| 235 235 234 235 233 21 232 233 233 233 234 166 70 233 234 8 8 7 1 7 7 229 229 165 165 165 165 165 166 165 1 165 9 165 165 165 165 165 165 165 165 14 165 151 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The Internet Protocol (IP) output module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <Alan.Cox@linux.org> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Hirokazu Takahashi, <taka@valinux.co.jp> * * See ip_input.c for original log * * Fixes: * Alan Cox : Missing nonblock feature in ip_build_xmit. * Mike Kilburn : htons() missing in ip_build_xmit. * Bradford Johnson: Fix faulty handling of some frames when * no route is found. * Alexander Demenshin: Missing sk/skb free in ip_queue_xmit * (in case if packet not accepted by * output firewall rules) * Mike McLagan : Routing by source * Alexey Kuznetsov: use new route cache * Andi Kleen: Fix broken PMTU recovery and remove * some redundant tests. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 * and more readability. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. * Hirokazu Takahashi: HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi: sendfile() on UDP works now. */ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } EXPORT_SYMBOL(ip_send_check); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { int ttl = inet->uc_ttl; if (ttl < 0) ttl = ip4_dst_hoplimit(dst); return ttl; } /* * Add an ip header to a skbuff and send it out. * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; /* Do not bother generating IPID for small packets (eg SYNACK) */ if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; /* TCP packets here are SYNACK with fat IPv4/TCP options. * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) iph->id = (__force __be16)get_random_u16(); else __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; ip_options_build(skb, &opt->opt, daddr, rt); } skb->priority = READ_ONCE(sk->sk_priority); if (!skb->mark) skb->mark = READ_ONCE(sk->sk_mark); /* Send it out. */ return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return res; } rcu_read_unlock(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return PTR_ERR(neigh); } static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* common case: seglen is <= mtu */ if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. * * This can happen in several cases: * - Forwarding of a TCP GRO skb, when DF flag is not set. * - Forwarding of an skb that arrived on a virtualization interface * (virtio-net/vhost/tap) with TSO/GSO size set by other network * stack. * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an * insufficient MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; } return ret; } static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: return __ip_finish_output(net, sk, skb); case NET_XMIT_CN: return __ip_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *new_rt; bool do_cn = false; int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_CN: do_cn = true; fallthrough; case NET_XMIT_SUCCESS: break; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, * see ipv4_pktinfo_prepare(). */ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); if (new_rt) { new_rt->rt_iif = 0; skb_dst_drop(skb); skb_dst_set(skb, &new_rt->dst); } err = dev_loopback_xmit(net, sk, skb); return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. */ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); /* * Multicasts are looped back for other local users */ if (rt->rt_flags&RTCF_MULTICAST) { if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped by ip_mr_input in any case. Note, that local frames are looped back to be delivered to local recipients. This check is duplicated in ip_mr_input at the moment. */ && ((rt->rt_flags & RTCF_LOCAL) || !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } /* Multicasts with ttl 0 must not go beyond the host */ if (ip_hdr(skb)->ttl == 0) { kfree_skb(skb); return 0; } } if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores * Equivalent to : * iph->saddr = fl4->saddr; * iph->daddr = fl4->daddr; */ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); iph->saddr = fl4->saddr; iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); if (!rt) { __be32 daddr; /* Use correct destination address if we have options. */ daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(net, fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS_TOS(sk, tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); } skb_dst_set_noref(skb, &rt->dst); packet_routed: if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_IP_OUTNOROUTES); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos); } EXPORT_SYMBOL(ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, from); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); #if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); } static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter) { unsigned int first_len = skb_pagelen(skb); iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->iph = iph; iter->hlen = hlen; skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_init); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; struct iphdr *iph = iter->iph; struct sk_buff *frag; frag = iter->frag; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iph, hlen); iter->iph = ip_hdr(frag); iph = iter->iph; iph->tot_len = htons(frag->len); ip_copy_metadata(frag, skb); iter->offset += skb->len - hlen; iph->frag_off = htons(iter->offset >> 3); if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; state->not_last_frag = iph->frag_off & htons(IP_MF); } EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE * on the initial skb, so that all the following fragments * will inherit fixed options. */ if (first_frag) ip_options_fragment(from); } struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) { unsigned int len = state->left; struct sk_buff *skb2; struct iphdr *iph; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) { len &= ~7; } /* Allocate buffer */ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip_copy_metadata(skb2, skb); skb_reserve(skb2, state->ll_rs); skb_put(skb2, len + state->hlen); skb_reset_network_header(skb2); skb2->transport_header = skb2->network_header + state->hlen; /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(skb2, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) BUG(); state->left -= len; /* * Fill in the new header fields. */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); if (state->DF) iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the * last fragment then keep MF on each bit */ if (state->left > 0 || state->not_last_frag) iph->frag_off |= htons(IP_MF); state->ptr += len; state->offset += len; iph->tot_len = htons(len + state->hlen); ip_send_check(iph); return skb2; } EXPORT_SYMBOL(ip_frag_next); /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus * a block of the data of the original IP data part) that will yet fit in a * single device frame, and queue such a frame for sending. */ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; struct sk_buff *skb2; bool mono_delivery_time = skb->mono_delivery_time; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; /* * Point into the IP datagram header. */ iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. */ hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing * one, it is not prohibited. In this case fall back to copying. * * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { struct sk_buff *frag, *frag2; unsigned int first_len = skb_pagelen(skb); if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || skb_cloned(skb) || skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen + ll_rs) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { bool first_frag = (iter.offset == 0); IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); if (first_frag && IPCB(skb)->opt.optlen) { /* ipcb->opt is not populated for frags * coming from __ip_make_skb(), * ip_options_fragment() needs optlen */ IPCB(iter.frag)->opt.optlen = IPCB(skb)->opt.optlen; ip_options_fragment(iter.frag); ip_send_check(iter.iph); } } skb_set_delivery_time(skb, tstamp, mono_delivery_time); err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip_fraglist_next(&iter); } if (err == 0) { IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { bool first_frag = (state.offset == 0); skb2 = ip_frag_next(skb, &state); if (IS_ERR(skb2)) { err = PTR_ERR(skb2); goto fail; } ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. */ skb_set_delivery_time(skb2, tstamp, mono_delivery_time); err = output(net, sk, skb2); if (err) goto fail; IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { if (!copy_from_iter_full(to, len, &msg->msg_iter)) return -EFAULT; } else { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } return 0; } EXPORT_SYMBOL(ip_generic_getfrag); static inline __wsum csum_page(struct page *page, int offset, int copy) { char *kaddr; __wsum csum; kaddr = kmap(page); csum = csum_partial(kaddr + offset, copy, 0); kunmap(page); return csum; } static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; int mtu; int copy; int err; int offset = 0; bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; unsigned int wmem_alloc_delta = 0; bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; if (cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } /* * transhdrlen > 0 means that this is the first fragment and we wish * it won't be fragmented in the future. */ if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && (!(flags & MSG_MORE) || cork->gso_size) && (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } cork->length += length; /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, * each of segments is IP fragment ready for sending to network after * adding appropriate IP header. */ if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = mtu - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len + 15; alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ if (datalen == length + fraggap) alloc_extra += rt->dst.trailer_len; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen; pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; /* only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue. */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb_len_add(skb, copy); wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return err; } static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct ip_options_rcu *opt; struct rtable *rt; rt = *rtp; if (unlikely(!rt)) return -EFAULT; cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; /* * setup for corking. */ opt = ipc->opt; if (opt) { if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; /* We stole this route, caller should not release it. */ *rtp = NULL; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; cork->priority = ipc->priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); return 0; } /* * ip_append_data() and ip_append_page() can make one large IP datagram * from many pieces of data. Each pieces will be holded on the socket * until ip_push_pending_frames() is called. Each piece can be a page * or non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. * * LATER: length must be adjusted by pad at tail, when it is required. */ int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); if (err) return err; } else { transhdrlen = 0; } return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, int offset, size_t size, int flags) { struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; struct rtable *rt; struct ip_options *opt = NULL; struct inet_cork *cork; int hh_len; int mtu; int len; int err; unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize; if (inet->hdrincl) return -EPERM; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) return -EINVAL; cork = &inet->cork.base; rt = (struct rtable *)cork->dst; if (cork->flags & IPCORK_OPT) opt = cork->opt; if (!(rt->dst.dev->features & NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } skb = skb_peek_tail(&sk->sk_write_queue); if (!skb) return -EINVAL; cork->length += size; while (size > 0) { /* Check if the remaining data fits into current packet. */ len = mtu - skb->len; if (len < size) len = maxfraglen - skb->len; if (len <= 0) { struct sk_buff *skb_prev; int alloclen; skb_prev = skb; fraggap = skb_prev->len - maxfraglen; alloclen = fragheaderlen + hh_len + fraggap + 15; skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation); if (unlikely(!skb)) { err = -ENOBUFS; goto error; } /* * Fill in the control structures */ skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ skb_put(skb, fragheaderlen + fraggap); skb_reset_network_header(skb); skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits(skb_prev, maxfraglen, skb_transport_header(skb), fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); pskb_trim_unique(skb_prev, maxfraglen); } /* * Put the packet on the pending queue. */ __skb_queue_tail(&sk->sk_write_queue, skb); continue; } if (len > size) len = size; if (skb_append_pagefrags(skb, page, offset, len)) { err = -EMSGSIZE; goto error; } if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum; csum = csum_page(page, offset, len); skb->csum = csum_block_add(skb->csum, csum, skb->len); } skb_len_add(skb, len); refcount_add(len, &sk->sk_wmem_alloc); offset += len; size -= len; } return 0; error: cork->length -= size; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); return err; } static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; kfree(cork->opt); cork->opt = NULL; dst_release(cork->dst); cork->dst = NULL; } /* * Combined all pending IP fragments on the socket as one IP datagram * and push them out. */ struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; struct rtable *rt = (struct rtable *)cork->dst; struct iphdr *iph; __be16 df = 0; __u8 ttl; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ skb->ignore_df = ip_sk_ignore_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ if (inet->pmtudisc == IP_PMTUDISC_DO || inet->pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); if (cork->flags & IPCORK_OPT) opt = cork->opt; if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) ttl = inet->mc_ttl; else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = (cork->tos != -1) ? cork->tos : inet->tos; iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt); } skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; skb->mark = cork->mark; skb->tstamp = cork->transmit_time; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount */ cork->dst = NULL; skb_dst_set(skb, &rt->dst); if (iph->protocol == IPPROTO_ICMP) { u8 icmp_type; /* For such sockets, transhdrlen is zero when do ip_append_data(), * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; icmp_out_count(net, icmp_type); } ip_cork_release(cork); out: return skb; } int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); } return err; } int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) { struct sk_buff *skb; skb = ip_finish_skb(sk, fl4); if (!skb) return 0; /* Netfilter gets whole the not fragmented skb. */ return ip_send_skb(sock_net(sk), skb); } /* * Throw away all pending data on the socket. */ static void __ip_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) kfree_skb(skb); ip_cork_release(cork); } void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags) { struct sk_buff_head queue; int err; if (flags & MSG_PROBE) return NULL; __skb_queue_head_init(&queue); cork->flags = 0; cork->addr = 0; cork->opt = NULL; err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } return __ip_make_skb(sk, fl4, &queue, cork); } /* * Fetch data from kernel space and fill in checksum if needed. */ static int ip_reply_glue_bits(void *dptr, char *to, int offset, int len, int odd, struct sk_buff *skb) { __wsum csum; csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time, u32 txhash) { struct ip_options_data replyopts; struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct sk_buff *nskb; int err; int oif; if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; ipcm_init(&ipc); ipc.addr = daddr; ipc.sockc.transmit_time = transmit_time; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; if (replyopts.opt.opt.srr) daddr = replyopts.opt.opt.faddr; } oif = arg->bound_dev_if; if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { ip_flush_pending_frames(sk); goto out; } nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) *((__sum16 *)skb_transport_header(nskb) + arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; nskb->mono_delivery_time = !!transmit_time; if (txhash) skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); } out: ip_rt_put(rt); } void __init ip_init(void) { ip_rt_init(); inet_initpeers(); #if defined(CONFIG_IP_MULTICAST) igmp_mc_init(); #endif } |
| 286 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm4_policy.c * * Changes: * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion * */ #include <linux/err.h> #include <linux/kernel.h> #include <linux/inetdevice.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/l3mdev.h> static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct rtable *rt; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(net, oif); fl4->flowi4_mark = mark; if (saddr) fl4->saddr = saddr->a4; rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; return ERR_CAST(rt); } static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct flowi4 fl4; return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark); } static int xfrm4_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr, u32 mark) { struct dst_entry *dst; struct flowi4 fl4; dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; saddr->a4 = fl4.saddr; dst_release(dst); return 0; } static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { struct rtable *rt = (struct rtable *)xdst->route; const struct flowi4 *fl4 = &fl->u.ip4; xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt.rt_is_input = rt->rt_is_input; xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) xdst->u.rt.rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) xdst->u.rt.rt_gw6 = rt->rt_gw6; xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); rt_add_uncached_list(&xdst->u.rt); return 0; } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->redirect(path, sk, skb); } static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); if (xdst->u.rt.rt_uncached_list) rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int unregister) { if (!unregister) return; xfrm_dst_ifdown(dst, dev); } static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .update_pmtu = xfrm4_update_pmtu, .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 32768, }; static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .fill_dst = xfrm4_fill_dst, .blackhole_route = ipv4_blackhole_route, }; #ifdef CONFIG_SYSCTL static struct ctl_table xfrm4_policy_table[] = { { .procname = "xfrm4_gc_thresh", .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static __net_init int xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = xfrm4_policy_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; } hdr = register_net_sysctl(net, "net/ipv4", table); if (!hdr) goto err_reg; net->ipv4.xfrm4_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static __net_exit void xfrm4_net_sysctl_exit(struct net *net) { struct ctl_table *table; if (!net->ipv4.xfrm4_hdr) return; table = net->ipv4.xfrm4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else /* CONFIG_SYSCTL */ static inline int xfrm4_net_sysctl_init(struct net *net) { return 0; } static inline void xfrm4_net_sysctl_exit(struct net *net) { } #endif static int __net_init xfrm4_net_init(struct net *net) { int ret; memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, sizeof(xfrm4_dst_ops_template)); ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); if (ret) return ret; ret = xfrm4_net_sysctl_init(net); if (ret) dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); return ret; } static void __net_exit xfrm4_net_exit(struct net *net) { xfrm4_net_sysctl_exit(net); dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); } static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; static void __init xfrm4_policy_init(void) { xfrm_policy_register_afinfo(&xfrm4_policy_afinfo, AF_INET); } void __init xfrm4_init(void) { xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } |
| 251 251 251 251 89 89 89 89 13 13 13 13 13 13 13 13 18 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/percpu-refcount.h> /* * Initially, a percpu refcount is just a set of percpu counters. Initially, we * don't try to detect the ref hitting 0 - which means that get/put can just * increment or decrement the local counter. Note that the counter on a * particular cpu can (and will) wrap - this is fine, when we go to shutdown the * percpu counters will all sum to the correct value * * (More precisely: because modular arithmetic is commutative the sum of all the * percpu_count vars will be equal to what it would have been if all the gets * and puts were done to a single integer, even if some of the percpu integers * overflow or underflow). * * The real trick to implementing percpu refcounts is shutdown. We can't detect * the ref hitting 0 on every put - this would require global synchronization * and defeat the whole purpose of using percpu refs. * * What we do is require the user to keep track of the initial refcount; we know * the ref can't hit 0 before the user drops the initial ref, so as long as we * convert to non percpu mode before the initial ref is dropped everything * works. * * Converting to non percpu mode is done with some RCUish stuff in * percpu_ref_kill. Additionally, we need a bias value so that the * atomic_long_t can't hit 0 before we've added up all the percpu refs. */ #define PERCPU_COUNT_BIAS (1LU << (BITS_PER_LONG - 1)) static DEFINE_SPINLOCK(percpu_ref_switch_lock); static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq); static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref) { return (unsigned long __percpu *) (ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD); } /** * percpu_ref_init - initialize a percpu refcount * @ref: percpu_ref to initialize * @release: function which will be called when refcount hits 0 * @flags: PERCPU_REF_INIT_* flags * @gfp: allocation mask to use * * Initializes @ref. @ref starts out in percpu mode with a refcount of 1 unless * @flags contains PERCPU_REF_INIT_ATOMIC or PERCPU_REF_INIT_DEAD. These flags * change the start state to atomic with the latter setting the initial refcount * to 0. See the definitions of PERCPU_REF_INIT_* flags for flag behaviors. * * Note that @release must not sleep - it may potentially be called from RCU * callback context by percpu_ref_kill(). */ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp) { size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS, __alignof__(unsigned long)); unsigned long start_count = 0; struct percpu_ref_data *data; ref->percpu_count_ptr = (unsigned long) __alloc_percpu_gfp(sizeof(unsigned long), align, gfp); if (!ref->percpu_count_ptr) return -ENOMEM; data = kzalloc(sizeof(*ref->data), gfp); if (!data) { free_percpu((void __percpu *)ref->percpu_count_ptr); ref->percpu_count_ptr = 0; return -ENOMEM; } data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) { ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; data->allow_reinit = true; } else { start_count += PERCPU_COUNT_BIAS; } if (flags & PERCPU_REF_INIT_DEAD) ref->percpu_count_ptr |= __PERCPU_REF_DEAD; else start_count++; atomic_long_set(&data->count, start_count); data->release = release; data->confirm_switch = NULL; data->ref = ref; ref->data = data; return 0; } EXPORT_SYMBOL_GPL(percpu_ref_init); static void __percpu_ref_exit(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); if (percpu_count) { /* non-NULL confirm_switch indicates switching in progress */ WARN_ON_ONCE(ref->data && ref->data->confirm_switch); free_percpu(percpu_count); ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD; } } /** * percpu_ref_exit - undo percpu_ref_init() * @ref: percpu_ref to exit * * This function exits @ref. The caller is responsible for ensuring that * @ref is no longer in active use. The usual places to invoke this * function from are the @ref->release() callback or in init failure path * where percpu_ref_init() succeeded but other parts of the initialization * of the embedding object failed. */ void percpu_ref_exit(struct percpu_ref *ref) { struct percpu_ref_data *data = ref->data; unsigned long flags; __percpu_ref_exit(ref); if (!data) return; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) << __PERCPU_REF_FLAG_BITS; ref->data = NULL; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); kfree(data); } EXPORT_SYMBOL_GPL(percpu_ref_exit); static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; data->confirm_switch(ref); data->confirm_switch = NULL; wake_up_all(&percpu_ref_switch_waitq); if (!data->allow_reinit) __percpu_ref_exit(ref); /* drop ref from percpu_ref_switch_to_atomic() */ percpu_ref_put(ref); } static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); static atomic_t underflows; unsigned long count = 0; int cpu; for_each_possible_cpu(cpu) count += *per_cpu_ptr(percpu_count, cpu); pr_debug("global %lu percpu %lu\n", atomic_long_read(&data->count), count); /* * It's crucial that we sum the percpu counters _before_ adding the sum * to &ref->count; since gets could be happening on one cpu while puts * happen on another, adding a single cpu's count could cause * @ref->count to hit 0 before we've got a consistent value - but the * sum of all the counts will be consistent and correct. * * Subtracting the bias value then has to happen _after_ adding count to * &ref->count; we need the bias value to prevent &ref->count from * reaching 0 before we add the percpu counts. But doing it at the same * time is equivalent and saves us atomic operations: */ atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); if (WARN_ONCE(atomic_long_read(&data->count) <= 0, "percpu ref (%ps) <= 0 (%ld) after switching to atomic", data->release, atomic_long_read(&data->count)) && atomic_inc_return(&underflows) < 4) { pr_err("%s(): percpu_ref underflow", __func__); mem_dump_obj(data); } /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); } static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref) { } static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { if (ref->percpu_count_ptr & __PERCPU_REF_ATOMIC) { if (confirm_switch) confirm_switch(ref); return; } /* switching from percpu to atomic */ ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; /* * Non-NULL ->confirm_switch is used to indicate that switching is * in progress. Use noop one if unspecified. */ ref->data->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch; percpu_ref_get(ref); /* put after confirmation */ call_rcu_hurry(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu); } static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); int cpu; BUG_ON(!percpu_count); if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) return; if (WARN_ON_ONCE(!ref->data->allow_reinit)) return; atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count); /* * Restore per-cpu operation. smp_store_release() is paired * with READ_ONCE() in __ref_is_percpu() and guarantees that the * zeroing is visible to all percpu accesses which can see the * following __PERCPU_REF_ATOMIC clearing. */ for_each_possible_cpu(cpu) *per_cpu_ptr(percpu_count, cpu) = 0; smp_store_release(&ref->percpu_count_ptr, ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC); } static void __percpu_ref_switch_mode(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { struct percpu_ref_data *data = ref->data; lockdep_assert_held(&percpu_ref_switch_lock); /* * If the previous ATOMIC switching hasn't finished yet, wait for * its completion. If the caller ensures that ATOMIC switching * isn't in progress, this function can be called from any context. */ wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); if (data->force_atomic || percpu_ref_is_dying(ref)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); } /** * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * @confirm_switch: optional confirmation callback * * There's no reason to use this function for the usual reference counting. * Use percpu_ref_kill[_and_confirm](). * * Schedule switching of @ref to atomic mode. All its percpu counts will * be collected to the main atomic counter. On completion, when all CPUs * are guaraneed to be in atomic mode, @confirm_switch, which may not * block, is invoked. This function may be invoked concurrently with all * the get/put operations and can safely be mixed with kill and reinit * operations. Note that @ref will stay in atomic mode across kill/reinit * cycles until percpu_ref_switch_to_percpu() is called. * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = true; __percpu_ref_switch_mode(ref, confirm_switch); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic); /** * percpu_ref_switch_to_atomic_sync - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * * Schedule switching the ref to atomic mode, and wait for the * switch to complete. Caller must ensure that no other thread * will switch back to percpu mode. */ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref) { percpu_ref_switch_to_atomic(ref, NULL); wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync); /** * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode * @ref: percpu_ref to switch to percpu mode * * There's no reason to use this function for the usual reference counting. * To re-use an expired ref, use percpu_ref_reinit(). * * Switch @ref to percpu mode. This function may be invoked concurrently * with all the get/put operations and can safely be mixed with kill and * reinit operations. This function reverses the sticky atomic state set * by PERCPU_REF_INIT_ATOMIC or percpu_ref_switch_to_atomic(). If @ref is * dying or dead, the actual switching takes place on the following * percpu_ref_reinit(). * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = false; __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); /** * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation * @ref: percpu_ref to kill * @confirm_kill: optional confirmation callback * * Equivalent to percpu_ref_kill() but also schedules kill confirmation if * @confirm_kill is not NULL. @confirm_kill, which may not block, will be * called after @ref is seen as dead from all CPUs at which point all * further invocations of percpu_ref_tryget_live() will fail. See * percpu_ref_tryget_live() for details. * * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). * * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ONCE(percpu_ref_is_dying(ref), "%s called more than once on %ps!", __func__, ref->data->release); ref->percpu_count_ptr |= __PERCPU_REF_DEAD; __percpu_ref_switch_mode(ref, confirm_kill); percpu_ref_put(ref); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test * * Returns %true if @ref reached zero. * * This function is safe to call as long as @ref is between init and exit. */ bool percpu_ref_is_zero(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long count, flags; if (__ref_is_percpu(ref, &percpu_count)) return false; /* protect us from being destroyed */ spin_lock_irqsave(&percpu_ref_switch_lock, flags); if (ref->data) count = atomic_long_read(&ref->data->count); else count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); return count == 0; } EXPORT_SYMBOL_GPL(percpu_ref_is_zero); /** * percpu_ref_reinit - re-initialize a percpu refcount * @ref: perpcu_ref to re-initialize * * Re-initialize @ref so that it's in the same state as when it finished * percpu_ref_init() ignoring %PERCPU_REF_INIT_DEAD. @ref must have been * initialized successfully and reached 0 but not exited. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_reinit(struct percpu_ref *ref) { WARN_ON_ONCE(!percpu_ref_is_zero(ref)); percpu_ref_resurrect(ref); } EXPORT_SYMBOL_GPL(percpu_ref_reinit); /** * percpu_ref_resurrect - modify a percpu refcount from dead to live * @ref: perpcu_ref to resurrect * * Modify @ref so that it's in the same state as before percpu_ref_kill() was * called. @ref must be dead but must not yet have exited. * * If @ref->release() frees @ref then the caller is responsible for * guaranteeing that @ref->release() does not get called while this * function is in progress. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_resurrect(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ON_ONCE(!percpu_ref_is_dying(ref)); WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count)); ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD; percpu_ref_get(ref); __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_resurrect); |
