&rx->sk); switch (rx->sk.sk_state) { case RXRPC_UNBOUND: case RXRPC_CLIENT_UNBOUND: rx->srx.srx_family = AF_RXRPC; rx->srx.srx_service = 0; rx->srx.transport_type = SOCK_DGRAM; rx->srx.transport.family = rx->family; switch (rx->family) { case AF_INET: rx->srx.transport_len = sizeof(struct sockaddr_in); break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: rx->srx.transport_len = sizeof(struct sockaddr_in6); break; #endif default: ret = -EAFNOSUPPORT; goto error_unlock; } local = rxrpc_lookup_local(sock_net(sock->sk), &rx->srx); if (IS_ERR(local)) { ret = PTR_ERR(local); goto error_unlock; } rx->local = local; rx->sk.sk_state = RXRPC_CLIENT_BOUND; fallthrough; case RXRPC_CLIENT_BOUND: if (!m->msg_name && test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) { m->msg_name = &rx->connect_srx; m->msg_namelen = sizeof(rx->connect_srx); } fallthrough; case RXRPC_SERVER_BOUND: case RXRPC_SERVER_LISTENING: if (m->msg_flags & MSG_OOB) ret = rxrpc_sendmsg_oob(rx, m, len); else ret = rxrpc_do_sendmsg(rx, m, len); /* The socket has been unlocked */ goto out; default: ret = -EINVAL; goto error_unlock; } error_unlock: release_sock(&rx->sk); out: _leave(" = %d", ret); return ret; } int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val) { if (sk->sk_state != RXRPC_UNBOUND) return -EISCONN; if (val > RXRPC_SECURITY_MAX) return -EINVAL; lock_sock(sk); rxrpc_sk(sk)->min_sec_level = val; release_sock(sk); return 0; } EXPORT_SYMBOL(rxrpc_sock_set_min_security_level); /* * set RxRPC socket options */ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct rxrpc_sock *rx = rxrpc_sk(sock->sk); unsigned int min_sec_level, val; u16 service_upgrade[2]; int ret; _enter(",%d,%d,,%d", level, optname, optlen); lock_sock(&rx->sk); ret = -EOPNOTSUPP; if (level == SOL_RXRPC) { switch (optname) { case RXRPC_EXCLUSIVE_CONNECTION: ret = -EINVAL; if (optlen != 0) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; rx->exclusive = true; goto success; case RXRPC_SECURITY_KEY: ret = -EINVAL; if (rx->key) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = rxrpc_request_key(rx, optval, optlen); goto error; case RXRPC_SECURITY_KEYRING: ret = -EINVAL; if (rx->key) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = rxrpc_server_keyring(rx, optval, optlen); goto error; case RXRPC_MIN_SECURITY_LEVEL: ret = -EINVAL; if (optlen != sizeof(unsigned int)) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = copy_safe_from_sockptr(&min_sec_level, sizeof(min_sec_level), optval, optlen); if (ret) goto error; ret = -EINVAL; if (min_sec_level > RXRPC_SECURITY_MAX) goto error; rx->min_sec_level = min_sec_level; goto success; case RXRPC_UPGRADEABLE_SERVICE: ret = -EINVAL; if (optlen != sizeof(service_upgrade) || rx->service_upgrade.from != 0) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_SERVER_BOUND2) goto error; ret = -EFAULT; if (copy_from_sockptr(service_upgrade, optval, sizeof(service_upgrade)) != 0) goto error; ret = -EINVAL; if ((service_upgrade[0] != rx->srx.srx_service || service_upgrade[1] != rx->second_service) && (service_upgrade[0] != rx->second_service || service_upgrade[1] != rx->srx.srx_service)) goto error; rx->service_upgrade.from = service_upgrade[0]; rx->service_upgrade.to = service_upgrade[1]; goto success; case RXRPC_MANAGE_RESPONSE: ret = -EINVAL; if (optlen != sizeof(unsigned int)) goto error; ret = -EISCONN; if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = copy_safe_from_sockptr(&val, sizeof(val), optval, optlen); if (ret) goto error; ret = -EINVAL; if (val > 1) goto error; if (val) set_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); else clear_bit(RXRPC_SOCK_MANAGE_RESPONSE, &rx->flags); goto success; default: break; } } success: ret = 0; error: release_sock(&rx->sk); return ret; } /* * Get socket options. */ static int rxrpc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *_optlen) { int optlen; if (level != SOL_RXRPC) return -EOPNOTSUPP; if (get_user(optlen, _optlen)) return -EFAULT; switch (optname) { case RXRPC_SUPPORTED_CMSG: if (optlen < sizeof(int)) return -ETOOSMALL; if (put_user(RXRPC__SUPPORTED - 1, (int __user *)optval) || put_user(sizeof(int), _optlen)) return -EFAULT; return 0; default: return -EOPNOTSUPP; } } /* * permit an RxRPC socket to be polled */ static __poll_t rxrpc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct rxrpc_sock *rx = rxrpc_sk(sk); __poll_t mask; sock_poll_wait(file, sock, wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx * queue */ if (!list_empty(&rx->recvmsg_q)) mask |= EPOLLIN | EPOLLRDNORM; /* the socket is writable if there is space to add new data to the * socket; there is no guarantee that any particular call in progress * on the socket may have space in the Tx ACK window */ if (rxrpc_writable(sk)) mask |= EPOLLOUT | EPOLLWRNORM; return mask; } /* * create an RxRPC socket */ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, int kern) { struct rxrpc_net *rxnet; struct rxrpc_sock *rx; struct sock *sk; _enter("%p,%d", sock, protocol); /* we support transport protocol UDP/UDP6 only */ if (protocol != PF_INET && IS_ENABLED(CONFIG_AF_RXRPC_IPV6) && protocol != PF_INET6) return -EPROTONOSUPPORT; if (sock->type != SOCK_DGRAM) return -ESOCKTNOSUPPORT; sock->ops = &rxrpc_rpc_ops; sock->state = SS_UNCONNECTED; sk = sk_alloc(net, PF_RXRPC, GFP_KERNEL, &rxrpc_proto, kern); if (!sk) return -ENOMEM; sock_init_data(sock, sk); sock_set_flag(sk, SOCK_RCU_FREE); sk->sk_state = RXRPC_UNBOUND; sk->sk_write_space = rxrpc_write_space; sk->sk_max_ack_backlog = 0; sk->sk_destruct = rxrpc_sock_destructor; rx = rxrpc_sk(sk); rx->family = protocol; rx->calls = RB_ROOT; spin_lock_init(&rx->incoming_lock); skb_queue_head_init(&rx->recvmsg_oobq); rx->pending_oobq = RB_ROOT; INIT_LIST_HEAD(&rx->sock_calls); INIT_LIST_HEAD(&rx->to_be_accepted); INIT_LIST_HEAD(&rx->recvmsg_q); spin_lock_init(&rx->recvmsg_lock); rwlock_init(&rx->call_lock); memset(&rx->srx, 0, sizeof(rx->srx)); rxnet = rxrpc_net(sock_net(&rx->sk)); timer_reduce(&rxnet->peer_keepalive_timer, jiffies + 1); _leave(" = 0 [%p]", rx); return 0; } /* * Kill all the calls on a socket and shut it down. */ static int rxrpc_shutdown(struct socket *sock, int flags) { struct sock *sk = sock->sk; struct rxrpc_sock *rx = rxrpc_sk(sk); int ret = 0; _enter("%p,%d", sk, flags); if (flags != SHUT_RDWR) return -EOPNOTSUPP; if (sk->sk_state == RXRPC_CLOSE) return -ESHUTDOWN; lock_sock(sk); if (sk->sk_state < RXRPC_CLOSE) { spin_lock_irq(&rx->recvmsg_lock); sk->sk_state = RXRPC_CLOSE; sk->sk_shutdown = SHUTDOWN_MASK; spin_unlock_irq(&rx->recvmsg_lock); } else { ret = -ESHUTDOWN; } rxrpc_discard_prealloc(rx); release_sock(sk); return ret; } /* * Purge the out-of-band queue. */ static void rxrpc_purge_oob_queue(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); struct sk_buff *skb; while ((skb = skb_dequeue(&rx->recvmsg_oobq))) rxrpc_kernel_free_oob(skb); while (!RB_EMPTY_ROOT(&rx->pending_oobq)) { skb = rb_entry(rx->pending_oobq.rb_node, struct sk_buff, rbnode); rb_erase(&skb->rbnode, &rx->pending_oobq); rxrpc_kernel_free_oob(skb); } } /* * RxRPC socket destructor */ static void rxrpc_sock_destructor(struct sock *sk) { _enter("%p", sk); rxrpc_purge_oob_queue(sk); rxrpc_purge_queue(&sk->sk_receive_queue); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); WARN_ON(!sk_unhashed(sk)); WARN_ON(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { printk("Attempt to release alive rxrpc socket: %p\n", sk); return; } } /* * release an RxRPC socket */ static int rxrpc_release_sock(struct sock *sk) { struct rxrpc_sock *rx = rxrpc_sk(sk); _enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt)); /* declare the socket closed for business */ sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; /* We want to kill off all connections from a service socket * as fast as possible because we can't share these; client * sockets, on the other hand, can share an endpoint. */ switch (sk->sk_state) { case RXRPC_SERVER_BOUND: case RXRPC_SERVER_BOUND2: case RXRPC_SERVER_LISTENING: case RXRPC_SERVER_LISTEN_DISABLED: rx->local->service_closed = true; break; } spin_lock_irq(&rx->recvmsg_lock); sk->sk_state = RXRPC_CLOSE; spin_unlock_irq(&rx->recvmsg_lock); if (rx->local && rx->local->service == rx) { write_lock(&rx->local->services_lock); rx->local->service = NULL; write_unlock(&rx->local->services_lock); } /* try to flush out this socket */ rxrpc_discard_prealloc(rx); rxrpc_release_calls_on_socket(rx); flush_workqueue(rxrpc_workqueue); rxrpc_purge_oob_queue(sk); rxrpc_purge_queue(&sk->sk_receive_queue); rxrpc_unuse_local(rx->local, rxrpc_local_unuse_release_sock); rxrpc_put_local(rx->local, rxrpc_local_put_release_sock); rx->local = NULL; key_put(rx->key); rx->key = NULL; key_put(rx->securities); rx->securities = NULL; sock_put(sk); _leave(" = 0"); return 0; } /* * release an RxRPC BSD socket on close() or equivalent */ static int rxrpc_release(struct socket *sock) { struct sock *sk = sock->sk; _enter("%p{%p}", sock, sk); if (!sk) return 0; sock->sk = NULL; return rxrpc_release_sock(sk); } /* * RxRPC network protocol */ static const struct proto_ops rxrpc_rpc_ops = { .family = PF_RXRPC, .owner = THIS_MODULE, .release = rxrpc_release, .bind = rxrpc_bind, .connect = rxrpc_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = rxrpc_poll, .ioctl = sock_no_ioctl, .listen = rxrpc_listen, .shutdown = rxrpc_shutdown, .setsockopt = rxrpc_setsockopt, .getsockopt = rxrpc_getsockopt, .sendmsg = rxrpc_sendmsg, .recvmsg = rxrpc_recvmsg, .mmap = sock_no_mmap, }; static struct proto rxrpc_proto = { .name = "RXRPC", .owner = THIS_MODULE, .obj_size = sizeof(struct rxrpc_sock), .max_header = sizeof(struct rxrpc_wire_header), }; static const struct net_proto_family rxrpc_family_ops = { .family = PF_RXRPC, .create = rxrpc_create, .owner = THIS_MODULE, }; /* * initialise and register the RxRPC protocol */ static int __init af_rxrpc_init(void) { int ret = -1; BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); ret = -ENOMEM; rxrpc_gen_version_string(); rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); if (!rxrpc_call_jar) { pr_notice("Failed to allocate call jar\n"); goto error_call_jar; } rxrpc_workqueue = alloc_ordered_workqueue("krxrpcd", WQ_HIGHPRI | WQ_MEM_RECLAIM); if (!rxrpc_workqueue) { pr_notice("Failed to allocate work queue\n"); goto error_work_queue; } ret = rxrpc_init_security(); if (ret < 0) { pr_crit("Cannot initialise security\n"); goto error_security; } ret = register_pernet_device(&rxrpc_net_ops); if (ret) goto error_pernet; ret = proto_register(&rxrpc_proto, 1); if (ret < 0) { pr_crit("Cannot register protocol\n"); goto error_proto; } ret = sock_register(&rxrpc_family_ops); if (ret < 0) { pr_crit("Cannot register socket family\n"); goto error_sock; } ret = register_key_type(&key_type_rxrpc); if (ret < 0) { pr_crit("Cannot register client key type\n"); goto error_key_type; } ret = register_key_type(&key_type_rxrpc_s); if (ret < 0) { pr_crit("Cannot register server key type\n"); goto error_key_type_s; } ret = rxrpc_sysctl_init(); if (ret < 0) { pr_crit("Cannot register sysctls\n"); goto error_sysctls; } return 0; error_sysctls: unregister_key_type(&key_type_rxrpc_s); error_key_type_s: unregister_key_type(&key_type_rxrpc); error_key_type: sock_unregister(PF_RXRPC); error_sock: proto_unregister(&rxrpc_proto); error_proto: unregister_pernet_device(&rxrpc_net_ops); error_pernet: rxrpc_exit_security(); error_security: destroy_workqueue(rxrpc_workqueue); error_work_queue: kmem_cache_destroy(rxrpc_call_jar); error_call_jar: return ret; } /* * unregister the RxRPC protocol */ static void __exit af_rxrpc_exit(void) { _enter(""); rxrpc_sysctl_exit(); unregister_key_type(&key_type_rxrpc_s); unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); unregister_pernet_device(&rxrpc_net_ops); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); /* Make sure the local and peer records pinned by any dying connections * are released. */ rcu_barrier(); destroy_workqueue(rxrpc_workqueue); rxrpc_exit_security(); kmem_cache_destroy(rxrpc_call_jar); _leave(""); } module_init(af_rxrpc_init); module_exit(af_rxrpc_exit); |
| 225 3 223 224 141 137 8 8 2 489 489 6 6 489 489 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto_tcp.c: TCP load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * * Network name space (netns) aware. * Global data moved to netns i.e struct netns_ipvs * tcp_timeouts table has copy per netns in a hash table per * protocol ip_vs_proto_data and is handled by netns */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> /* for tcphdr */ #include <net/ip.h> #include <net/tcp.h> /* for csum_tcpudp_magic */ #include <net/ip6_checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/indirect_call_wrapper.h> #include <net/ip_vs.h> static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; struct tcphdr _tcph, *th; __be16 _ports[2], *ports = NULL; /* In the event of icmp, we're only guaranteed to have the first 8 * bytes of the transport header, so we only check the rest of the * TCP packet for non-ICMP packets */ if (likely(!ip_vs_iph_icmp(iph))) { th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th) { if (th->rst || !(sysctl_sloppy_tcp(ipvs) || th->syn)) return 1; ports = &th->source; } } else { ports = skb_header_pointer( skb, iph->len, sizeof(_ports), &_ports); } if (!ports) { *verdict = NF_DROP; return 0; } /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (likely(!ip_vs_iph_inverse(iph))) svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( */ *verdict = NF_DROP; return 0; } /* * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) *verdict = ip_vs_leave(svc, skb, pd, iph); else *verdict = NF_DROP; return 0; } } /* NF_ACCEPT */ return 1; } static inline void tcp_fast_csum_update(int af, struct tcphdr *tcph, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldport, __be16 newport) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); else #endif tcph->check = csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); } static inline void tcp_partial_csum_update(int af, struct tcphdr *tcph, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldlen, __be16 newlen) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldlen, newlen, csum_unfold(tcph->check)))); else #endif tcph->check = ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldlen, newlen, csum_unfold(tcph->check)))); } INDIRECT_CALLABLE_SCOPE int tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; unsigned int tcphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ if (!(ret = ip_vs_app_pkt_out(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - tcphoff; else payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) tcph->check = csum_ipv6_magic(&cp->vaddr.in6, &cp->caddr.in6, skb->len - tcphoff, cp->protocol, skb->csum); else #endif tcph->check = csum_tcpudp_magic(cp->vaddr.ip, cp->caddr.ip, skb->len - tcphoff, cp->protocol, skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, tcph->check, (char*)&(tcph->check) - (char*)tcph); } return 1; } static int tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; unsigned int tcphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* * Attempt ip_vs_app call. * It will fix ip_vs_conn and iph ack_seq stuff */ if (!(ret = ip_vs_app_pkt_in(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - tcphoff; else payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; tcph->dest = cp->dport; /* * Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { tcp_partial_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) tcph->check = csum_ipv6_magic(&cp->caddr.in6, &cp->daddr.in6, skb->len - tcphoff, cp->protocol, skb->csum); else #endif tcph->check = csum_tcpudp_magic(cp->caddr.ip, cp->daddr.ip, skb->len - tcphoff, cp->protocol, skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; } static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int tcphoff; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcphoff = sizeof(struct ipv6hdr); else #endif tcphoff = ip_hdrlen(skb); switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); fallthrough; case CHECKSUM_COMPLETE: #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - tcphoff, ipv6_hdr(skb)->nexthdr, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } } else #endif if (csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - tcphoff, ip_hdr(skb)->protocol, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } break; default: /* No need to checksum. */ break; } return 1; } #define TCP_DIR_INPUT 0 #define TCP_DIR_OUTPUT 4 #define TCP_DIR_INPUT_ONLY 8 static const int tcp_state_off[IP_VS_DIR_LAST] = { [IP_VS_DIR_INPUT] = TCP_DIR_INPUT, [IP_VS_DIR_OUTPUT] = TCP_DIR_OUTPUT, [IP_VS_DIR_INPUT_ONLY] = TCP_DIR_INPUT_ONLY, }; /* * Timeout table[state] */ static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = 2*HZ, [IP_VS_TCP_S_ESTABLISHED] = 15*60*HZ, [IP_VS_TCP_S_SYN_SENT] = 2*60*HZ, [IP_VS_TCP_S_SYN_RECV] = 1*60*HZ, [IP_VS_TCP_S_FIN_WAIT] = 2*60*HZ, [IP_VS_TCP_S_TIME_WAIT] = 2*60*HZ, [IP_VS_TCP_S_CLOSE] = 10*HZ, [IP_VS_TCP_S_CLOSE_WAIT] = 60*HZ, [IP_VS_TCP_S_LAST_ACK] = 30*HZ, [IP_VS_TCP_S_LISTEN] = 2*60*HZ, [IP_VS_TCP_S_SYNACK] = 120*HZ, [IP_VS_TCP_S_LAST] = 2*HZ, }; static const char *const tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = "NONE", [IP_VS_TCP_S_ESTABLISHED] = "ESTABLISHED", [IP_VS_TCP_S_SYN_SENT] = "SYN_SENT", [IP_VS_TCP_S_SYN_RECV] = "SYN_RECV", [IP_VS_TCP_S_FIN_WAIT] = "FIN_WAIT", [IP_VS_TCP_S_TIME_WAIT] = "TIME_WAIT", [IP_VS_TCP_S_CLOSE] = "CLOSE", [IP_VS_TCP_S_CLOSE_WAIT] = "CLOSE_WAIT", [IP_VS_TCP_S_LAST_ACK] = "LAST_ACK", [IP_VS_TCP_S_LISTEN] = "LISTEN", [IP_VS_TCP_S_SYNACK] = "SYNACK", [IP_VS_TCP_S_LAST] = "BUG!", }; static const bool tcp_state_active_table[IP_VS_TCP_S_LAST] = { [IP_VS_TCP_S_NONE] = false, [IP_VS_TCP_S_ESTABLISHED] = true, [IP_VS_TCP_S_SYN_SENT] = true, [IP_VS_TCP_S_SYN_RECV] = true, [IP_VS_TCP_S_FIN_WAIT] = false, [IP_VS_TCP_S_TIME_WAIT] = false, [IP_VS_TCP_S_CLOSE] = false, [IP_VS_TCP_S_CLOSE_WAIT] = false, [IP_VS_TCP_S_LAST_ACK] = false, [IP_VS_TCP_S_LISTEN] = false, [IP_VS_TCP_S_SYNACK] = true, }; #define sNO IP_VS_TCP_S_NONE #define sES IP_VS_TCP_S_ESTABLISHED #define sSS IP_VS_TCP_S_SYN_SENT #define sSR IP_VS_TCP_S_SYN_RECV #define sFW IP_VS_TCP_S_FIN_WAIT #define sTW IP_VS_TCP_S_TIME_WAIT #define sCL IP_VS_TCP_S_CLOSE #define sCW IP_VS_TCP_S_CLOSE_WAIT #define sLA IP_VS_TCP_S_LAST_ACK #define sLI IP_VS_TCP_S_LISTEN #define sSA IP_VS_TCP_S_SYNACK struct tcp_states_t { int next_state[IP_VS_TCP_S_LAST]; }; static const char * tcp_state_name(int state) { if (state >= IP_VS_TCP_S_LAST) return "ERR!"; return tcp_state_name_table[state] ? tcp_state_name_table[state] : "?"; } static bool tcp_state_active(int state) { if (state >= IP_VS_TCP_S_LAST) return false; return tcp_state_active_table[state]; } static struct tcp_states_t tcp_states[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }}, /* OUTPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSS, sES, sSS, sSR, sSS, sSS, sSS, sSS, sSS, sLI, sSR }}, /*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }}, /*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }}, /* INPUT-ONLY */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; static struct tcp_states_t tcp_states_dos[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }}, /*ack*/ {{sES, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, /* OUTPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSS, sES, sSS, sSA, sSS, sSS, sSS, sSS, sSS, sLI, sSA }}, /*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }}, /*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }}, /* INPUT-ONLY */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags) { int on = (flags & 1); /* secure_tcp */ /* ** FIXME: change secure_tcp to independent sysctl var ** or make it per-service or per-app because it is valid ** for most if not for all of the applications. Something ** like "capabilities" (flags) for each object. */ pd->tcp_state_table = (on ? tcp_states_dos : tcp_states); } static inline int tcp_state_idx(struct tcphdr *th) { if (th->rst) return 3; if (th->syn) return 0; if (th->fin) return 1; if (th->ack) return 2; return -1; } static inline void set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, struct tcphdr *th) { int state_idx; int new_state = IP_VS_TCP_S_CLOSE; int state_off = tcp_state_off[direction]; /* * Update state offset to INPUT_ONLY if necessary * or delete NO_OUTPUT flag if output packet detected */ if (cp->flags & IP_VS_CONN_F_NOOUTPUT) { if (state_off == TCP_DIR_OUTPUT) cp->flags &= ~IP_VS_CONN_F_NOOUTPUT; else state_off = TCP_DIR_INPUT_ONLY; } if ((state_idx = tcp_state_idx(th)) < 0) { IP_VS_DBG(8, "tcp_state_idx=%d!!!\n", state_idx); goto tcp_state_out; } new_state = pd->tcp_state_table[state_off+state_idx].next_state[cp->state]; tcp_state_out: if (new_state != cp->state) { struct ip_vs_dest *dest = cp->dest; IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] c:%s:%d v:%s:%d " "d:%s:%d state: %s->%s conn->refcnt:%d\n", pd->pp->name, ((state_off == TCP_DIR_OUTPUT) ? "output " : "input "), th->syn ? 'S' : '.', th->fin ? 'F' : '.', th->ack ? 'A' : '.', th->rst ? 'R' : '.', IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), tcp_state_name(cp->state), tcp_state_name(new_state), refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } if (new_state == IP_VS_TCP_S_ESTABLISHED) ip_vs_control_assure_ct(cp); } if (likely(pd)) cp->timeout = pd->timeout_table[cp->state = new_state]; else /* What to do ? */ cp->timeout = tcp_timeouts[cp->state = new_state]; } /* * Handle state transitions */ static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { struct tcphdr _tcph, *th; #ifdef CONFIG_IP_VS_IPV6 int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); #else int ihl = ip_hdrlen(skb); #endif th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); if (th == NULL) return; spin_lock_bh(&cp->lock); set_tcp_state(pd, cp, direction, th); spin_unlock_bh(&cp->lock); } static inline __u16 tcp_app_hashkey(__be16 port) { return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port) & TCP_APP_TAB_MASK; } static int tcp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); hash = tcp_app_hashkey(port); list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } list_add_rcu(&inc->p_list, &ipvs->tcp_apps[hash]); atomic_inc(&pd->appcnt); out: return ret; } static void tcp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); } static int tcp_app_conn_bind(struct ip_vs_conn *cp) { struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; /* Default binding: bind app only for NAT */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) return 0; /* Lookup application incarnations and bind the right one */ hash = tcp_app_hashkey(cp->vport); list_for_each_entry_rcu(inc, &ipvs->tcp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), inc->name, ntohs(inc->port)); cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); break; } } return result; } /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(cp->ipvs, IPPROTO_TCP); spin_lock_bh(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN] : tcp_timeouts[IP_VS_TCP_S_LISTEN]); spin_unlock_bh(&cp->lock); } /* --------------------------------------------- * timeouts is netns related now. * --------------------------------------------- */ static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); if (!pd->timeout_table) return -ENOMEM; pd->tcp_state_table = tcp_states; return 0; } static void __ip_vs_tcp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_tcp = { .name = "TCP", .protocol = IPPROTO_TCP, .num_states = IP_VS_TCP_S_LAST, .dont_defrag = 0, .init = NULL, .exit = NULL, .init_netns = __ip_vs_tcp_init, .exit_netns = __ip_vs_tcp_exit, .register_app = tcp_register_app, .unregister_app = tcp_unregister_app, .conn_schedule = tcp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = tcp_snat_handler, .dnat_handler = tcp_dnat_handler, .state_name = tcp_state_name, .state_transition = tcp_state_transition, .app_conn_bind = tcp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = tcp_timeout_change, }; |