| 286 286 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 | // 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 fragmentation functionality. * * Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * Alan Cox : Split from ip.c , see ip_input.c for history. * David S. Miller : Begin massive cleanup... * Andi Kleen : Add sysctls. * xxxx : Overlapfrag bug. * Ultima : ip_expire() kernel panic. * Bill Hawes : Frag accounting and evictor fixes. * John McDonald : 0 length frag bug. * Alexey Kuznetsov: SMP races, threading, cleanup. * Patrick McHardy : LRU queue of frag heads for evictor. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/compiler.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/jiffies.h> #include <linux/skbuff.h> #include <linux/list.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/netdevice.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/slab.h> #include <net/route.h> #include <net/dst.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_frag.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/inet.h> #include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> #include <net/l3mdev.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c * as well. Or notify me, at least. --ANK */ static const char ip_frag_cache_name[] = "ip4-frags"; /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; unsigned int rid; struct inet_peer *peer; }; static u8 ip4_frag_ecn(u8 tos) { return 1 << (tos & INET_ECN_MASK); } static struct inet_frags ip4_frags; static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev); static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { struct ipq *qp = container_of(q, struct ipq, q); struct net *net = q->fqdir->net; const struct frag_v4_compare_key *key = a; q->key.v4 = *key; qp->ecn = 0; qp->peer = q->fqdir->max_dist ? inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) : NULL; } static void ip4_frag_free(struct inet_frag_queue *q) { struct ipq *qp; qp = container_of(q, struct ipq, q); if (qp->peer) inet_putpeer(qp->peer); } /* Destruction primitives. */ static void ipq_put(struct ipq *ipq) { inet_frag_put(&ipq->q); } /* Kill ipq entry. It is not destroyed immediately, * because caller (and someone more) holds reference count. */ static void ipq_kill(struct ipq *ipq) { inet_frag_kill(&ipq->q); } static bool frag_expire_skip_icmp(u32 user) { return user == IP_DEFRAG_AF_PACKET || ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_IN, __IP_DEFRAG_CONNTRACK_IN_END) || ip_defrag_user_in_between(user, IP_DEFRAG_CONNTRACK_BRIDGE_IN, __IP_DEFRAG_CONNTRACK_BRIDGE_IN); } /* * Oops, a fragment queue timed out. Kill it and send an ICMP reply. */ static void ip_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); const struct iphdr *iph; struct sk_buff *head = NULL; struct net *net; struct ipq *qp; int err; qp = container_of(frag, struct ipq, q); net = qp->q.fqdir->net; rcu_read_lock(); /* Paired with WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(qp->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&qp->q.lock); if (qp->q.flags & INET_FRAG_COMPLETE) goto out; ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); if (!(qp->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&qp->q); if (!head) goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); if (err) goto out; /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ if (frag_expire_skip_icmp(qp->q.key.v4.user) && (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out; spin_unlock(&qp->q.lock); icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); goto out_rcu_unlock; out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); kfree_skb(head); ipq_put(qp); } /* Find the correct entry in the "incomplete datagrams" queue for * this IP datagram, and create new one, if nothing is found. */ static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user, int vif) { struct frag_v4_compare_key key = { .saddr = iph->saddr, .daddr = iph->daddr, .user = user, .vif = vif, .id = iph->id, .protocol = iph->protocol, }; struct inet_frag_queue *q; q = inet_frag_find(net->ipv4.fqdir, &key); if (!q) return NULL; return container_of(q, struct ipq, q); } /* Is the fragment too far ahead to be part of ipq? */ static int ip_frag_too_far(struct ipq *qp) { struct inet_peer *peer = qp->peer; unsigned int max = qp->q.fqdir->max_dist; unsigned int start, end; int rc; if (!peer || !max) return 0; start = qp->rid; end = atomic_inc_return(&peer->rid); qp->rid = end; rc = qp->q.fragments_tail && (end - start) > max; if (rc) __IP_INC_STATS(qp->q.fqdir->net, IPSTATS_MIB_REASMFAILS); return rc; } static int ip_frag_reinit(struct ipq *qp) { unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.fqdir->timeout)) { refcount_inc(&qp->q.refcnt); return -ETIMEDOUT; } sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; qp->q.len = 0; qp->q.meat = 0; qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; qp->iif = 0; qp->ecn = 0; return 0; } /* Add new segment to existing queue. */ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = qp->q.fqdir->net; int ihl, end, flags, offset; struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; int err = -ENOENT; u8 ecn; if (qp->q.flags & INET_FRAG_COMPLETE) goto err; if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && unlikely(err = ip_frag_reinit(qp))) { ipq_kill(qp); goto err; } ecn = ip4_frag_ecn(ip_hdr(skb)->tos); offset = ntohs(ip_hdr(skb)->frag_off); flags = offset & ~IP_OFFSET; offset &= IP_OFFSET; offset <<= 3; /* offset is in 8-byte chunks */ ihl = ip_hdrlen(skb); /* Determine the position of this fragment. */ end = offset + skb->len - skb_network_offset(skb) - ihl; err = -EINVAL; /* Is this the final fragment? */ if ((flags & IP_MF) == 0) { /* If we already have some bits beyond end * or have different end, the segment is corrupted. */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { if (end&7) { end &= ~7; if (skb->ip_summed != CHECKSUM_UNNECESSARY) skb->ip_summed = CHECKSUM_NONE; } if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) goto discard_qp; qp->q.len = end; } } if (end == offset) goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); prev_tail = qp->q.fragments_tail; err = inet_frag_queue_insert(&qp->q, skb, offset, end); if (err) goto insert_error; if (dev) qp->iif = dev->ifindex; qp->q.stamp = skb->tstamp; qp->q.mono_delivery_time = skb->mono_delivery_time; qp->q.meat += skb->len; qp->ecn |= ecn; add_frag_mem_limit(qp->q.fqdir, skb->truesize); if (offset == 0) qp->q.flags |= INET_FRAG_FIRST_IN; fragsize = skb->len + ihl; if (fragsize > qp->q.max_size) qp->q.max_size = fragsize; if (ip_hdr(skb)->frag_off & htons(IP_DF) && fragsize > qp->max_df_size) qp->max_df_size = fragsize; if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) { unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; if (err) inet_frag_kill(&qp->q); return err; } skb_dst_drop(skb); skb_orphan(skb); return -EINPROGRESS; insert_error: if (err == IPFRAG_DUP) { kfree_skb(skb); return -EINVAL; } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; } static bool ip_frag_coalesce_ok(const struct ipq *qp) { return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER; } /* Build a new IP datagram from all its fragments. */ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, struct sk_buff *prev_tail, struct net_device *dev) { struct net *net = qp->q.fqdir->net; struct iphdr *iph; void *reasm_data; int len, err; u8 ecn; ipq_kill(qp); ecn = ip_frag_ecn_table[qp->ecn]; if (unlikely(ecn == 0xff)) { err = -EINVAL; goto out_fail; } /* Make the one we just received the head. */ reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); if (!reasm_data) goto out_nomem; len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; inet_frag_reasm_finish(&qp->q, skb, reasm_data, ip_frag_coalesce_ok(qp)); skb->dev = dev; IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; /* When we set IP_DF on a refragmented skb we must also force a * call to ip_fragment to avoid forwarding a DF-skb of size s while * original sender only sent fragments of size f (where f < s). * * We only set DF/IPSKB_FRAG_PMTU if such DF fragment was the largest * frag seen to avoid sending tiny DF-fragments in case skb was built * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; } ip_send_check(iph); __IP_INC_STATS(net, IPSTATS_MIB_REASMOKS); qp->q.rb_fragments = RB_ROOT; qp->q.fragments_tail = NULL; qp->q.last_run_head = NULL; return 0; out_nomem: net_dbg_ratelimited("queue_glue: no memory for gluing queue %p\n", qp); err = -ENOMEM; goto out_fail; out_oversize: net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr); out_fail: __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); return err; } /* Process an incoming IP datagram fragment. */ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; int vif = l3mdev_master_ifindex_rcu(dev); struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { int ret; spin_lock(&qp->q.lock); ret = ip_frag_queue(qp, skb); spin_unlock(&qp->q.lock); ipq_put(qp); return ret; } __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); kfree_skb(skb); return -ENOMEM; } EXPORT_SYMBOL(ip_defrag); struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) { struct iphdr iph; int netoff; u32 len; if (skb->protocol != htons(ETH_P_IP)) return skb; netoff = skb_network_offset(skb); if (skb_copy_bits(skb, netoff, &iph, sizeof(iph)) < 0) return skb; if (iph.ihl < 5 || iph.version != 4) return skb; len = ntohs(iph.tot_len); if (skb->len < netoff + len || len < (iph.ihl * 4)) return skb; if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { kfree_skb(skb); return NULL; } if (pskb_trim_rcsum(skb, netoff + len)) { kfree_skb(skb); return NULL; } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; skb_clear_hash(skb); } } return skb; } EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL static int dist_min; static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "ipfrag_low_thresh", .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "ipfrag_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "ipfrag_max_dist", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &dist_min, }, { } }; /* secret interval has been deprecated */ static int ip4_frags_secret_interval_unused; static struct ctl_table ip4_frags_ctl_table[] = { { .procname = "ipfrag_secret_interval", .data = &ip4_frags_secret_interval_unused, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { } }; static int __net_init ip4_frags_ns_ctl_register(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = ip4_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); if (!table) goto err_alloc; } table[0].data = &net->ipv4.fqdir->high_thresh; table[0].extra1 = &net->ipv4.fqdir->low_thresh; table[1].data = &net->ipv4.fqdir->low_thresh; table[1].extra2 = &net->ipv4.fqdir->high_thresh; table[2].data = &net->ipv4.fqdir->timeout; table[3].data = &net->ipv4.fqdir->max_dist; hdr = register_net_sysctl(net, "net/ipv4", table); if (!hdr) goto err_reg; net->ipv4.frags_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static void __net_exit ip4_frags_ns_ctl_unregister(struct net *net) { struct ctl_table *table; table = net->ipv4.frags_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.frags_hdr); kfree(table); } static void __init ip4_frags_ctl_register(void) { register_net_sysctl(&init_net, "net/ipv4", ip4_frags_ctl_table); } #else static int ip4_frags_ns_ctl_register(struct net *net) { return 0; } static void ip4_frags_ns_ctl_unregister(struct net *net) { } static void __init ip4_frags_ctl_register(void) { } #endif static int __net_init ipv4_frags_init_net(struct net *net) { int res; res = fqdir_init(&net->ipv4.fqdir, &ip4_frags, net); if (res < 0) return res; /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for * the real memory usage, by measuring both the size of frag * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) * and the SKB's truesize. * * A 64K fragment consumes 129736 bytes (44*2944)+200 * (1500 truesize == 2944, sizeof(struct ipq) == 200) * * We will commit 4MB at one time. Should we cross that limit * we will prune down to 3MB, making room for approx 8 big 64K * fragments 8x128k. */ net->ipv4.fqdir->high_thresh = 4 * 1024 * 1024; net->ipv4.fqdir->low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival * by TTL. */ net->ipv4.fqdir->timeout = IP_FRAG_TIME; net->ipv4.fqdir->max_dist = 64; res = ip4_frags_ns_ctl_register(net); if (res < 0) fqdir_exit(net->ipv4.fqdir); return res; } static void __net_exit ipv4_frags_pre_exit_net(struct net *net) { fqdir_pre_exit(net->ipv4.fqdir); } static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); fqdir_exit(net->ipv4.fqdir); } static struct pernet_operations ip4_frags_ops = { .init = ipv4_frags_init_net, .pre_exit = ipv4_frags_pre_exit_net, .exit = ipv4_frags_exit_net, }; static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); } static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v4, sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); } static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v4_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static const struct rhashtable_params ip4_rhash_params = { .head_offset = offsetof(struct inet_frag_queue, node), .key_offset = offsetof(struct inet_frag_queue, key), .key_len = sizeof(struct frag_v4_compare_key), .hashfn = ip4_key_hashfn, .obj_hashfn = ip4_obj_hashfn, .obj_cmpfn = ip4_obj_cmpfn, .automatic_shrinking = true, }; void __init ipfrag_init(void) { ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; ip4_frags.qsize = sizeof(struct ipq); ip4_frags.frag_expire = ip_expire; ip4_frags.frags_cache_name = ip_frag_cache_name; ip4_frags.rhash_params = ip4_rhash_params; if (inet_frags_init(&ip4_frags)) panic("IP: failed to allocate ip4_frags cache\n"); ip4_frags_ctl_register(); register_pernet_subsys(&ip4_frags_ops); } |
| 89 89 89 89 89 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | #include <linux/gfp.h> #include <linux/initrd.h> #include <linux/ioport.h> #include <linux/swap.h> #include <linux/memblock.h> #include <linux/swapfile.h> #include <linux/swapops.h> #include <linux/kmemleak.h> #include <linux/sched/task.h> #include <asm/set_memory.h> #include <asm/cpu_device_id.h> #include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> #include <asm/page_types.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/proto.h> #include <asm/dma.h> /* for MAX_DMA_PFN */ #include <asm/microcode.h> #include <asm/kaslr.h> #include <asm/hypervisor.h> #include <asm/cpufeature.h> #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> #include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c * is only compiled when SMP=y. */ #include <trace/events/tlb.h> #include "mm_internal.h" /* * Tables translating between page_cache_type_t and pte encoding. * * The default values are defined statically as minimal supported mode; * WC and WT fall back to UC-. pat_init() updates these values to support * more cache modes, WC and WT, when it is safe to do so. See pat_init() * for the details. Note, __early_ioremap() used during early boot-time * takes pgprot_t (pte encoding) and does not use these tables. * * Index into __cachemode2pte_tbl[] is the cachemode. * * Index into __pte2cachemode_tbl[] are the caching attribute bits of the pte * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2. */ static uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WB ] = 0 | 0 , [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_WP ] = 0 | _PAGE_PCD, }; unsigned long cachemode2protval(enum page_cache_mode pcm) { if (likely(pcm == 0)) return 0; return __cachemode2pte_tbl[pcm]; } EXPORT_SYMBOL(cachemode2protval); static uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; /* * Check that the write-protect PAT entry is set for write-protect. * To do this without making assumptions how PAT has been set up (Xen has * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache * mode via the __cachemode2pte_tbl[] into protection bits (those protection * bits will select a cache mode of WP or better), and then translate the * protection bits back into the cache mode using __pte2cm_idx() and the * __pte2cachemode_tbl[] array. This will return the really used cache mode. */ bool x86_has_pat_wp(void) { uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP]; return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP; } enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) { unsigned long masked; masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK; if (likely(masked == 0)) return 0; return __pte2cachemode_tbl[__pte2cm_idx(masked)]; } static unsigned long __initdata pgt_buf_start; static unsigned long __initdata pgt_buf_end; static unsigned long __initdata pgt_buf_top; static unsigned long min_pfn_mapped; static bool __initdata can_use_brk_pgt = true; /* * Provide a run-time mean of disabling ZONE_DMA32 if it is enabled via * CONFIG_ZONE_DMA32. */ static bool disable_dma32 __ro_after_init; /* * Pages returned are already directly mapped. * * Changing that is likely to break Xen, see commit: * * 279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve * * for detailed information. */ __ref void *alloc_low_pages(unsigned int num) { unsigned long pfn; int i; if (after_bootmem) { unsigned int order; order = get_order((unsigned long)num << PAGE_SHIFT); return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); } if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) { unsigned long ret = 0; if (min_pfn_mapped < max_pfn_mapped) { ret = memblock_phys_alloc_range( PAGE_SIZE * num, PAGE_SIZE, min_pfn_mapped << PAGE_SHIFT, max_pfn_mapped << PAGE_SHIFT); } if (!ret && can_use_brk_pgt) ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE)); if (!ret) panic("alloc_low_pages: can not alloc memory"); pfn = ret >> PAGE_SHIFT; } else { pfn = pgt_buf_end; pgt_buf_end += num; } for (i = 0; i < num; i++) { void *adr; adr = __va((pfn + i) << PAGE_SHIFT); clear_page(adr); } return __va(pfn << PAGE_SHIFT); } /* * By default need to be able to allocate page tables below PGD firstly for * the 0-ISA_END_ADDRESS range and secondly for the initial PMD_SIZE mapping. * With KASLR memory randomization, depending on the machine e820 memory and the * PUD alignment, twice that many pages may be needed when KASLR memory * randomization is enabled. */ #ifndef CONFIG_X86_5LEVEL #define INIT_PGD_PAGE_TABLES 3 #else #define INIT_PGD_PAGE_TABLES 4 #endif #ifndef CONFIG_RANDOMIZE_MEMORY #define INIT_PGD_PAGE_COUNT (2 * INIT_PGD_PAGE_TABLES) #else #define INIT_PGD_PAGE_COUNT (4 * INIT_PGD_PAGE_TABLES) #endif #define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { unsigned long tables = INIT_PGT_BUF_SIZE; phys_addr_t base; base = __pa(extend_brk(tables, PAGE_SIZE)); pgt_buf_start = base >> PAGE_SHIFT; pgt_buf_end = pgt_buf_start; pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); } int after_bootmem; early_param_on_off("gbpages", "nogbpages", direct_gbpages, CONFIG_X86_DIRECT_GBPAGES); struct map_range { unsigned long start; unsigned long end; unsigned page_size_mask; }; static int page_size_mask; /* * Save some of cr4 feature set we're using (e.g. Pentium 4MB * enable and PPro Global page enable), so that any CPU's that boot * up after us can get the correct flags. Invoked on the boot CPU. */ static inline void cr4_set_bits_and_update_boot(unsigned long mask) { mmu_cr4_features |= mask; if (trampoline_cr4_features) *trampoline_cr4_features = mmu_cr4_features; cr4_set_bits(mask); } static void __init probe_page_size_mask(void) { /* * For pagealloc debugging, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; else direct_gbpages = 0; /* Enable PSE if available */ if (boot_cpu_has(X86_FEATURE_PSE)) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ __supported_pte_mask &= ~_PAGE_GLOBAL; if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; } /* By the default is everything supported: */ __default_kernel_pte_mask = __supported_pte_mask; /* Except when with PTI where the kernel is mostly non-Global: */ if (cpu_feature_enabled(X86_FEATURE_PTI)) __default_kernel_pte_mask &= ~_PAGE_GLOBAL; /* Enable 1 GB linear kernel mappings if available: */ if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { printk(KERN_INFO "Using GB pages for direct mapping\n"); page_size_mask |= 1 << PG_LEVEL_1G; } else { direct_gbpages = 0; } } #define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ .family = 6, \ .model = _model, \ } /* * INVLPG may not properly flush Global entries * on these CPUs when PCIDs are enabled. */ static const struct x86_cpu_id invlpg_miss_ids[] = { INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), {} }; static void setup_pcid(void) { if (!IS_ENABLED(CONFIG_X86_64)) return; if (!boot_cpu_has(X86_FEATURE_PCID)) return; if (x86_match_cpu(invlpg_miss_ids)) { pr_info("Incomplete global flushes, disabling PCID"); setup_clear_cpu_cap(X86_FEATURE_PCID); return; } if (boot_cpu_has(X86_FEATURE_PGE)) { /* * This can't be cr4_set_bits_and_update_boot() -- the * trampoline code can't handle CR4.PCIDE and it wouldn't * do any good anyway. Despite the name, * cr4_set_bits_and_update_boot() doesn't actually cause * the bits in question to remain set all the way through * the secondary boot asm. * * Instead, we brute-force it and set CR4.PCIDE manually in * start_secondary(). */ cr4_set_bits(X86_CR4_PCIDE); /* * INVPCID's single-context modes (2/3) only work if we set * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable * on systems that have X86_CR4_PCIDE clear, or that have * no INVPCID support at all. */ if (boot_cpu_has(X86_FEATURE_INVPCID)) setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE); } else { /* * flush_tlb_all(), as currently implemented, won't work if * PCID is on but PGE is not. Since that combination * doesn't exist on real hardware, there's no reason to try * to fully support it, but it's polite to avoid corrupting * data if we're on an improperly configured VM. */ setup_clear_cpu_cap(X86_FEATURE_PCID); } } #ifdef CONFIG_X86_32 #define NR_RANGE_MR 3 #else /* CONFIG_X86_64 */ #define NR_RANGE_MR 5 #endif static int __meminit save_mr(struct map_range *mr, int nr_range, unsigned long start_pfn, unsigned long end_pfn, unsigned long page_size_mask) { if (start_pfn < end_pfn) { if (nr_range >= NR_RANGE_MR) panic("run out of range for init_memory_mapping\n"); mr[nr_range].start = start_pfn<<PAGE_SHIFT; mr[nr_range].end = end_pfn<<PAGE_SHIFT; mr[nr_range].page_size_mask = page_size_mask; nr_range++; } return nr_range; } /* * adjust the page_size_mask for small range to go with * big page size instead small one if nearby are ram too. */ static void __ref adjust_range_page_size_mask(struct map_range *mr, int nr_range) { int i; for (i = 0; i < nr_range; i++) { if ((page_size_mask & (1<<PG_LEVEL_2M)) && !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) { unsigned long start = round_down(mr[i].start, PMD_SIZE); unsigned long end = round_up(mr[i].end, PMD_SIZE); #ifdef CONFIG_X86_32 if ((end >> PAGE_SHIFT) > max_low_pfn) continue; #endif if (memblock_is_region_memory(start, end - start)) mr[i].page_size_mask |= 1<<PG_LEVEL_2M; } if ((page_size_mask & (1<<PG_LEVEL_1G)) && !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) { unsigned long start = round_down(mr[i].start, PUD_SIZE); unsigned long end = round_up(mr[i].end, PUD_SIZE); if (memblock_is_region_memory(start, end - start)) mr[i].page_size_mask |= 1<<PG_LEVEL_1G; } } } static const char *page_size_string(struct map_range *mr) { static const char str_1g[] = "1G"; static const char str_2m[] = "2M"; static const char str_4m[] = "4M"; static const char str_4k[] = "4k"; if (mr->page_size_mask & (1<<PG_LEVEL_1G)) return str_1g; /* * 32-bit without PAE has a 4M large page size. * PG_LEVEL_2M is misnamed, but we can at least * print out the right size in the string. */ if (IS_ENABLED(CONFIG_X86_32) && !IS_ENABLED(CONFIG_X86_PAE) && mr->page_size_mask & (1<<PG_LEVEL_2M)) return str_4m; if (mr->page_size_mask & (1<<PG_LEVEL_2M)) return str_2m; return str_4k; } static int __meminit split_mem_range(struct map_range *mr, int nr_range, unsigned long start, unsigned long end) { unsigned long start_pfn, end_pfn, limit_pfn; unsigned long pfn; int i; limit_pfn = PFN_DOWN(end); /* head if not big page alignment ? */ pfn = start_pfn = PFN_DOWN(start); #ifdef CONFIG_X86_32 /* * Don't use a large page for the first 2/4MB of memory * because there are often fixed size MTRRs in there * and overlapping MTRRs into large pages can cause * slowdowns. */ if (pfn == 0) end_pfn = PFN_DOWN(PMD_SIZE); else end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #endif if (end_pfn > limit_pfn) end_pfn = limit_pfn; if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); pfn = end_pfn; } /* big page (2M) range */ start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); #ifdef CONFIG_X86_32 end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #else /* CONFIG_X86_64 */ end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE))) end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); #endif if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); pfn = end_pfn; } #ifdef CONFIG_X86_64 /* big page (1G) range */ start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE)); end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G))); pfn = end_pfn; } /* tail is not big page (1G) alignment */ start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE)); end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE)); if (start_pfn < end_pfn) { nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, page_size_mask & (1<<PG_LEVEL_2M)); pfn = end_pfn; } #endif /* tail is not big page (2M) alignment */ start_pfn = pfn; end_pfn = limit_pfn; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); if (!after_bootmem) adjust_range_page_size_mask(mr, nr_range); /* try to merge same page size and continuous */ for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { unsigned long old_start; if (mr[i].end != mr[i+1].start || mr[i].page_size_mask != mr[i+1].page_size_mask) continue; /* move it */ old_start = mr[i].start; memmove(&mr[i], &mr[i+1], (nr_range - 1 - i) * sizeof(struct map_range)); mr[i--].start = old_start; nr_range--; } for (i = 0; i < nr_range; i++) pr_debug(" [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, page_size_string(&mr[i])); return nr_range; } struct range pfn_mapped[E820_MAX_ENTRIES]; int nr_pfn_mapped; static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn) { nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES, nr_pfn_mapped, start_pfn, end_pfn); nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES); max_pfn_mapped = max(max_pfn_mapped, end_pfn); if (start_pfn < (1UL<<(32-PAGE_SHIFT))) max_low_pfn_mapped = max(max_low_pfn_mapped, min(end_pfn, 1UL<<(32-PAGE_SHIFT))); } bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn) { int i; for (i = 0; i < nr_pfn_mapped; i++) if ((start_pfn >= pfn_mapped[i].start) && (end_pfn <= pfn_mapped[i].end)) return true; return false; } /* * Setup the direct mapping of the physical memory at PAGE_OFFSET. * This runs before bootmem is initialized and gets pages directly from * the physical memory. To access them they are temporarily mapped. */ unsigned long __ref init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot) { struct map_range mr[NR_RANGE_MR]; unsigned long ret = 0; int nr_range, i; pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n", start, end - 1); memset(mr, 0, sizeof(mr)); nr_range = split_mem_range(mr, 0, start, end); for (i = 0; i < nr_range; i++) ret = kernel_physical_mapping_init(mr[i].start, mr[i].end, mr[i].page_size_mask, prot); add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT); return ret >> PAGE_SHIFT; } /* * We need to iterate through the E820 memory map and create direct mappings * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply * create direct mappings for all pfns from [0 to max_low_pfn) and * [4GB to max_pfn) because of possible memory holes in high addresses * that cannot be marked as UC by fixed/variable range MTRRs. * Depending on the alignment of E820 ranges, this may possibly result * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. * * init_mem_mapping() calls init_range_memory_mapping() with big range. * That range would have hole in the middle or ends, and only ram parts * will be mapped in init_range_memory_mapping(). */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, unsigned long r_end) { unsigned long start_pfn, end_pfn; unsigned long mapped_ram_size = 0; int i; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end); u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end); if (start >= end) continue; /* * if it is overlapping with brk pgt, we need to * alloc pgt buf from memblock instead. */ can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >= min(end, (u64)pgt_buf_top<<PAGE_SHIFT); init_memory_mapping(start, end, PAGE_KERNEL); mapped_ram_size += end - start; can_use_brk_pgt = true; } return mapped_ram_size; } static unsigned long __init get_new_step_size(unsigned long step_size) { /* * Initial mapped size is PMD_SIZE (2M). * We can not set step_size to be PUD_SIZE (1G) yet. * In worse case, when we cross the 1G boundary, and * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k) * to map 1G range with PTE. Hence we use one less than the * difference of page table level shifts. * * Don't need to worry about overflow in the top-down case, on 32bit, * when step_size is 0, round_down() returns 0 for start, and that * turns it into 0x100000000ULL. * In the bottom-up case, round_up(x, 0) returns 0 though too, which * needs to be taken into consideration by the code below. */ return step_size << (PMD_SHIFT - PAGE_SHIFT - 1); } /** * memory_map_top_down - Map [map_start, map_end) top down * @map_start: start address of the target memory range * @map_end: end address of the target memory range * * This function will setup direct mapping for memory range * [map_start, map_end) in top-down. That said, the page tables * will be allocated at the end of the memory, and we map the * memory in top-down. */ static void __init memory_map_top_down(unsigned long map_start, unsigned long map_end) { unsigned long real_end, last_start; unsigned long step_size; unsigned long addr; unsigned long mapped_ram_size = 0; /* * Systems that have many reserved areas near top of the memory, * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will * require lots of 4K mappings which may exhaust pgt_buf. * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure * there is enough mapped memory that can be allocated from * memblock. */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); memblock_phys_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ step_size = PMD_SIZE; max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = real_end; /* * We start from the top (end of memory) and go to the bottom. * The memblock_find_in_range() gets us a block of RAM from the * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ while (last_start > map_start) { unsigned long start; if (last_start > step_size) { start = round_down(last_start - 1, step_size); if (start < map_start) start = map_start; } else start = map_start; mapped_ram_size += init_range_memory_mapping(start, last_start); last_start = start; min_pfn_mapped = last_start >> PAGE_SHIFT; if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); } if (real_end < map_end) init_range_memory_mapping(real_end, map_end); } /** * memory_map_bottom_up - Map [map_start, map_end) bottom up * @map_start: start address of the target memory range * @map_end: end address of the target memory range * * This function will setup direct mapping for memory range * [map_start, map_end) in bottom-up. Since we have limited the * bottom-up allocation above the kernel, the page tables will * be allocated just above the kernel and we map the memory * in [map_start, map_end) in bottom-up. */ static void __init memory_map_bottom_up(unsigned long map_start, unsigned long map_end) { unsigned long next, start; unsigned long mapped_ram_size = 0; /* step_size need to be small so pgt_buf from BRK could cover it */ unsigned long step_size = PMD_SIZE; start = map_start; min_pfn_mapped = start >> PAGE_SHIFT; /* * We start from the bottom (@map_start) and go to the top (@map_end). * The memblock_find_in_range() gets us a block of RAM from the * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages * for page table. */ while (start < map_end) { if (step_size && map_end - start > step_size) { next = round_up(start + 1, step_size); if (next > map_end) next = map_end; } else { next = map_end; } mapped_ram_size += init_range_memory_mapping(start, next); start = next; if (mapped_ram_size >= step_size) step_size = get_new_step_size(step_size); } } /* * The real mode trampoline, which is required for bootstrapping CPUs * occupies only a small area under the low 1MB. See reserve_real_mode() * for details. * * If KASLR is disabled the first PGD entry of the direct mapping is copied * to map the real mode trampoline. * * If KASLR is enabled, copy only the PUD which covers the low 1MB * area. This limits the randomization granularity to 1GB for both 4-level * and 5-level paging. */ static void __init init_trampoline(void) { #ifdef CONFIG_X86_64 /* * The code below will alias kernel page-tables in the user-range of the * address space, including the Global bit. So global TLB entries will * be created when using the trampoline page-table. */ if (!kaslr_memory_enabled()) trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)]; else init_trampoline_kaslr(); #endif } void __init init_mem_mapping(void) { unsigned long end; pti_check_boottime_disable(); probe_page_size_mask(); setup_pcid(); #ifdef CONFIG_X86_64 end = max_pfn << PAGE_SHIFT; #else end = max_low_pfn << PAGE_SHIFT; #endif /* the ISA range is always mapped regardless of memory holes */ init_memory_mapping(0, ISA_END_ADDRESS, PAGE_KERNEL); /* Init the trampoline, possibly with KASLR memory offset */ init_trampoline(); /* * If the allocation is in bottom-up direction, we setup direct mapping * in bottom-up, otherwise we setup direct mapping in top-down. */ if (memblock_bottom_up()) { unsigned long kernel_end = __pa_symbol(_end); /* * we need two separate calls here. This is because we want to * allocate page tables above the kernel. So we first map * [kernel_end, end) to make memory above the kernel be mapped * as soon as possible. And then use page tables allocated above * the kernel to map [ISA_END_ADDRESS, kernel_end). */ memory_map_bottom_up(kernel_end, end); memory_map_bottom_up(ISA_END_ADDRESS, kernel_end); } else { memory_map_top_down(ISA_END_ADDRESS, end); } #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { /* can we preserve max_low_pfn ?*/ max_low_pfn = max_pfn; } #else early_ioremap_page_table_range_init(); #endif load_cr3(swapper_pg_dir); __flush_tlb_all(); x86_init.hyper.init_mem_mapping(); early_memtest(0, max_pfn_mapped << PAGE_SHIFT); } /* * Initialize an mm_struct to be used during poking and a pointer to be used * during patching. */ void __init poking_init(void) { spinlock_t *ptl; pte_t *ptep; poking_mm = mm_alloc(); BUG_ON(!poking_mm); /* Xen PV guests need the PGD to be pinned. */ paravirt_arch_dup_mmap(NULL, poking_mm); /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, * and adjust the address if the PMD ends after the first one. */ poking_addr = TASK_UNMAPPED_BASE; if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) % (TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE); if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0) poking_addr += PAGE_SIZE; /* * We need to trigger the allocation of the page-tables that will be * needed for poking now. Later, poking may be performed in an atomic * section, which might cause allocation to fail. */ ptep = get_locked_pte(poking_mm, poking_addr, &ptl); BUG_ON(!ptep); pte_unmap_unlock(ptep, ptl); } /* * devmem_is_allowed() checks to see if /dev/mem access to a certain address * is valid. The argument is a physical page number. * * On x86, access has to be given to the first megabyte of RAM because that * area traditionally contains BIOS code and data regions used by X, dosemu, * and similar apps. Since they map the entire memory range, the whole range * must be allowed (for mapping), but any areas that would otherwise be * disallowed are flagged as being "zero filled" instead of rejected. * Access has to be given to non-kernel-ram areas as well, these contain the * PCI mmio resources as well as potential bios/acpi data regions. */ int devmem_is_allowed(unsigned long pagenr) { if (region_intersects(PFN_PHYS(pagenr), PAGE_SIZE, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE) != REGION_DISJOINT) { /* * For disallowed memory regions in the low 1MB range, * request that the page be shown as all zeros. */ if (pagenr < 256) return 2; return 0; } /* * This must follow RAM test, since System RAM is considered a * restricted resource under CONFIG_STRICT_DEVMEM. */ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) { /* Low 1MB bypasses iomem restrictions. */ if (pagenr < 256) return 1; return 0; } return 1; } void free_init_pages(const char *what, unsigned long begin, unsigned long end) { unsigned long begin_aligned, end_aligned; /* Make sure boundaries are page aligned */ begin_aligned = PAGE_ALIGN(begin); end_aligned = end & PAGE_MASK; if (WARN_ON(begin_aligned != begin || end_aligned != end)) { begin = begin_aligned; end = end_aligned; } if (begin >= end) return; /* * If debugging page accesses then do not free this memory but * mark them not present - any buggy init-section access will * create a kernel page fault: */ if (debug_pagealloc_enabled()) { pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n", begin, end - 1); /* * Inform kmemleak about the hole in the memory since the * corresponding pages will be unmapped. */ kmemleak_free_part((void *)begin, end - begin); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); } else { /* * We just marked the kernel text read only above, now that * we are going to free part of that, we need to make that * writeable and non-executable first. */ set_memory_nx(begin, (end - begin) >> PAGE_SHIFT); set_memory_rw(begin, (end - begin) >> PAGE_SHIFT); free_reserved_area((void *)begin, (void *)end, POISON_FREE_INITMEM, what); } } /* * begin/end can be in the direct map or the "high kernel mapping" * used for the kernel image only. free_init_pages() will do the * right thing for either kind of address. */ void free_kernel_image_pages(const char *what, void *begin, void *end) { unsigned long begin_ul = (unsigned long)begin; unsigned long end_ul = (unsigned long)end; unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT; free_init_pages(what, begin_ul, end_ul); /* * PTI maps some of the kernel into userspace. For performance, * this includes some kernel areas that do not contain secrets. * Those areas might be adjacent to the parts of the kernel image * being freed, which may contain secrets. Remove the "high kernel * image mapping" for these freed areas, ensuring they are not even * potentially vulnerable to Meltdown regardless of the specific * optimizations PTI is currently using. * * The "noalias" prevents unmapping the direct map alias which is * needed to access the freed pages. * * This is only valid for 64bit kernels. 32bit has only one mapping * which can't be treated in this way for obvious reasons. */ if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI)) set_memory_np_noalias(begin_ul, len_pages); } void __ref free_initmem(void) { e820__reallocate_tables(); mem_encrypt_free_decrypted_mem(); free_kernel_image_pages("unused kernel image (initmem)", &__init_begin, &__init_end); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, * decompressor could be confused by aligned initrd_end * We already reserve the end partial page before in * - i386_start_kernel() * - x86_64_start_kernel() * - relocate_initrd() * So here We can do PAGE_ALIGN() safely to get partial page to be freed */ free_init_pages("initrd", start, PAGE_ALIGN(end)); } #endif /* * Calculate the precise size of the DMA zone (first 16 MB of RAM), * and pass it to the MM layer - to help it set zone watermarks more * accurately. * * Done on 64-bit systems only for the time being, although 32-bit systems * might benefit from this as well. */ void __init memblock_find_dma_reserve(void) { #ifdef CONFIG_X86_64 u64 nr_pages = 0, nr_free_pages = 0; unsigned long start_pfn, end_pfn; phys_addr_t start_addr, end_addr; int i; u64 u; /* * Iterate over all memory ranges (free and reserved ones alike), * to calculate the total number of pages in the first 16 MB of RAM: */ nr_pages = 0; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { start_pfn = min(start_pfn, MAX_DMA_PFN); end_pfn = min(end_pfn, MAX_DMA_PFN); nr_pages += end_pfn - start_pfn; } /* * Iterate over free memory ranges to calculate the number of free * pages in the DMA zone, while not counting potential partial * pages at the beginning or the end of the range: */ nr_free_pages = 0; for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); if (start_pfn < end_pfn) nr_free_pages += end_pfn - start_pfn; } set_dma_reserve(nr_pages - nr_free_pages); #endif } void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); #ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = min(MAX_DMA_PFN, max_low_pfn); #endif #ifdef CONFIG_ZONE_DMA32 max_zone_pfns[ZONE_DMA32] = disable_dma32 ? 0 : min(MAX_DMA32_PFN, max_low_pfn); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM max_zone_pfns[ZONE_HIGHMEM] = max_pfn; #endif free_area_init(max_zone_pfns); } static int __init early_disable_dma32(char *buf) { if (!buf) return -EINVAL; if (!strcmp(buf, "on")) disable_dma32 = true; return 0; } early_param("disable_dma32", early_disable_dma32); __visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) { /* entry 0 MUST be WB (hardwired to speed up translations) */ BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB); __cachemode2pte_tbl[cache] = __cm_idx2pte(entry); __pte2cachemode_tbl[entry] = cache; } #ifdef CONFIG_SWAP unsigned long arch_max_swapfile_size(void) { unsigned long pages; pages = generic_max_swapfile_size(); if (boot_cpu_has_bug(X86_BUG_L1TF) && l1tf_mitigation != L1TF_MITIGATION_OFF) { /* Limit the swap file size to MAX_PA/2 for L1TF workaround */ unsigned long long l1tf_limit = l1tf_pfn_limit(); /* * We encode swap offsets also with 3 bits below those for pfn * which makes the usable limit higher. */ #if CONFIG_PGTABLE_LEVELS > 2 l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT; #endif pages = min_t(unsigned long long, l1tf_limit, pages); } return pages; } #endif |
| 32 69 386 1 385 97 5 291 379 379 100 289 324 65 101 287 1 100 288 379 317 65 19 2 32 32 32 32 32 32 32 32 32 32 32 32 32 32 111 111 69 69 69 285 285 285 285 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * PF_INET6 socket protocol family * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/af_inet.c * * Fixes: * piggy, Karl Knutson : Socket protocol table * Hideaki YOSHIFUJI : sin6_scope_id support * Arnaldo Melo : check proc_net_create return, cleanups */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/icmpv6.h> #include <linux/netfilter_ipv6.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/udplite.h> #include <net/tcp.h> #include <net/ping.h> #include <net/protocol.h> #include <net/inet_common.h> #include <net/route.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ipv6_stubs.h> #include <net/ndisc.h> #ifdef CONFIG_IPV6_TUNNEL #include <net/ip6_tunnel.h> #endif #include <net/calipso.h> #include <net/seg6.h> #include <net/rpl.h> #include <net/compat.h> #include <net/xfrm.h> #include <net/ioam6.h> #include <net/rawv6.h> #include <linux/uaccess.h> #include <linux/mroute6.h> #include "ip6_offload.h" MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); MODULE_LICENSE("GPL"); /* The inetsw6 table contains everything that inet6_create needs to * build a new socket. */ static struct list_head inetsw6[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw6_lock); struct ipv6_params ipv6_defaults = { .disable_ipv6 = 0, .autoconf = 1, }; static int disable_ipv6_mod; module_param_named(disable, disable_ipv6_mod, int, 0444); MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); module_param_named(disable_ipv6, ipv6_defaults.disable_ipv6, int, 0444); MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); bool ipv6_mod_enabled(void) { return disable_ipv6_mod == 0; } EXPORT_SYMBOL_GPL(ipv6_mod_enabled); static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } void inet6_sock_destruct(struct sock *sk) { inet6_cleanup_sock(sk); inet_sock_destruct(sk); } EXPORT_SYMBOL_GPL(inet6_sock_destruct); static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) { struct inet_sock *inet; struct ipv6_pinfo *np; struct sock *sk; struct inet_protosw *answer; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw6[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (err) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-10-proto-132-type-1 * (net-pf-PF_INET6-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET6, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-10-proto-132 * (net-pf-PF_INET6-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET6, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOBUFS; sk = sk_alloc(net, PF_INET6, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; sock_init_data(sock, sk); err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; if (INET_PROTOSW_ICSK & answer_flags) inet_init_csk_locks(sk); inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } sk->sk_destruct = inet6_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol; sk->sk_backlog_rcv = answer->prot->backlog_rcv; inet_sk(sk)->pinet6 = np = inet6_sk_generic(sk); np->hop_limit = -1; np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->mc_all = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. */ inet->uc_ttl = -1; inet->mc_loop = 1; inet->mc_ttl = 1; inet->mc_index = 0; RCU_INIT_POINTER(inet->mc_list, NULL); inet->rcv_tos = 0; if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; /* * Increment only the relevant sk_prot->socks debug field, this changes * the previous behaviour of incrementing both the equivalent to * answer->prot->socks (inet6_sock_nr) and inet_sock_nr. * * This allows better debug granularity as we'll know exactly how many * UDPv6, TCPv6, etc socks were allocated, not the sum of all IPv6 * transport protocol socks. -acme */ sk_refcnt_debug_inc(sk); if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically shares. */ inet->inet_sport = htons(inet->inet_num); err = sk->sk_prot->hash(sk); if (err) { sk_common_release(sk); goto out; } } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) { sk_common_release(sk); goto out; } } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) { sk_common_release(sk); goto out; } } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; } static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); __be32 v4addr = 0; unsigned short snum; bool saved_ipv6only; int addr_type = 0; int err = 0; if (addr->sin6_family != AF_INET6) return -EAFNOSUPPORT; addr_type = ipv6_addr_type(&addr->sin6_addr); if ((addr_type & IPV6_ADDR_MULTICAST) && sk->sk_type == SOCK_STREAM) return -EINVAL; snum = ntohs(addr->sin6_port); if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; if (flags & BIND_WITH_LOCK) lock_sock(sk); /* Check these errors (active socket, double bind). */ if (sk->sk_state != TCP_CLOSE || inet->inet_num) { err = -EINVAL; goto out; } /* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { struct net_device *dev = NULL; int chk_addr_ret; /* Binding to v4-mapped address on a v6-only socket * makes no sense */ if (ipv6_only_sock(sk)) { err = -EINVAL; goto out; } rcu_read_lock(); if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; goto out_unlock; } } /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr); rcu_read_unlock(); if (!inet_addr_valid_or_nonlocal(net, inet, v4addr, chk_addr_ret)) { err = -EADDRNOTAVAIL; goto out; } } else { if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; rcu_read_lock(); if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another one * is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; goto out_unlock; } } if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; goto out_unlock; } } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { if (!ipv6_can_nonlocal_bind(net, inet) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; goto out_unlock; } } rcu_read_unlock(); } } inet->inet_rcv_saddr = v4addr; inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; saved_ipv6only = sk->sk_ipv6only; if (addr_type != IPV6_ADDR_ANY && addr_type != IPV6_ADDR_MAPPED) sk->sk_ipv6only = 1; /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); goto out; } if (!(flags & BIND_FROM_BPF)) { err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk); if (err) { sk->sk_ipv6only = saved_ipv6only; inet_reset_saddr(sk); if (sk->sk_prot->put_port) sk->sk_prot->put_port(sk); goto out; } } } if (addr_type != IPV6_ADDR_ANY) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); inet->inet_dport = 0; inet->inet_daddr = 0; out: if (flags & BIND_WITH_LOCK) release_sock(sk); return err; out_unlock: rcu_read_unlock(); goto out; } /* bind for INET6 API */ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; u32 flags = BIND_WITH_LOCK; const struct proto *prot; int err = 0; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); /* If the socket has its own bind function then use it. */ if (prot->bind) return prot->bind(sk, uaddr, addr_len); if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, CGROUP_INET6_BIND, &flags); if (err) return err; return __inet6_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet6_bind); int inet6_release(struct socket *sock) { struct sock *sk = sock->sk; if (!sk) return -EINVAL; /* Free mc lists */ ipv6_sock_mc_close(sk); /* Free ac lists */ ipv6_sock_ac_close(sk); return inet_release(sock); } EXPORT_SYMBOL(inet6_release); void inet6_destroy_sock(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct ipv6_txoptions *opt; /* Release rx options */ skb = xchg(&np->pktoptions, NULL); kfree_skb(skb); skb = xchg(&np->rxpmtu, NULL); kfree_skb(skb); /* Free flowlabels */ fl6_free_socklist(sk); /* Free tx options */ opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL); if (opt) { atomic_sub(opt->tot_len, &sk->sk_omem_alloc); txopt_put(opt); } } EXPORT_SYMBOL_GPL(inet6_destroy_sock); void inet6_cleanup_sock(struct sock *sk) { inet6_destroy_sock(sk); } EXPORT_SYMBOL_GPL(inet6_cleanup_sock); /* * This does both peername and sockname. */ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; lock_sock(sk); if (peer) { if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) { release_sock(sk); return -ENOTCONN; } sin->sin6_port = inet->inet_dport; sin->sin6_addr = sk->sk_v6_daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, CGROUP_INET6_GETPEERNAME); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, CGROUP_INET6_GETSOCKNAME); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); release_sock(sk); return sizeof(*sin); } EXPORT_SYMBOL(inet6_getname); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct sock *sk = sock->sk; struct net *net = sock_net(sk); const struct proto *prot; switch (cmd) { case SIOCADDRT: case SIOCDELRT: { struct in6_rtmsg rtmsg; if (copy_from_user(&rtmsg, argp, sizeof(rtmsg))) return -EFAULT; return ipv6_route_ioctl(net, cmd, &rtmsg); } case SIOCSIFADDR: return addrconf_add_ifaddr(net, argp); case SIOCDIFADDR: return addrconf_del_ifaddr(net, argp); case SIOCSIFDSTADDR: return addrconf_set_dstaddr(net, argp); default: /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (!prot->ioctl) return -ENOIOCTLCMD; return prot->ioctl(sk, cmd, arg); } /*NOTREACHED*/ return 0; } EXPORT_SYMBOL(inet6_ioctl); #ifdef CONFIG_COMPAT struct compat_in6_rtmsg { struct in6_addr rtmsg_dst; struct in6_addr rtmsg_src; struct in6_addr rtmsg_gateway; u32 rtmsg_type; u16 rtmsg_dst_len; u16 rtmsg_src_len; u32 rtmsg_metric; u32 rtmsg_info; u32 rtmsg_flags; s32 rtmsg_ifindex; }; static int inet6_compat_routing_ioctl(struct sock *sk, unsigned int cmd, struct compat_in6_rtmsg __user *ur) { struct in6_rtmsg rt; if (copy_from_user(&rt.rtmsg_dst, &ur->rtmsg_dst, 3 * sizeof(struct in6_addr)) || get_user(rt.rtmsg_type, &ur->rtmsg_type) || get_user(rt.rtmsg_dst_len, &ur->rtmsg_dst_len) || get_user(rt.rtmsg_src_len, &ur->rtmsg_src_len) || get_user(rt.rtmsg_metric, &ur->rtmsg_metric) || get_user(rt.rtmsg_info, &ur->rtmsg_info) || get_user(rt.rtmsg_flags, &ur->rtmsg_flags) || get_user(rt.rtmsg_ifindex, &ur->rtmsg_ifindex)) return -EFAULT; return ipv6_route_ioctl(sock_net(sk), cmd, &rt); } int inet6_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; switch (cmd) { case SIOCADDRT: case SIOCDELRT: return inet6_compat_routing_ioctl(sk, cmd, argp); default: return -ENOIOCTLCMD; } } EXPORT_SYMBOL_GPL(inet6_compat_ioctl); #endif /* CONFIG_COMPAT */ INDIRECT_CALLABLE_DECLARE(int udpv6_sendmsg(struct sock *, struct msghdr *, size_t)); int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; const struct proto *prot; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); return INDIRECT_CALL_2(prot->sendmsg, tcp_sendmsg, udpv6_sendmsg, sk, msg, size); } INDIRECT_CALLABLE_DECLARE(int udpv6_recvmsg(struct sock *, struct msghdr *, size_t, int, int *)); int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; const struct proto *prot; int addr_len = 0; int err; if (likely(!(flags & MSG_ERRQUEUE))) sock_rps_record_flow(sk); /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); err = INDIRECT_CALL_2(prot->recvmsg, tcp_recvmsg, udpv6_recvmsg, sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } const struct proto_ops inet6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_stream_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = inet_accept, /* ok */ .getname = inet6_getname, .poll = tcp_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = inet_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet6_sendmsg, /* retpoline's sake */ .recvmsg = inet6_recvmsg, /* retpoline's sake */ #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif .set_rcvlowat = tcp_set_rcvlowat, }; const struct proto_ops inet6_dgram_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = udp_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet6_sendmsg, /* retpoline's sake */ .recvmsg = inet6_recvmsg, /* retpoline's sake */ .read_skb = udp_read_skb, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static const struct net_proto_family inet6_family_ops = { .family = PF_INET6, .create = inet6_create, .owner = THIS_MODULE, }; int inet6_register_protosw(struct inet_protosw *p) { struct list_head *lh; struct inet_protosw *answer; struct list_head *last_perm; int protocol = p->protocol; int ret; spin_lock_bh(&inetsw6_lock); ret = -EINVAL; if (p->type >= SOCK_MAX) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ answer = NULL; ret = -EPERM; last_perm = &inetsw6[p->type]; list_for_each(lh, &inetsw6[p->type]) { answer = list_entry(lh, struct inet_protosw, list); /* Check only the non-wild match. */ if (INET_PROTOSW_PERMANENT & answer->flags) { if (protocol == answer->protocol) break; last_perm = lh; } answer = NULL; } if (answer) goto out_permanent; /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with * a wild-card protocol. But it is allowed to override any existing * non-permanent entry. This means that when we remove this entry, the * system automatically returns to the old behavior. */ list_add_rcu(&p->list, last_perm); ret = 0; out: spin_unlock_bh(&inetsw6_lock); return ret; out_permanent: pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } EXPORT_SYMBOL(inet6_register_protosw); void inet6_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw6_lock); list_del_rcu(&p->list); spin_unlock_bh(&inetsw6_lock); synchronize_net(); } } EXPORT_SYMBOL(inet6_unregister_protosw); int inet6_sk_rebuild_header(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct dst_entry *dst; dst = __sk_dst_check(sk, np->dst_cookie); if (!dst) { struct inet_sock *inet = inet_sk(sk); struct in6_addr *final_p, final; struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; fl6.flowi6_uid = sk->sk_uid; security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); rcu_read_lock(); final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); return PTR_ERR(dst); } ip6_dst_store(sk, dst, NULL, NULL); } return 0; } EXPORT_SYMBOL_GPL(inet6_sk_rebuild_header); bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt) { const struct ipv6_pinfo *np = inet6_sk(sk); if (np->rxopt.all) { if (((opt->flags & IP6SKB_HOPBYHOP) && (np->rxopt.bits.hopopts || np->rxopt.bits.ohopopts)) || (ip6_flowinfo((struct ipv6hdr *) skb_network_header(skb)) && np->rxopt.bits.rxflow) || (opt->srcrt && (np->rxopt.bits.srcrt || np->rxopt.bits.osrcrt)) || ((opt->dst1 || opt->dst0) && (np->rxopt.bits.dstopts || np->rxopt.bits.odstopts))) return true; } return false; } EXPORT_SYMBOL_GPL(ipv6_opt_accepted); static struct packet_type ipv6_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IPV6), .func = ipv6_rcv, .list_func = ipv6_list_rcv, }; static int __init ipv6_packet_init(void) { dev_add_pack(&ipv6_packet_type); return 0; } static void ipv6_packet_cleanup(void) { dev_remove_pack(&ipv6_packet_type); } static int __net_init ipv6_init_mibs(struct net *net) { int i; net->mib.udp_stats_in6 = alloc_percpu(struct udp_mib); if (!net->mib.udp_stats_in6) return -ENOMEM; net->mib.udplite_stats_in6 = alloc_percpu(struct udp_mib); if (!net->mib.udplite_stats_in6) goto err_udplite_mib; net->mib.ipv6_statistics = alloc_percpu(struct ipstats_mib); if (!net->mib.ipv6_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet6_stats; af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics, i); u64_stats_init(&af_inet6_stats->syncp); } net->mib.icmpv6_statistics = alloc_percpu(struct icmpv6_mib); if (!net->mib.icmpv6_statistics) goto err_icmp_mib; net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib), GFP_KERNEL); if (!net->mib.icmpv6msg_statistics) goto err_icmpmsg_mib; return 0; err_icmpmsg_mib: free_percpu(net->mib.icmpv6_statistics); err_icmp_mib: free_percpu(net->mib.ipv6_statistics); err_ip_mib: free_percpu(net->mib.udplite_stats_in6); err_udplite_mib: free_percpu(net->mib.udp_stats_in6); return -ENOMEM; } static void ipv6_cleanup_mibs(struct net *net) { free_percpu(net->mib.udp_stats_in6); free_percpu(net->mib.udplite_stats_in6); free_percpu(net->mib.ipv6_statistics); free_percpu(net->mib.icmpv6_statistics); kfree(net->mib.icmpv6msg_statistics); } static int __net_init inet6_net_init(struct net *net) { int err = 0; net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; net->ipv6.sysctl.icmpv6_echo_ignore_all = 0; net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0; net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0; /* By default, rate limit error messages. * Except for pmtu discovery, it would break it. * proc_do_large_bitmap needs pointer to the bitmap. */ bitmap_set(net->ipv6.sysctl.icmpv6_ratemask, 0, ICMPV6_ERRMSG_MAX + 1); bitmap_clear(net->ipv6.sysctl.icmpv6_ratemask, ICMPV6_PKT_TOOBIG, 1); net->ipv6.sysctl.icmpv6_ratemask_ptr = net->ipv6.sysctl.icmpv6_ratemask; net->ipv6.sysctl.flowlabel_consistency = 1; net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS; net->ipv6.sysctl.idgen_retries = 3; net->ipv6.sysctl.idgen_delay = 1 * HZ; net->ipv6.sysctl.flowlabel_state_ranges = 0; net->ipv6.sysctl.max_dst_opts_cnt = IP6_DEFAULT_MAX_DST_OPTS_CNT; net->ipv6.sysctl.max_hbh_opts_cnt = IP6_DEFAULT_MAX_HBH_OPTS_CNT; net->ipv6.sysctl.max_dst_opts_len = IP6_DEFAULT_MAX_DST_OPTS_LEN; net->ipv6.sysctl.max_hbh_opts_len = IP6_DEFAULT_MAX_HBH_OPTS_LEN; net->ipv6.sysctl.fib_notify_on_flag_change = 0; atomic_set(&net->ipv6.fib6_sernum, 1); net->ipv6.sysctl.ioam6_id = IOAM6_DEFAULT_ID; net->ipv6.sysctl.ioam6_id_wide = IOAM6_DEFAULT_ID_WIDE; err = ipv6_init_mibs(net); if (err) return err; #ifdef CONFIG_PROC_FS err = udp6_proc_init(net); if (err) goto out; err = tcp6_proc_init(net); if (err) goto proc_tcp6_fail; err = ac6_proc_init(net); if (err) goto proc_ac6_fail; #endif return err; #ifdef CONFIG_PROC_FS proc_ac6_fail: tcp6_proc_exit(net); proc_tcp6_fail: udp6_proc_exit(net); out: ipv6_cleanup_mibs(net); return err; #endif } static void __net_exit inet6_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS udp6_proc_exit(net); tcp6_proc_exit(net); ac6_proc_exit(net); #endif ipv6_cleanup_mibs(net); } static struct pernet_operations inet6_net_ops = { .init = inet6_net_init, .exit = inet6_net_exit, }; static int ipv6_route_input(struct sk_buff *skb) { ip6_route_input(skb); return skb_dst(skb)->error; } static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup, .fib6_lookup = fib6_lookup, .fib6_select_path = fib6_select_path, .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .fib6_nh_init = fib6_nh_init, .fib6_nh_release = fib6_nh_release, .fib6_nh_release_dsts = fib6_nh_release_dsts, .fib6_update_sernum = fib6_update_sernum_stub, .fib6_rt_update = fib6_rt_update, .ip6_del_rt = ip6_del_rt, .udpv6_encap_enable = udpv6_encap_enable, .ndisc_send_na = ndisc_send_na, #if IS_ENABLED(CONFIG_XFRM) .xfrm6_local_rxpmtu = xfrm6_local_rxpmtu, .xfrm6_udp_encap_rcv = xfrm6_udp_encap_rcv, .xfrm6_rcv_encap = xfrm6_rcv_encap, #endif .nd_tbl = &nd_tbl, .ipv6_fragment = ip6_fragment, .ipv6_dev_find = ipv6_dev_find, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { .inet6_bind = __inet6_bind, .udp6_lib_lookup = __udp6_lib_lookup, .ipv6_setsockopt = do_ipv6_setsockopt, .ipv6_getsockopt = do_ipv6_getsockopt, .ipv6_dev_get_saddr = ipv6_dev_get_saddr, }; static int __init inet6_init(void) { struct list_head *r; int err = 0; sock_skb_cb_check_size(sizeof(struct inet6_skb_parm)); /* Register the socket-side information for inet6_create. */ for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); raw_hashinfo_init(&raw_v6_hashinfo); if (disable_ipv6_mod) { pr_info("Loaded, but administratively disabled, reboot required to enable\n"); goto out; } err = proto_register(&tcpv6_prot, 1); if (err) goto out; err = proto_register(&udpv6_prot, 1); if (err) goto out_unregister_tcp_proto; err = proto_register(&udplitev6_prot, 1); if (err) goto out_unregister_udp_proto; err = proto_register(&rawv6_prot, 1); if (err) goto out_unregister_udplite_proto; err = proto_register(&pingv6_prot, 1); if (err) goto out_unregister_raw_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ err = rawv6_init(); if (err) goto out_unregister_ping_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) */ err = sock_register(&inet6_family_ops); if (err) goto out_sock_register_fail; /* * ipngwg API draft makes clear that the correct semantics * for TCP and UDP is to consider one TCP and UDP instance * in a host available by both INET and INET6 APIs and * able to communicate via both network protocols. */ err = register_pernet_subsys(&inet6_net_ops); if (err) goto register_pernet_fail; err = ip6_mr_init(); if (err) goto ipmr_fail; err = icmpv6_init(); if (err) goto icmp_fail; err = ndisc_init(); if (err) goto ndisc_fail; err = igmp6_init(); if (err) goto igmp_fail; err = ipv6_netfilter_init(); if (err) goto netfilter_fail; /* Create /proc/foo6 entries. */ #ifdef CONFIG_PROC_FS err = -ENOMEM; if (raw6_proc_init()) goto proc_raw6_fail; if (udplite6_proc_init()) goto proc_udplite6_fail; if (ipv6_misc_proc_init()) goto proc_misc6_fail; if (if6_proc_init()) goto proc_if6_fail; #endif err = ip6_route_init(); if (err) goto ip6_route_fail; err = ndisc_late_init(); if (err) goto ndisc_late_fail; err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; err = ipv6_anycast_init(); if (err) goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; /* Init v6 extension headers. */ err = ipv6_exthdrs_init(); if (err) goto ipv6_exthdrs_fail; err = ipv6_frag_init(); if (err) goto ipv6_frag_fail; /* Init v6 transport protocols. */ err = udpv6_init(); if (err) goto udpv6_fail; err = udplitev6_init(); if (err) goto udplitev6_fail; err = udpv6_offload_init(); if (err) goto udpv6_offload_fail; err = tcpv6_init(); if (err) goto tcpv6_fail; err = ipv6_packet_init(); if (err) goto ipv6_packet_fail; err = pingv6_init(); if (err) goto pingv6_fail; err = calipso_init(); if (err) goto calipso_fail; err = seg6_init(); if (err) goto seg6_fail; err = rpl_init(); if (err) goto rpl_fail; err = ioam6_init(); if (err) goto ioam6_fail; err = igmp6_late_init(); if (err) goto igmp6_late_err; #ifdef CONFIG_SYSCTL err = ipv6_sysctl_register(); if (err) goto sysctl_fail; #endif /* ensure that ipv6 stubs are visible only after ipv6 is ready */ wmb(); ipv6_stub = &ipv6_stub_impl; ipv6_bpf_stub = &ipv6_bpf_stub_impl; out: return err; #ifdef CONFIG_SYSCTL sysctl_fail: igmp6_late_cleanup(); #endif igmp6_late_err: ioam6_exit(); ioam6_fail: rpl_exit(); rpl_fail: seg6_exit(); seg6_fail: calipso_exit(); calipso_fail: pingv6_exit(); pingv6_fail: ipv6_packet_cleanup(); ipv6_packet_fail: tcpv6_exit(); tcpv6_fail: udpv6_offload_exit(); udpv6_offload_fail: udplitev6_exit(); udplitev6_fail: udpv6_exit(); udpv6_fail: ipv6_frag_exit(); ipv6_frag_fail: ipv6_exthdrs_exit(); ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: ipv6_anycast_cleanup(); ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); ndisc_late_fail: ip6_route_cleanup(); ip6_route_fail: #ifdef CONFIG_PROC_FS if6_proc_exit(); proc_if6_fail: ipv6_misc_proc_exit(); proc_misc6_fail: udplite6_proc_exit(); proc_udplite6_fail: raw6_proc_exit(); proc_raw6_fail: #endif ipv6_netfilter_fini(); netfilter_fail: igmp6_cleanup(); igmp_fail: ndisc_cleanup(); ndisc_fail: icmpv6_cleanup(); icmp_fail: ip6_mr_cleanup(); ipmr_fail: unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); out_sock_register_fail: rawv6_exit(); out_unregister_ping_proto: proto_unregister(&pingv6_prot); out_unregister_raw_proto: proto_unregister(&rawv6_prot); out_unregister_udplite_proto: proto_unregister(&udplitev6_prot); out_unregister_udp_proto: proto_unregister(&udpv6_prot); out_unregister_tcp_proto: proto_unregister(&tcpv6_prot); goto out; } module_init(inet6_init); MODULE_ALIAS_NETPROTO(PF_INET6); |
| 207 207 207 204 1517 10 1518 3360 2776 3086 2710 2255 1827 638 573 573 575 574 3359 3285 565 3584 3130 2598 3555 172 795 796 3359 1515 3574 2 754 3579 1 460 3554 5 171 5 172 3 3577 4 591 3581 3583 1482 3578 3579 2 2 733 733 3218 3213 733 3210 3220 819 3206 3211 3212 5 5 5 1 1 10 3 2 4 4 10 3 3 3 3 3 3 3 3 3 3 3 3 3 6 1 5 6 6 6 3 3 9 60 84 19 3 60 1 1 4 4938 454 3 4942 4821 3 454 2 172 1511 3894 454 3898 3 3898 1033 3547 1199 3208 84 156 818 1 2356 1033 35 3508 454 3 3891 3891 1999 3744 455 3 1199 455 1199 1 1198 3208 74 74 1 154 2353 1033 35 2600 2864 1402 3892 1662 1886 2665 251 251 2136 2479 2481 2 14 1840 7 4 3 3 17 2 471 2206 517 232 517 4 508 221 4 221 5 216 4 4 216 216 215 204 3 204 3 206 517 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <linux/stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/errname.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/time.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #include <linux/property.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <asm/unaligned.h> #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); static noinline unsigned long long simple_strntoull(const char *startp, size_t max_chars, char **endp, unsigned int base) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoull instead. */ noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, unsigned int base) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, max_chars - 1, endp, base); return simple_strntoull(cp, max_chars, endp, base); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function has caveats. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ static_assert(SIGN == 1); static_assert(ZEROPAD == ('0' - ' ')); static_assert(SMALL == ('a' ^ 'A')); enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } static char *err_ptr(char *buf, char *end, void *ptr, struct printf_spec spec) { int err = PTR_ERR(ptr); const char *sym = errname(err); if (sym) return string_nocheck(buf, end, sym, spec); /* * Somebody passed ERR_PTR(-1234) or some other non-existing * Efoo - or perhaps CONFIG_SYMBOLIC_ERRNAME=n. Fall back to * printing it as its decimal representation. */ spec.flags |= SIGN; spec.base = 10; return number(buf, end, err, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static bool filled_random_ptr_key __read_mostly; static siphash_key_t ptr_key __read_mostly; static void fill_ptr_key_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(fill_ptr_key_work, fill_ptr_key_workfn); static void fill_ptr_key_workfn(struct work_struct *work) { if (!rng_is_initialized()) { queue_delayed_work(system_unbound_wq, &fill_ptr_key_work, HZ * 2); return; } get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Pairs with smp_rmb() before reading ptr_key. */ smp_wmb(); WRITE_ONCE(filled_random_ptr_key, true); } static int __init vsprintf_init_hashval(void) { fill_ptr_key_workfn(NULL); return 0; } subsys_initcall(vsprintf_init_hashval) /* Maps a pointer to a 32 bit unique identifier. */ static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (!READ_ONCE(filled_random_ptr_key)) return -EBUSY; /* Pairs with smp_wmb() after writing ptr_key. */ smp_rmb(); #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_irq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev->bd_partno) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev->bd_partno, spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B' && fmt[1] == 'b') sprint_backtrace_build_id(sym, value); else if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt == 'S' && (fmt[1] == 'b' || (fmt[1] == 'R' && fmt[2] == 'b'))) sprint_symbol_build_id(sym, value); else if (*fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = number(p, pend, res->start, *specp); if (res->start != res->end) { *p++ = '-'; p = number(p, pend, res->end, *specp); } } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, const unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); bool first = true; int rbot, rtop; if (check_pointer(&buf, end, bitmap, spec)) return buf; for_each_set_bitrange(rbot, rtop, bitmap, nr_bits) { if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rtop == rbot + 1) continue; if (buf < end) *buf = '-'; buf = number(++buf, end, rtop - 1, default_dec_spec); } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; fallthrough; default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; fallthrough; case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *fourcc_string(char *buf, char *end, const u32 *fourcc, struct printf_spec spec, const char *fmt) { char output[sizeof("0123 little-endian (0x01234567)")]; char *p = output; unsigned int i; u32 orig, val; if (fmt[1] != 'c' || fmt[2] != 'c') return error_string(buf, end, "(%p4?)", spec); if (check_pointer(&buf, end, fourcc, spec)) return buf; orig = get_unaligned(fourcc); val = orig & ~BIT(31); for (i = 0; i < sizeof(u32); i++) { unsigned char c = val >> (i * 8); /* Print non-control ASCII characters as-is, dot otherwise */ *p++ = isascii(c) && isprint(c) ? c : '.'; } *p++ = ' '; strcpy(p, orig & BIT(31) ? "big-endian" : "little-endian"); p += strlen(p); *p++ = ' '; *p++ = '('; p = special_hex_number(p, output + sizeof(output) - 2, orig, sizeof(u32)); *p++ = ')'; *p = '\0'; return string(buf, end, output, spec); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false, iso8601_separator = true; bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } do { switch (fmt[count++]) { case 'r': raw = true; break; case 's': iso8601_separator = false; break; default: found = false; break; } } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { if (buf < end) *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time64_str(char *buf, char *end, const time64_t time, struct printf_spec spec, const char *fmt) { struct rtc_time rtc_time; struct tm tm; time64_to_tm(time, 0, &tm); rtc_time.tm_sec = tm.tm_sec; rtc_time.tm_min = tm.tm_min; rtc_time.tm_hour = tm.tm_hour; rtc_time.tm_mday = tm.tm_mday; rtc_time.tm_mon = tm.tm_mon; rtc_time.tm_year = tm.tm_year; rtc_time.tm_wday = tm.tm_wday; rtc_time.tm_yday = tm.tm_yday; rtc_time.tm_isdst = 0; return rtc_str(buf, end, &rtc_time, spec, fmt); } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); case 'T': return time64_str(buf, end, *(const time64_t *)ptr, spec, fmt); default: return error_string(buf, end, "(%pt?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } struct page_flags_fields { int width; int shift; int mask; const struct printf_spec *spec; const char *name; }; static const struct page_flags_fields pff[] = { {SECTIONS_WIDTH, SECTIONS_PGSHIFT, SECTIONS_MASK, &default_dec_spec, "section"}, {NODES_WIDTH, NODES_PGSHIFT, NODES_MASK, &default_dec_spec, "node"}, {ZONES_WIDTH, ZONES_PGSHIFT, ZONES_MASK, &default_dec_spec, "zone"}, {LAST_CPUPID_WIDTH, LAST_CPUPID_PGSHIFT, LAST_CPUPID_MASK, &default_flag_spec, "lastcpupid"}, {KASAN_TAG_WIDTH, KASAN_TAG_PGSHIFT, KASAN_TAG_MASK, &default_flag_spec, "kasantag"}, }; static char *format_page_flags(char *buf, char *end, unsigned long flags) { unsigned long main_flags = flags & PAGEFLAGS_MASK; bool append = false; int i; buf = number(buf, end, flags, default_flag_spec); if (buf < end) *buf = '('; buf++; /* Page flags from the main area. */ if (main_flags) { buf = format_flags(buf, end, main_flags, pageflag_names); append = true; } /* Page flags from the fields area */ for (i = 0; i < ARRAY_SIZE(pff); i++) { /* Skip undefined fields. */ if (!pff[i].width) continue; /* Format: Flag Name + '=' (equals sign) + Number + '|' (separator) */ if (append) { if (buf < end) *buf = '|'; buf++; } buf = string(buf, end, pff[i].name, default_str_spec); if (buf < end) *buf = '='; buf++; buf = number(buf, end, (flags >> pff[i].shift) & pff[i].mask, *pff[i].spec); append = true; } if (buf < end) *buf = ')'; buf++; return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': return format_page_flags(buf, end, *(unsigned long *)flags_ptr); case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = (__force unsigned long)(*(gfp_t *)flags_ptr); names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static noinline_for_stack char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, char *end) { int depth; /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { /* * Only get a reference for other nodes (i.e. parent nodes). * fwnode refcount may be 0 here. */ struct fwnode_handle *__fwnode = depth ? fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); if (depth) fwnode_handle_put(__fwnode); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (fmt[0] != 'F') return error_string(buf, end, "(%pO?)", spec); if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = fwnode_full_name_string(of_fwnode_handle(dn), buf, end); break; case 'n': /* name */ p = fwnode_get_name(of_fwnode_handle(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, default_dec_spec); break; case 'P': /* path-spec */ p = fwnode_get_name(of_fwnode_handle(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static noinline_for_stack char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, struct printf_spec spec, const char *fmt) { struct printf_spec str_spec = spec; char *buf_start = buf; str_spec.field_width = -1; if (*fmt != 'w') return error_string(buf, end, "(%pf?)", spec); if (check_pointer(&buf, end, fwnode, spec)) return buf; fmt++; switch (*fmt) { case 'P': /* name */ buf = string(buf, end, fwnode_get_name(fwnode), str_spec); break; case 'f': /* full_name */ default: buf = fwnode_full_name_string(fwnode, buf, end); break; } return widen_string(buf, buf - buf_start, end, spec); } int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* Used for Rust formatting ('%pA'). */ char *rust_fmt_argument(char *buf, char *end, void *ptr); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - '[Ss]R' as above with __builtin_extract_return_addr() translation * - 'S[R]b' as above with module build ID (for use in backtraces) * - '[Ff]' %pf and %pF were obsoleted and later removed in favor of * %ps and %pS. Be careful when re-using these specifiers. * - 'B' For backtraced symbolic direct pointers with offset * - 'Bb' as above with module build ID (for use in backtraces) * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * https://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users. * Use only for procfs, sysfs and similar files, not printk(); please * read the documentation (path below) first. * - 'NF' For a netdev_features_t * - '4cc' V4L2 or DRM FourCC code, with endianness and raw numerical value. * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'fw[fP]' For a firmware node (struct fwnode_handle) pointer * Without an option prints the full name of the node * f full name * P node name, including a possible unit address * - 'x' For printing the address unmodified. Equivalent to "%lx". * Please read the documentation (path below) before using! * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of * bpf_trace_printk() where [ku] prefix specifies either kernel (k) * or user (u) memory to probe, and: * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. * * There is also a '%pA' format specifier, but it is only intended to be used * from Rust code to format core::fmt::Arguments. Do *not* use it from C. * See rust/kernel/print.rs for details. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); fallthrough; case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_string(buf, end, ptr, spec, fmt); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case '4': return fourcc_string(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); case 'A': if (!IS_ENABLED(CONFIG_RUST)) { WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); return error_string(buf, end, "(%pA?)", spec); } return rust_fmt_argument(buf, end, ptr); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': /* %pe with a non-ERR_PTR gets treated as plain %p */ if (!IS_ERR(ptr)) return default_pointer(buf, end, ptr, spec); return err_ptr(buf, end, ptr, spec); case 'u': case 'k': switch (fmt[1]) { case 's': return string(buf, end, ptr, spec); default: return error_string(buf, end, "(einval)", spec); } default: return default_pointer(buf, end, ptr, spec); } } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; fallthrough; case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; break; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ fallthrough; default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; if (unlikely(!size)) return 0; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; return size - 1; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'x': case 'K': case 'e': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'x': case 'K': case 'e': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); /** * bprintf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of words(u32) written * into @bin_buf. */ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = vbin_printf(bin_buf, size, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL_GPL(bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matches any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) __set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ __clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; fallthrough; case 'd': is_sign = true; fallthrough; case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') { if (field_width == 1) break; digit = *(str + 1); } if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && (!isdigit(digit) || digit > '7')) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, field_width >= 0 ? field_width : INT_MAX, &next, base); else val.u = simple_strntoull(str, field_width >= 0 ? field_width : INT_MAX, &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 1092 814 557 557 412 412 706 18 2125 2011 1093 412 706 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Intel Corporation. */ /* A common module to handle registrations and notifications for paravirtual * drivers to enable accelerated datapath and support VF live migration. * * The notifier and event handling code is based on netvsc driver. */ #include <linux/module.h> #include <linux/etherdevice.h> #include <uapi/linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> #include <net/failover.h> static LIST_HEAD(failover_list); static DEFINE_SPINLOCK(failover_lock); static struct net_device *failover_get_bymac(u8 *mac, struct failover_ops **ops) { struct net_device *failover_dev; struct failover *failover; spin_lock(&failover_lock); list_for_each_entry(failover, &failover_list, list) { failover_dev = rtnl_dereference(failover->failover_dev); if (ether_addr_equal(failover_dev->perm_addr, mac)) { *ops = rtnl_dereference(failover->ops); spin_unlock(&failover_lock); return failover_dev; } } spin_unlock(&failover_lock); return NULL; } /** * failover_slave_register - Register a slave netdev * * @slave_dev: slave netdev that is being registered * * Registers a slave device to a failover instance. Only ethernet devices * are supported. */ static int failover_slave_register(struct net_device *slave_dev) { struct netdev_lag_upper_info lag_upper_info; struct net_device *failover_dev; struct failover_ops *fops; int err; if (slave_dev->type != ARPHRD_ETHER) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (fops && fops->slave_pre_register && fops->slave_pre_register(slave_dev, failover_dev)) goto done; err = netdev_rx_handler_register(slave_dev, fops->slave_handle_frame, failover_dev); if (err) { netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n", err); goto done; } lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; err = netdev_master_upper_dev_link(slave_dev, failover_dev, NULL, &lag_upper_info, NULL); if (err) { netdev_err(slave_dev, "can not set failover device %s (err = %d)\n", failover_dev->name, err); goto err_upper_link; } slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); err_upper_link: netdev_rx_handler_unregister(slave_dev); done: return NOTIFY_DONE; } /** * failover_slave_unregister - Unregister a slave netdev * * @slave_dev: slave netdev that is being unregistered * * Unregisters a slave device from a failover instance. */ int failover_slave_unregister(struct net_device *slave_dev) { struct net_device *failover_dev; struct failover_ops *fops; if (!netif_is_failover_slave(slave_dev)) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (fops && fops->slave_pre_unregister && fops->slave_pre_unregister(slave_dev, failover_dev)) goto done; netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) return NOTIFY_OK; done: return NOTIFY_DONE; } EXPORT_SYMBOL_GPL(failover_slave_unregister); static int failover_slave_link_change(struct net_device *slave_dev) { struct net_device *failover_dev; struct failover_ops *fops; if (!netif_is_failover_slave(slave_dev)) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (!netif_running(failover_dev)) goto done; if (fops && fops->slave_link_change && !fops->slave_link_change(slave_dev, failover_dev)) return NOTIFY_OK; done: return NOTIFY_DONE; } static int failover_slave_name_change(struct net_device *slave_dev) { struct net_device *failover_dev; struct failover_ops *fops; if (!netif_is_failover_slave(slave_dev)) goto done; ASSERT_RTNL(); failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); if (!failover_dev) goto done; if (!netif_running(failover_dev)) goto done; if (fops && fops->slave_name_change && !fops->slave_name_change(slave_dev, failover_dev)) return NOTIFY_OK; done: return NOTIFY_DONE; } static int failover_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); /* Skip parent events */ if (netif_is_failover(event_dev)) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: return failover_slave_register(event_dev); case NETDEV_UNREGISTER: return failover_slave_unregister(event_dev); case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: return failover_slave_link_change(event_dev); case NETDEV_CHANGENAME: return failover_slave_name_change(event_dev); default: return NOTIFY_DONE; } } static struct notifier_block failover_notifier = { .notifier_call = failover_event, }; static void failover_existing_slave_register(struct net_device *failover_dev) { struct net *net = dev_net(failover_dev); struct net_device *dev; rtnl_lock(); for_each_netdev(net, dev) { if (netif_is_failover(dev)) continue; if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) failover_slave_register(dev); } rtnl_unlock(); } /** * failover_register - Register a failover instance * * @dev: failover netdev * @ops: failover ops * * Allocate and register a failover instance for a failover netdev. ops * provides handlers for slave device register/unregister/link change/ * name change events. * * Return: pointer to failover instance */ struct failover *failover_register(struct net_device *dev, struct failover_ops *ops) { struct failover *failover; if (dev->type != ARPHRD_ETHER) return ERR_PTR(-EINVAL); failover = kzalloc(sizeof(*failover), GFP_KERNEL); if (!failover) return ERR_PTR(-ENOMEM); rcu_assign_pointer(failover->ops, ops); netdev_hold(dev, &failover->dev_tracker, GFP_KERNEL); dev->priv_flags |= IFF_FAILOVER; rcu_assign_pointer(failover->failover_dev, dev); spin_lock(&failover_lock); list_add_tail(&failover->list, &failover_list); spin_unlock(&failover_lock); netdev_info(dev, "failover master:%s registered\n", dev->name); failover_existing_slave_register(dev); return failover; } EXPORT_SYMBOL_GPL(failover_register); /** * failover_unregister - Unregister a failover instance * * @failover: pointer to failover instance * * Unregisters and frees a failover instance. */ void failover_unregister(struct failover *failover) { struct net_device *failover_dev; failover_dev = rcu_dereference(failover->failover_dev); netdev_info(failover_dev, "failover master:%s unregistered\n", failover_dev->name); failover_dev->priv_flags &= ~IFF_FAILOVER; netdev_put(failover_dev, &failover->dev_tracker); spin_lock(&failover_lock); list_del(&failover->list); spin_unlock(&failover_lock); kfree(failover); } EXPORT_SYMBOL_GPL(failover_unregister); static __init int failover_init(void) { register_netdevice_notifier(&failover_notifier); return 0; } module_init(failover_init); static __exit void failover_exit(void) { unregister_netdevice_notifier(&failover_notifier); } module_exit(failover_exit); MODULE_DESCRIPTION("Generic failover infrastructure/interface"); MODULE_LICENSE("GPL v2"); |
| 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 /* * Page Size Migration * * This file contains the core logic of mitigations to ensure * app compatibility during the transition from 4kB to 16kB * page size in Android. * * Copyright (c) 2024, Google LLC. * Author: Kalesh Singh <kaleshsingh@goole.com> */ #include <linux/pgsize_migration.h> #include <linux/init.h> #include <linux/jump_label.h> #include <linux/kobject.h> #include <linux/kstrtox.h> #include <linux/sched/task_stack.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/sysfs.h> typedef void (*show_pad_maps_fn) (struct seq_file *m, struct vm_area_struct *vma); typedef int (*show_pad_smaps_fn) (struct seq_file *m, void *v); #ifdef CONFIG_64BIT #if PAGE_SIZE == SZ_4K DEFINE_STATIC_KEY_TRUE(pgsize_migration_enabled); #define is_pgsize_migration_enabled() (static_branch_likely(&pgsize_migration_enabled)) #else /* PAGE_SIZE != SZ_4K */ DEFINE_STATIC_KEY_FALSE(pgsize_migration_enabled); #define is_pgsize_migration_enabled() (static_branch_unlikely(&pgsize_migration_enabled)) #endif /* PAGE_SIZE == SZ_4K */ static ssize_t show_pgsize_migration_enabled(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { if (is_pgsize_migration_enabled()) return sprintf(buf, "%d\n", 1); else return sprintf(buf, "%d\n", 0); } static ssize_t store_pgsize_migration_enabled(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t n) { unsigned long val; /* Migration is only applicable to 4kB kernels */ if (PAGE_SIZE != SZ_4K) return n; if (kstrtoul(buf, 10, &val)) return -EINVAL; if (val > 1) return -EINVAL; if (val == 1) static_branch_enable(&pgsize_migration_enabled); else if (val == 0) static_branch_disable(&pgsize_migration_enabled); return n; } static struct kobj_attribute pgsize_migration_enabled_attr = __ATTR( enabled, 0644, show_pgsize_migration_enabled, store_pgsize_migration_enabled ); static struct attribute *pgsize_migration_attrs[] = { &pgsize_migration_enabled_attr.attr, NULL }; static struct attribute_group pgsize_migration_attr_group = { .name = "pgsize_migration", .attrs = pgsize_migration_attrs, }; /** * What: /sys/kernel/mm/pgsize_migration/enabled * Date: April 2024 * KernelVersion: v5.4+ (GKI kernels) * Contact: Kalesh Singh <kaleshsingh@google.com> * Description: /sys/kernel/mm/pgsize_migration/enabled * allows for userspace to turn on or off page size * migration mitigations necessary for app compatibility * during Android's transition from 4kB to 16kB page size. * Such mitigations include preserving /proc/<pid>/[s]maps * output as if there was no segment extension by the * dynamic loader; and preventing fault around in the padding * sections of ELF LOAD segment mappings. * Users: Bionic's dynamic linker */ static int __init init_pgsize_migration(void) { if (sysfs_create_group(mm_kobj, &pgsize_migration_attr_group)) pr_err("pgsize_migration: failed to create sysfs group\n"); return 0; }; late_initcall(init_pgsize_migration); #if PAGE_SIZE == SZ_4K void vma_set_pad_pages(struct vm_area_struct *vma, unsigned long nr_pages) { if (!is_pgsize_migration_enabled()) return; /* * Usually to modify vm_flags we need to take exclusive mmap_lock but here * only have the lock in read mode, to avoid all DONTNEED/DONTNEED_LOCKED * calls needing the write lock. * * A race to the flags update can only happen with another MADV_DONTNEED on * the same process and same range (VMA). * * In practice, this specific scenario is not possible because the action that * could cause it is usually performed at most once per VMA and only by the * dynamic linker. * * Forego protection for this case, to avoid penalties in the common cases. */ __vm_flags_mod(vma, 0, VM_PAD_MASK); __vm_flags_mod(vma, nr_pages << VM_PAD_SHIFT, 0); } unsigned long vma_pad_pages(struct vm_area_struct *vma) { if (!is_pgsize_migration_enabled()) return 0; return vma->vm_flags >> VM_PAD_SHIFT; } static __always_inline bool str_has_suffix(const char *str, const char *suffix) { size_t str_len = strlen(str); size_t suffix_len = strlen(suffix); if (str_len < suffix_len) return false; return !strncmp(str + str_len - suffix_len, suffix, suffix_len); } /* * The dynamic linker, or interpreter, operates within the process context * of the binary that necessitated dynamic linking. * * Consequently, process context identifiers; like PID, comm, ...; cannot * be used to differentiate whether the execution context belongs to the * dynamic linker or not. * * linker_ctx() deduces whether execution is currently in the dynamic linker's * context by correlating the current userspace instruction pointer with the * VMAs of the current task. * * Returns true if in linker context, otherwise false. * * Caller must hold mmap lock in read mode. */ static inline bool linker_ctx(void) { struct pt_regs *regs = task_pt_regs(current); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct file *file; if (!regs) return false; vma = find_vma(mm, instruction_pointer(regs)); /* Current execution context, the VMA must be present */ BUG_ON(!vma); file = vma->vm_file; if (!file) return false; if ((vma->vm_flags & VM_EXEC)) { char buf[64]; const int bufsize = sizeof(buf); char *path; memset(buf, 0, bufsize); path = d_path(&file->f_path, buf, bufsize); /* * Depending on interpreter requested, valid paths could be any of: * 1. /system/bin/bootstrap/linker64 * 2. /system/bin/linker64 * 3. /apex/com.android.runtime/bin/linker64 * * Check the base name (linker64). */ if (!strcmp(kbasename(path), "linker64")) return true; } return false; } /* * Saves the number of padding pages for an ELF segment mapping * in vm_flags. * * The number of padding pages is deduced from the madvise DONTNEED range [start, end) * if the following conditions are met: * 1) The range is enclosed by a single VMA * 2) The range ends at the end address of the VMA * 3) The range starts at an address greater than the start address of the VMA * 4) The number of the pages in the range does not exceed VM_TOTAL_PAD_PAGES. * 5) The VMA is a file backed VMA. * 6) The file backing the VMA is a shared library (*.so) * 7) The madvise was requested by bionic's dynamic linker. */ void madvise_vma_pad_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { unsigned long nr_pad_pages; if (!is_pgsize_migration_enabled()) return; /* * If the madvise range is it at the end of the file save the number of * pages in vm_flags (only need 4 bits are needed for up to 64kB aligned ELFs). */ if (start <= vma->vm_start || end != vma->vm_end) return; nr_pad_pages = (end - start) >> PAGE_SHIFT; if (!nr_pad_pages || nr_pad_pages > VM_TOTAL_PAD_PAGES) return; /* Only handle this for file backed VMAs */ if (!vma->vm_file) return; /* Limit this to only shared libraries (*.so) */ if (!str_has_suffix(vma->vm_file->f_path.dentry->d_name.name, ".so")) return; /* Only bionic's dynamic linker needs to hint padding pages. */ if (!linker_ctx()) return; vma_set_pad_pages(vma, nr_pad_pages); } static const char *pad_vma_name(struct vm_area_struct *vma) { return "[page size compat]"; } static const struct vm_operations_struct pad_vma_ops = { .name = pad_vma_name, }; /* * Returns a new VMA representing the padding in @vma, if no padding * in @vma returns NULL. */ struct vm_area_struct *get_pad_vma(struct vm_area_struct *vma) { struct vm_area_struct *pad; if (!is_pgsize_migration_enabled() || !(vma->vm_flags & VM_PAD_MASK)) return NULL; pad = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL); memcpy(pad, vma, sizeof(struct vm_area_struct)); /* Remove file */ pad->vm_file = NULL; /* Add vm_ops->name */ pad->vm_ops = &pad_vma_ops; /* Adjust the start to begin at the start of the padding section */ pad->vm_start = VMA_PAD_START(pad); /* * The below modifications to vm_flags don't need mmap write lock, * since, pad does not belong to the VMA tree. */ /* Make the pad vma PROT_NONE */ __vm_flags_mod(pad, 0, VM_READ|VM_WRITE|VM_EXEC); /* Remove padding bits */ __vm_flags_mod(pad, 0, VM_PAD_MASK); return pad; } /* * Returns a new VMA exclusing the padding from @vma; if no padding in * @vma returns @vma. */ struct vm_area_struct *get_data_vma(struct vm_area_struct *vma) { struct vm_area_struct *data; if (!is_pgsize_migration_enabled() || !(vma->vm_flags & VM_PAD_MASK)) return vma; data = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL); memcpy(data, vma, sizeof(struct vm_area_struct)); /* Adjust the end to the start of the padding section */ data->vm_end = VMA_PAD_START(data); return data; } /* * Calls the show_pad_vma_fn on the @pad VMA, and frees the copies of @vma * and @pad. */ void show_map_pad_vma(struct vm_area_struct *vma, struct vm_area_struct *pad, struct seq_file *m, void *func, bool smaps) { if (!pad) return; /* * This cannot happen. If @pad vma was allocated the corresponding * @vma should have the VM_PAD_MASK bit(s) set. */ BUG_ON(!(vma->vm_flags & VM_PAD_MASK)); /* * This cannot happen. @pad is a section of the original VMA. * Therefore @vma cannot be null if @pad is not null. */ BUG_ON(!vma); if (smaps) ((show_pad_smaps_fn)func)(m, pad); else ((show_pad_maps_fn)func)(m, pad); kfree(pad); kfree(vma); } /* * When splitting a padding VMA there are a couple of cases to handle. * * Given: * * | DDDDPPPP | * * where: * - D represents 1 page of data; * - P represents 1 page of padding; * - | represents the boundaries (start/end) of the VMA * * * 1) Split exactly at the padding boundary * * | DDDDPPPP | --> | DDDD | PPPP | * * - Remove padding flags from the first VMA. * - The second VMA is all padding * * 2) Split within the padding area * * | DDDDPPPP | --> | DDDDPP | PP | * * - Subtract the length of the second VMA from the first VMA's padding. * - The second VMA is all padding, adjust its padding length (flags) * * 3) Split within the data area * * | DDDDPPPP | --> | DD | DDPPPP | * * - Remove padding flags from the first VMA. * - The second VMA is has the same padding as from before the split. */ void split_pad_vma(struct vm_area_struct *vma, struct vm_area_struct *new, unsigned long addr, int new_below) { unsigned long nr_pad_pages = vma_pad_pages(vma); unsigned long nr_vma2_pages; struct vm_area_struct *first; struct vm_area_struct *second; if (!nr_pad_pages) return; if (new_below) { first = new; second = vma; } else { first = vma; second = new; } nr_vma2_pages = vma_pages(second); if (nr_vma2_pages >= nr_pad_pages) { /* Case 1 & 3*/ vm_flags_clear(first, VM_PAD_MASK); vma_set_pad_pages(second, nr_pad_pages); } else { /* Case 2 */ vma_set_pad_pages(first, nr_pad_pages - nr_vma2_pages); vma_set_pad_pages(second, nr_vma2_pages); } } /* * Sets the correct padding bits / flags for a VMA split. */ unsigned long vma_pad_fixup_flags(struct vm_area_struct *vma, unsigned long newflags) { if (newflags & VM_PAD_MASK) return (newflags & ~VM_PAD_MASK) | (vma->vm_flags & VM_PAD_MASK); else return newflags; } /* * Merging of padding VMAs is uncommon, as padding is only allowed * from the linker context. * * To simplify the semantics, adjacent VMAs with padding are not * allowed to merge. */ bool is_mergable_pad_vma(struct vm_area_struct *vma, unsigned long vm_flags) { /* Padding VMAs cannot be merged with other padding or real VMAs */ return !((vma->vm_flags | vm_flags) & VM_PAD_MASK); } unsigned long vma_data_pages(struct vm_area_struct *vma) { return vma_pages(vma) - vma_pad_pages(vma); } #endif /* PAGE_SIZE == SZ_4K */ #endif /* CONFIG_64BIT */ |
| 1703 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #define TRACE_INCLUDE_PATH trace/hooks #if !defined(_TRACE_HOOK_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HOOK_TIMER_H #include <trace/hooks/vendor_hooks.h> DECLARE_HOOK(android_vh_timer_calc_index, TP_PROTO(unsigned int lvl, unsigned long *expires), TP_ARGS(lvl, expires)); #endif /* _TRACE_HOOK_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMER_H #define _LINUX_TIMER_H #include <linux/list.h> #include <linux/ktime.h> #include <linux/stddef.h> #include <linux/debugobjects.h> #include <linux/stringify.h> #include <linux/android_kabi.h> struct timer_list { /* * All fields that change during normal runtime grouped to the * same cacheline */ struct hlist_node entry; unsigned long expires; void (*function)(struct timer_list *); u32 flags; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting the lockdep_map key * (second argument) here is required, otherwise it could be initialised to * the copy of the lockdep_map later! We use the pointer to and the string * "<file>:<line>" as the key resp. the name of the lockdep_map. */ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(_kn, &_kn), #else #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif /** * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU * eventually wakes up with a subsequent non-deferrable timer. * * @TIMER_IRQSAFE: An irqsafe timer is executed with IRQ disabled and * it's safe to wait for the completion of the running instance from * IRQ handlers, for example, by calling del_timer_sync(). * * Note: The irq disabled callback execution is a special case for * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! * * @TIMER_PINNED: A pinned timer will not be affected by any timer * placement heuristics (like, NOHZ) and will always expire on the CPU * on which the timer was enqueued. * * Note: Because enqueuing of timers can migrate the timer from one * CPU to another, pinned timers are not guaranteed to stay on the * initialy selected CPU. They move to the CPU on which the enqueue * function is invoked via mod_timer() or add_timer(). If the timer * should be placed on a particular CPU, then add_timer_on() has to be * used. */ #define TIMER_CPUMASK 0x0003FFFF #define TIMER_MIGRATING 0x00040000 #define TIMER_BASEMASK (TIMER_CPUMASK | TIMER_MIGRATING) #define TIMER_DEFERRABLE 0x00080000 #define TIMER_PINNED 0x00100000 #define TIMER_IRQSAFE 0x00200000 #define TIMER_INIT_FLAGS (TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) #define TIMER_ARRAYSHIFT 22 #define TIMER_ARRAYMASK 0xFFC00000 #define TIMER_TRACE_FLAGMASK (TIMER_MIGRATING | TIMER_DEFERRABLE | TIMER_PINNED | TIMER_IRQSAFE) #define __TIMER_INITIALIZER(_function, _flags) { \ .entry = { .next = TIMER_ENTRY_STATIC }, \ .function = (_function), \ .flags = (_flags), \ __TIMER_LOCKDEP_MAP_INITIALIZER( \ __FILE__ ":" __stringify(__LINE__)) \ } #define DEFINE_TIMER(_name, _function) \ struct timer_list _name = \ __TIMER_INITIALIZER(_function, 0) /* * LOCKDEP and DEBUG timer interfaces. */ void init_timer_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key); #else static inline void init_timer_on_stack_key(struct timer_list *timer, void (*func)(struct timer_list *), unsigned int flags, const char *name, struct lock_class_key *key) { init_timer_key(timer, func, flags, name, key); } #endif #ifdef CONFIG_LOCKDEP #define __init_timer(_timer, _fn, _flags) \ do { \ static struct lock_class_key __key; \ init_timer_key((_timer), (_fn), (_flags), #_timer, &__key);\ } while (0) #define __init_timer_on_stack(_timer, _fn, _flags) \ do { \ static struct lock_class_key __key; \ init_timer_on_stack_key((_timer), (_fn), (_flags), \ #_timer, &__key); \ } while (0) #else #define __init_timer(_timer, _fn, _flags) \ init_timer_key((_timer), (_fn), (_flags), NULL, NULL) #define __init_timer_on_stack(_timer, _fn, _flags) \ init_timer_on_stack_key((_timer), (_fn), (_flags), NULL, NULL) #endif /** * timer_setup - prepare a timer for first use * @timer: the timer in question * @callback: the function to call when timer expires * @flags: any TIMER_* flags * * Regular timer initialization should use either DEFINE_TIMER() above, * or timer_setup(). For timers on the stack, timer_setup_on_stack() must * be used and must be balanced with a call to destroy_timer_on_stack(). */ #define timer_setup(timer, callback, flags) \ __init_timer((timer), (callback), (flags)) #define timer_setup_on_stack(timer, callback, flags) \ __init_timer_on_stack((timer), (callback), (flags)) #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void destroy_timer_on_stack(struct timer_list *timer); #else static inline void destroy_timer_on_stack(struct timer_list *timer) { } #endif #define from_timer(var, callback_timer, timer_fieldname) \ container_of(callback_timer, typeof(*var), timer_fieldname) /** * timer_pending - is a timer pending? * @timer: the timer in question * * timer_pending will tell whether a given timer is currently pending, * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * * return value: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { return !hlist_unhashed_lockless(&timer->entry); } extern void add_timer_on(struct timer_list *timer, int cpu); extern int del_timer(struct timer_list * timer); extern int mod_timer(struct timer_list *timer, unsigned long expires); extern int mod_timer_pending(struct timer_list *timer, unsigned long expires); extern int timer_reduce(struct timer_list *timer, unsigned long expires); /* * The jiffies value which is added to now, when there is no timer * in the timer wheel: */ #define NEXT_TIMER_MAX_DELTA ((1UL << 30) - 1) extern void add_timer(struct timer_list *timer); extern int try_to_del_timer_sync(struct timer_list *timer); extern int del_timer_sync(struct timer_list *timer); #define del_singleshot_timer_sync(t) del_timer_sync(t) extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); unsigned long round_jiffies_relative(unsigned long j); unsigned long __round_jiffies_up(unsigned long j, int cpu); unsigned long __round_jiffies_up_relative(unsigned long j, int cpu); unsigned long round_jiffies_up(unsigned long j); unsigned long round_jiffies_up_relative(unsigned long j); #ifdef CONFIG_HOTPLUG_CPU int timers_prepare_cpu(unsigned int cpu); int timers_dead_cpu(unsigned int cpu); #else #define timers_prepare_cpu NULL #define timers_dead_cpu NULL #endif #endif |
| 5 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * TCPv6 GSO/GRO support */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> #include <net/gro.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, ip6_gro_compute_pseudo)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } return tcp_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr, &iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6; return tcp_gro_complete(skb); } static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct tcphdr *th; if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL); if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct tcphdr *th = tcp_hdr(skb); /* Set up pseudo header, usually expect stack to have done * this. */ th->check = 0; skb->ip_summed = CHECKSUM_PARTIAL; __tcp_v6_send_check(skb, &ipv6h->saddr, &ipv6h->daddr); } return tcp_gso_segment(skb, features); } static const struct net_offload tcpv6_offload = { .callbacks = { .gso_segment = tcp6_gso_segment, .gro_receive = tcp6_gro_receive, .gro_complete = tcp6_gro_complete, }, }; int __init tcpv6_offload_init(void) { return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); } |
| 903 903 901 902 903 903 903 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ #include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/file.h> #include <linux/bug.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/userfaultfd_k.h> #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/swapops.h> #include <linux/miscdevice.h> int sysctl_unprivileged_userfaultfd __read_mostly; static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; struct list_head list; }; struct userfaultfd_unmap_ctx { struct userfaultfd_ctx *ctx; unsigned long start; unsigned long end; struct list_head list; }; struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; struct userfaultfd_wake_range { unsigned long start; unsigned long len; }; /* internal indication that UFFD_API ioctl was successfully executed */ #define UFFD_FEATURE_INITIALIZED (1u << 31) static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) { return ctx->features & UFFD_FEATURE_INITIALIZED; } static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, vm_flags_t flags) { const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP; vm_flags_reset(vma, flags); /* * For shared mappings, we want to enable writenotify while * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply * recalculate vma->vm_page_prot whenever userfaultfd-wp changes. */ if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed) vma_set_page_prot(vma); } static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; int ret; struct userfaultfd_wait_queue *uwq; unsigned long start, len; uwq = container_of(wq, struct userfaultfd_wait_queue, wq); ret = 0; /* len == 0 means wake all */ start = range->start; len = range->len; if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; WRITE_ONCE(uwq->waken, true); /* * The Program-Order guarantees provided by the scheduler * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); if (ret) { /* * Wake only once, autoremove behavior. * * After the effect of list_del_init is visible to the other * CPUs, the waitqueue may disappear from under us, see the * !list_empty_careful() in handle_userfault(). * * try_to_wake_up() has an implicit smp_mb(), and the * wq->private is read before calling the extern function * "wake_up_state" (which in turns calls try_to_wake_up). */ list_del_init(&wq->entry); } out: return ret; } /** * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { refcount_inc(&ctx->refcount); } /** * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to userfaultfd context. * * The userfaultfd context reference must have been previously acquired either * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget(). */ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } } static inline void msg_init(struct uffd_msg *msg) { BUILD_BUG_ON(sizeof(struct uffd_msg) != 32); /* * Must use memset to zero out the paddings or kernel data is * leaked to userland. */ memset(msg, 0, sizeof(struct uffd_msg)); } static inline struct uffd_msg userfault_msg(unsigned long address, unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? real_address : address; /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. * - Neither of these flags being set indicates a MISSING fault. * * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write * fault. Otherwise, it was a read fault. */ if (flags & FAULT_FLAG_WRITE) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (reason & VM_UFFD_MINOR) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } #ifdef CONFIG_HUGETLB_PAGE /* * Same functionality as userfaultfd_must_wait below with modifications for * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = ctx->mm; pte_t *ptep, pte; bool ret = true; assert_fault_locked(vmf); ptep = huge_pte_offset(mm, vmf->address, vma_mmu_pagesize(vma)); if (!ptep) goto out; ret = false; pte = huge_ptep_get(ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ if (huge_pte_none_mostly(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { return false; /* should never get here */ } #endif /* CONFIG_HUGETLB_PAGE */ /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any * userfault that has already been resolved, if userfaultfd_read and * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different * threads. */ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = ctx->mm; unsigned long address = vmf->address; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; bool ret = true; assert_fault_locked(vmf); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * READ_ONCE must function as a barrier with narrower scope * and it must be equivalent to: * _pmd = *pmd; barrier(); * * This is to deal with the instability (as in * pmd_trans_unstable) of the pmd. */ _pmd = READ_ONCE(*pmd); if (pmd_none(_pmd)) goto out; ret = false; if (!pmd_present(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) ret = true; goto out; } /* * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it * and use the standard pte_offset_map() instead of parsing _pmd. */ pte = pte_offset_map(pmd, address); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ if (pte_none_mostly(*pte)) ret = true; if (!pte_write(*pte) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); out: return ret; } static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) { if (flags & FAULT_FLAG_INTERRUPTIBLE) return TASK_INTERRUPTIBLE; if (flags & FAULT_FLAG_KILLABLE) return TASK_KILLABLE; return TASK_UNINTERRUPTIBLE; } /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = vmf->vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; bool must_wait; unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update. * * We also don't do userfault handling during * coredumping. hugetlbfs has the special * follow_hugetlb_page() to skip missing pages in the * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with * the no_page_table() helper in follow_page_mask(), but the * shmem_vm_ops->fault method is invoked even during * coredumping without mmap_lock and it ends up here. */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; /* * Coredumping runs without mmap_lock so we can only check that * the mmap_lock is held, if PF_DUMPCORE was not set. */ assert_fault_locked(vmf); ctx = vmf->vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; BUG_ON(ctx->mm != mm); /* Any unrecognized flag is a bug. */ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); /* 0 or > 1 flags set is a bug; we expect exactly 1. */ VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY)) goto out; /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_lock. */ if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the * last UFFDIO_COPY, without risking to trigger an * involuntary SIGBUS if the process was starting the * userfaultfd while the userfaultfd was still armed * (but after the last UFFDIO_COPY). If the uffd * wasn't already closed when the userfault reached * this point, that would normally be solved by * userfaultfd_must_wait