| 56592 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H #include <asm/processor.h> #if defined(__KERNEL__) && !defined(__ASSEMBLER__) #include <asm/asm.h> #include <linux/bitops.h> #include <asm/alternative.h> #include <asm/cpufeaturemasks.h> enum cpuid_leafs { CPUID_1_EDX = 0, CPUID_8000_0001_EDX, CPUID_8086_0001_EDX, CPUID_LNX_1, CPUID_1_ECX, CPUID_C000_0001_EDX, CPUID_8000_0001_ECX, CPUID_LNX_2, CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, CPUID_LNX_4, CPUID_7_1_EAX, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, CPUID_LNX_5, NR_CPUID_WORDS, }; extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; /* * In order to save room, we index into this array by doing * X86_BUG_<name> - NCAPINTS*32. */ extern const char * const x86_bug_flags[NBUGINTS*32]; #define x86_bug_flag(flag) x86_bug_flags[flag] #define test_cpu_cap(c, bit) \ arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* * This is the default CPU features testing macro to use in code. * * It is for detection of features which need kernel infrastructure to be * used. It may *not* directly test the CPU itself. Use the cpu_has() family * if you want true runtime testing of CPU features, like in hypervisor code * where you are supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) extern void setup_clear_cpu_cap(unsigned int bit); extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); void check_cpufeature_deps(struct cpuinfo_x86 *c); #define setup_force_cpu_cap(bit) do { \ \ if (!boot_cpu_has(bit)) \ WARN_ON(alternatives_patched); \ \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) /* * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know * that this is only used on a fallback path and will sometimes cause * it to manifest the address of boot_cpu_data in a register, fouling * the mainline (post-initialization) code. */ static __always_inline bool _static_cpu_has(u16 bit) { asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum], %a[cap_byte]\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".popsection\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "i" (&((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; t_no: return false; } #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) #define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) #define cpu_have_feature boot_cpu_has #define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */ #endif /* _ASM_X86_CPUFEATURE_H */ |
| 55 730 47 33 499 499 9402 9359 9408 9352 9370 9357 9360 74 74 74 74 74 74 74 74 74 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/list_nulls.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/local_lock.h> #include <linux/zswap.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER #define MAX_PAGE_ORDER 10 #else #define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif #define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER) #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1) /* Defines the order for the number of pages that have a migrate type. */ #ifndef CONFIG_PAGE_BLOCK_ORDER #define PAGE_BLOCK_ORDER MAX_PAGE_ORDER #else #define PAGE_BLOCK_ORDER CONFIG_PAGE_BLOCK_ORDER #endif /* CONFIG_PAGE_BLOCK_ORDER */ /* * The MAX_PAGE_ORDER, which defines the max order of pages to be allocated * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_ORDER, * which defines the order for the number of pages that can have a migrate type */ #if (PAGE_BLOCK_ORDER > MAX_PAGE_ORDER) #error MAX_PAGE_ORDER must be >= PAGE_BLOCK_ORDER #endif /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) # define is_migrate_cma_folio(folio, pfn) (MIGRATE_CMA == \ get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK)) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false # define is_migrate_cma_folio(folio, pfn) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } /* * Check whether a migratetype can be merged with another migratetype. * * It is only mergeable when it can fall back to other migratetypes for * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. */ static inline bool migratetype_is_mergeable(int mt) { return mt < MIGRATE_PCPTYPES; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < NR_PAGE_ORDERS; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) #define folio_migratetype(folio) \ get_pfnblock_flags_mask(&folio->page, folio_pfn(folio), \ MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; struct pglist_data; #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_EVENT_ITEMS }; #else #define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_FREE_PAGES_BLOCKS, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ /* Second 128 byte cacheline */ #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, #ifdef CONFIG_UNACCEPTED_MEMORY NR_UNACCEPTED, #endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ #ifdef CONFIG_IOMMU_SUPPORT NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ #endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ PGPROMOTE_CANDIDATE, /* candidate pages to promote */ #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, PGDEMOTE_DIRECT, PGDEMOTE_KHUGEPAGED, PGDEMOTE_PROACTIVE, #ifdef CONFIG_HUGETLB_PAGE NR_HUGETLB, #endif NR_BALLOON_PAGES, NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the item should be printed in THPs (/proc/vmstat * currently prints number of anon, file and shmem THPs. But the item * is charged in pages). */ static __always_inline bool vmstat_item_print_in_thp(enum node_stat_item item) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return false; return item == NR_ANON_THPS || item == NR_FILE_THPS || item == NR_SHMEM_THPS || item == NR_SHMEM_PMDMAPPED || item == NR_FILE_PMDMAPPED; } /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define WORKINGSET_ANON 0 #define WORKINGSET_FILE 1 #define ANON_AND_FILE 2 enum lruvec_flags { /* * An lruvec has many dirty pages backed by a congested BDI: * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim. * It can be cleared by cgroup reclaim or kswapd. * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim. * It can only be cleared by kswapd. * * Essentially, kswapd can unthrottle an lruvec throttled by cgroup * reclaim, but not vice versa. This only applies to the root cgroup. * The goal is to prevent cgroup reclaim on the root cgroup (e.g. * memory.reclaim) to unthrottle an unbalanced node (that was throttled * by kswapd). */ LRUVEC_CGROUP_CONGESTED, LRUVEC_NODE_CONGESTED, }; #endif /* !__GENERATING_BOUNDS_H */ /* * Evictable folios are divided into multiple generations. The youngest and the * oldest generation numbers, max_seq and min_seq, are monotonically increasing. * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the * corresponding generation. The gen counter in folio->flags stores gen+1 while * a folio is on one of lrugen->folios[]. Otherwise it stores 0. * * After a folio is faulted in, the aging needs to check the accessed bit at * least twice before handing this folio over to the eviction. The first check * clears the accessed bit from the initial fault; the second check makes sure * this folio hasn't been used since then. This process, AKA second chance, * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two * generations are considered active; the rest of generations, if they exist, * are considered inactive. See lru_gen_is_active(). * * PG_active is always cleared while a folio is on one of lrugen->folios[] so * that the sliding window needs not to worry about it. And it's set again when * a folio considered active is isolated for non-reclaiming purposes, e.g., * migration. See lru_gen_add_folio() and lru_gen_del_folio(). * * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits * in folio->flags, masked by LRU_GEN_MASK. */ #define MIN_NR_GENS 2U #define MAX_NR_GENS 4U /* * Each generation is divided into multiple tiers. A folio accessed N times * through file descriptors is in tier order_base_2(N). A folio in the first * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by * PG_workingset. A folio in any other tier (1<N<5) between the first and last * is marked by additional bits of LRU_REFS_WIDTH in folio->flags. * * In contrast to moving across generations which requires the LRU lock, moving * across tiers only involves atomic operations on folio->flags and therefore * has a negligible cost in the buffered access path. In the eviction path, * comparisons of refaulted/(evicted+protected) from the first tier and the rest * infer whether folios accessed multiple times through file descriptors are * statistically hot and thus worth protecting. * * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the * number of categories of the active/inactive LRU when keeping track of * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in * folio->flags, masked by LRU_REFS_MASK. */ #define MAX_NR_TIERS 4U #ifndef __GENERATING_BOUNDS_H #define LRU_GEN_MASK ((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF) #define LRU_REFS_MASK ((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF) /* * For folios accessed multiple times through file descriptors, * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily * promoted into the second oldest generation in the eviction path. And when * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is * only valid when PG_referenced is set. * * For folios accessed multiple times through page tables, folio_update_gen() * from a page table walk or lru_gen_set_refs() from a rmap walk sets * PG_referenced after the accessed bit is cleared for the first time. * Thereafter, those two paths set PG_workingset and promote folios to the * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears * PG_referenced. Note that for this case, LRU_REFS_MASK is not used. * * For both cases above, after PG_workingset is set on a folio, it remains until * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It * can be set again if lru_gen_test_recent() returns true upon a refault. */ #define LRU_REFS_FLAGS (LRU_REFS_MASK | BIT(PG_referenced)) struct lruvec; struct page_vma_mapped_walk; #ifdef CONFIG_LRU_GEN enum { LRU_GEN_ANON, LRU_GEN_FILE, }; enum { LRU_GEN_CORE, LRU_GEN_MM_WALK, LRU_GEN_NONLEAF_YOUNG, NR_LRU_GEN_CAPS }; #define MIN_LRU_BATCH BITS_PER_LONG #define MAX_LRU_BATCH (MIN_LRU_BATCH * 64) /* whether to keep historical stats from evicted generations */ #ifdef CONFIG_LRU_GEN_STATS #define NR_HIST_GENS MAX_NR_GENS #else #define NR_HIST_GENS 1U #endif /* * The youngest generation number is stored in max_seq for both anon and file * types as they are aged on an equal footing. The oldest generation numbers are * stored in min_seq[] separately for anon and file types so that they can be * incremented independently. Ideally min_seq[] are kept in sync when both anon * and file types are evictable. However, to adapt to situations like extreme * swappiness, they are allowed to be out of sync by at most * MAX_NR_GENS-MIN_NR_GENS-1. * * The number of pages in each generation is eventually consistent and therefore * can be transiently negative when