returning 'false'. * * If we were to return VM_FAULT_SIGBUS here, the non * cooperative manager would be instead forced to * always call UFFDIO_UNREGISTER before it can safely * close the uffd. */ ret = VM_FAULT_NOPAGE; goto out; } /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY * even if FAULT_FLAG_TRIED is set without leading to gup() * -EBUSY failures, if the userfaultfd is to be extended for * VM_UFFD_WP tracking and we intend to arm the userfault * without first stopping userland access to the memory. For * VM_UFFD_MISSING userfaults this is enough for now. */ if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) { /* * Validate the invariant that nowait must allow retry * to be sure not to return SIGBUS erroneously on * nowait invocations. */ BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT); #ifdef CONFIG_DEBUG_VM if (printk_ratelimit()) { printk(KERN_WARNING "FAULT_FLAG_ALLOW_RETRY missing %x\n", vmf->flags); dump_stack(); } #endif goto out; } /* * Handle nowait, not much to do other than tell it to retry * and wait. */ ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; blocking_state = userfaultfd_get_blocking_state(vmf->flags); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq); /* * The smp_mb() after __set_current_state prevents the reads * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vmf->vma)) must_wait = userfaultfd_must_wait(ctx, vmf, reason); else must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason); release_fault_lock(vmf); if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); } __set_current_state(TASK_RUNNING); /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run * list_del_init() to refile across the two lists, the prev * and next pointers will never point to self. list_add also * would never let any of the two pointers to point to * self. So list_empty_careful won't risk to see both pointers * pointing to self at any time during the list refile. The * only case where list_del_init() is called is the full * removal in the wake function and there we don't re-list_add * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ userfaultfd_ctx_put(ctx); out: return ret; } static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { struct userfaultfd_ctx *release_new_ctx; if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->event_wqh, &ewq->wq); for (;;) { set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but * __remove_wait_queue ignores the head * parameter. It would be a problem if it * didn't. */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; release_new_ctx = new; } break; } spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { struct vm_area_struct *vma; struct mm_struct *mm = release_new_ctx->mm; VMA_ITERATOR(vmi, mm, 0); /* the various vma->vm_userfaultfd_ctx still points to it */ mmap_write_lock(mm); for_each_vma(vmi, vma) { if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma_start_write(vma); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); } } mmap_write_unlock(mm); userfaultfd_ctx_put(release_new_ctx); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ out: atomic_dec(&ctx->mmap_changing); VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { ewq->msg.event = 0; wake_up_locked(&ctx->event_wqh); __remove_wait_queue(&ctx->event_wqh, &ewq->wq); } int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) { struct userfaultfd_ctx *ctx = NULL, *octx; struct userfaultfd_fork_ctx *fctx; octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma_start_write(vma); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); return 0; } list_for_each_entry(fctx, fcs, list) if (fctx->orig == octx) { ctx = fctx->new; break; } if (!ctx) { fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); if (!fctx) return -ENOMEM; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) { kfree(fctx); return -ENOMEM; } refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); down_write(&octx->map_changing_lock); atomic_inc(&octx->mmap_changing); up_write(&octx->map_changing_lock); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); } vma->vm_userfaultfd_ctx.ctx = ctx; return 0; } static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } } void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return; if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ vma_start_write(vma); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); } } void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, unsigned long from, unsigned long to, unsigned long len) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; struct userfaultfd_wait_queue ewq; if (!ctx) return; if (to & ~PAGE_MASK) { userfaultfd_ctx_put(ctx); return; } msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMAP; ewq.msg.arg.remap.from = from; ewq.msg.arg.remap.to = to; ewq.msg.arg.remap.len = len; userfaultfd_event_wait_completion(ctx, &ewq); } bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue ewq; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) return true; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); mmap_read_unlock(mm); msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; ewq.msg.arg.remove.start = start; ewq.msg.arg.remove.end = end; userfaultfd_event_wait_completion(ctx, &ewq); return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, unsigned long start, unsigned long end) { struct userfaultfd_unmap_ctx *unmap_ctx; list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && unmap_ctx->end == end) return true; return false; } int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end)) return 0; unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); if (!unmap_ctx) return -ENOMEM; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; list_add_tail(&unmap_ctx->list, unmaps); return 0; } void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { struct userfaultfd_unmap_ctx *ctx, *n; struct userfaultfd_wait_queue ewq; list_for_each_entry_safe(ctx, n, uf, list) { msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_UNMAP; ewq.msg.arg.remove.start = ctx->start; ewq.msg.arg.remove.end = ctx->end; userfaultfd_event_wait_completion(ctx->ctx, &ewq); list_del(&ctx->list); kfree(ctx); } } static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; unsigned long new_flags; MA_STATE(mas, &mm->mm_mt, 0, 0); WRITE_ONCE(ctx->released, true); if (!mmget_not_zero(mm)) goto wakeup; /* * Flush page faults out of all CPUs. NOTE: all page faults * must be retried without returning VM_FAULT_SIGBUS if * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx * changes while handle_userfault released the mmap_lock. So * it's critical that released is set to true (above), before * taking the mmap_lock for writing. */ mmap_write_lock(mm); prev = NULL; mas_for_each(&mas, vma, ULONG_MAX) { cond_resched(); BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ !!(vma->vm_flags & __VM_UFFD_FLAGS)); if (vma->vm_userfaultfd_ctx.ctx != ctx) { prev = vma; continue; } new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { mas_pause(&mas); vma = prev; } else { prev = vma; } vma_start_write(vma); userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } mmap_write_unlock(mm); mmput(mm); wakeup: /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on * the fault_*wqh. */ spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } /* fault_pending_wqh.lock must be hold by the caller */ static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; lockdep_assert_held(&wqh->lock); uwq = NULL; if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } static inline struct userfaultfd_wait_queue *find_userfault( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->fault_pending_wqh); } static inline struct userfaultfd_wait_queue *find_userfault_evt( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->event_wqh); } static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; __poll_t ret; poll_wait(file, &ctx->fd_wqh, wait); if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but * the spin_unlock would allow the waitqueue_active to * pass above the actual list_add inside * add_wait_queue critical section. So use a full * memory barrier to serialize the list_add write of * add_wait_queue() with the waitqueue_active read * below. */ ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) ret = EPOLLIN; return ret; } static const struct file_operations userfaultfd_fops; static int resolve_userfault_fork(struct userfaultfd_ctx *new, struct inode *inode, struct uffd_msg *msg) { int fd; fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; msg->arg.reserved.reserved1 = 0; msg->arg.fork.ufd = fd; return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; /* * Handling fork event requires sleeping operations, so * we drop the event_wqh lock, then do these ops, then * lock it back and wake up the waiter. While the lock is * dropped the ewq may go away so we keep track of it * carefully. */ LIST_HEAD(fork_event); struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock_irq(&ctx->fd_wqh.lock); __add_wait_queue(&ctx->fd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&ctx->fault_pending_wqh.lock); uwq = find_userfault(ctx); if (uwq) { /* * Use a seqcount to repeat the lockless check * in wake_userfault() to avoid missing * wakeups because during the refile both * waitqueue could become empty if this is the * only userfault. */ write_seqcount_begin(&ctx->refile_seq); /* * The fault_pending_wqh.lock prevents the uwq * to disappear from under us. * * Refile this userfault from * fault_pending_wqh to fault_wqh, it's not * pending anymore after we read it. * * Use list_del() by hand (as * userfaultfd_wake_function also uses * list_del_init() by hand) to be sure nobody * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ list_del(&uwq->wq.entry); add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); /* careful to always initialize msg if ret == 0 */ *msg = uwq->msg; spin_unlock(&ctx->fault_pending_wqh.lock); ret = 0; break; } spin_unlock(&ctx->fault_pending_wqh.lock); spin_lock(&ctx->event_wqh.lock); uwq = find_userfault_evt(ctx); if (uwq) { *msg = uwq->msg; if (uwq->msg.event == UFFD_EVENT_FORK) { fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); /* * fork_nctx can be freed as soon as * we drop the lock, unless we take a * reference on it. */ userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } userfaultfd_event_complete(ctx, uwq); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } spin_unlock(&ctx->event_wqh.lock); if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (no_wait) { ret = -EAGAIN; break; } spin_unlock_irq(&ctx->fd_wqh.lock); schedule(); spin_lock_irq(&ctx->fd_wqh.lock); } __remove_wait_queue(&ctx->fd_wqh, &wait); __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can * drop the temporary refcount. */ userfaultfd_ctx_put(fork_nctx); uwq = list_first_entry(&fork_event, typeof(*uwq), wq.entry); /* * If fork_event list wasn't empty and in turn * the event wasn't already released by fork * (the event is allocated on fork kernel * stack), put the event back to its place in * the event_wq. fork_event head will be freed * as soon as we return so the event cannot * stay queued there no matter the current * "ret" value. */ list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); /* * Leave the event in the waitqueue and report * error to userland if we failed to resolve * the userfault fork. */ if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); } else { /* * Here the fork thread aborted and the * refcount from the fork thread on fork_nctx * has already been released. We still hold * the reference we took before releasing the * lock above. If resolve_userfault_fork * failed we've to drop it because the * fork_nctx has to be freed in such case. If * it succeeded we'll hold it because the new * uffd references it. */ if (ret) userfaultfd_ctx_put(fork_nctx); } spin_unlock_irq(&ctx->event_wqh.lock); } return ret; } static ssize_t userfaultfd_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct userfaultfd_ctx *ctx = file->private_data; ssize_t _ret, ret = 0; struct uffd_msg msg; int no_wait = file->f_flags & O_NONBLOCK; struct inode *inode = file_inode(file); if (!userfaultfd_is_initialized(ctx)) return -EINVAL; for (;;) { if (count < sizeof(msg)) return ret ? ret : -EINVAL; _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg))) return ret ? ret : -EFAULT; ret += sizeof(msg); buf += sizeof(msg); count -= sizeof(msg); /* * Allow to read more than one fault at time but only * block if waiting for the very first one. */ no_wait = O_NONBLOCK; } } static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { unsigned seq; bool need_wakeup; /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ smp_mb(); /* * Use waitqueue_active because it's very frequent to * change the address space atomically even if there are no * userfaults yet. So we take the spinlock only when we're * sure we've userfaults to wake. */ do { seq = read_seqcount_begin(&ctx->refile_seq); need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || waitqueue_active(&ctx->fault_wqh); cond_resched(); } while (read_seqcount_retry(&ctx->refile_seq, seq)); if (need_wakeup) __wake_userfault(ctx, range); } static __always_inline int validate_range(struct mm_struct *mm, __u64 start, __u64 len) { __u64 task_size = mm->task_size; if (start & ~PAGE_MASK) return -EINVAL; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; if (start < mmap_min_addr) return -EINVAL; if (start >= task_size) return -EINVAL; if (len > task_size - start) return -EINVAL; return 0; } static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; bool basic_ioctls; unsigned long start, end, vma_end; MA_STATE(mas, &mm->mm_mt, 0, 0); user_uffdio_register = (struct uffdio_register __user *) arg; ret = -EFAULT; if (copy_from_user(&uffdio_register, user_uffdio_register, sizeof(uffdio_register)-sizeof(__u64))) goto out; ret = -EINVAL; if (!uffdio_register.mode) goto out; if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP goto out; #endif vm_flags |= VM_UFFD_WP; } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; #endif vm_flags |= VM_UFFD_MINOR; } ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; start = uffdio_register.range.start; end = start + uffdio_register.range.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); mas_set(&mas, start); vma = mas_find(&mas, ULONG_MAX); if (!vma) goto out_unlock; /* check that there's at least one vma in the range */ ret = -EINVAL; if (vma->vm_start >= end) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; basic_ioctls = false; for (cur = vma; cur; cur = mas_next(&mas, end - 1)) { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; if (!vma_can_userfault(cur, vm_flags)) goto out_unlock; /* * UFFDIO_COPY will fill file holes even without * PROT_WRITE. This check enforces that if this is a * MAP_SHARED, the process has write permission to the backing * file. If VM_MAYWRITE is set it also enforces that on a * MAP_SHARED vma: there is no F_WRITE_SEAL and no further * F_WRITE_SEAL can be taken until the vma is destroyed. */ ret = -EPERM; if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) goto out_unlock; /* * If this vma contains ending address, and huge pages * check alignment. */ if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && end > cur->vm_start) { unsigned long vma_hpagesize = vma_kernel_pagesize(cur); ret = -EINVAL; if (end & (vma_hpagesize - 1)) goto out_unlock; } if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) goto out_unlock; /* * Check that this vma isn't already owned by a * different userfaultfd. We can't allow more than one * userfaultfd to own a single vma simultaneously or we * wouldn't know which one to deliver the userfaults to. */ ret = -EBUSY; if (cur->vm_userfaultfd_ctx.ctx && cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; /* * Note vmas containing huge pages */ if (is_vm_hugetlb_page(cur)) basic_ioctls = true; found = true; } BUG_ON(!found); mas_set(&mas, start); prev = mas_prev(&mas, 0); if (prev != vma) mas_next(&mas, ULONG_MAX); ret = 0; do { cond_resched(); BUG_ON(!vma_can_userfault(vma, vm_flags)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (vma->vm_userfaultfd_ctx.ctx == ctx && (vma->vm_flags & vm_flags) == vm_flags) goto skip; if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), anon_vma_name(vma)); if (prev) { /* vma_merge() invalidated the mas */ mas_pause(&mas); vma = prev; goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; /* split_vma() invalidated the mas */ mas_pause(&mas); } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; /* split_vma() invalidated the mas */ mas_pause(&mas); } next: /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and * the current one has not been updated yet. */ vma_start_write(vma); userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx.ctx = ctx; if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) hugetlb_unshare_all_pmds(vma); skip: prev = vma; start = vma->vm_end; vma = mas_next(&mas, end - 1); } while (vma); out_unlock: mmap_write_unlock(mm); mmput(mm); if (!ret) { __u64 ioctls_out; ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS; /* * Declare the WP ioctl only if the WP mode is * specified and all checks passed with the range */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); /* CONTINUE ioctl is only supported for MINOR ranges. */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: return ret; } static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; unsigned long new_flags; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; MA_STATE(mas, &mm->mm_mt, 0, 0); ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; start = uffdio_unregister.start; end = start + uffdio_unregister.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); mas_set(&mas, start); vma = mas_find(&mas, ULONG_MAX); if (!vma) goto out_unlock; /* check that there's at least one vma in the range */ ret = -EINVAL; if (vma->vm_start >= end) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; ret = -EINVAL; for (cur = vma; cur; cur = mas_next(&mas, end - 1)) { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required * here as not compatible vmas cannot have an * userfaultfd_ctx registered on them, but this * provides for more strict behavior to notice * unregistration errors. */ if (!vma_can_userfault(cur, cur->vm_flags)) goto out_unlock; found = true; } BUG_ON(!found); mas_set(&mas, start); prev = mas_prev(&mas, 0); if (prev != vma) mas_next(&mas, ULONG_MAX); ret = 0; do { cond_resched(); BUG_ON(!vma_can_userfault(vma, vma->vm_flags)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (!vma->vm_userfaultfd_ctx.ctx) goto skip; WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); if (userfaultfd_missing(vma)) { /* * Wake any concurrent pending userfault while * we unregister, so they will not hang * permanently and it avoids userland to call * UFFDIO_WAKE explicitly. */ struct userfaultfd_wake_range range; range.start = start; range.len = vma_end - start; wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } /* Reset ptes for the whole vma range if wr-protected */ if (userfaultfd_wp(vma)) uffd_wp_range(mm, vma, start, vma_end - start, false); new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { vma = prev; mas_pause(&mas); goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; mas_pause(&mas); } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; mas_pause(&mas); } next: /* * In the vma_merge() successful mprotect-like case 8: * the next vma was merged into the current one and * the current one has not been updated yet. */ vma_start_write(vma); userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; skip: prev = vma; start = vma->vm_end; vma = mas_next(&mas, end - 1); } while (vma); out_unlock: mmap_write_unlock(mm); mmput(mm); out: return ret; } /* * userfaultfd_wake may be used in combination with the * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches. */ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_range uffdio_wake; struct userfaultfd_wake_range range; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; range.start = uffdio_wake.start; range.len = uffdio_wake.len; /* * len == 0 means wake all and we don't want to wake all here, * so check it again to be sure. */ VM_BUG_ON(!range.len); wake_userfault(ctx, &range); ret = 0; out: return ret; } static int userfaultfd_copy(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ sizeof(uffdio_copy)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; /* * double check for wraparound just in case. copy_from_user() * will later check uffdio_copy.src + uffdio_copy.len to fit * in the userland range. */ ret = -EINVAL; if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src) goto out; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_atomic(ctx, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, uffdio_copy.mode); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) goto out; BUG_ON(!ret); /* len == 0 would wake all */ range.len = ret; if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { range.start = uffdio_copy.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_zeropage uffdio_zeropage; struct uffdio_zeropage __user *user_uffdio_zeropage; struct userfaultfd_wake_range range; user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_zeropage(ctx, uffdio_zeropage.range.start, uffdio_zeropage.range.len); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { range.start = uffdio_zeropage.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_writeprotect uffdio_wp; struct uffdio_writeprotect __user *user_uffdio_wp; struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; if (copy_from_user(&uffdio_wp, user_uffdio_wp, sizeof(struct uffdio_writeprotect))) return -EFAULT; ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | UFFDIO_WRITEPROTECT_MODE_WP)) return -EINVAL; mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; if (mode_wp && mode_dontwake) return -EINVAL; if (mmget_not_zero(ctx->mm)) { ret = mwriteprotect_range(ctx, uffdio_wp.range.start, uffdio_wp.range.len, mode_wp); mmput(ctx->mm); } else { return -ESRCH; } if (ret) return ret; if (!mode_wp && !mode_dontwake) { range.start = uffdio_wp.range.start; range.len = uffdio_wp.range.len; wake_userfault(ctx, &range); } return ret; } static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, /* don't copy the output fields */ sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; ret = -EINVAL; /* double check for wraparound just in case. */ if (uffdio_continue.range.start + uffdio_continue.range.len <= uffdio_continue.range.start) { goto out; } if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_continue(ctx, uffdio_continue.range.start, uffdio_continue.range.len); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { range.start = uffdio_continue.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; out: return ret; } static inline unsigned int uffd_ctx_features(__u64 user_features) { /* * For the current set of features the bits just coincide. Set * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } static int userfaultfd_move(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_move uffdio_move; struct uffdio_move __user *user_uffdio_move; struct userfaultfd_wake_range range; struct mm_struct *mm = ctx->mm; user_uffdio_move = (struct uffdio_move __user *) arg; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */ sizeof(uffdio_move)-sizeof(__s64))) return -EFAULT; /* Do not allow cross-mm moves. */ if (mm != current->mm) return -EINVAL; ret = validate_range(mm, uffdio_move.dst, uffdio_move.len); if (ret) return ret; ret = validate_range(mm, uffdio_move.src, uffdio_move.len); if (ret) return ret; if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES| UFFDIO_MOVE_MODE_DONTWAKE)) return -EINVAL; if (mmget_not_zero(mm)) { ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src, uffdio_move.len, uffdio_move.mode); mmput(mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_move->move))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON(!ret); range.len = ret; if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) { range.start = uffdio_move.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_move.len ? 0 : -EAGAIN; out: return ret; } /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API * version or -EINVAL if unknown. */ static int userfaultfd_api(struct userfaultfd_ctx *ctx, unsigned long arg) { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; unsigned int ctx_features; int ret; __u64 features; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; ret = -EINVAL; if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &= ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif #ifndef CONFIG_PTE_MARKER_UFFD_WP uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; #endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; /* only enable the requested features for this uffd context */ ctx_features = uffd_ctx_features(features); ret = -EINVAL; if (cmpxchg(&ctx->features, 0, ctx_features) != 0) goto err_out; ret = 0; out: return ret; err_out: memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) ret = -EFAULT; goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { case UFFDIO_API: ret = userfaultfd_api(ctx, arg); break; case UFFDIO_REGISTER: ret = userfaultfd_register(ctx, arg); break; case UFFDIO_UNREGISTER: ret = userfaultfd_unregister(ctx, arg); break; case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; case UFFDIO_COPY: ret = userfaultfd_copy(ctx, arg); break; case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; case UFFDIO_MOVE: ret = userfaultfd_move(ctx, arg); break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; case UFFDIO_CONTINUE: ret = userfaultfd_continue(ctx, arg); break; } return ret; } #ifdef CONFIG_PROC_FS static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; } list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown * separated by a space. Like this: * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif static const struct file_operations userfaultfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = userfaultfd_show_fdinfo, #endif .release = userfaultfd_release, .poll = userfaultfd_poll, .read = userfaultfd_read, .unlocked_ioctl = userfaultfd_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static void init_once_userfaultfd_ctx(void *mem) { struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem; init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } static int new_userfaultfd(int flags) { struct userfaultfd_ctx *ctx; int fd; BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK); if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) return -ENOMEM; refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; /* prevent the mm struct to be freed */ mmgrab(ctx->mm); fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (fd < 0) { mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } return fd; } static inline bool userfaultfd_syscall_allowed(int flags) { /* Userspace-only page faults are always allowed */ if (flags & UFFD_USER_MODE_ONLY) return true; /* * The user is requesting a userfaultfd which can handle kernel faults. * Privileged users are always allowed to do this. */ if (capable(CAP_SYS_PTRACE)) return true; /* Otherwise, access to kernel fault handling is sysctl controlled. */ return sysctl_unprivileged_userfaultfd; } SYSCALL_DEFINE1(userfaultfd, int, flags) { if (!userfaultfd_syscall_allowed(flags)) return -EPERM; return new_userfaultfd(flags); } static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags) { if (cmd != USERFAULTFD_IOC_NEW) return -EINVAL; return new_userfaultfd(flags); } static const struct file_operations userfaultfd_dev_fops = { .unlocked_ioctl = userfaultfd_dev_ioctl, .compat_ioctl = userfaultfd_dev_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice userfaultfd_misc = { .minor = MISC_DYNAMIC_MINOR, .name = "userfaultfd", .fops = &userfaultfd_dev_fops }; static int __init userfaultfd_init(void) { int ret; ret = misc_register(&userfaultfd_misc); if (ret) return ret; userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); return 0; } __initcall(userfaultfd_init); |
| 1 1 6 1 4 1 1 6 3 1 1 1 1 1 1 1 5 1 2 2 3 1 2 288 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/bpf-netns.h> #include <linux/filter.h> #include <net/net_namespace.h> /* * Functions to manage BPF programs attached to netns */ struct bpf_netns_link { struct bpf_link link; enum bpf_attach_type type; enum netns_bpf_attach_type netns_type; /* We don't hold a ref to net in order to auto-detach the link * when netns is going away. Instead we rely on pernet * pre_exit callback to clear this pointer. Must be accessed * with netns_bpf_mutex held. */ struct net *net; struct list_head node; /* node in list of links attached to net */ }; /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type) { switch (type) { #ifdef CONFIG_INET case NETNS_BPF_SK_LOOKUP: static_branch_dec(&bpf_sk_lookup_enabled); break; #endif default: break; } } static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type) { switch (type) { #ifdef CONFIG_INET case NETNS_BPF_SK_LOOKUP: static_branch_inc(&bpf_sk_lookup_enabled); break; #endif default: break; } } /* Must be called with netns_bpf_mutex held. */ static void netns_bpf_run_array_detach(struct net *net, enum netns_bpf_attach_type type) { struct bpf_prog_array *run_array; run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL, lockdep_is_held(&netns_bpf_mutex)); bpf_prog_array_free(run_array); } static int link_index(struct net *net, enum netns_bpf_attach_type type, struct bpf_netns_link *link) { struct bpf_netns_link *pos; int i = 0; list_for_each_entry(pos, &net->bpf.links[type], node) { if (pos == link) return i; i++; } return -ENOENT; } static int link_count(struct net *net, enum netns_bpf_attach_type type) { struct list_head *pos; int i = 0; list_for_each(pos, &net->bpf.links[type]) i++; return i; } static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type, struct bpf_prog_array *prog_array) { struct bpf_netns_link *pos; unsigned int i = 0; list_for_each_entry(pos, &net->bpf.links[type], node) { prog_array->items[i].prog = pos->link.prog; i++; } } static void bpf_netns_link_release(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *old_array, *new_array; struct net *net; int cnt, idx; mutex_lock(&netns_bpf_mutex); /* We can race with cleanup_net, but if we see a non-NULL * struct net pointer, pre_exit has not run yet and wait for * netns_bpf_mutex. */ net = net_link->net; if (!net) goto out_unlock; /* Mark attach point as unused */ netns_bpf_attach_type_unneed(type); /* Remember link position in case of safe delete */ idx = link_index(net, type, net_link); list_del(&net_link->node); cnt = link_count(net, type); if (!cnt) { netns_bpf_run_array_detach(net, type); goto out_unlock; } old_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL); if (!new_array) { WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx)); goto out_unlock; } fill_prog_array(net, type, new_array); rcu_assign_pointer(net->bpf.run_array[type], new_array); bpf_prog_array_free(old_array); out_unlock: net_link->net = NULL; mutex_unlock(&netns_bpf_mutex); } static int bpf_netns_link_detach(struct bpf_link *link) { bpf_netns_link_release(link); return 0; } static void bpf_netns_link_dealloc(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); kfree(net_link); } static int bpf_netns_link_update_prog(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *run_array; struct net *net; int idx, ret; if (old_prog && old_prog != link->prog) return -EPERM; if (new_prog->type != link->prog->type) return -EINVAL; mutex_lock(&netns_bpf_mutex); net = net_link->net; if (!net || !check_net(net)) { /* Link auto-detached or netns dying */ ret = -ENOLINK; goto out_unlock; } run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); idx = link_index(net, type, net_link); ret = bpf_prog_array_update_at(run_array, idx, new_prog); if (ret) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; } static int bpf_netns_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info) { const struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); unsigned int inum = 0; struct net *net; mutex_lock(&netns_bpf_mutex); net = net_link->net; if (net && check_net(net)) inum = net->ns.inum; mutex_unlock(&netns_bpf_mutex); info->netns.netns_ino = inum; info->netns.attach_type = net_link->type; return 0; } static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_link_info info = {}; bpf_netns_link_fill_info(link, &info); seq_printf(seq, "netns_ino:\t%u\n" "attach_type:\t%u\n", info.netns.netns_ino, info.netns.attach_type); } static const struct bpf_link_ops bpf_netns_link_ops = { .release = bpf_netns_link_release, .dealloc = bpf_netns_link_dealloc, .detach = bpf_netns_link_detach, .update_prog = bpf_netns_link_update_prog, .fill_link_info = bpf_netns_link_fill_info, .show_fdinfo = bpf_netns_link_show_fdinfo, }; /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct net *net, enum netns_bpf_attach_type type) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); struct bpf_prog_array *run_array; u32 prog_cnt = 0, flags = 0; run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); if (run_array) prog_cnt = bpf_prog_array_length(run_array); if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) return -EFAULT; if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) return 0; return bpf_prog_array_copy_to_user(run_array, prog_ids, attr->query.prog_cnt); } int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { enum netns_bpf_attach_type type; struct net *net; int ret; if (attr->query.query_flags) return -EINVAL; type = to_netns_bpf_attach_type(attr->query.attach_type); if (type < 0) return -EINVAL; net = get_net_ns_by_fd(attr->query.target_fd); if (IS_ERR(net)) return PTR_ERR(net); mutex_lock(&netns_bpf_mutex); ret = __netns_bpf_prog_query(attr, uattr, net, type); mutex_unlock(&netns_bpf_mutex); put_net(net); return ret; } int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_prog_array *run_array; enum netns_bpf_attach_type type; struct bpf_prog *attached; struct net *net; int ret; if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; net = current->nsproxy->net_ns; mutex_lock(&netns_bpf_mutex); /* Attaching prog directly is not compatible with links */ if (!list_empty(&net->bpf.links[type])) { ret = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: ret = flow_dissector_bpf_prog_attach_check(net, prog); break; default: ret = -EINVAL; break; } if (ret) goto out_unlock; attached = net->bpf.progs[type]; if (attached == prog) { /* The same program cannot be attached twice */ ret = -EINVAL; goto out_unlock; } run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); if (run_array) { WRITE_ONCE(run_array->items[0].prog, prog); } else { run_array = bpf_prog_array_alloc(1, GFP_KERNEL); if (!run_array) { ret = -ENOMEM; goto out_unlock; } run_array->items[0].prog = prog; rcu_assign_pointer(net->bpf.run_array[type], run_array); } net->bpf.progs[type] = prog; if (attached) bpf_prog_put(attached); out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; } /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_detach(struct net *net, enum netns_bpf_attach_type type, struct bpf_prog *old) { struct bpf_prog *attached; /* Progs attached via links cannot be detached */ if (!list_empty(&net->bpf.links[type])) return -EINVAL; attached = net->bpf.progs[type]; if (!attached || attached != old) return -ENOENT; netns_bpf_run_array_detach(net, type); net->bpf.progs[type] = NULL; bpf_prog_put(attached); return 0; } int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { enum netns_bpf_attach_type type; struct bpf_prog *prog; int ret; if (attr->target_fd) return -EINVAL; type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); mutex_lock(&netns_bpf_mutex); ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); mutex_unlock(&netns_bpf_mutex); bpf_prog_put(prog); return ret; } static int netns_bpf_max_progs(enum netns_bpf_attach_type type) { switch (type) { case NETNS_BPF_FLOW_DISSECTOR: return 1; case NETNS_BPF_SK_LOOKUP: return 64; default: return 0; } } static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, enum netns_bpf_attach_type type) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); struct bpf_prog_array *run_array; int cnt, err; mutex_lock(&netns_bpf_mutex); cnt = link_count(net, type); if (cnt >= netns_bpf_max_progs(type)) { err = -E2BIG; goto out_unlock; } /* Links are not compatible with attaching prog directly */ if (net->bpf.progs[type]) { err = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: err = flow_dissector_bpf_prog_attach_check(net, link->prog); break; case NETNS_BPF_SK_LOOKUP: err = 0; /* nothing to check */ break; default: err = -EINVAL; break; } if (err) goto out_unlock; run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL); if (!run_array) { err = -ENOMEM; goto out_unlock; } list_add_tail(&net_link->node, &net->bpf.links[type]); fill_prog_array(net, type, run_array); run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array, lockdep_is_held(&netns_bpf_mutex)); bpf_prog_array_free(run_array); /* Mark attach point as used */ netns_bpf_attach_type_need(type); out_unlock: mutex_unlock(&netns_bpf_mutex); return err; } int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { enum netns_bpf_attach_type netns_type; struct bpf_link_primer link_primer; struct bpf_netns_link *net_link; enum bpf_attach_type type; struct net *net; int err; if (attr->link_create.flags) return -EINVAL; type = attr->link_create.attach_type; netns_type = to_netns_bpf_attach_type(type); if (netns_type < 0) return -EINVAL; net = get_net_ns_by_fd(attr->link_create.target_fd); if (IS_ERR(net)) return PTR_ERR(net); net_link = kzalloc(sizeof(*net_link), GFP_USER); if (!net_link) { err = -ENOMEM; goto out_put_net; } bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS, &bpf_netns_link_ops, prog); net_link->net = net; net_link->type = type; net_link->netns_type = netns_type; err = bpf_link_prime(&net_link->link, &link_primer); if (err) { kfree(net_link); goto out_put_net; } err = netns_bpf_link_attach(net, &net_link->link, netns_type); if (err) { bpf_link_cleanup(&link_primer); goto out_put_net; } put_net(net); return bpf_link_settle(&link_primer); out_put_net: put_net(net); return err; } static int __net_init netns_bpf_pernet_init(struct net *net) { int type; for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) INIT_LIST_HEAD(&net->bpf.links[type]); return 0; } static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { enum netns_bpf_attach_type type; struct bpf_netns_link *net_link; mutex_lock(&netns_bpf_mutex); for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { netns_bpf_run_array_detach(net, type); list_for_each_entry(net_link, &net->bpf.links[type], node) { net_link->net = NULL; /* auto-detach link */ netns_bpf_attach_type_unneed(type); } if (net->bpf.progs[type]) bpf_prog_put(net->bpf.progs[type]); } mutex_unlock(&netns_bpf_mutex); } static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { .init = netns_bpf_pernet_init, .pre_exit = netns_bpf_pernet_pre_exit, }; static int __init netns_bpf_init(void) { return register_pernet_subsys(&netns_bpf_pernet_ops); } subsys_initcall(netns_bpf_init); |
| 142 142 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 | // 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 = from_timer(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) { del_timer_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 = xchg((__force struct net_rate_estimator **)rate_est, NULL); if (est) { del_timer_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); |
| 3414 3414 147 109 46 74 74 74 74 74 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/task_work.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <linux/kcov.h> #include <linux/kmsan.h> #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/kprobes.h> #include <linux/rethook.h> #include <linux/sysfs.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/mmu_context.h> #include <trace/hooks/mm.h> #include <trace/hooks/dtask.h> /* * The default value should be high enough to not crash a system that randomly * crashes its kernel from time to time, but low enough to at least not permit * overflowing 32-bit refcounts or the ldsem writer count. */ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL static struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, .maxlen = sizeof(oops_limit), .mode = 0644, .proc_handler = proc_douintvec, }, { } }; static __init int kernel_exit_sysctls_init(void) { register_sysctl_init("kernel", kern_exit_table); return 0; } late_initcall(kernel_exit_sysctls_init); #endif static atomic_t oops_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); } static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); static __init int kernel_exit_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); return 0; } late_initcall(kernel_exit_sysfs_init); #endif static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_TGID); detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk); #endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exec_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); kprobe_flush_task(tsk); rethook_flush_task(tsk); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void put_task_struct_rcu_user(struct task_struct *task) { if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct); } void __weak release_thread(struct task_struct *dead_task) { } void release_task(struct task_struct *p) { struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); rcu_read_unlock(); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); seccomp_filter_release(p); proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat; } int rcuwait_wake_up(struct rcuwait *w) { int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } static void coredump_task_exit(struct task_struct *tsk) { struct core_state *core_state; /* * Serialize with any possible pending coredump. * We must hold siglock around checking core_state * and setting PF_POSTCOREDUMP. The core-inducing thread * will increment ->nr_threads for each thread in the * group without PF_POSTCOREDUMP set. */ spin_lock_irq(&tsk->sighand->siglock); tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); if (core_state) { struct core_thread self; self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE|TASK_FREEZABLE); if (!self.task) /* see coredump_finish() */ break; schedule(); } __set_current_state(TASK_RUNNING); } } #ifdef CONFIG_MEMCG /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(c, &p->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search in the siblings */ list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); /* * Delay read_unlock() till we have the task_lock() * to ensure that c does not slip away underneath us */ read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); put_task_struct(c); goto retry; } WRITE_ONCE(mm->owner, c); lru_gen_migrate_mm(mm); task_unlock(c); put_task_struct(c); } #endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(void) { struct mm_struct *mm = current->mm; exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); mmap_read_lock(mm); mmgrab(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); /* * When a thread stops operating on an address space, the loop * in membarrier_private_expedited() may not observe that * tsk->mm, and the loop in membarrier_global_expedited() may * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED * rq->membarrier_state, so those would not issue an IPI. * Membarrier requires a memory barrier after accessing * user-space memory, before clearing tsk->mm or the * rq->membarrier_state. */ smp_mb__after_spinlock(); local_irq_disable(); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); local_irq_enable(); task_unlock(current); mmap_read_unlock(mm); mm_update_next_owner(mm); trace_android_vh_exit_mm(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) { struct task_struct *t; for_each_thread(p, t) { if (!(t->flags & PF_EXITING)) return t; } return NULL; } static struct task_struct *find_child_reaper(struct task_struct *father, struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; struct task_struct *p, *n; if (likely(reaper != father)) return reaper; reaper = find_alive_thread(father); if (reaper) { pid_ns->child_reaper = reaper; return reaper; } write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); return father; } /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father, struct task_struct *child_reaper) { struct task_struct *thread, *reaper; thread = find_alive_thread(father); if (thread) return thread; if (father->signal->has_child_subreaper) { unsigned int ns_level = task_pid(father)->level; /* * Find the first ->is_child_subreaper ancestor in our pid_ns. * We can't check reaper != child_reaper to ensure we do not * cross the namespaces, the exiting parent could be injected * by setns() + fork(). * We check pid->level, this is slightly more efficient than * task_active_pid_ns(reaper) != task_active_pid_ns(father). */ for (reaper = father->real_parent; task_pid(reaper)->level == ns_level; reaper = reaper->real_parent) { if (reaper == &init_task) break; if (!reaper->signal->is_child_subreaper) continue; thread = find_alive_thread(reaper); if (thread) return thread; } } return child_reaper; } /* * Any that need to be release_task'd are put on the @dead list. */ static void reparent_leader(struct task_struct *father, struct task_struct *p, struct list_head *dead) { if (unlikely(p->exit_state == EXIT_DEAD)) return; /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_add(&p->ptrace_entry, dead); } } kill_orphaned_pgrp(p, father); } /* * This does two things: * * A. Make init inherit all the child processes * B. Check to see if any process groups have become orphaned * as a result of our exiting, and if they have any stopped * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void forget_original_parent(struct task_struct *father, struct list_head *dead) { struct task_struct *p, *t, *reaper; if (unlikely(!list_empty(&father->ptraced))) exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { RCU_INIT_POINTER(t->real_parent, reaper); BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) group_send_sig_info(t->pdeath_signal, SEND_SIG_NOINFO, t, PIDTYPE_TGID); } /* * If this is a threaded reparent there is no need to * notify anyone anything has happened. */ if (!same_thread_group(reaper, father)) reparent_leader(father, p, dead); } list_splice_tail_init(&father->children, &reaper->children); } /* * Send signals to all our closest relatives so that they know * to properly mourn us.. */ static void exit_notify(struct task_struct *tsk, int group_dead) { bool autoreap; struct task_struct *p, *n; LIST_HEAD(dead); write_lock_irq(&tasklist_lock); forget_original_parent(tsk, &dead); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && !ptrace_reparented(tsk) ? tsk->exit_signal : SIGCHLD; autoreap = do_notify_parent(tsk, sig); } else if (thread_group_leader(tsk)) { autoreap = thread_group_empty(tsk) && do_notify_parent(tsk, tsk->exit_signal); } else { autoreap = true; } if (autoreap) { tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exec_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } } #ifdef CONFIG_DEBUG_STACK_USAGE static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; unsigned long free; free = stack_not_used(current); if (free >= lowest_to_date) return; spin_lock(&low_water_lock); if (free < lowest_to_date) { pr_info("%s (%d) used greatest stack depth: %lu bytes left\n", current->comm, task_pid_nr(current), free); lowest_to_date = free; } spin_unlock(&low_water_lock); } #else static inline void check_stack_usage(void) {} #endif static void synchronize_group_exit(struct task_struct *tsk, long code) { struct sighand_struct *sighand = tsk->sighand; struct signal_struct *signal = tsk->signal; spin_lock_irq(&sighand->siglock); signal->quick_threads--; if ((signal->quick_threads == 0) && !(signal->flags & SIGNAL_GROUP_EXIT)) { signal->flags = SIGNAL_GROUP_EXIT; signal->group_exit_code = code; signal->group_stop_count = 0; } spin_unlock_irq(&sighand->siglock); } void __noreturn do_exit(long code) { struct task_struct *tsk = current; int group_dead; WARN_ON(irqs_disabled()); synchronize_group_exit(tsk, code); WARN_ON(tsk->plug); profile_task_exit(tsk); kcov_task_exit(tsk); kmsan_task_exit(tsk); coredump_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ trace_android_vh_exit_check(current); /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm); acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { /* * If the last thread of global init has exited, panic * immediately to get a useable coredump. */ if (unlikely(is_global_init(tsk))) panic("Attempted to kill init! exitcode=0x%08x\n", tsk->signal->group_exit_code ?: (int)code); #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); } acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); exit_mm(); if (group_dead) acct_process(); trace_sched_process_exit(tsk); exit_sem(tsk); exit_shm(tsk); exit_files(tsk); exit_fs(tsk); if (group_dead) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); exit_thread(tsk); /* * Flush inherited counters to the parent - before the parent * gets woken up by child-exit notifications. * * because of cgroup mode, must be called before cgroup_exit() */ perf_event_exit_task(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); exit_tasks_rcu_start(); exit_notify(tsk, group_dead); proc_exit_connector(tsk); mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); #endif /* * Make sure we are holding no locks: */ debug_check_no_locks_held(); if (tsk->io_context) exit_io_context(tsk); if (tsk->splice_pipe) free_pipe_info(tsk->splice_pipe); if (tsk->task_frag.page) put_page(tsk->task_frag.page); validate_creds_for_do_exit(tsk); exit_task_stack_account(tsk); check_stack_usage(); preempt_disable(); if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); exit_tasks_rcu_finish(); lockdep_free_task(tsk); do_task_dead(); } void __noreturn make_task_dead(int signr) { /* * Take the task off the cpu after something catastrophic has * happened. * * We can get here from a kernel oops, sometimes with preemption off. * Start by checking for critical errors. * Then fix up important state like USER_DS and preemption. * Then do everything else. */ struct task_struct *tsk = current; unsigned int limit; if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); if (unlikely(irqs_disabled())) { pr_info("note: %s[%d] exited with irqs disabled\n", current->comm, task_pid_nr(current)); local_irq_enable(); } if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), preempt_count()); preempt_count_set(PREEMPT_ENABLED); } /* * Every time the system oopses, if the oops happens while a reference * to an object was held, the reference leaks. * If the oops doesn't also leak memory, repeated oopsing can cause * reference counters to wrap around (if they're not using refcount_t). * This means that repeated oopsing can make unexploitable-looking bugs * exploitable through repeated oopsing. * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ limit = READ_ONCE(oops_limit); if (atomic_inc_return(&oops_count) >= limit && limit) panic("Oopsed too often (kernel.oops_limit is %d)", limit); /* * We're taking recursive faults here in make_task_dead. Safest is to just * leave this task alone and wait for reboot. */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); futex_exit_recursive(tsk); tsk->exit_state = EXIT_DEAD; refcount_inc(&tsk->rcu_users); do_task_dead(); } do_exit(signr); } SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); } /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ void __noreturn do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; if (sig->flags & SIGNAL_GROUP_EXIT) exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; else { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); } do_exit(exit_code); /* NOTREACHED */ } /* * this kills every thread in the thread group. Note that any externally * wait4()-ing process will get the correct exit code - even if this * thread is not the thread group leader. */ SYSCALL_DEFINE1(exit_group, int, error_code) { do_group_exit((error_code & 0xff) << 8); /* NOTREACHED */ return 0; } struct waitid_info { pid_t pid; uid_t uid; int status; int cause; }; struct wait_opts { enum pid_type wo_type; int wo_flags; struct pid *wo_pid; struct waitid_info *wo_info; int wo_stat; struct rusage *wo_rusage; wait_queue_entry_t child_wait; int notask_error; }; static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { return wo->wo_type == PIDTYPE_MAX || task_pid_type(p, wo->wo_type) == wo->wo_pid; } static int eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; /* * Wait for all children (clone and not) if __WALL is set or * if it is traced by us. */ if (ptrace || (wo->wo_flags & __WALL)) return 1; /* * Otherwise, wait for clone children *only* if __WCLONE is set; * otherwise, wait for non-clone children *only*. * * Note: a "clone" child here is one that reports to its parent * using a signal other than SIGCHLD, or a non-leader thread which * we can only see if it is traced by us. */ if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; } /* * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { int state, status; pid_t pid = task_pid_vnr(p); uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); struct waitid_info *infop; if (!likely(wo->wo_flags & WEXITED)) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); goto out_info; } /* * Move the task's state to DEAD/TRACE, only one thread can do this. */ state = (ptrace_reparented(p) && thread_group_leader(p)) ? EXIT_TRACE : EXIT_DEAD; if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; /* * We own this thread, nobody else can reap it. */ read_unlock(&tasklist_lock); sched_annotate_sleep(); /* * Check thread_group_leader() to exclude the traced sub-threads. */ if (state == EXIT_DEAD && thread_group_leader(p)) { struct signal_struct *sig = p->signal; struct signal_struct *psig = current->signal; unsigned long maxrss; u64 tgutime, tgstime; /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group * are in its signal_struct, as are those for the child * processes it has previously reaped. All these * accumulate in the parent's signal_struct c* fields. * * We don't bother to take a lock here to protect these * p->signal fields because the whole thread group is dead * and nobody can change them. * * psig->stats_lock also protects us from our sub-threads * which can reap other children at the same time. Until * we change k_getrusage()-like users to rely on this lock * we have to take ->siglock as well. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); spin_lock_irq(¤t->sighand->siglock); write_seqlock(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += p->maj_flt + sig->maj_flt + sig->cmaj_flt; psig->cnvcsw += p->nvcsw + sig->nvcsw + sig->cnvcsw; psig->cnivcsw += p->nivcsw + sig->nivcsw + sig->cnivcsw; psig->cinblock += task_io_get_inblock(p) + sig->inblock + sig->cinblock; psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; maxrss = max(sig->maxrss, sig->cmaxrss); if (psig->cmaxrss < maxrss) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); write_sequnlock(&psig->stats_lock); spin_unlock_irq(¤t->sighand->siglock); } if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; wo->wo_stat = status; if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); /* If parent wants a zombie, don't release it now */ state = EXIT_ZOMBIE; if (do_notify_parent(p, p->exit_signal)) state = EXIT_DEAD; p->exit_state = state; write_unlock_irq(&tasklist_lock); } if (state == EXIT_DEAD) release_task(p); out_info: infop = wo->wo_info; if (infop) { if ((status & 0x7f) == 0) { infop->cause = CLD_EXITED; infop->status = status >> 8; } else { infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; infop->status = status & 0x7f; } infop->pid = pid; infop->uid = uid; } return pid; } static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) return &p->signal->group_exit_code; } return NULL; } /** * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED * @wo: wait options * @ptrace: is the wait for ptrace * @p: task to wait for * * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. * * CONTEXT: * read_lock(&tasklist_lock), which is released if return value is * non-zero. Also, grabs and releases @p->sighand->siglock. * * RETURNS: * 0 if wait condition didn't exist and search for other wait conditions * should continue. Non-zero return, -errno on failure and @p's pid on * success, implies that tasklist_lock is released and wait condition * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) { struct waitid_info *infop; int exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; if (!task_stopped_code(p, ptrace)) return 0; exit_code = 0; spin_lock_irq(&p->sighand->siglock); p_code = task_stopped_code(p, ptrace); if (unlikely(!p_code)) goto unlock_sig; exit_code = *p_code; if (!exit_code) goto unlock_sig; if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) return 0; /* * Now we are pretty sure this task is interesting. * Make sure it doesn't get reaped out from under us while we * give up the lock and then examine it below. We don't want to * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ get_task_struct(p); pid = task_pid_vnr(p); why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); if (likely(!(wo->wo_flags & WNOWAIT))) wo->wo_stat = (exit_code << 8) | 0x7f; infop = wo->wo_info; if (infop) { infop->cause = why; infop->status = exit_code; infop->pid = pid; infop->uid = uid; } return pid; } /* * Handle do_wait work for one task in a live, non-stopped state. * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { struct waitid_info *infop; pid_t pid; uid_t uid; if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; spin_lock_irq(&p->sighand->siglock); /* Re-check with the lock held. */ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { spin_unlock_irq(&p->sighand->siglock); return 0; } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); infop = wo->wo_info; if (!infop) { wo->wo_stat = 0xffff; } else { infop->cause = CLD_CONTINUED; infop->pid = pid; infop->uid = uid; infop->status = SIGCONT; } return pid; } /* * Consider @p for a wait by @parent. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; * then ->notask_error is 0 if @p is an eligible child, * or still -ECHILD. */ static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { /* * We can race with wait_task_zombie() from another thread. * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) return 0; ret = eligible_child(wo, ptrace, p); if (!ret) return ret; if (unlikely(exit_state == EXIT_TRACE)) { /* * ptrace == 0 means we are the natural parent. In this case * we should clear notask_error, debugger will notify us. */ if (likely(!ptrace)) wo->notask_error = 0; return 0; } if (likely(!ptrace) && unlikely(p->ptrace)) { /* * If it is traced by its real parent's group, just pretend * the caller is ptrace_do_wait() and reap this child if it * is zombie. * * This also hides group stop state from real parent; otherwise * a single stop can be reported twice as group and ptrace stop. * If a ptracer wants to distinguish these two events for its * own children it should create a separate process which takes * the role of real parent. */ if (!ptrace_reparented(p)) ptrace = 1; } /* slay zombie? */ if (exit_state == EXIT_ZOMBIE) { /* we don't reap group leaders with subthreads */ if (!delay_group_leader(p)) { /* * A zombie ptracee is only visible to its ptracer. * Notification and reaping will be cascaded to the * real parent when the ptracer detaches. */ if (unlikely(ptrace) || likely(!p->ptrace)) return wait_task_zombie(wo, p); } /* * Allow access to stopped/continued state via zombie by * falling through. Clearing of notask_error is complex. * * When !@ptrace: * * If WEXITED is set, notask_error should naturally be * cleared. If not, subset of WSTOPPED|WCONTINUED is set, * so, if there are live subthreads, there are events to * wait for. If all subthreads are dead, it's still safe * to clear - this function will be called again in finite * amount time once all the subthreads are released and * will then return without clearing. * * When @ptrace: * * Stopped state is per-task and thus can't change once the * target task dies. Only continued and exited can happen. * Clear notask_error if WCONTINUED | WEXITED. */ if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) wo->notask_error = 0; } else { /* * @p is alive and it's gonna stop, continue or exit, so * there always is something to wait for. */ wo->notask_error = 0; } /* * Wait for stopped. Depending on @ptrace, different stopped state * is used and the two don't interact with each other. */ ret = wait_task_stopped(wo, ptrace, p); if (ret) return ret; /* * Wait for continued. There's only one continued state and the * ptracer can consume it which can confuse the real parent. Don't * use WCONTINUED from ptracer. You don't need or want it. */ return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then * ->notask_error is 0 if there were any eligible children, * or still -ECHILD. */ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->children, sibling) { int ret = wait_consider_task(wo, 0, p); if (ret) return ret; } return 0; } static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { int ret = wait_consider_task(wo, 1, p); if (ret) return ret; } return 0; } static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct task_struct *p = key; if (!eligible_pid(wo, p)) return 0; if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent) return 0; return default_wake_function(wait, mode, sync, key); } void __wake_up_parent(struct task_struct *p, struct task_struct *parent) { __wake_up_sync_key(&parent->signal->wait_chldexit, TASK_INTERRUPTIBLE, p); } static bool is_effectively_child(struct wait_opts *wo, bool ptrace, struct task_struct *target) { struct task_struct *parent = !ptrace ? target->real_parent : target->parent; return current == parent || (!(wo->wo_flags & __WNOTHREAD) && same_thread_group(current, parent)); } /* * Optimization for waiting on PIDTYPE_PID. No need to iterate through child * and tracee lists to find the target task. */ static int do_wait_pid(struct wait_opts *wo) { bool ptrace; struct task_struct *target; int retval; ptrace = false; target = pid_task(wo->wo_pid, PIDTYPE_TGID); if (target && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } ptrace = true; target = pid_task(wo->wo_pid, PIDTYPE_PID); if (target && target->ptrace && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } return 0; } static long do_wait(struct wait_opts *wo) { int retval; trace_sched_process_wait(wo->wo_pid); init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); wo->child_wait.private = current; add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); repeat: /* * If there is nothing that can match our criteria, just get out. * We will clear ->notask_error to zero if we see any child that * might later match our criteria, even if we are not able to reap * it yet. */ wo->notask_error = -ECHILD; if ((wo->wo_type < PIDTYPE_MAX) && (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type))) goto notask; set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); if (wo->wo_type == PIDTYPE_PID) { retval = do_wait_pid(wo); if (retval) goto end; } else { struct task_struct *tsk = current; do { retval = do_wait_thread(wo, tsk); if (retval) goto end; retval = ptrace_do_wait(wo, tsk); if (retval) goto end; if (wo->wo_flags & __WNOTHREAD) break; } while_each_thread(current, tsk); } read_unlock(&tasklist_lock); notask: retval = wo->notask_error; if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; if (!signal_pending(current)) { schedule(); goto repeat; } } end: __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; } static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; unsigned int f_flags = 0; if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; switch (which) { case P_ALL: type = PIDTYPE_MAX; break; case P_PID: type = PIDTYPE_PID; if (upid <= 0) return -EINVAL; pid = find_get_pid(upid); break; case P_PGID: type = PIDTYPE_PGID; if (upid < 0) return -EINVAL; if (upid) pid = find_get_pid(upid); else pid = get_task_pid(current, PIDTYPE_PGID); break; case P_PIDFD: type = PIDTYPE_PID; if (upid < 0) return -EINVAL; pid = pidfd_get_pid(upid, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); break; default: return -EINVAL; } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options; wo.wo_info = infop; wo.wo_rusage = ru; if (f_flags & O_NONBLOCK) wo.wo_flags |= WNOHANG; ret = do_wait(&wo); if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK)) ret = -EAGAIN; put_pid(pid); return ret; } SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { struct rusage r; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } long kernel_wait4(pid_t upid, int __user *stat_addr, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; /* -INT_MIN is not defined */ if (upid == INT_MIN) return -ESRCH; if (upid == -1) type = PIDTYPE_MAX; else if (upid < 0) { type = PIDTYPE_PGID; pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options | WEXITED; wo.wo_info = NULL; wo.wo_stat = 0; wo.wo_rusage = ru; ret = do_wait(&wo); put_pid(pid); if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr)) ret = -EFAULT; return ret; } int kernel_wait(pid_t pid, int *stat) { struct wait_opts wo = { .wo_type = PIDTYPE_PID, .wo_pid = find_get_pid(pid), .wo_flags = WEXITED, }; int ret; ret = do_wait(&wo); if (ret > 0 && wo.wo_stat) *stat = wo.wo_stat; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { struct rusage r; long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } return err; } #ifdef __ARCH_WANT_SYS_WAITPID /* * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) { return kernel_wait4(pid, stat_addr, options, NULL); } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(wait4, compat_pid_t, pid, compat_uint_t __user *, stat_addr, int, options, struct compat_rusage __user *, ru) { struct rusage r; long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && put_compat_rusage(&r, ru)) return -EFAULT; } return err; } COMPAT_SYSCALL_DEFINE5(waitid, int, which, compat_pid_t, pid, struct compat_siginfo __user *, infop, int, options, struct compat_rusage __user *, uru) { struct rusage ru; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (uru) { /* kernel_waitid() overwrites everything in ru */ if (COMPAT_USE_64BIT_TIME) err = copy_to_user(uru, &ru, sizeof(ru)); else err = put_compat_rusage(&ru, uru); if (err) return -EFAULT; } } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } #endif /** * thread_group_exited - check that a thread group has exited * @pid: tgid of thread group to be checked. * * Test if the thread group represented by tgid has exited (all * threads are zombies, dead or completely gone). * * Return: true if the thread group has exited. false otherwise. */ bool thread_group_exited(struct pid *pid) { struct task_struct *task; bool exited; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); exited = !task || (READ_ONCE(task->exit_state) && thread_group_empty(task)); rcu_read_unlock(); return exited; } EXPORT_SYMBOL(thread_group_exited); __weak void abort(void) { BUG(); /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } EXPORT_SYMBOL(abort); |
| 66 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resultion entity * * Authors: * net_random Alan Cox * net_ratelimit Andi Kleen * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/ratelimit.h> #include <linux/socket.h> #include <net/sock.h> #include <net/net_ratelimit.h> #include <net/ipv6.h> #include <asm/byteorder.h> #include <linux/uaccess.h> DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. */ int net_ratelimit(void) { return __ratelimit(&net_ratelimit_state); } EXPORT_SYMBOL(net_ratelimit); /* * Convert an ASCII string to binary IP. * This is outside of net/ipv4/ because various code that uses IP addresses * is otherwise not dependent on the TCP/IP stack. */ __be32 in_aton(const char *str) { unsigned int l; unsigned int val; int i; l = 0; for (i = 0; i < 4; i++) { l <<= 8; if (*str != '\0') { val = 0; while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; } l |= val; if (*str != '\0') str++; } } return htonl(l); } EXPORT_SYMBOL(in_aton); #define IN6PTON_XDIGIT 0x00010000 #define IN6PTON_DIGIT 0x00020000 #define IN6PTON_COLON_MASK 0x00700000 #define IN6PTON_COLON_1 0x00100000 /* single : requested */ #define IN6PTON_COLON_2 0x00200000 /* second : requested */ #define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ #define IN6PTON_DOT 0x00800000 /* . */ #define IN6PTON_DELIM 0x10000000 #define IN6PTON_NULL 0x20000000 /* first/tail */ #define IN6PTON_UNKNOWN 0x40000000 static inline int xdigit2bin(char c, int delim) { int val; if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; val = hex_to_bin(c); if (val >= 0) return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; } /** * in4_pton - convert an IPv4 address from literal to binary representation * @src: the start of the IPv4 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[4] array) representation of the IPv4 address * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s; u8 *d; u8 dbuf[4]; int ret = 0; int i; int w = 0; if (srclen < 0) srclen = strlen(src); s = src; d = dbuf; i = 0; while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) { goto out; } if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (w == 0) goto out; *d++ = w & 0xff; w = 0; i++; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (i != 4) goto out; break; } goto cont; } w = (w * 10) + c; if ((w & 0xffff) > 255) { goto out; } cont: if (i >= 4) goto out; s++; srclen--; } ret = 1; memcpy(dst, dbuf, sizeof(dbuf)); out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in4_pton); /** * in6_pton - convert an IPv6 address from literal to binary representation * @src: the start of the IPv6 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[16] array) representation of the IPv6 address * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s, *tok = NULL; u8 *d, *dc = NULL; u8 dbuf[16]; int ret = 0; int i; int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; int w = 0; memset(dbuf, 0, sizeof(dbuf)); s = src; d = dbuf; if (srclen < 0) srclen = strlen(src); while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & state)) goto out; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { /* process one 16-bit word */ if (!(state & IN6PTON_NULL)) { *d++ = (w >> 8) & 0xff; *d++ = w & 0xff; } w = 0; if (c & IN6PTON_DELIM) { /* We've processed last word */ break; } /* * COLON_1 => XDIGIT * COLON_2 => XDIGIT|DELIM * COLON_1_2 => COLON_2 */ switch (state & IN6PTON_COLON_MASK) { case IN6PTON_COLON_2: dc = d; state = IN6PTON_XDIGIT | IN6PTON_DELIM; if (dc - dbuf >= sizeof(dbuf)) state |= IN6PTON_NULL; break; case IN6PTON_COLON_1|IN6PTON_COLON_1_2: state = IN6PTON_XDIGIT | IN6PTON_COLON_2; break; case IN6PTON_COLON_1: state = IN6PTON_XDIGIT; break; case IN6PTON_COLON_1_2: state = IN6PTON_COLON_2; break; default: state = 0; } tok = s + 1; goto cont; } if (c & IN6PTON_DOT) { ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); if (ret > 0) { d += 4; break; } goto out; } w = (w << 4) | (0xff & c); state = IN6PTON_COLON_1 | IN6PTON_DELIM; if (!(w & 0xf000)) { state |= IN6PTON_XDIGIT; } if (!dc && d + 2 < dbuf + sizeof(dbuf)) { state |= IN6PTON_COLON_1_2; state &= ~IN6PTON_DELIM; } if (d + 2 >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); } cont: if ((dc && d + 4 < dbuf + sizeof(dbuf)) || d + 4 == dbuf + sizeof(dbuf)) { state |= IN6PTON_DOT; } if (d >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); } s++; srclen--; } i = 15; d--; if (dc) { while (d >= dc) dst[i--] = *d--; while (i >= dc - dbuf) dst[i--] = 0; while (i >= 0) dst[i--] = *d--; } else memcpy(dst, dbuf, sizeof(dbuf)); ret = 1; out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in6_pton); static int inet4_pton(const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; int srclen = strlen(src); if (srclen > INET_ADDRSTRLEN) return -EINVAL; if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr, '\n', NULL) == 0) return -EINVAL; addr4->sin_family = AF_INET; addr4->sin_port = htons(port_num); return 0; } static int inet6_pton(struct net *net, const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; const char *scope_delim; int srclen = strlen(src); if (srclen > INET6_ADDRSTRLEN) return -EINVAL; if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr, '%', &scope_delim) == 0) return -EINVAL; if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL && src + srclen != scope_delim && *scope_delim == '%') { struct net_device *dev; char scope_id[16]; size_t scope_len = min_t(size_t, sizeof(scope_id) - 1, src + srclen - scope_delim - 1); memcpy(scope_id, scope_delim + 1, scope_len); scope_id[scope_len] = '\0'; dev = dev_get_by_name(net, scope_id); if (dev) { addr6->sin6_scope_id = dev->ifindex; dev_put(dev); } else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) { return -EINVAL; } } addr6->sin6_family = AF_INET6; addr6->sin6_port = htons(port_num); return 0; } /** * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address * @net: net namespace (used for scope handling) * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either * @src: the start of the address string * @port: the start of the port string (or NULL for none) * @addr: output socket address * * Return zero on success, return errno when any error occurs. */ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, const char *src, const char *port, struct sockaddr_storage *addr) { u16 port_num; int ret = -EINVAL; if (port) { if (kstrtou16(port, 0, &port_num)) return -EINVAL; } else { port_num = 0; } switch (af) { case AF_INET: ret = inet4_pton(src, port_num, addr); break; case AF_INET6: ret = inet6_pton(net, src, port_num, addr); break; case AF_UNSPEC: ret = inet4_pton(src, port_num, addr); if (ret) ret = inet6_pton(net, src, port_num, addr); break; default: pr_err("unexpected address family %d\n", af); } return ret; } EXPORT_SYMBOL(inet_pton_with_scope); bool inet_addr_is_any(struct sockaddr *addr) { if (addr->sa_family == AF_INET6) { struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)addr; const struct sockaddr_in6 in6_any = { .sin6_addr = IN6ADDR_ANY_INIT }; if (!memcmp(in6->sin6_addr.s6_addr, in6_any.sin6_addr.s6_addr, 16)) return true; } else if (addr->sa_family == AF_INET) { struct sockaddr_in *in = (struct sockaddr_in *)addr; if (in->sin_addr.s_addr == htonl(INADDR_ANY)) return true; } else { pr_warn("unexpected address family %u\n", addr->sa_family); } return false; } EXPORT_SYMBOL(inet_addr_is_any); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(csum_sub(~(skb->csum), (__force __wsum)from), (__force __wsum)to); } else if (pseudohdr) *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), (__force __wsum)from), (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); /** * inet_proto_csum_replace16 - update layer 4 header checksum field * @sum: Layer 4 header checksum field * @skb: sk_buff for the packet * @from: old IPv6 address * @to: new IPv6 address * @pseudohdr: True if layer 4 header checksum includes pseudoheader * * Update layer 4 header as per the update in IPv6 src/dst address. * * There is no need to update skb->csum in this function, because update in two * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as * L4 Header checksum for skb->csum calculation. */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace16); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace_by_diff(sum, diff); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_sub(diff, skb->csum); } else if (pseudohdr) { *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); |