reset_batch_size() is pending. */ struct lru_gen_folio { /* the aging increments the youngest generation number */ unsigned long max_seq; /* the eviction increments the oldest generation numbers */ unsigned long min_seq[ANON_AND_FILE]; /* the birth time of each generation in jiffies */ unsigned long timestamps[MAX_NR_GENS]; /* the multi-gen LRU lists, lazily sorted on eviction */ struct list_head folios[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the multi-gen LRU sizes, eventually consistent */ long nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* the exponential moving average of refaulted */ unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS]; /* the exponential moving average of evicted+protected */ unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS]; /* can only be modified under the LRU lock */ unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* can be modified without holding the LRU lock */ atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS]; /* whether the multi-gen LRU is enabled */ bool enabled; /* the memcg generation this lru_gen_folio belongs to */ u8 gen; /* the list segment this lru_gen_folio belongs to */ u8 seg; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_node list; }; enum { MM_LEAF_TOTAL, /* total leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS }; /* double-buffering Bloom filters */ #define NR_BLOOM_FILTERS 2 struct lru_gen_mm_state { /* synced with max_seq after each iteration */ unsigned long seq; /* where the current iteration continues after */ struct list_head *head; /* where the last iteration ended before */ struct list_head *tail; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; }; struct lru_gen_mm_walk { /* the lruvec under reclaim */ struct lruvec *lruvec; /* max_seq from lru_gen_folio: can be out of date */ unsigned long seq; /* the next address within an mm to scan */ unsigned long next_addr; /* to batch promoted pages */ int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES]; /* to batch the mm stats */ int mm_stats[NR_MM_STATS]; /* total batched items */ int batched; int swappiness; bool force_scan; }; /* * For each node, memcgs are divided into two generations: the old and the * young. For each generation, memcgs are randomly sharded into multiple bins * to improve scalability. For each bin, the hlist_nulls is virtually divided * into three segments: the head, the tail and the default. * * An onlining memcg is added to the tail of a random bin in the old generation. * The eviction starts at the head of a random bin in the old generation. The * per-node memcg generation counter, whose reminder (mod MEMCG_NR_GENS) indexes * the old generation, is incremented when all its bins become empty. * * There are four operations: * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; * 3. The first attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_TAIL; * 4. The second attempt to reclaim a memcg offlined or below reclaimable size * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * * Notes: * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing * of their max_seq counters ensures the eventual fairness to all eligible * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). * 2. There are only two valid generations: old (seq) and young (seq+1). * MEMCG_NR_GENS is set to three so that when reading the generation counter * locklessly, a stale value (seq-1) does not wraparound to young. */ #define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { /* the per-node memcg generation counter */ unsigned long seq; /* each memcg has one lru_gen_folio per node */ unsigned long nr_memcgs[MEMCG_NR_GENS]; /* per-node lru_gen_folio list for global reclaim */ struct hlist_nulls_head fifo[MEMCG_NR_GENS][MEMCG_NR_BINS]; /* protects the above */ spinlock_t lock; }; void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); void lru_gen_online_memcg(struct mem_cgroup *memcg); void lru_gen_offline_memcg(struct mem_cgroup *memcg); void lru_gen_release_memcg(struct mem_cgroup *memcg); void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid); #else /* !CONFIG_LRU_GEN */ static inline void lru_gen_init_pgdat(struct pglist_data *pgdat) { } static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_exit_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_online_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_offline_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_release_memcg(struct mem_cgroup *memcg) { } static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { } #endif /* CONFIG_LRU_GEN */ struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* per lruvec lru_lock for memcg */ spinlock_t lru_lock; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_LRU_GEN /* evictable pages divided into generations */ struct lru_gen_folio lrugen; #ifdef CONFIG_LRU_GEN_WALKS_MMU /* to concurrently iterate lru_gen_mm_list */ struct lru_gen_mm_state mm_state; #endif #endif /* CONFIG_LRU_GEN */ #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif struct zswap_lruvec_state zswap_lruvec_state; }; /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, WMARK_PROMO, NR_WMARK }; /* * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1)) #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP) /* * Flags used in pcp->flags field. * * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the * previous page freeing. To avoid to drain PCP for an accident * high-order page freeing. * * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before * draining PCP for consecutive high-order pages freeing without * allocation if data cache slice of CPU is large enough. To reduce * zone lock contention and keep cache-hot pages reusing. */ #define PCPF_PREV_FREE_HIGH_ORDER BIT(0) #define PCPF_FREE_HIGH_BATCH BIT(1) struct per_cpu_pages { spinlock_t lock; /* Protects lists field */ int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int high_min; /* min high watermark */ int high_max; /* max high watermark */ int batch; /* chunk size for buddy add/remove */ u8 flags; /* protected by pcp->lock */ u8 alloc_factor; /* batch scaling factor during allocate */ #ifdef CONFIG_NUMA u8 expire; /* When 0, remote pagesets are drained */ #endif short free_count; /* consecutive free count */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[NR_PCP_LISTS]; } ____cacheline_aligned_in_smp; struct per_cpu_zonestat { #ifdef CONFIG_SMP s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; s8 stat_threshold; #endif #ifdef CONFIG_NUMA /* * Low priority inaccurate counters that are only folded * on demand. Use a large type to avoid the overhead of * folding during refresh_cpu_vm_stats. */ unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Therefore, we do not allow * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and * faulted, they come from the right zone right away. However, it is * still possible that address space already has pages in * ZONE_MOVABLE at the time when pages are pinned (i.e. user has * touches that memory before pinning). In such case we migrate them * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * 6. ZERO_PAGE(0), kernelcore/movablecore setups might create * situations where ZERO_PAGE(0) which is allocated differently * on different platforms may end up in a movable zone. ZERO_PAGE(0) * cannot be migrated. * 7. Memory-hotplug: when using memmap_on_memory and onlining the * memory to the MOVABLE zone, the vmemmap pages are also placed in * such zone. Such pages cannot be really moved around as they are * self-stored in the range, but they are treated as movable when * the range they describe is about to be offlined. * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pages __percpu *per_cpu_pageset; struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access */ int pageset_high_min; int pageset_high_max; int pageset_batch; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * present_early_pages is present pages existing within the zone * located on memory available since early boot, excluding hotplugged * memory. * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * cma pages is present pages that are assigned for CMA use * (MIGRATE_CMA). * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/done(). Any reader who can't tolerant drift of * present_pages should use get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; #if defined(CONFIG_MEMORY_HOTPLUG) unsigned long present_early_pages; #endif #ifdef CONFIG_CMA unsigned long cma_pages; #endif const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ struct free_area free_area[NR_PAGE_ORDERS]; #ifdef CONFIG_UNACCEPTED_MEMORY /* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */ struct list_head unaccepted_pages; /* To be called once the last page in the zone is accepted */ struct work_struct unaccepted_cleanup; #endif /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Pages to be freed when next trylock succeeds */ struct llist_head trylock_free_pages; /* Write-intensive fields used by compaction and vmstats. */ CACHELINE_PADDING(_pad2_); /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; CACHELINE_PADDING(_pad3_); /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ ZONE_BELOW_HIGH, /* zone is below high watermark. */ }; static inline unsigned long wmark_pages(const struct zone *z, enum zone_watermarks w) { return z->_watermark[w] + z->watermark_boost; } static inline unsigned long min_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_MIN); } static inline unsigned long low_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_LOW); } static inline unsigned long high_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_HIGH); } static inline unsigned long promo_wmark_pages(const struct zone *z) { return wmark_pages(z, WMARK_PROMO); } static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_cma_pages(struct zone *zone) { #ifdef CONFIG_CMA return zone->cma_pages; #else return 0; #endif } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } #ifndef BUILD_VDSO32_64 /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) #define LRU_GEN_PGOFF (KASAN_TAG_PGOFF - LRU_GEN_WIDTH) #define LRU_REFS_PGOFF (LRU_GEN_PGOFF - LRU_REFS_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF) ? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF) ? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } static inline enum zone_type folio_zonenum(const struct folio *folio) { return page_zonenum(&folio->page); } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } static inline struct dev_pagemap *page_pgmap(const struct page *page) { VM_WARN_ON_ONCE_PAGE(!is_zone_device_page(page), page); return page_folio(page)->pgmap; } /* * Consecutive zone device pages should not be merged into the same sgl * or bvec segment with other types of pages or if they belong to different * pgmaps. Otherwise getting the pgmap of a given segment is not possible * without scanning the entire segment. This helper returns true either if * both pages are not zone device pages or both pages are zone device pages * with the same pgmap. */ static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { if (is_zone_device_page(a) != is_zone_device_page(b)) return false; if (!is_zone_device_page(a)) return true; return page_pgmap(a) == page_pgmap(b); } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } static inline bool zone_device_pages_have_same_pgmap(const struct page *a, const struct page *b) { return true; } static inline struct dev_pagemap *page_pgmap(const struct page *page) { return NULL; } #endif static inline bool folio_is_zone_device(const struct folio *folio) { return is_zone_device_page(&folio->page); } static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } static inline bool folio_is_zone_movable(const struct folio *folio) { return folio_zonenum(folio) == ZONE_MOVABLE; } #endif /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; /* * The array of struct pages for flatmem. * It must be declared for SPARSEMEM as well because there are configurations * that rely on that. */ extern struct page *mem_map; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. */ struct memory_failure_stats { /* * Number of raw pages poisoned. * Cases not accounted: memory outside kernel control, offline page, * arch-specific memory_failure (SGX), hwpoison_filter() filtered * error events, and unpoison actions from hwpoison_unpoison. */ unsigned long total; /* * Recovery results of poisoned raw pages handled by memory_failure, * in sync with mf_result. * total = ignored + failed + delayed + recovered. * total * PAGE_SIZE * #nodes = /proc/meminfo/HardwareCorrupted. */ unsigned long ignored; unsigned long failed; unsigned long delayed; unsigned long recovered; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; /* workqueues for throttling reclaim for different reasons. */ wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ unsigned long nr_reclaim_start; /* nr pages written while throttled * when throttling started. */ #ifdef CONFIG_MEMORY_HOTPLUG struct mutex kswapd_lock; #endif struct task_struct *kswapd; /* Protected by kswapd_lock */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ CACHELINE_PADDING(_pad1_); #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; /* number of promote candidate pages at start time of current rate limit period */ unsigned long nbp_rl_nr_cand; /* promote threshold in ms */ unsigned int nbp_threshold; /* start time in ms of current promote threshold adjustment period */ unsigned int nbp_th_start; /* * number of promote candidate pages at start time of current promote * threshold adjustment period */ unsigned long nbp_th_nr_cand; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif CACHELINE_PADDING(_pad2_); /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA struct memory_tier __rcu *memtier; #endif #ifdef CONFIG_MEMORY_FAILURE struct memory_failure_stats mf_stats; #endif } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) #ifdef CONFIG_ZONE_DEVICE static inline bool zone_is_zone_device(struct zone *zone) { return zone_idx(zone) == ZONE_DEVICE; } #else static inline bool zone_is_zone_device(struct zone *zone) { return false; } #endif /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NUMA static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif } /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone: pointer to struct zone variable * Return: 1 for a highmem zone, 0 otherwise */ static inline int is_highmem(struct zone *zone) { return is_highmem_idx(zone_idx(zone)); } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } #else /* CONFIG_NUMA */ #include <asm/mmzone.h> #endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat: pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone: pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z: The cursor used as a starting point for the search * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. * * Return: the next zone at or below highest_zoneidx within the allowed * nodemask using a cursor within a zonelist as a starting point */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist: The zonelist to search for a suitable zone * @highest_zoneidx: The zone index of the highest zone to return * @nodes: An optional nodemask to filter the zonelist with * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. * * Return: Zoneref pointer for the first suitable zone found */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone: The current zone in the iterator * @z: The current pointer within zonelist->_zonerefs being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * @nodemask: Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone: The current zone in the iterator * @z: The current pointer within zonelist->zones being iterated * @zlist: The zonelist being iterated * @highidx: The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!zonelist_zone(z)) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available on all architectures. * However, we can exceed 6 bits on some other architectures except * powerpc (e.g. 15 bits are available on x86_64, 13 bits are available * with the worst case of 64K pages on arm64) if we make sure the * exceeded bit is not applicable to powerpc. */ enum { SECTION_MARKED_PRESENT_BIT, SECTION_HAS_MEM_MAP_BIT, SECTION_IS_ONLINE_BIT, SECTION_IS_EARLY_BIT, #ifdef CONFIG_ZONE_DEVICE SECTION_TAINT_ZONE_DEVICE_BIT, #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT SECTION_IS_VMEMMAP_PREINIT_BIT, #endif SECTION_MAP_LAST_BIT, }; #define SECTION_MARKED_PRESENT BIT(SECTION_MARKED_PRESENT_BIT) #define SECTION_HAS_MEM_MAP BIT(SECTION_HAS_MEM_MAP_BIT) #define SECTION_IS_ONLINE BIT(SECTION_IS_ONLINE_BIT) #define SECTION_IS_EARLY BIT(SECTION_IS_EARLY_BIT) #ifdef CONFIG_ZONE_DEVICE #define SECTION_TAINT_ZONE_DEVICE BIT(SECTION_TAINT_ZONE_DEVICE_BIT) #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT #define SECTION_IS_VMEMMAP_PREINIT BIT(SECTION_IS_VMEMMAP_PREINIT_BIT) #endif #define SECTION_MAP_MASK (~(BIT(SECTION_MAP_LAST_BIT) - 1)) #define SECTION_NID_SHIFT SECTION_MAP_LAST_BIT static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } #ifdef CONFIG_ZONE_DEVICE static inline int online_device_section(struct mem_section *section) { unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE; return section && ((section->section_mem_map & flags) == flags); } #else static inline int online_device_section(struct mem_section *section) { return 0; } #endif #ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT static inline int preinited_vmemmap_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT)); } void sparse_vmemmap_init_nid_early(int nid); void sparse_vmemmap_init_nid_late(int nid); #else static inline int preinited_vmemmap_section(struct mem_section *section) { return 0; } static inline void sparse_vmemmap_init_nid_early(int nid) { } static inline void sparse_vmemmap_init_nid_late(int nid) { } #endif static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) { struct mem_section_usage *usage = READ_ONCE(ms->usage); int idx = subsection_map_index(*pfn); unsigned long bit; if (!usage) return false; if (test_bit(idx, usage->subsection_map)) return true; /* Find the next subsection that exists */ bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx); if (bit == SUBSECTIONS_PER_SECTION) return false; *pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION); return true; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn) { return true; } #endif void sparse_init_early_section(int nid, struct page *map, unsigned long pnum, unsigned long flags); #ifndef CONFIG_HAVE_ARCH_PFN_VALID /** * pfn_valid - check if there is a valid memory map entry for a PFN * @pfn: the page frame number to check * * Check if there is a valid memory map entry aka struct page for the @pfn. * Note, that availability of the memory map entry does not imply that * there is actual usable memory at that @pfn. The struct page may * represent a hole or an unusable page frame. * * Return: 1 for PFNs that have memory map entries and 0 otherwise */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; /* * Ensure the upper PAGE_SHIFT bits are clear in the * pfn. Else it might lead to false positives when * some of the upper bits are set, but the lower bits * match a valid pfn. */ if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) return 0; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock_sched(); if (!valid_section(ms)) { rcu_read_unlock_sched(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock_sched(); return ret; } /* Returns end_pfn or higher if no valid PFN remaining in range */ static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn) { unsigned long nr = pfn_to_section_nr(pfn); rcu_read_lock_sched(); while (nr <= __highest_present_section_nr && pfn < end_pfn) { struct mem_section *ms = __pfn_to_section(pfn); if (valid_section(ms) && (early_section(ms) || pfn_section_first_valid(ms, &pfn))) { rcu_read_unlock_sched(); return pfn; } /* Nothing left in this section? Skip to next section */ nr++; pfn = section_nr_to_pfn(nr); } rcu_read_unlock_sched(); return end_pfn; } static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn) { pfn++; if (pfn >= end_pfn) return end_pfn; /* * Either every PFN within the section (or subsection for VMEMMAP) is * valid, or none of them are. So there's no point repeating the check * for every PFN; only call first_valid_pfn() again when crossing a * (sub)section boundary (i.e. !(pfn & ~PAGE_{SUB,}SECTION_MASK)). */ if (pfn & ~(IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ? PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK)) return pfn; return first_valid_pfn(pfn, end_pfn); } #define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn)); \ (_pfn) < (_end_pfn); \ (_pfn) = next_valid_pfn((_pfn), (_end_pfn))) #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } #define for_each_present_section_nr(start, section_nr) \ for (section_nr = next_present_section_nr(start - 1); \ section_nr != -1; \ section_nr = next_present_section_nr(section_nr)) /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0) #define sparse_vmemmap_init_nid_late(_nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ /* * Fallback case for when the architecture provides its own pfn_valid() but * not a corresponding for_each_valid_pfn(). */ #ifndef for_each_valid_pfn #define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn) \ for ((_pfn) = (_start_pfn); (_pfn) < (_end_pfn); (_pfn)++) \ if (pfn_valid(_pfn)) #endif #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 721 4 126 1 3 41 4 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SIGNAL_H #define _LINUX_SIGNAL_H #include <linux/bug.h> #include <linux/list.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_TRAPNO, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, SIL_FAULT_PERF_EVENT, 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 #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 send_signal_locked(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); 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); \ } while (0); #ifdef CONFIG_DYNAMIC_SIGFRAME bool sigaltstack_size_valid(size_t ss_size); #else static inline bool sigaltstack_size_valid(size_t size) { return true; } #endif /* !CONFIG_DYNAMIC_SIGFRAME */ #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 */ |
| 5 7 6 1 1 6 6 1 1 6 6 6 6 6 8 8 7 5 5 5 6 6 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org> * Copyright 2001-2006 Ian Kent <raven@themaw.net> */ #include <linux/capability.h> #include <linux/compat.h> #include "autofs_i.h" static int autofs_dir_permission(struct mnt_idmap *, struct inode *, int); static int autofs_dir_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); static int autofs_dir_unlink(struct inode *, struct dentry *); static int autofs_dir_rmdir(struct inode *, struct dentry *); static struct dentry *autofs_dir_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); static long autofs_root_ioctl(struct file *, unsigned int, unsigned long); #ifdef CONFIG_COMPAT static long autofs_root_compat_ioctl(struct file *, unsigned int, unsigned long); #endif static int autofs_dir_open(struct inode *inode, struct file *file); static struct dentry *autofs_lookup(struct inode *, struct dentry *, unsigned int); static struct vfsmount *autofs_d_automount(struct path *); static int autofs_d_manage(const struct path *, bool); static void autofs_dentry_release(struct dentry *); const struct file_operations autofs_root_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .read = generic_read_dir, .iterate_shared = dcache_readdir, .llseek = dcache_dir_lseek, .unlocked_ioctl = autofs_root_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = autofs_root_compat_ioctl, #endif }; const struct file_operations autofs_dir_operations = { .open = autofs_dir_open, .release = dcache_dir_close, .read = generic_read_dir, .iterate_shared = dcache_readdir, .llseek = dcache_dir_lseek, }; const struct inode_operations autofs_dir_inode_operations = { .lookup = autofs_lookup, .permission = autofs_dir_permission, .unlink = autofs_dir_unlink, .symlink = autofs_dir_symlink, .mkdir = autofs_dir_mkdir, .rmdir = autofs_dir_rmdir, }; const struct dentry_operations autofs_dentry_operations = { .d_automount = autofs_d_automount, .d_manage = autofs_d_manage, .d_release = autofs_dentry_release, }; static void autofs_del_active(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino; ino = autofs_dentry_ino(dentry); spin_lock(&sbi->lookup_lock); list_del_init(&ino->active); spin_unlock(&sbi->lookup_lock); } static int autofs_dir_open(struct inode *inode, struct file *file) { struct dentry *dentry = file->f_path.dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); pr_debug("file=%p dentry=%p %pd\n", file, dentry, dentry); if (autofs_oz_mode(sbi)) goto out; /* * An empty directory in an autofs file system is always a * mount point. The daemon must have failed to mount this * during lookup so it doesn't exist. This can happen, for * example, if user space returns an incorrect status for a * mount request. Otherwise we're doing a readdir on the * autofs file system so just let the libfs routines handle * it. */ spin_lock(&sbi->lookup_lock); if (!path_is_mountpoint(&file->f_path) && autofs_empty(ino)) { spin_unlock(&sbi->lookup_lock); return -ENOENT; } spin_unlock(&sbi->lookup_lock); out: return dcache_dir_open(inode, file); } static void autofs_dentry_release(struct dentry *de) { struct autofs_info *ino = autofs_dentry_ino(de); struct autofs_sb_info *sbi = autofs_sbi(de->d_sb); pr_debug("releasing %p\n", de); if (!ino) return; if (sbi) { spin_lock(&sbi->lookup_lock); if (!list_empty(&ino->active)) list_del(&ino->active); if (!list_empty(&ino->expiring)) list_del(&ino->expiring); spin_unlock(&sbi->lookup_lock); } autofs_free_ino(ino); } static struct dentry *autofs_lookup_active(struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct dentry *parent = dentry->d_parent; const struct qstr *name = &dentry->d_name; unsigned int len = name->len; unsigned int hash = name->hash; const unsigned char *str = name->name; struct list_head *p, *head; head = &sbi->active_list; if (list_empty(head)) return NULL; spin_lock(&sbi->lookup_lock); list_for_each(p, head) { struct autofs_info *ino; struct dentry *active; const struct qstr *qstr; ino = list_entry(p, struct autofs_info, active); active = ino->dentry; spin_lock(&active->d_lock); /* Already gone? */ if ((int) d_count(active) <= 0) goto next; qstr = &active->d_name; if (active->d_name.hash != hash) goto next; if (active->d_parent != parent) goto next; if (qstr->len != len) goto next; if (memcmp(qstr->name, str, len)) goto next; if (d_unhashed(active)) { dget_dlock(active); spin_unlock(&active->d_lock); spin_unlock(&sbi->lookup_lock); return active; } next: spin_unlock(&active->d_lock); } spin_unlock(&sbi->lookup_lock); return NULL; } static struct dentry *autofs_lookup_expiring(struct dentry *dentry, bool rcu_walk) { struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct dentry *parent = dentry->d_parent; const struct qstr *name = &dentry->d_name; unsigned int len = name->len; unsigned int hash = name->hash; const unsigned char *str = name->name; struct list_head *p, *head; head = &sbi->expiring_list; if (list_empty(head)) return NULL; spin_lock(&sbi->lookup_lock); list_for_each(p, head) { struct autofs_info *ino; struct dentry *expiring; const struct qstr *qstr; if (rcu_walk) { spin_unlock(&sbi->lookup_lock); return ERR_PTR(-ECHILD); } ino = list_entry(p, struct autofs_info, expiring); expiring = ino->dentry; spin_lock(&expiring->d_lock); /* We've already been dentry_iput or unlinked */ if (d_really_is_negative(expiring)) goto next; qstr = &expiring->d_name; if (expiring->d_name.hash != hash) goto next; if (expiring->d_parent != parent) goto next; if (qstr->len != len) goto next; if (memcmp(qstr->name, str, len)) goto next; if (d_unhashed(expiring)) { dget_dlock(expiring); spin_unlock(&expiring->d_lock); spin_unlock(&sbi->lookup_lock); return expiring; } next: spin_unlock(&expiring->d_lock); } spin_unlock(&sbi->lookup_lock); return NULL; } static int autofs_mount_wait(const struct path *path, bool rcu_walk) { struct autofs_sb_info *sbi = autofs_sbi(path->dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(path->dentry); int status = 0; if (ino->flags & AUTOFS_INF_PENDING) { if (rcu_walk) return -ECHILD; pr_debug("waiting for mount name=%pd\n", path->dentry); status = autofs_wait(sbi, path, NFY_MOUNT); pr_debug("mount wait done status=%d\n", status); ino->last_used = jiffies; return status; } if (!(sbi->flags & AUTOFS_SBI_STRICTEXPIRE)) ino->last_used = jiffies; return status; } static int do_expire_wait(const struct path *path, bool rcu_walk) { struct dentry *dentry = path->dentry; struct dentry *expiring; expiring = autofs_lookup_expiring(dentry, rcu_walk); if (IS_ERR(expiring)) return PTR_ERR(expiring); if (!expiring) return autofs_expire_wait(path, rcu_walk); else { const struct path this = { .mnt = path->mnt, .dentry = expiring }; /* * If we are racing with expire the request might not * be quite complete, but the directory has been removed * so it must have been successful, just wait for it. */ autofs_expire_wait(&this, 0); autofs_del_expiring(expiring); dput(expiring); } return 0; } static struct dentry *autofs_mountpoint_changed(struct path *path) { struct dentry *dentry = path->dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); /* If this is an indirect mount the dentry could have gone away * and a new one created. * * This is unusual and I can't remember the case for which it * was originally added now. But an example of how this can * happen is an autofs indirect mount that has the "browse" * option set and also has the "symlink" option in the autofs * map entry. In this case the daemon will remove the browse * directory and create a symlink as the mount leaving the * struct path stale. * * Another not so obvious case is when a mount in an autofs * indirect mount that uses the "nobrowse" option is being * expired at the same time as a path walk. If the mount has * been umounted but the mount point directory seen before * becoming unhashed (during a lockless path walk) when a stat * family system call is made the mount won't be re-mounted as * it should. In this case the mount point that's been removed * (by the daemon) will be stale and the a new mount point * dentry created. */ if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) { struct dentry *parent = dentry->d_parent; struct autofs_info *ino; struct dentry *new; new = d_lookup(parent, &dentry->d_name); if (!new) return NULL; ino = autofs_dentry_ino(new); ino->last_used = jiffies; dput(path->dentry); path->dentry = new; } return path->dentry; } static struct vfsmount *autofs_d_automount(struct path *path) { struct dentry *dentry = path->dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); int status; pr_debug("dentry=%p %pd\n", dentry, dentry); /* The daemon never triggers a mount. */ if (autofs_oz_mode(sbi)) return NULL; /* * If an expire request is pending everyone must wait. * If the expire fails we're still mounted so continue * the follow and return. A return of -EAGAIN (which only * happens with indirect mounts) means the expire completed * and the directory was removed, so just go ahead and try * the mount. */ status = do_expire_wait(path, 0); if (status && status != -EAGAIN) return NULL; /* Callback to the daemon to perform the mount or wait */ spin_lock(&sbi->fs_lock); if (ino->flags & AUTOFS_INF_PENDING) { spin_unlock(&sbi->fs_lock); status = autofs_mount_wait(path, 0); if (status) return ERR_PTR(status); goto done; } /* * If the dentry is a symlink it's equivalent to a directory * having path_is_mountpoint() true, so there's no need to call * back to the daemon. */ if (d_really_is_positive(dentry) && d_is_symlink(dentry)) { spin_unlock(&sbi->fs_lock); goto done; } if (!path_is_mountpoint(path)) { /* * It's possible that user space hasn't removed directories * after umounting a rootless multi-mount, although it * should. For v5 path_has_submounts() is sufficient to * handle this because the leaves of the directory tree under * the mount never trigger mounts themselves (they have an * autofs trigger mount mounted on them). But v4 pseudo direct * mounts do need the leaves to trigger mounts. In this case * we have no choice but to use the autofs_empty() check and * require user space behave. */ if (sbi->version > 4) { if (path_has_submounts(path)) { spin_unlock(&sbi->fs_lock); goto done; } } else { if (!autofs_empty(ino)) { spin_unlock(&sbi->fs_lock); goto done; } } ino->flags |= AUTOFS_INF_PENDING; spin_unlock(&sbi->fs_lock); status = autofs_mount_wait(path, 0); spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_PENDING; if (status) { spin_unlock(&sbi->fs_lock); return ERR_PTR(status); } } spin_unlock(&sbi->fs_lock); done: /* Mount succeeded, check if we ended up with a new dentry */ dentry = autofs_mountpoint_changed(path); if (!dentry) return ERR_PTR(-ENOENT); return NULL; } static int autofs_d_manage(const struct path *path, bool rcu_walk) { struct dentry *dentry = path->dentry; struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); int status; pr_debug("dentry=%p %pd\n", dentry, dentry); /* The daemon never waits. */ if (autofs_oz_mode(sbi)) { if (!path_is_mountpoint(path)) return -EISDIR; return 0; } /* Wait for pending expires */ if (do_expire_wait(path, rcu_walk) == -ECHILD) return -ECHILD; /* * This dentry may be under construction so wait on mount * completion. */ status = autofs_mount_wait(path, rcu_walk); if (status) return status; if (rcu_walk) { /* We don't need fs_lock in rcu_walk mode, * just testing 'AUTOFS_INF_WANT_EXPIRE' is enough. * * We only return -EISDIR when certain this isn't * a mount-trap. */ struct inode *inode; if (ino->flags & AUTOFS_INF_WANT_EXPIRE) return 0; if (path_is_mountpoint(path)) return 0; inode = d_inode_rcu(dentry); if (inode && S_ISLNK(inode->i_mode)) return -EISDIR; if (!autofs_empty(ino)) return -EISDIR; return 0; } spin_lock(&sbi->fs_lock); /* * If the dentry has been selected for expire while we slept * on the lock then it might go away. We'll deal with that in * ->d_automount() and wait on a new mount if the expire * succeeds or return here if it doesn't (since there's no * mount to follow with a rootless multi-mount). */ if (!(ino->flags & AUTOFS_INF_EXPIRING)) { /* * Any needed mounting has been completed and the path * updated so check if this is a rootless multi-mount so * we can avoid needless calls ->d_automount() and avoid * an incorrect ELOOP error return. */ if ((!path_is_mountpoint(path) && !autofs_empty(ino)) || (d_really_is_positive(dentry) && d_is_symlink(dentry))) status = -EISDIR; } spin_unlock(&sbi->fs_lock); return status; } /* Lookups in the root directory */ static struct dentry *autofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct autofs_sb_info *sbi; struct autofs_info *ino; struct dentry *active; pr_debug("name = %pd\n", dentry); /* File name too long to exist */ if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); sbi = autofs_sbi(dir->i_sb); pr_debug("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n", current->pid, task_pgrp_nr(current), sbi->flags & AUTOFS_SBI_CATATONIC, autofs_oz_mode(sbi)); active = autofs_lookup_active(dentry); if (active) return active; else { /* * A dentry that is not within the root can never trigger a * mount operation, unless the directory already exists, so we * can return fail immediately. The daemon however does need * to create directories within the file system. */ if (!autofs_oz_mode(sbi) && !IS_ROOT(dentry->d_parent)) return ERR_PTR(-ENOENT); ino = autofs_new_ino(sbi); if (!ino) return ERR_PTR(-ENOMEM); spin_lock(&sbi->lookup_lock); spin_lock(&dentry->d_lock); /* Mark entries in the root as mount triggers */ if (IS_ROOT(dentry->d_parent) && autofs_type_indirect(sbi->type)) __managed_dentry_set_managed(dentry); dentry->d_fsdata = ino; ino->dentry = dentry; list_add(&ino->active, &sbi->active_list); spin_unlock(&sbi->lookup_lock); spin_unlock(&dentry->d_lock); } return NULL; } static int autofs_dir_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { if (mask & MAY_WRITE) { struct autofs_sb_info *sbi = autofs_sbi(inode->i_sb); if (!autofs_oz_mode(sbi)) return -EACCES; /* autofs_oz_mode() needs to allow path walks when the * autofs mount is catatonic but the state of an autofs * file system needs to be preserved over restarts. */ if (sbi->flags & AUTOFS_SBI_CATATONIC) return -EACCES; } return generic_permission(idmap, inode, mask); } static int autofs_dir_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; struct inode *inode; size_t size = strlen(symname); char *cp; pr_debug("%s <- %pd\n", symname, dentry); BUG_ON(!ino); autofs_clean_ino(ino); autofs_del_active(dentry); cp = kmalloc(size + 1, GFP_KERNEL); if (!cp) return -ENOMEM; strcpy(cp, symname); inode = autofs_get_inode(dir->i_sb, S_IFLNK | 0555); if (!inode) { kfree(cp); return -ENOMEM; } inode->i_private = cp; inode->i_size = size; d_add(dentry, inode); dget(dentry); p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return 0; } /* * NOTE! * * Normal filesystems would do a "d_delete()" to tell the VFS dcache * that the file no longer exists. However, doing that means that the * VFS layer can turn the dentry into a negative dentry. We don't want * this, because the unlink is probably the result of an expire. * We simply d_drop it and add it to a expiring list in the super block, * which allows the dentry lookup to check for an incomplete expire. * * If a process is blocked on the dentry waiting for the expire to finish, * it will invalidate the dentry and try to mount with a new one. * * Also see autofs_dir_rmdir().. */ static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count--; dput(ino->dentry); d_inode(dentry)->i_size = 0; clear_nlink(d_inode(dentry)); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); spin_lock(&sbi->lookup_lock); __autofs_add_expiring(dentry); d_drop(dentry); spin_unlock(&sbi->lookup_lock); return 0; } /* * Version 4 of autofs provides a pseudo direct mount implementation * that relies on directories at the leaves of a directory tree under * an indirect mount to trigger mounts. To allow for this we need to * set the DMANAGED_AUTOMOUNT and DMANAGED_TRANSIT flags on the leaves * of the directory tree. There is no need to clear the automount flag * following a mount or restore it after an expire because these mounts * are always covered. However, it is necessary to ensure that these * flags are clear on non-empty directories to avoid unnecessary calls * during path walks. */ static void autofs_set_leaf_automount_flags(struct dentry *dentry) { struct dentry *parent; /* root and dentrys in the root are already handled */ if (IS_ROOT(dentry->d_parent)) return; managed_dentry_set_managed(dentry); parent = dentry->d_parent; /* only consider parents below dentrys in the root */ if (IS_ROOT(parent->d_parent)) return; managed_dentry_clear_managed(parent); } static void autofs_clear_leaf_automount_flags(struct dentry *dentry) { struct dentry *parent; /* flags for dentrys in the root are handled elsewhere */ if (IS_ROOT(dentry->d_parent)) return; managed_dentry_clear_managed(dentry); parent = dentry->d_parent; /* only consider parents below dentrys in the root */ if (IS_ROOT(parent->d_parent)) return; if (autofs_dentry_ino(parent)->count == 2) managed_dentry_set_managed(parent); } static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) { struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; pr_debug("dentry %p, removing %pd\n", dentry, dentry); if (ino->count != 1) return -ENOTEMPTY; spin_lock(&sbi->lookup_lock); __autofs_add_expiring(dentry); d_drop(dentry); spin_unlock(&sbi->lookup_lock); if (sbi->version < 5) autofs_clear_leaf_automount_flags(dentry); p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count--; dput(ino->dentry); d_inode(dentry)->i_size = 0; clear_nlink(d_inode(dentry)); if (dir->i_nlink) drop_nlink(dir); return 0; } static struct dentry *autofs_dir_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; struct inode *inode; pr_debug("dentry %p, creating %pd\n", dentry, dentry); BUG_ON(!ino); autofs_clean_ino(ino); autofs_del_active(dentry); inode = autofs_get_inode(dir->i_sb, S_IFDIR | mode); if (!inode) return ERR_PTR(-ENOMEM); d_add(dentry, inode); if (sbi->version < 5) autofs_set_leaf_automount_flags(dentry); dget(dentry); p_ino = autofs_dentry_ino(dentry->d_parent); p_ino->count++; inc_nlink(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return NULL; } /* Get/set timeout ioctl() operation */ #ifdef CONFIG_COMPAT static inline int autofs_compat_get_set_timeout(struct autofs_sb_info *sbi, compat_ulong_t __user *p) { unsigned long ntimeout; int rv; rv = get_user(ntimeout, p); if (rv) goto error; rv = put_user(sbi->exp_timeout/HZ, p); if (rv) goto error; if (ntimeout > UINT_MAX/HZ) sbi->exp_timeout = 0; else sbi->exp_timeout = ntimeout * HZ; return 0; error: return rv; } #endif static inline int autofs_get_set_timeout(struct autofs_sb_info *sbi, unsigned long __user *p) { unsigned long ntimeout; int rv; rv = get_user(ntimeout, p); if (rv) goto error; rv = put_user(sbi->exp_timeout/HZ, p); if (rv) goto error; if (ntimeout > ULONG_MAX/HZ) sbi->exp_timeout = 0; else sbi->exp_timeout = ntimeout * HZ; return 0; error: return rv; } /* Return protocol version */ static inline int autofs_get_protover(struct autofs_sb_info *sbi, int __user *p) { return put_user(sbi->version, p); } /* Return protocol sub version */ static inline int autofs_get_protosubver(struct autofs_sb_info *sbi, int __user *p) { return put_user(sbi->sub_version, p); } /* * Tells the daemon whether it can umount the autofs mount. */ static inline int autofs_ask_umount(struct vfsmount *mnt, int __user *p) { int status = 0; if (may_umount(mnt)) status = 1; pr_debug("may umount %d\n", status); status = put_user(status, p); return status; } /* Identify autofs_dentries - this is so we can tell if there's * an extra dentry refcount or not. We only hold a refcount on the * dentry if its non-negative (ie, d_inode != NULL) */ int is_autofs_dentry(struct dentry *dentry) { return dentry && d_really_is_positive(dentry) && dentry->d_op == &autofs_dentry_operations && dentry->d_fsdata != NULL; } /* * ioctl()'s on the root directory is the chief method for the daemon to * generate kernel reactions */ static int autofs_root_ioctl_unlocked(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg) { struct autofs_sb_info *sbi = autofs_sbi(inode->i_sb); void __user *p = (void __user *)arg; pr_debug("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n", cmd, arg, sbi, task_pgrp_nr(current)); if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) || _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT) return -ENOTTY; if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) return -EPERM; switch (cmd) { case AUTOFS_IOC_READY: /* Wait queue: go ahead and retry */ return autofs_wait_release(sbi, (autofs_wqt_t) arg, 0); case AUTOFS_IOC_FAIL: /* Wait queue: fail with ENOENT */ return autofs_wait_release(sbi, (autofs_wqt_t) arg, -ENOENT); case AUTOFS_IOC_CATATONIC: /* Enter catatonic mode (daemon shutdown) */ autofs_catatonic_mode(sbi); return 0; case AUTOFS_IOC_PROTOVER: /* Get protocol version */ return autofs_get_protover(sbi, p); case AUTOFS_IOC_PROTOSUBVER: /* Get protocol sub version */ return autofs_get_protosubver(sbi, p); case AUTOFS_IOC_SETTIMEOUT: return autofs_get_set_timeout(sbi, p); #ifdef CONFIG_COMPAT case AUTOFS_IOC_SETTIMEOUT32: return autofs_compat_get_set_timeout(sbi, p); #endif case AUTOFS_IOC_ASKUMOUNT: return autofs_ask_umount(filp->f_path.mnt, p); /* return a single thing to expire */ case AUTOFS_IOC_EXPIRE: return autofs_expire_run(inode->i_sb, filp->f_path.mnt, sbi, p); /* same as above, but can send multiple expires through pipe */ case AUTOFS_IOC_EXPIRE_MULTI: return autofs_expire_multi(inode->i_sb, filp->f_path.mnt, sbi, p); default: return -EINVAL; } } static long autofs_root_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); return autofs_root_ioctl_unlocked(inode, filp, cmd, arg); } #ifdef CONFIG_COMPAT static long autofs_root_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); int ret; if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL) ret = autofs_root_ioctl_unlocked(inode, filp, cmd, arg); else ret = autofs_root_ioctl_unlocked(inode, filp, cmd, (unsigned long) compat_ptr(arg)); return ret; } #endif |
| 2 2 2 1 1 5 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/netfilter/nf_dup_netdev.h> #include <net/neighbour.h> #include <net/ip.h> struct nft_fwd_netdev { u8 sreg_dev; }; static void nft_fwd_netdev_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_fwd_netdev *priv = nft_expr_priv(expr); int oif = regs->data[priv->sreg_dev]; struct sk_buff *skb = pkt->skb; /* This is used by ifb only. */ skb->skb_iif = skb->dev->ifindex; skb_set_redirected(skb, nft_hook(pkt) == NF_NETDEV_INGRESS); nf_fwd_netdev_egress(pkt, oif); regs->verdict.code = NF_STOLEN; } static const struct nla_policy nft_fwd_netdev_policy[NFTA_FWD_MAX + 1] = { [NFTA_FWD_SREG_DEV] = { .type = NLA_U32 }, [NFTA_FWD_SREG_ADDR] = { .type = NLA_U32 }, [NFTA_FWD_NFPROTO] = NLA_POLICY_MAX(NLA_BE32, 255), }; static int nft_fwd_netdev_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_fwd_netdev *priv = nft_expr_priv(expr); if (tb[NFTA_FWD_SREG_DEV] == NULL) return -EINVAL; return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); } static int nft_fwd_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_fwd_netdev *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_FWD_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int nft_fwd_netdev_offload(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr) { const struct nft_fwd_netdev *priv = nft_expr_priv(expr); int oif = ctx->regs[priv->sreg_dev].data.data[0]; return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_REDIRECT, oif); } static bool nft_fwd_netdev_offload_action(const struct nft_expr *expr) { return true; } struct nft_fwd_neigh { u8 sreg_dev; u8 sreg_addr; u8 nfproto; }; static void nft_fwd_neigh_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_fwd_neigh *priv = nft_expr_priv(expr); void *addr = ®s->data[priv->sreg_addr]; int oif = regs->data[priv->sreg_dev]; unsigned int verdict = NF_STOLEN; struct sk_buff *skb = pkt->skb; struct net_device *dev; int neigh_table; switch (priv->nfproto) { case NFPROTO_IPV4: { struct iphdr *iph; if (skb->protocol != htons(ETH_P_IP)) { verdict = NFT_BREAK; goto out; } if (skb_try_make_writable(skb, sizeof(*iph))) { verdict = NF_DROP; goto out; } iph = ip_hdr(skb); ip_decrease_ttl(iph); neigh_table = NEIGH_ARP_TABLE; break; } case NFPROTO_IPV6: { struct ipv6hdr *ip6h; if (skb->protocol != htons(ETH_P_IPV6)) { verdict = NFT_BREAK; goto out; } if (skb_try_make_writable(skb, sizeof(*ip6h))) { verdict = NF_DROP; goto out; } ip6h = ipv6_hdr(skb); ip6h->hop_limit--; neigh_table = NEIGH_ND_TABLE; break; } default: verdict = NFT_BREAK; goto out; } dev = dev_get_by_index_rcu(nft_net(pkt), oif); if (dev == NULL) return; skb->dev = dev; skb_clear_tstamp(skb); neigh_xmit(neigh_table, dev, addr, skb); out: regs->verdict.code = verdict; } static int nft_fwd_neigh_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_fwd_neigh *priv = nft_expr_priv(expr); unsigned int addr_len; int err; if (!tb[NFTA_FWD_SREG_DEV] || !tb[NFTA_FWD_SREG_ADDR] || !tb[NFTA_FWD_NFPROTO]) return -EINVAL; priv->nfproto = ntohl(nla_get_be32(tb[NFTA_FWD_NFPROTO])); switch (priv->nfproto) { case NFPROTO_IPV4: addr_len = sizeof(struct in_addr); break; case NFPROTO_IPV6: addr_len = sizeof(struct in6_addr); break; default: return -EOPNOTSUPP; } err = nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); if (err < 0) return err; return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, addr_len); } static int nft_fwd_neigh_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_fwd_neigh *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_FWD_SREG_DEV, priv->sreg_dev) || nft_dump_register(skb, NFTA_FWD_SREG_ADDR, priv->sreg_addr) || nla_put_be32(skb, NFTA_FWD_NFPROTO, htonl(priv->nfproto))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int nft_fwd_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS) | (1 << NF_NETDEV_EGRESS)); } static struct nft_expr_type nft_fwd_netdev_type; static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = { .type = &nft_fwd_netdev_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fwd_neigh)), .eval = nft_fwd_neigh_eval, .init = nft_fwd_neigh_init, .dump = nft_fwd_neigh_dump, .validate = nft_fwd_validate, .reduce = NFT_REDUCE_READONLY, }; static const struct nft_expr_ops nft_fwd_netdev_ops = { .type = &nft_fwd_netdev_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fwd_netdev)), .eval = nft_fwd_netdev_eval, .init = nft_fwd_netdev_init, .dump = nft_fwd_netdev_dump, .validate = nft_fwd_validate, .reduce = NFT_REDUCE_READONLY, .offload = nft_fwd_netdev_offload, .offload_action = nft_fwd_netdev_offload_action, }; static const struct nft_expr_ops * nft_fwd_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { if (tb[NFTA_FWD_SREG_ADDR]) return &nft_fwd_neigh_netdev_ops; if (tb[NFTA_FWD_SREG_DEV]) return &nft_fwd_netdev_ops; return ERR_PTR(-EOPNOTSUPP); } static struct nft_expr_type nft_fwd_netdev_type __read_mostly = { .family = NFPROTO_NETDEV, .name = "fwd", .select_ops = nft_fwd_select_ops, .policy = nft_fwd_netdev_policy, .maxattr = NFTA_FWD_MAX, .owner = THIS_MODULE, }; static int __init nft_fwd_netdev_module_init(void) { return nft_register_expr(&nft_fwd_netdev_type); } static void __exit nft_fwd_netdev_module_exit(void) { nft_unregister_expr(&nft_fwd_netdev_type); } module_init(nft_fwd_netdev_module_init); module_exit(nft_fwd_netdev_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("nftables netdev packet forwarding support"); MODULE_ALIAS_NFT_AF_EXPR(5, "fwd"); |
| 37 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007-2012 Siemens AG * * Written by: * Pavel Smolenskiy <pavel.smolenskiy@gmail.com> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/crc-ccitt.h> #include <linux/unaligned.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/nl802154.h> #include "ieee802154_i.h" static int ieee802154_deliver_skb(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->protocol = htons(ETH_P_IEEE802154); return netif_receive_skb(skb); } void mac802154_rx_beacon_worker(struct work_struct *work) { struct ieee802154_local *local = container_of(work, struct ieee802154_local, rx_beacon_work); struct cfg802154_mac_pkt *mac_pkt; mac_pkt = list_first_entry_or_null(&local->rx_beacon_list, struct cfg802154_mac_pkt, node); if (!mac_pkt) return; mac802154_process_beacon(local, mac_pkt->skb, mac_pkt->page, mac_pkt->channel); list_del(&mac_pkt->node); kfree_skb(mac_pkt->skb); kfree(mac_pkt); } static bool mac802154_should_answer_beacon_req(struct ieee802154_local *local) { struct cfg802154_beacon_request *beacon_req; unsigned int interval; rcu_read_lock(); beacon_req = rcu_dereference(local->beacon_req); if (!beacon_req) { rcu_read_unlock(); return false; } interval = beacon_req->interval; rcu_read_unlock(); if (!mac802154_is_beaconing(local)) return false; return interval == IEEE802154_ACTIVE_SCAN_DURATION; } void mac802154_rx_mac_cmd_worker(struct work_struct *work) { struct ieee802154_local *local = container_of(work, struct ieee802154_local, rx_mac_cmd_work); struct cfg802154_mac_pkt *mac_pkt; u8 mac_cmd; int rc; mac_pkt = list_first_entry_or_null(&local->rx_mac_cmd_list, struct cfg802154_mac_pkt, node); if (!mac_pkt) return; rc = ieee802154_get_mac_cmd(mac_pkt->skb, &mac_cmd); if (rc) goto out; switch (mac_cmd) { case IEEE802154_CMD_BEACON_REQ: dev_dbg(&mac_pkt->sdata->dev->dev, "processing BEACON REQ\n"); if (!mac802154_should_answer_beacon_req(local)) break; queue_delayed_work(local->mac_wq, &local->beacon_work, 0); break; case IEEE802154_CMD_ASSOCIATION_RESP: dev_dbg(&mac_pkt->sdata->dev->dev, "processing ASSOC RESP\n"); if (!mac802154_is_associating(local)) break; mac802154_process_association_resp(mac_pkt->sdata, mac_pkt->skb); break; case IEEE802154_CMD_ASSOCIATION_REQ: dev_dbg(&mac_pkt->sdata->dev->dev, "processing ASSOC REQ\n"); if (mac_pkt->sdata->wpan_dev.iftype != NL802154_IFTYPE_COORD) break; mac802154_process_association_req(mac_pkt->sdata, mac_pkt->skb); break; case IEEE802154_CMD_DISASSOCIATION_NOTIFY: dev_dbg(&mac_pkt->sdata->dev->dev, "processing DISASSOC NOTIF\n"); if (mac_pkt->sdata->wpan_dev.iftype != NL802154_IFTYPE_COORD) break; mac802154_process_disassociation_notif(mac_pkt->sdata, mac_pkt->skb); break; default: break; } out: list_del(&mac_pkt->node); kfree_skb(mac_pkt->skb); kfree(mac_pkt); } static int ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, struct sk_buff *skb, const struct ieee802154_hdr *hdr) { struct wpan_phy *wpan_phy = sdata->local->hw.phy; struct wpan_dev *wpan_dev = &sdata->wpan_dev; struct cfg802154_mac_pkt *mac_pkt; __le16 span, sshort; int rc; pr_debug("getting packet via slave interface %s\n", sdata->dev->name); span = wpan_dev->pan_id; sshort = wpan_dev->short_addr; /* Level 3 filtering: Only beacons are accepted during scans */ if (sdata->required_filtering == IEEE802154_FILTERING_3_SCAN && sdata->required_filtering > wpan_phy->filtering) { if (mac_cb(skb)->type != IEEE802154_FC_TYPE_BEACON) { dev_dbg(&sdata->dev->dev, "drop non-beacon frame (0x%x) during scan\n", mac_cb(skb)->type); goto fail; } } switch (mac_cb(skb)->dest.mode) { case IEEE802154_ADDR_NONE: if (hdr->source.mode == IEEE802154_ADDR_NONE) /* ACK comes with both addresses empty */ skb->pkt_type = PACKET_HOST; else if (!wpan_dev->parent) /* No dest means PAN coordinator is the recipient */ skb->pkt_type = PACKET_HOST; else /* We are not the PAN coordinator, just relaying */ skb->pkt_type = PACKET_OTHERHOST; break; case IEEE802154_ADDR_LONG: if (mac_cb(skb)->dest.pan_id != span && mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) skb->pkt_type = PACKET_OTHERHOST; else if (mac_cb(skb)->dest.extended_addr == wpan_dev->extended_addr) skb->pkt_type = PACKET_HOST; else skb->pkt_type = PACKET_OTHERHOST; break; case IEEE802154_ADDR_SHORT: if (mac_cb(skb)->dest.pan_id != span && mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) skb->pkt_type = PACKET_OTHERHOST; else if (mac_cb(skb)->dest.short_addr == sshort) skb->pkt_type = PACKET_HOST; else if (mac_cb(skb)->dest.short_addr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_OTHERHOST; break; default: pr_debug("invalid dest mode\n"); goto fail; } skb->dev = sdata->dev; /* TODO this should be moved after netif_receive_skb call, otherwise * wireshark will show a mac header with security fields and the * payload is already decrypted. */ rc = mac802154_llsec_decrypt(&sdata->sec, skb); if (rc) { pr_debug("decryption failed: %i\n", rc); goto fail; } sdata->dev->stats.rx_packets++; sdata->dev->stats.rx_bytes += skb->len; switch (mac_cb(skb)->type) { case IEEE802154_FC_TYPE_BEACON: dev_dbg(&sdata->dev->dev, "BEACON received\n"); if (!mac802154_is_scanning(sdata->local)) goto fail; mac_pkt = kzalloc(sizeof(*mac_pkt), GFP_ATOMIC); if (!mac_pkt) goto fail; mac_pkt->skb = skb_get(skb); mac_pkt->sdata = sdata; mac_pkt->page = sdata->local->scan_page; mac_pkt->channel = sdata->local->scan_channel; list_add_tail(&mac_pkt->node, &sdata->local->rx_beacon_list); queue_work(sdata->local->mac_wq, &sdata->local->rx_beacon_work); return NET_RX_SUCCESS; case IEEE802154_FC_TYPE_MAC_CMD: dev_dbg(&sdata->dev->dev, "MAC COMMAND received\n"); mac_pkt = kzalloc(sizeof(*mac_pkt), GFP_ATOMIC); if (!mac_pkt) goto fail; mac_pkt->skb = skb_get(skb); mac_pkt->sdata = sdata; list_add_tail(&mac_pkt->node, &sdata->local->rx_mac_cmd_list); queue_work(sdata->local->mac_wq, &sdata->local->rx_mac_cmd_work); return NET_RX_SUCCESS; case IEEE802154_FC_TYPE_ACK: goto fail; case IEEE802154_FC_TYPE_DATA: return ieee802154_deliver_skb(skb); default: pr_warn_ratelimited("ieee802154: bad frame received " "(type = %d)\n", mac_cb(skb)->type); goto fail; } fail: kfree_skb(skb); return NET_RX_DROP; } static void ieee802154_print_addr(const char *name, const struct ieee802154_addr *addr) { if (addr->mode == IEEE802154_ADDR_NONE) { pr_debug("%s not present\n", name); return; } pr_debug("%s PAN ID: %04x\n", name, le16_to_cpu(addr->pan_id)); if (addr->mode == IEEE802154_ADDR_SHORT) { pr_debug("%s is short: %04x\n", name, le16_to_cpu(addr->short_addr)); } else { u64 hw = swab64((__force u64)addr->extended_addr); pr_debug("%s is hardware: %8phC\n", name, &hw); } } static int ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr) { int hlen; struct ieee802154_mac_cb *cb = mac_cb(skb); skb_reset_mac_header(skb); hlen = ieee802154_hdr_pull(skb, hdr); if (hlen < 0) return -EINVAL; skb->mac_len = hlen; pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr->fc), hdr->seq); cb->type = hdr->fc.type; cb->ackreq = hdr->fc.ack_request; cb->secen = hdr->fc.security_enabled; ieee802154_print_addr("destination", &hdr->dest); ieee802154_print_addr("source", &hdr->source); cb->source = hdr->source; cb->dest = hdr->dest; if (hdr->fc.security_enabled) { u64 key; pr_debug("seclevel %i\n", hdr->sec.level); switch (hdr->sec.key_id_mode) { case IEEE802154_SCF_KEY_IMPLICIT: pr_debug("implicit key\n"); break; case IEEE802154_SCF_KEY_INDEX: pr_debug("key %02x\n", hdr->sec.key_id); break; case IEEE802154_SCF_KEY_SHORT_INDEX: pr_debug("key %04x:%04x %02x\n", le32_to_cpu(hdr->sec.short_src) >> 16, le32_to_cpu(hdr->sec.short_src) & 0xffff, hdr->sec.key_id); break; case IEEE802154_SCF_KEY_HW_INDEX: key = swab64((__force u64)hdr->sec.extended_src); pr_debug("key source %8phC %02x\n", &key, hdr->sec.key_id); break; } } return 0; } static void __ieee802154_rx_handle_packet(struct ieee802154_local *local, struct sk_buff *skb) { int ret; struct ieee802154_sub_if_data *sdata; struct ieee802154_hdr hdr; struct sk_buff *skb2; ret = ieee802154_parse_frame_start(skb, &hdr); if (ret) { pr_debug("got invalid frame\n"); return; } list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (sdata->wpan_dev.iftype == NL802154_IFTYPE_MONITOR) continue; if (!ieee802154_sdata_running(sdata)) continue; /* Do not deliver packets received on interfaces expecting * AACK=1 if the address filters where disabled. */ if (local->hw.phy->filtering < IEEE802154_FILTERING_4_FRAME_FIELDS && sdata->required_filtering == IEEE802154_FILTERIN |