| 288 288 286 286 5 5 5 5 288 288 288 288 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/proc/net.c * * Copyright (C) 2007 * * Author: Eric Biederman <ebiederm@xmission.com> * * proc net directory handling functions */ #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/mount.h> #include <linux/nsproxy.h> #include <linux/uidgid.h> #include <net/net_namespace.h> #include <linux/seq_file.h> #include "internal.h" static inline struct net *PDE_NET(struct proc_dir_entry *pde) { return pde->parent->data; } static struct net *get_proc_net(const struct inode *inode) { return maybe_get_net(PDE_NET(PDE(inode))); } static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; struct seq_net_private *p; struct net *net; WARN_ON_ONCE(state_size < sizeof(*p)); if (file->f_mode & FMODE_WRITE && !PDE(inode)->write) return -EACCES; net = get_proc_net(inode); if (!net) return -ENXIO; p = __seq_open_private(file, PDE(inode)->seq_ops, state_size); if (!p) { put_net(net); return -ENOMEM; } #ifdef CONFIG_NET_NS p->net = net; netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } static void seq_file_net_put_net(struct seq_file *seq) { #ifdef CONFIG_NET_NS struct seq_net_private *priv = seq->private; put_net_track(priv->net, &priv->ns_tracker); #else put_net(&init_net); #endif } static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; seq_file_net_put_net(seq); seq_release_private(ino, f); return 0; } static const struct proc_ops proc_net_seq_ops = { .proc_open = seq_open_net, .proc_read = seq_read, .proc_write = proc_simple_write, .proc_lseek = seq_lseek, .proc_release = seq_release_net, }; int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) { #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker, GFP_KERNEL); #endif return 0; } void bpf_iter_fini_seq_net(void *priv_data) { #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; put_net_track(p->net, &p->ns_tracker); #endif } struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_data); /** * proc_create_net_data_write - Create a writable net_ns-specific proc file * @name: The name of the file. * @mode: The file's access mode. * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a * series of elements and also provides for the file accepting writes that have * some arbitrary effect. * * The functions in the @ops table are used to iterate over items to be * presented and extract the readable content using the seq_file interface. * * The @write function is called with the data copied into a kernel space * scratch buffer and has a NUL appended for convenience. The buffer may be * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, proc_write_t write, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; p->write = write; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_data_write); static int single_open_net(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); struct net *net; int err; net = get_proc_net(inode); if (!net) return -ENXIO; err = single_open(file, de->single_show, net); if (err) put_net(net); return err; } static int single_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; put_net(seq->private); return single_release(ino, f); } static const struct proc_ops proc_net_single_ops = { .proc_open = single_open_net, .proc_read = seq_read, .proc_write = proc_simple_write, .proc_lseek = seq_lseek, .proc_release = single_release_net, }; struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_single_ops; p->single_show = show; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_single); /** * proc_create_net_single_write - Create a writable net_ns-specific proc file * @name: The name of the file. * @mode: The file's access mode. * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. * @write: The write method with which to 'modify' the file. * @data: Data for retrieval by pde_data(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a * single element rather than a series and also provides for the file accepting * writes that have some arbitrary effect. * * The @show function is called to extract the readable content via the * seq_file interface. * * The @write function is called with the data copied into a kernel space * scratch buffer and has a NUL appended for convenience. The buffer may be * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), proc_write_t write, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_single_ops; p->single_show = show; p->write = write; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_single_write); static struct net *get_proc_task_net(struct inode *dir) { struct task_struct *task; struct nsproxy *ns; struct net *net = NULL; rcu_read_lock(); task = pid_task(proc_pid(dir), PIDTYPE_PID); if (task != NULL) { task_lock(task); ns = task->nsproxy; if (ns != NULL) net = get_net(ns->net_ns); task_unlock(task); } rcu_read_unlock(); return net; } static struct dentry *proc_tgid_net_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct dentry *de; struct net *net; de = ERR_PTR(-ENOENT); net = get_proc_task_net(dir); if (net != NULL) { de = proc_lookup_de(dir, dentry, net->proc_net); put_net(net); } return de; } static int proc_tgid_net_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct net *net; net = get_proc_task_net(inode); generic_fillattr(&init_user_ns, inode, stat); if (net != NULL) { stat->nlink = net->proc_net->nlink; put_net(net); } return 0; } const struct inode_operations proc_net_inode_operations = { .lookup = proc_tgid_net_lookup, .getattr = proc_tgid_net_getattr, }; static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx) { int ret; struct net *net; ret = -EINVAL; net = get_proc_task_net(file_inode(file)); if (net != NULL) { ret = proc_readdir_de(file, ctx, net->proc_net); put_net(net); } return ret; } const struct file_operations proc_net_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = proc_tgid_net_readdir, }; static __net_init int proc_net_ns_init(struct net *net) { struct proc_dir_entry *netd, *net_statd; kuid_t uid; kgid_t gid; int err; /* * This PDE acts only as an anchor for /proc/${pid}/net hierarchy. * Corresponding inode (PDE(inode) == net->proc_net) is never * instantiated therefore blanket zeroing is fine. * net->proc_net_stat inode is instantiated normally. */ err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) goto out; netd->subdir = RB_ROOT; netd->data = net; netd->nlink = 2; netd->namelen = 3; netd->parent = &proc_root; netd->name = netd->inline_name; memcpy(netd->name, "net", 4); uid = make_kuid(net->user_ns, 0); if (!uid_valid(uid)) uid = netd->uid; gid = make_kgid(net->user_ns, 0); if (!gid_valid(gid)) gid = netd->gid; proc_set_user(netd, uid, gid); /* Seed dentry revalidation for /proc/${pid}/net */ pde_force_lookup(netd); err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) goto free_net; net->proc_net = netd; net->proc_net_stat = net_statd; return 0; free_net: pde_free(netd); out: return err; } static __net_exit void proc_net_ns_exit(struct net *net) { remove_proc_entry("stat", net->proc_net); pde_free(net->proc_net); } static struct pernet_operations __net_initdata proc_net_ns_ops = { .init = proc_net_ns_init, .exit = proc_net_ns_exit, }; int __init proc_net_init(void) { proc_symlink("net", NULL, "self/net"); return register_pernet_subsys(&proc_net_ns_ops); } |
| 903 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 | // SPDX-License-Identifier: GPL-2.0 /* * Creating audit events from TTY input. * * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * * Authors: Miloslav Trmac <mitr@redhat.com> */ #include <linux/audit.h> #include <linux/slab.h> #include <linux/tty.h> #include "tty.h" struct tty_audit_buf { struct mutex mutex; /* Protects all data below */ dev_t dev; /* The TTY which the data is from */ unsigned icanon:1; size_t valid; unsigned char *data; /* Allocated size N_TTY_BUF_SIZE */ }; static struct tty_audit_buf *tty_audit_buf_ref(void) { struct tty_audit_buf *buf; buf = current->signal->tty_audit_buf; WARN_ON(buf == ERR_PTR(-ESRCH)); return buf; } static struct tty_audit_buf *tty_audit_buf_alloc(void) { struct tty_audit_buf *buf; buf = kmalloc(sizeof(*buf), GFP_KERNEL); if (!buf) goto err; buf->data = kmalloc(N_TTY_BUF_SIZE, GFP_KERNEL); if (!buf->data) goto err_buf; mutex_init(&buf->mutex); buf->dev = MKDEV(0, 0); buf->icanon = 0; buf->valid = 0; return buf; err_buf: kfree(buf); err: return NULL; } static void tty_audit_buf_free(struct tty_audit_buf *buf) { WARN_ON(buf->valid != 0); kfree(buf->data); kfree(buf); } static void tty_audit_log(const char *description, dev_t dev, unsigned char *data, size_t size) { struct audit_buffer *ab; pid_t pid = task_pid_nr(current); uid_t uid = from_kuid(&init_user_ns, task_uid(current)); uid_t loginuid = from_kuid(&init_user_ns, audit_get_loginuid(current)); unsigned int sessionid = audit_get_sessionid(current); ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_TTY); if (ab) { char name[sizeof(current->comm)]; audit_log_format(ab, "%s pid=%u uid=%u auid=%u ses=%u major=%d" " minor=%d comm=", description, pid, uid, loginuid, sessionid, MAJOR(dev), MINOR(dev)); get_task_comm(name, current); audit_log_untrustedstring(ab, name); audit_log_format(ab, " data="); audit_log_n_hex(ab, data, size); audit_log_end(ab); } } /* * tty_audit_buf_push - Push buffered data out * * Generate an audit message from the contents of @buf, which is owned by * the current task. @buf->mutex must be locked. */ static void tty_audit_buf_push(struct tty_audit_buf *buf) { if (buf->valid == 0) return; if (audit_enabled == AUDIT_OFF) { buf->valid = 0; return; } tty_audit_log("tty", buf->dev, buf->data, buf->valid); buf->valid = 0; } /** * tty_audit_exit - Handle a task exit * * Make sure all buffered data is written out and deallocate the buffer. * Only needs to be called if current->signal->tty_audit_buf != %NULL. * * The process is single-threaded at this point; no other threads share * current->signal. */ void tty_audit_exit(void) { struct tty_audit_buf *buf; buf = xchg(¤t->signal->tty_audit_buf, ERR_PTR(-ESRCH)); if (!buf) return; tty_audit_buf_push(buf); tty_audit_buf_free(buf); } /* * tty_audit_fork - Copy TTY audit state for a new task * * Set up TTY audit state in @sig from current. @sig needs no locking. */ void tty_audit_fork(struct signal_struct *sig) { sig->audit_tty = current->signal->audit_tty; } /* * tty_audit_tiocsti - Log TIOCSTI */ void tty_audit_tiocsti(struct tty_struct *tty, char ch) { dev_t dev; dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; if (tty_audit_push()) return; if (audit_enabled) tty_audit_log("ioctl=TIOCSTI", dev, &ch, 1); } /* * tty_audit_push - Flush current's pending audit data * * Returns 0 if success, -EPERM if tty audit is disabled */ int tty_audit_push(void) { struct tty_audit_buf *buf; if (~current->signal->audit_tty & AUDIT_TTY_ENABLE) return -EPERM; buf = tty_audit_buf_ref(); if (!IS_ERR_OR_NULL(buf)) { mutex_lock(&buf->mutex); tty_audit_buf_push(buf); mutex_unlock(&buf->mutex); } return 0; } /* * tty_audit_buf_get - Get an audit buffer. * * Get an audit buffer, allocate it if necessary. Return %NULL * if out of memory or ERR_PTR(-ESRCH) if tty_audit_exit() has already * occurred. Otherwise, return a new reference to the buffer. */ static struct tty_audit_buf *tty_audit_buf_get(void) { struct tty_audit_buf *buf; buf = tty_audit_buf_ref(); if (buf) return buf; buf = tty_audit_buf_alloc(); if (buf == NULL) { audit_log_lost("out of memory in TTY auditing"); return NULL; } /* Race to use this buffer, free it if another wins */ if (cmpxchg(¤t->signal->tty_audit_buf, NULL, buf) != NULL) tty_audit_buf_free(buf); return tty_audit_buf_ref(); } /* * tty_audit_add_data - Add data for TTY auditing. * * Audit @data of @size from @tty, if necessary. */ void tty_audit_add_data(struct tty_struct *tty, const void *data, size_t size) { struct tty_audit_buf *buf; unsigned int icanon = !!L_ICANON(tty); unsigned int audit_tty; dev_t dev; audit_tty = READ_ONCE(current->signal->audit_tty); if (~audit_tty & AUDIT_TTY_ENABLE) return; if (unlikely(size == 0)) return; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) return; if ((~audit_tty & AUDIT_TTY_LOG_PASSWD) && icanon && !L_ECHO(tty)) return; buf = tty_audit_buf_get(); if (IS_ERR_OR_NULL(buf)) return; mutex_lock(&buf->mutex); dev = MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; if (buf->dev != dev || buf->icanon != icanon) { tty_audit_buf_push(buf); buf->dev = dev; buf->icanon = icanon; } do { size_t run; run = N_TTY_BUF_SIZE - buf->valid; if (run > size) run = size; memcpy(buf->data + buf->valid, data, run); buf->valid += run; data += run; size -= run; if (buf->valid == N_TTY_BUF_SIZE) tty_audit_buf_push(buf); } while (size != 0); mutex_unlock(&buf->mutex); } |
| 4 371 1 2 301 244 3 366 368 303 260 367 9 238 239 148 148 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IP/TCP/UDP checksumming routines * * Authors: Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Tom May, <ftom@netcom.com> * Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de> * Lots of code moved from tcp.c and ip.c; see those files * for more names. * * 03/02/96 Jes Sorensen, Andreas Schwab, Roman Hodek: * Fixed some nasty bugs, causing some horrible crashes. * A: At some points, the sum (%0) was used as * length-counter instead of the length counter * (%1). Thanks to Roman Hodek for pointing this out. * B: GCC seems to mess up if one uses too many * data-registers to hold input values and one tries to * specify d0 and d1 as scratch registers. Letting gcc * choose these registers itself solves the problem. */ /* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access kills, so most of the assembly has to go. */ #include <linux/export.h> #include <net/checksum.h> #include <asm/byteorder.h> #ifndef do_csum static inline unsigned short from32to16(unsigned int x) { /* add up 16-bit and 16-bit for 16+c bit */ x = (x & 0xffff) + (x >> 16); /* add up carry.. */ x = (x & 0xffff) + (x >> 16); return x; } static unsigned int do_csum(const unsigned char *buff, int len) { int odd; unsigned int result = 0; if (len <= 0) goto out; odd = 1 & (unsigned long) buff; if (odd) { #ifdef __LITTLE_ENDIAN result += (*buff << 8); #else result = *buff; #endif len--; buff++; } if (len >= 2) { if (2 & (unsigned long) buff) { result += *(unsigned short *) buff; len -= 2; buff += 2; } if (len >= 4) { const unsigned char *end = buff + ((unsigned)len & ~3); unsigned int carry = 0; do { unsigned int w = *(unsigned int *) buff; buff += 4; result += carry; result += w; carry = (w > result); } while (buff < end); result += carry; result = (result & 0xffff) + (result >> 16); } if (len & 2) { result += *(unsigned short *) buff; buff += 2; } } if (len & 1) #ifdef __LITTLE_ENDIAN result += *buff; #else result += (*buff << 8); #endif result = from32to16(result); if (odd) result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); out: return result; } #endif #ifndef ip_fast_csum /* * This is a version of ip_compute_csum() optimized for IP headers, * which always checksum on 4 octet boundaries. */ __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { return (__force __sum16)~do_csum(iph, ihl*4); } EXPORT_SYMBOL(ip_fast_csum); #endif /* * computes the checksum of a memory block at buff, length len, * and adds in "sum" (32-bit) * * returns a 32-bit number suitable for feeding into itself * or csum_tcpudp_magic * * this function must be called with even lengths, except * for the last fragment, which may be odd * * it's best to have buff aligned on a 32-bit boundary */ __wsum csum_partial(const void *buff, int len, __wsum wsum) { unsigned int sum = (__force unsigned int)wsum; unsigned int result = do_csum(buff, len); /* add in old sum, and carry.. */ result += sum; if (sum > result) result += 1; return (__force __wsum)result; } EXPORT_SYMBOL(csum_partial); /* * this routine is used for miscellaneous IP-like checksums, mainly * in icmp.c */ __sum16 ip_compute_csum(const void *buff, int len) { return (__force __sum16)~do_csum(buff, len); } EXPORT_SYMBOL(ip_compute_csum); #ifndef csum_tcpudp_nofold static inline u32 from64to32(u64 x) { /* add up 32-bit and 32-bit for 32+c bit */ x = (x & 0xffffffff) + (x >> 32); /* add up carry.. */ x = (x & 0xffffffff) + (x >> 32); return (u32)x; } __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __wsum sum) { unsigned long long s = (__force u32)sum; s += (__force u32)saddr; s += (__force u32)daddr; #ifdef __BIG_ENDIAN s += proto + len; #else s += (proto + len) << 8; #endif return (__force __wsum)from64to32(s); } EXPORT_SYMBOL(csum_tcpudp_nofold); #endif |
| 30 136 136 13 3 1 1 9 86 86 118 171 20 2 299 27 16 86 332 151 26 151 152 296 296 15 15 121 121 673 144 143 12 134 144 142 142 144 145 676 649 144 145 145 145 145 14 539 677 677 161 160 16 16 16 16 16 16 16 16 1 16 11 6 16 26 21 8 13 24 24 24 151 151 151 144 47 144 144 144 144 144 143 144 144 3 144 151 151 24 144 144 144 143 144 136 11 69 71 73 71 166 152 152 162 162 54 162 172 336 155 212 336 335 155 212 336 37 307 335 13 4 13 13 168 19 37 118 136 136 55 132 55 132 151 3 151 6 145 111 145 110 145 136 137 136 137 172 30 145 130 106 172 145 145 30 145 135 130 1 1 172 172 145 144 69 70 172 172 145 172 145 151 114 69 151 151 151 151 151 151 172 172 151 6 6 6 145 3 145 137 35 117 148 35 117 149 1 149 165 5 160 18 144 39 118 153 153 153 7 153 151 153 153 153 24 17 24 24 3 24 37 37 37 37 37 10 10 17 24 172 172 172 172 172 172 143 143 172 172 172 172 172 19 136 136 143 143 24 24 24 24 19 19 19 13 19 24 24 24 24 24 14 14 14 32 31 5 30 30 1 18 20 28 5 17 28 8 14 13 16 20 19 19 11 1 8 8 8 8 14 2 12 4 2 2 1 4 2 2 1 19 4 1 14 1 1 1 1 4 2 1 1 162 162 162 3 2 1 3 368 3 364 336 32 7 18 2 6 3 162 162 162 162 166 166 166 166 166 166 166 162 13 20 81 76 8 80 103 103 57 242 57 57 12 12 2 25 25 37 25 25 23 80 80 38 80 80 38 1 38 3 37 38 80 80 38 16 38 15 38 38 80 38 79 66 14 79 79 38 80 80 38 80 54 38 79 80 1 1 54 71 71 71 71 61 11 77 6 71 8 67 64 14 136 136 136 136 136 118 136 136 66 132 136 136 136 136 136 151 1 152 152 151 1 150 3 104 53 152 37 118 146 3 1 155 149 152 152 152 13 13 903 18 80 546 546 546 546 546 546 538 7 546 546 546 546 7 7 7 538 539 539 539 1 539 531 8 8 538 7 7 95 18 79 80 24 97 115 115 17 74 5 3032 3034 3034 1618 1615 1615 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "cgroup-internal.h" #include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/hashtable.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/cgroup.h> #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) /* let's not notify more than 100 times per second */ #define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0) /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); #ifdef CONFIG_PROVE_RCU EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif DEFINE_SPINLOCK(trace_cgroup_path_lock); char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; static bool cgroup_debug __read_mostly; /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */ static DEFINE_SPINLOCK(cgroup_idr_lock); /* * Protects cgroup_file->kn for !self csses. It synchronizes notifications * against file removal/re-creation across css hiding. */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); EXPORT_SYMBOL_GPL(cgroup_threadgroup_rwsem); #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required"); /* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_destroy_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, struct cgroup_subsys *cgroup_subsys[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of cgroup subsystem names */ #define SUBSYS(_x) [_x ## _cgrp_id] = #_x, static const char *cgroup_subsys_name[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ #define SUBSYS(_x) \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key); #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key, static struct static_key_true *cgroup_subsys_enabled_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key, static struct static_key_true *cgroup_subsys_on_dfl_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS static DEFINE_PER_CPU(struct cgroup_rstat_cpu, cgrp_dfl_root_rstat_cpu); /* the default hierarchy */ struct cgroup_root cgrp_dfl_root = { .cgrp.rstat_cpu = &cgrp_dfl_root_rstat_cpu }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ static bool cgrp_dfl_visible; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; /* some controllers can be threaded on the default hierarchy */ static u16 cgrp_dfl_threaded_ss_mask; /* The list of hierarchy roots */ LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); /* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */ static u64 css_serial_nr_next = 1; /* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = { .ns.count = REFCOUNT_INIT(2), .user_ns = &init_user_ns, .ns.ops = &cgroupns_operations, .ns.inum = PROC_CGROUP_INIT_INO, .root_cset = &init_css_set, }; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_base_files[]; static struct cftype cgroup_psi_files[]; /* cgroup optional features */ enum cgroup_opt_features { #ifdef CONFIG_PSI OPT_FEATURE_PRESSURE, #endif OPT_FEATURE_COUNT }; static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = { #ifdef CONFIG_PSI "pressure", #endif }; static u16 cgroup_feature_disable_mask __read_mostly; static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); /** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ bool cgroup_ssid_enabled(int ssid) { if (!CGROUP_HAS_SUBSYS_CONFIG) return false; return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. * * - debug: disallowed on the default hierarchy. */ bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { int ret; idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; } static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { void *ret; spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret; } static void cgroup_idr_remove(struct idr *idr, int id) { spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock); } static bool cgroup_has_tasks(struct cgroup *cgrp) { return cgrp->nr_populated_csets; } bool cgroup_is_threaded(struct cgroup *cgrp) { return cgrp->dom_cgrp != cgrp; } /* can @cgrp host both domain and threaded children? */ static bool cgroup_is_mixable(struct cgroup *cgrp) { /* * Root isn't under domain level resource control exempting it from * the no-internal-process constraint, so it can serve as a thread * root and a parent of resource domains at the same time. */ return !cgroup_parent(cgrp); } /* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return true; /* domain roots can't be nested under threaded */ if (cgroup_is_threaded(cgrp)) return false; /* can only have either domain or threaded children */ if (cgrp->nr_populated_domain_children) return false; /* and no domain controllers can be enabled */ if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return false; return true; } /* is @cgrp root of a threaded subtree? */ bool cgroup_is_thread_root(struct cgroup *cgrp) { /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) return false; /* a domain w/ threaded children is a thread root */ if (cgrp->nr_threaded_children) return true; /* * A domain which has tasks and explicit threaded controllers * enabled is a thread root. */ if (cgroup_has_tasks(cgrp) && (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) return true; return false; } /* a domain which isn't connected to the root w/o brekage can't be used */ static bool cgroup_is_valid_domain(struct cgroup *cgrp) { /* the cgroup itself can be a thread root */ if (cgroup_is_threaded(cgrp)) return false; /* but the ancestors can't be unless mixable */ while ((cgrp = cgroup_parent(cgrp))) { if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) return false; if (cgroup_is_threaded(cgrp)) return false; } return true; } /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; if (parent) { u16 ss_mask = parent->subtree_control; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask; } /* subsystems enabled on a cgroup */ static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); if (parent) { u16 ss_mask = parent->subtree_ss_mask; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } return cgrp->root->subsys_mask; } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (CGROUP_HAS_SUBSYS_CONFIG && ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; } /** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; rcu_read_lock(); css = cgroup_css(cgrp, ss); if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock(); return css; } /** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); if (!ss) return &cgrp->self; /* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; } return cgroup_css(cgrp, ss); } /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; do { css = cgroup_css(cgrp, ss); if (css) return css; cgrp = cgroup_parent(cgrp); } while (cgrp); return init_css_set.subsys[ss->id]; } /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; rcu_read_lock(); do { css = cgroup_css(cgrp, ss); if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp); css = init_css_set.subsys[ss->id]; css_get(css); out_unlock: rcu_read_unlock(); return css; } EXPORT_SYMBOL_GPL(cgroup_get_e_css); static void cgroup_get_live(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); css_get(&cgrp->self); } /** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */ int __cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks; return count; } /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */ int cgroup_task_count(const struct cgroup *cgrp) { int count; spin_lock_irq(&css_set_lock); count = __cgroup_task_count(cgrp); spin_unlock_irq(&css_set_lock); return count; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); /* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self; } EXPORT_SYMBOL_GPL(of_css); /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_[tree_]mutex. */ #define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** * for_each_e_css - iterate all effective css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_[tree_]mutex. */ #define for_each_e_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = cgroup_e_css_by_mask(cgrp, \ cgroup_subsys[(ssid)]))) \ ; \ else /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_HAS_SUBSYS_CONFIG) { \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ { #define while_each_subsys_mask() \ } \ } \ } while (false) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* * The following field is re-initialized when this cset gets linked * in cgroup_init(). However, let's initialize the field * statically too so that the default cgroup can be accessed safely * early during boot. */ .dfl_cgrp = &cgrp_dfl_root.cgrp, }; static int css_set_count = 1; /* 1 for init_css_set */ static bool css_set_threaded(struct css_set *cset) { return cset->dom_cset != cset; } /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { lockdep_assert_held(&css_set_lock); return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); } /** * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->nr_populated_* accordingly. The * count is propagated towards root so that a given cgroup's * nr_populated_children is zero iff none of its descendants contain any * tasks. * * @cgrp's interface file "cgroup.populated" is zero if both * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and * 1 otherwise. When the sum changes from or to zero, userland is notified * that the content of the interface file has changed. This can be used to * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { struct cgroup *child = NULL; int adj = populated ? 1 : -1; lockdep_assert_held(&css_set_lock); do { bool was_populated = cgroup_is_populated(cgrp); if (!child) { cgrp->nr_populated_csets += adj; } else { if (cgroup_is_threaded(child)) cgrp->nr_populated_threaded_children += adj; else cgrp->nr_populated_domain_children += adj; } if (was_populated == cgroup_is_populated(cgrp)) break; cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); cgroup_file_notify(&cgrp->events_file); child = cgrp; cgrp = cgroup_parent(cgrp); } while (cgrp); } /** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) cgroup_update_populated(link->cgrp, populated); } /* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */ static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task) { struct css_task_iter *it, *pos; list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) css_task_iter_skip(it, task); } /** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { lockdep_assert_held(&css_set_lock); if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true); if (from_cset) { WARN_ON_ONCE(list_empty(&task->cg_list)); css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); } if (to_cset) { /* * We are synchronized through cgroup_threadgroup_rwsem * against PF_EXITING setting such that we can't race * against cgroup_exit()/cgroup_free() dropping the css_set. */ WARN_ON_ONCE(task->flags & PF_EXITING); cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } } /* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; } void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&css_set_lock); if (!refcount_dec_and_test(&cset->refcount)) return; WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); } if (css_set_threaded(cset)) { list_del(&cset->threaded_csets_node); put_css_set_locked(cset->dom_cset); } kfree_rcu(cset, rcu_head); } /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2; /* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; /* @cset's domain should match the default cgroup's */ if (cgroup_on_dfl(new_cgrp)) new_dfl_cgrp = new_cgrp; else new_dfl_cgrp = old_cset->dfl_cgrp; if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) return false; /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; } /** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state *template[]) { struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; } static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } } /** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */ static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; } /** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp; link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; /* * Always add links to the tail of the lists so that the lists are * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); if (cgroup_parent(cgrp)) cgroup_get_live(cgrp); } /** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */ static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } refcount_set(&cset->refcount, 1); cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->dying_tasks); INIT_LIST_HEAD(&cset->task_iters); INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_src_preload_node); INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid]; list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); } spin_unlock_irq(&css_set_lock); /* * If @cset should be threaded, look up the matching dom_cset and * link them up. We first fully initialize @cset then look for the * dom_cset. It's simpler this way and safe as @cset is guaranteed * to stay empty until we return. */ if (cgroup_is_threaded(cset->dfl_cgrp)) { struct css_set *dcset; dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); if (!dcset) { put_css_set(cset); return NULL; } spin_lock_irq(&css_set_lock); cset->dom_cset = dcset; list_add_tail(&cset->threaded_csets_node, &dcset->threaded_csets); spin_unlock_irq(&css_set_lock); } return cset; } struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv; return root_cgrp->root; } void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) { bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS; /* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */ if (favor && !favoring) { rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); root->flags |= CGRP_ROOT_FAVOR_DYNMODS; } else if (!favor && favoring) { rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; } } static int cgroup_init_root_id(struct cgroup_root *root) { int id; lockdep_assert_held(&cgroup_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; } static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } void cgroup_free_root(struct cgroup_root *root) { kfree(root); } static void cgroup_destroy_root(struct cgroup_root *root) { struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; trace_cgroup_destroy_root(root); cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); /* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } spin_unlock_irq(&css_set_lock); if (!list_empty(&root->root_list)) { list_del(&root->root_list); cgroup_root_count--; } cgroup_favor_dynmods(root, false); cgroup_exit_root_id(root); cgroup_unlock(); cgroup_rstat_exit(cgrp); kernfs_destroy_root(root->kf_root); cgroup_free_root(root); } /* * Returned cgroup is without refcount but it's valid as long as cset pins it. */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { struct cgroup *res_cgroup = NULL; if (cset == &init_css_set) { res_cgroup = &root->cgrp; } else if (root == &cgrp_dfl_root) { res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res_cgroup = c; break; } } } BUG_ON(!res_cgroup); return res_cgroup; } /* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */ static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { struct cgroup *res = NULL; struct css_set *cset; lockdep_assert_held(&css_set_lock); rcu_read_lock(); cset = current->nsproxy->cgroup_ns->root_cset; res = __cset_cgroup_from_root(cset, root); rcu_read_unlock(); return res; } /* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */ static struct cgroup *current_cgns_cgroup_dfl(void) { struct css_set *cset; cset = current->nsproxy->cgroup_ns->root_cset; return __cset_cgroup_from_root(cset, &cgrp_dfl_root); } /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with cgroup_mutex and css_set_lock held. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { /* * No need to lock the task - since we hold css_set_lock the * task can't change groups. */ return cset_cgroup_from_root(task_css_set(task), root); } /* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { struct cgroup_subsys *ss = cft->ss; if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : ""; snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); } else { strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); } return buf; } /** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */ static umode_t cgroup_file_mode(const struct cftype *cft) { umode_t mode = 0; if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO; if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; } return mode; } /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); cur_ss_mask |= cgrp_dfl_implicit_ss_mask; while (true) { u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; } return cur_ss_mask; } /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn->parent->priv; cgroup_unlock(); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); } /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn->parent->priv; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn); if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else cgroup_lock(); if (!cgroup_is_dead(cgrp)) return cgrp; cgroup_kn_unlock(kn); return NULL; } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); del_timer_sync(&cfile->notify_timer); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } /** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) return; css->flags &= ~CSS_VISIBLE; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); if (cgroup_psi_enabled()) cgroup_addrm_files(css, cgrp, cgroup_psi_files, false); } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, false); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); } } /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */ static int css_populate_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; if ((css->flags & CSS_VISIBLE) || !cgrp->kn) return 0; if (!css->ss) { if (cgroup_on_dfl(cgrp)) { ret = cgroup_addrm_files(&cgrp->self, cgrp, cgroup_base_files, true); if (ret < 0) return ret; if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(&cgrp->self, cgrp, cgroup_psi_files, true); if (ret < 0) return ret; } } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, true); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } } css->flags |= CSS_VISIBLE; return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret; } int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; /* * Collect ssid's that need to be disabled from default * hierarchy. */ if (ss->root == &cgrp_dfl_root) dfl_disable_ss_mask |= 1 << ssid; } while_each_subsys_mask(); if (dfl_disable_ss_mask) { struct cgroup *scgrp = &cgrp_dfl_root.cgrp; /* * Controllers from default hierarchy that need to be rebound * are all disabled together in one go. */ cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset, *cset_pos; struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); if (src_root != &cgrp_dfl_root) { /* disable from the source */ src_root->subsys_mask &= ~(1 << ssid); WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); /* * all css_sets of scgrp together in same order to dcgrp, * patch in-flight iterators to preserve correct iteration. * since the iterator is always advanced right away and * finished when it->cset_pos meets it->cset_head, so only * update it->cset_head is enough here. */ list_for_each_entry(it, &cset->task_iters, iters_node) if (it->cset_head == &scgrp->e_csets[ss->id]) it->cset_head = &dcgrp->e_csets[ss->id]; } spin_unlock_irq(&css_set_lock); if (ss->css_rstat_flush) { list_del_rcu(&css->rstat_css_node); synchronize_rcu(); list_add_rcu(&css->rstat_css_node, &dcgrp->rstat_css_list); } /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret); if (ss->bind) ss->bind(css); } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; } int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM; spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); if (len >= PATH_MAX) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len; } enum cgroup2_param { Opt_nsdelegate, Opt_favordynmods, Opt_memory_localevents, Opt_memory_recursiveprot, nr__cgroup2_params }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("favordynmods", Opt_favordynmods), fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), {} }; static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_nsdelegate: ctx->flags |= CGRP_ROOT_NS_DELEGATE; return 0; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; case Opt_memory_recursiveprot: ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; return 0; } return -EINVAL; } static void apply_cgroup_root_flags(unsigned int root_flags) { if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { if (root_flags & CGRP_ROOT_NS_DELEGATE) cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; else cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; cgroup_favor_dynmods(&cgrp_dfl_root, root_flags & CGRP_ROOT_FAVOR_DYNMODS); if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; } } static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) seq_puts(seq, ",memory_recursiveprot"); return 0; } static int cgroup_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); apply_cgroup_root_flags(ctx->flags); return 0; } static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; int ssid; INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; INIT_LIST_HEAD(&cgrp->rstat_css_list); prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } void init_cgroup_root(struct cgroup_fs_context *ctx) { struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); /* DYNMODS must be modified through cgroup_favor_dynmods() */ root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; if (ctx->release_agent) strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); if (ctx->name) strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret; lockdep_assert_held(&cgroup_mutex); ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out; /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; ret = cgroup_init_root_id(root); if (ret) goto cancel_ref; kf_sops = root == &cgrp_dfl_root ? &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | KERNFS_ROOT_SUPPORT_USER_XATTR, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = kernfs_root_to_node(root->kf_root); WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); root_cgrp->ancestors[0] = root_cgrp; ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; ret = cgroup_rstat_init(root_cgrp); if (ret) goto destroy_root; ret = rebind_subsystems(root, ss_mask); if (ret) goto exit_stats; ret = cgroup_bpf_inherit(root_cgrp); WARN_ON_ONCE(ret); trace_cgroup_setup_root(root); /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add(&root->root_list, &cgroup_roots); cgroup_root_count++; /* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); ret = 0; goto out; exit_stats: cgroup_rstat_exit(root_cgrp); destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL; exit_root_id: cgroup_exit_root_id(root); cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt); out: free_cgrp_cset_links(&tmp_links); return ret; } int cgroup_do_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; ctx->kfc.root = ctx->root->kf_root; if (fc->fs_type == &cgroup2_fs_type) ctx->kfc.magic = CGROUP2_SUPER_MAGIC; else ctx->kfc.magic = CGROUP_SUPER_MAGIC; ret = kernfs_get_tree(fc); /* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; cgroup_lock(); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); cgroup_unlock(); nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); if (IS_ERR(nsdentry)) { deactivate_locked_super(sb); ret = PTR_ERR(nsdentry); nsdentry = NULL; } fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) cgroup_put(&ctx->root->cgrp); return ret; } /* * Destroy a cgroup filesystem context. */ static void cgroup_fs_context_free(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); kfree(ctx->name); kfree(ctx->release_agent); put_cgroup_ns(ctx->ns); kernfs_free_fs_context(fc); kfree(ctx); } static int cgroup_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; WRITE_ONCE(cgrp_dfl_visible, true); cgroup_get_live(&cgrp_dfl_root.cgrp); ctx->root = &cgrp_dfl_root; ret = cgroup_do_get_tree(fc); if (!ret) apply_cgroup_root_flags(ctx->flags); return ret; } static const struct fs_context_operations cgroup_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup2_parse_param, .get_tree = cgroup_get_tree, .reconfigure = cgroup_reconfigure, }; static const struct fs_context_operations cgroup1_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup1_parse_param, .get_tree = cgroup1_get_tree, .reconfigure = cgroup1_reconfigure, }; /* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */ static int cgroup_init_fs_context(struct fs_context *fc) { struct cgroup_fs_context *ctx; ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; if (fc->fs_type == &cgroup2_fs_type) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; #ifdef CONFIG_CGROUP_FAVOR_DYNMODS ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; #endif return 0; } static void cgroup_kill_sb(struct super_block *sb) { struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); /* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && !percpu_ref_is_dying(&root->cgrp.self.refcnt)) { cgroup_bpf_offline(&root->cgrp); percpu_ref_kill(&root->cgrp.self.refcnt); } cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; #ifdef CONFIG_CPUSETS static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, }; /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ static int cpuset_init_fs_context(struct fs_context *fc) { char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); struct cgroup_fs_context *ctx; int err; err = cgroup_init_fs_context(fc); if (err) { kfree(agent); return err; } fc->ops = &cpuset_fs_context_ops; ctx = cgroup_fc2context(fc); ctx->subsys_mask = 1 << cpuset_cgrp_id; ctx->flags |= CGRP_ROOT_NOPREFIX; ctx->release_agent = agent; get_filesystem(&cgroup_fs_type); put_filesystem(fc->fs_type); fc->fs_type = &cgroup_fs_type; return 0; } static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, .fs_flags = FS_USERNS_MOUNT, }; #endif int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); } int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { int ret; cgroup_lock(); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); cgroup_unlock(); return ret; } EXPORT_SYMBOL_GPL(cgroup_path_ns); /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task * @buf: the buffer to write the path into * @buflen: the length of the buffer * * Determine @task's cgroup on the first (the one with the lowest non-zero * hierarchy_id) cgroup hierarchy and copy its path into @buf. This * function grabs cgroup_mutex and shouldn't be used inside locks used by * cgroup controller callbacks. * * Return value is the same as kernfs_path(). */ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroup_root *root; struct cgroup *cgrp; int hierarchy_id = 1; int ret; cgroup_lock(); spin_lock_irq(&css_set_lock); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); if (root) { cgrp = task_cgroup_from_root(task, root); ret = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); } else { /* if no hierarchy exists, everyone is in "/" */ ret = strscpy(buf, "/", buflen); } spin_unlock_irq(&css_set_lock); cgroup_unlock(); return ret; } EXPORT_SYMBOL_GPL(task_cgroup_path); /** * cgroup_attach_lock - Lock for ->attach() * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ void cgroup_attach_lock(bool lock_threadgroup) { cpus_read_lock(); if (lock_threadgroup) percpu_down_write(&cgroup_threadgroup_rwsem); } /** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ void cgroup_attach_unlock(bool lock_threadgroup) { if (lock_threadgroup) percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); } /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */ static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return; /* cgroup_threadgroup_rwsem protects racing against forks */ WARN_ON_ONCE(list_empty(&task->cg_list)); cset = task_css_set(task); if (!cset->mg_src_cgrp) return; mgctx->tset.nr_tasks++; list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_add_tail(&cset->mg_dst_cset->mg_node, &mgctx->tset.dst_csets); } /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; return cgroup_taskset_next(tset, dst_cssp); } EXPORT_SYMBOL_GPL(cgroup_taskset_first); /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list); if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; /* * This function may be called both before and * after cgroup_taskset_migrate(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid]; return task; } cset = list_next_entry(cset, mg_node); task = NULL; } return NULL; } EXPORT_SYMBOL_GPL(cgroup_taskset_next); /** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; /* check that we can legitimately attach to the cgroup */ if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); } /* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); from_cset->nr_tasks--; /* * If the source or destination cgroup is frozen, * the task might require to change its state. */ cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, to_cset->dfl_cgrp); put_css_set_locked(from_cset); } } spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets; if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; trace_android_vh_cgroup_attach(ss, tset); ss->attach(tset); } } while_each_subsys_mask(); } ret = 0; goto out_release_tset; out_cancel_attach: if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); } out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); /* * Re-initialize the cgroup_taskset structure in case it is reused * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() * iteration. */ tset->nr_tasks = 0; tset->csets = &tset->src_csets; return ret; } /** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { /* v1 doesn't have any restriction */ if (!cgroup_on_dfl(dst_cgrp)) return 0; /* verify @dst_cgrp can host resources */ if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) return -EOPNOTSUPP; /* * If @dst_cgrp is already or can become a thread root or is * threaded, it doesn't matter. */ if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) return 0; /* apply no-internal-process constraint */ if (dst_cgrp->subtree_control) return -EBUSY; return 0; } /** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_src_preload_node); put_css_set_locked(cset); } list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } spin_unlock_irq(&css_set_lock); } /** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx) { struct cgroup *src_cgrp; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); /* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return; if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) return -ENOMEM; WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); /* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; } src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_dst_preload_node)) list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); for_each_subsys(ss, ssid) if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) mgctx->ss_mask |= 1 << ssid; } return 0; } /** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx) { struct task_struct *task; /* * Prevent freeing of tasks while we take a snapshot. Tasks that are * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); return cgroup_migrate_execute(mgctx); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret = 0; /* look up all src csets */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) ret = cgroup_migrate(leader, threadgroup, &mgctx); cgroup_migrate_finish(&mgctx); if (!ret) TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); return ret; } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *threadgroup_locked, struct cgroup *dst_cgrp) { struct task_struct *tsk; pid_t pid; bool force_migration = false; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL); /* * If we migrate a single thread, we don't care about threadgroup * stability. If the thread is `current`, it won't exit(2) under our * hands or change PID through exec(2). We exclude * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write * callers by cgroup_mutex. * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); *threadgroup_locked = pid || threadgroup; cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { tsk = ERR_PTR(-ESRCH); goto out_unlock_threadgroup; } } else { tsk = current; } if (threadgroup) tsk = tsk->group_leader; if (tsk->flags & PF_KTHREAD) trace_android_rvh_cgroup_force_kthread_migration(tsk, dst_cgrp, &force_migration); /* * kthreads may acquire PF_NO_SETAFFINITY during initialization. * If userland migrates such a kthread to a non-root cgroup, it can * become trapped in a cpuset, or RT kthread may be born in a * cgroup with no rt_runtime allocated. Just say no. */ if (!force_migration && (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY))) { tsk = ERR_PTR(-EINVAL); goto out_unlock_threadgroup; } get_task_struct(tsk); goto out_unlock_rcu; out_unlock_threadgroup: cgroup_attach_unlock(*threadgroup_locked); *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; /* release reference from cgroup_procs_write_start() */ put_task_struct(task); cgroup_attach_unlock(threadgroup_locked); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); } /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; } /* show controllers which are enabled for a given cgroup's children */ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0; } /** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; bool has_tasks; int ret; lockdep_assert_held(&cgroup_mutex); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; /* * As cgroup_update_dfl_csses() is only called by * cgroup_apply_control(). The csses associated with the * given cgrp will not be affected by changes made to * its subtree_control file. We can skip them. */ if (dsct == cgrp) continue; list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock); /* * We need to write-lock threadgroup_rwsem while migrating tasks. * However, if there are no source csets for @cgrp, changing its * controllers isn't gonna produce any task migrations and the * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(has_tasks); return ret; } /** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; restart: cgroup_lock(); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get_live(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); cgroup_unlock(); schedule(); finish_wait(&dsct->offline_waitq, &wait); cgroup_put(dsct); goto restart; } } } /** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; dsct->old_dom_cgrp = dsct->dom_cgrp; } } /** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */ static void cgroup_propagate_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); } } /** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; dsct->dom_cgrp = dsct->old_dom_cgrp; } } static bool css_visible(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; } /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); } WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } } return 0; } /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */ static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!css) continue; WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } } } /** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */ static int cgroup_apply_control(struct cgroup *cgrp) { int ret; cgroup_propagate_control(cgrp); ret = cgroup_apply_control_enable(cgrp); if (ret) return ret; /* * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ return cgroup_update_dfl_csses(cgrp); } /** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); } cgroup_apply_control_disable(cgrp); } static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) { u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; /* if nothing is getting enabled, nothing to worry about */ if (!enable) return 0; /* can @cgrp host any resources? */ if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) return -EOPNOTSUPP; /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return 0; if (domain_enable) { /* can't enable domain controllers inside a thread subtree */ if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return -EOPNOTSUPP; } else { /* * Threaded controllers can handle internal competitions * and are always allowed inside a (prospective) thread * subtree. */ if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return 0; } /* * Controllers can't be enabled for a cgroup with tasks to avoid * child cgroups competing against tasks. */ if (cgroup_has_tasks(cgrp)) return -EBUSY; return 0; } /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { u16 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret; /* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; } if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; } /* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } } if (!enable && !disable) { ret = 0; goto out_unlock; } ret = cgroup_vet_subtree_control_enable(cgrp, enable); if (ret) goto out_unlock; /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); if (ret) goto out_unlock; kernfs_activate(cgrp->kn); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } /** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; struct cgroup *dsct; struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); /* noop if already threaded */ if (cgroup_is_threaded(cgrp)) return 0; /* * If @cgroup is populated or has domain controllers enabled, it * can't be switched. While the below cgroup_can_be_thread_root() * test can catch the same conditions, that's only when @parent is * not mixable, so let's check it explicitly. */ if (cgroup_is_populated(cgrp) || cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return -EOPNOTSUPP; /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP; /* * The following shouldn't cause actual migrations and should * always succeed. */ cgroup_save_control(cgrp); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) if (dsct == cgrp || cgroup_is_threaded(dsct)) dsct->dom_cgrp = dom_cgrp; ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; cgroup_finalize_control(cgrp, ret); return ret; } static int cgroup_type_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; if (cgroup_is_threaded(cgrp)) seq_puts(seq, "threaded\n"); else if (!cgroup_is_valid_domain(cgrp)) seq_puts(seq, "domain invalid\n"); else if (cgroup_is_thread_root(cgrp)) seq_puts(seq, "domain threaded\n"); else seq_puts(seq, "domain\n"); return 0; } static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int ret; /* only switching to threaded mode is supported */ if (strcmp(strstrip(buf), "threaded")) return -EINVAL; /* drain dying csses before we re-apply (threaded) subtree control */ cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; /* threaded can only be enabled */ ret = cgroup_enable_threaded(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_max_descendants_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int descendants = READ_ONCE(cgrp->max_descendants); if (descendants == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", descendants); return 0; } static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int descendants; ssize_t ret; buf = strstrip(buf); if (!strcmp(buf, "max")) { descendants = INT_MAX; } else { ret = kstrtoint(buf, 0, &descendants); if (ret) return ret; } if (descendants < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_descendants = descendants; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_max_depth_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int depth = READ_ONCE(cgrp->max_depth); if (depth == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", depth); return 0; } static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int depth; buf = strstrip(buf); if (!strcmp(buf, "max")) { depth = INT_MAX; } else { ret = kstrtoint(buf, 0, &depth); if (ret) return ret; } if (depth < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_depth = depth; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_events_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags)); return 0; } static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants); seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); return 0; } static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid) { struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_extra_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_extra_stat_show(seq, css); css_put(css); return ret; } static int cpu_stat_show(struct seq_file *seq, void *v) { struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; cgroup_base_stat_cputime_show(seq); #ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id); #endif return ret; } #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; cgroup_get(cgrp); cgroup_kn_unlock(of->kn); /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { cgroup_put(cgrp); return -EBUSY; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); } smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; } static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_CPU); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IRQ); } static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IRQ); } #endif static int cgroup_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); seq_printf(seq, "%d\n", psi->enabled); return 0; } static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret; int enable; struct cgroup *cgrp; struct psi_group *psi; ret = kstrtoint(strstrip(buf), 0, &enable); if (ret) return ret; if (enable < 0 || enable > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; psi = cgroup_psi(cgrp); if (psi->enabled != enable) { int i; /* show or hide {cpu,memory,io,irq}.pressure files */ for (i = 0; i < NR_PSI_RESOURCES; i++) cgroup_file_show(&cgrp->psi_files[i], enable); psi->enabled = enable; if (enable) psi_cgroup_restart(psi); } cgroup_kn_unlock(of->kn); return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { struct cgroup_file_ctx *ctx = of->priv; return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } static int cgroup_pressure_open(struct kernfs_open_file *of) { return (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) ? -EPERM : 0; } static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) { if (static_branch_likely(&psi_disabled)) return false; return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } #else /* CONFIG_PSI */ bool cgroup_psi_enabled(void) { return false; } #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "%d\n", cgrp->freezer.freeze); return 0; } static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int freeze; ret = kstrtoint(strstrip(buf), 0, &freeze); if (ret) return ret; if (freeze < 0 || freeze > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgroup_freeze(cgrp, freeze); cgroup_kn_unlock(of->kn); return nbytes; } static void __cgroup_kill(struct cgroup *cgrp) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); set_bit(CGRP_KILL, &cgrp->flags); spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); while ((task = css_task_iter_next(&it))) { /* Ignore kernel threads here. */ if (task->flags & PF_KTHREAD) continue; /* Skip tasks that are already dying. */ if (__fatal_signal_pending(task)) continue; send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); spin_lock_irq(&css_set_lock); clear_bit(CGRP_KILL, &cgrp->flags); spin_unlock_irq(&css_set_lock); } static void cgroup_kill(struct cgroup *cgrp) { struct cgroup_subsys_state *css; struct cgroup *dsct; lockdep_assert_held(&cgroup_mutex); cgroup_for_each_live_descendant_pre(dsct, css, cgrp) __cgroup_kill(dsct); } static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret = 0; int kill; struct cgroup *cgrp; ret = kstrtoint(strstrip(buf), 0, &kill); if (ret) return ret; if (kill != 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; /* * Killing is a process directed operation, i.e. the whole thread-group * is taken down so act like we do for cgroup.procs and only make this * writable in non-threaded cgroups. */ if (cgroup_is_threaded(cgrp)) ret = -EOPNOTSUPP; else cgroup_kill(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); of->priv = ctx; if (!cft->open) return 0; ret = cft->open(of); if (ret) { put_cgroup_ns(ctx->ns); kfree(ctx); } return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; if (!nbytes) return 0; /* * If namespaces are delegation boundaries, disallow writes to * files in an non-init namespace root from inside the namespace * except for the files explicitly marked delegatable - * cgroup.procs and cgroup.subtree_control. */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) return cft->write(of, buf, nbytes, off); /* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock(); if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; } return ret ?: nbytes; } static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); return kernfs_generic_poll(of, pt); } static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { return seq_cft(seq)->seq_next(seq, v, ppos); } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { if (seq_cft(seq)->seq_stop) seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m); if (cft->seq_show) return cft->seq_show(m, arg); if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0; } static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show, }; /* set uid and gid of cgroup dirs and files to that of the creator */ static int cgroup_kn_set_ugid(struct kernfs_node *kn) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = current_fsuid(), .ia_gid = current_fsgid(), }; if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) return 0; return kernfs_setattr(kn, &iattr); } static void cgroup_file_notify_timer(struct timer_list *timer) { cgroup_file_notify(container_of(timer, struct cgroup_file, notify_timer)); } static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; int ret; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); ret = cgroup_kn_set_ugid(kn); if (ret) { kernfs_remove(kn); return ret; } if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); } return 0; } /** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */ static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { struct cftype *cft, *cft_end = NULL; int ret = 0; lockdep_assert_held(&cgroup_mutex); restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret; } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0; lockdep_assert_held(&cgroup_mutex); /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; } if (is_add && !ret) kernfs_activate(root->kn); return ret; } static void cgroup_exit_cftypes(struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL; /* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | __CFTYPE_ADDED); } } static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; int ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops; WARN_ON(cft->ss || cft->kf_ops); if (cft->flags & __CFTYPE_ADDED) { ret = -EBUSY; break; } if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops; /* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { ret = -ENOMEM; break; } kf_ops->atomic_write_len = cft->max_write_len; } cft->kf_ops = kf_ops; cft->ss = ss; cft->flags |= __CFTYPE_ADDED; } if (ret) cgroup_exit_cftypes(cfts); return ret; } static int cgroup_rm_cftypes_locked(struct cftype *cfts) { lockdep_assert_held(&cgroup_mutex); list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts); return 0; } /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */ int cgroup_rm_cftypes(struct cftype *cfts) { int ret; if (!cfts || cfts[0].name[0] == '\0') return 0; if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT; cgroup_lock(); ret = cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return ret; } /** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { int ret; if (!cgroup_ssid_enabled(ss->id)) return 0; if (!cfts || cfts[0].name[0] == '\0') return 0; ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret; cgroup_lock(); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return ret; } /** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } EXPORT_SYMBOL_GPL(cgroup_add_dfl_cftypes); /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts); } EXPORT_SYMBOL_GPL(cgroup_add_legacy_cftypes); /** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */ void cgroup_file_notify(struct cgroup_file *cfile) { unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); if (cfile->kn) { unsigned long last = cfile->notified_at; unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; if (time_in_range(jiffies, last, next)) { timer_reduce(&cfile->notify_timer, next); } else { kernfs_notify(cfile->kn); cfile->notified_at = jiffies; } } spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); } /** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */ void cgroup_file_show(struct cgroup_file *cfile, bool show) { struct kernfs_node *kn; spin_lock_irq(&cgroup_file_kn_lock); kn = cfile->kn; kernfs_get(kn); spin_unlock_irq(&cgroup_file_kn_lock); if (kn) kernfs_show(kn, show); kernfs_put(kn); } /** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling, lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; } /* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL; } EXPORT_SYMBOL_GPL(css_next_child); /** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; } return NULL; } EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct rightmost descendant as * long as @pos is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; cgroup_assert_mutex_or_rcu_locked(); do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; } static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last; do { last = pos; pos = css_next_child(NULL, pos); } while (pos); return last; } /** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @cgroup are accessible and @pos is a descendant of * @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ return pos->parent; } /** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */ bool css_has_online_children(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *child; bool ret = false; rcu_read_lock(); css_for_each_child(child, css) { if (child->flags & CSS_ONLINE) { ret = true; break; } } rcu_read_unlock(); return ret; } static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) { struct list_head *l; struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* find the next threaded cset */ if (it->tcset_pos) { l = it->tcset_pos->next; if (l != it->tcset_head) { it->tcset_pos = l; return container_of(l, struct css_set, threaded_csets_node); } it->tcset_pos = NULL; } /* find the next cset */ l = it->cset_pos; l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; return NULL; } if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; } it->cset_pos = l; /* initialize threaded css_set walking */ if (it->flags & CSS_TASK_ITER_THREADED) { if (it->cur_dcset) put_css_set_locked(it->cur_dcset); it->cur_dcset = cset; get_css_set(cset); it->tcset_head = &cset->threaded_csets; it->tcset_pos = &cset->threaded_csets; } return cset; } /** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set and find first non-empty tasks list*/ while ((cset = css_task_iter_next_css_set(it))) { if (!list_empty(&cset->tasks)) { it->cur_tasks_head = &cset->tasks; break; } else if (!list_empty(&cset->mg_tasks)) { it->cur_tasks_head = &cset->mg_tasks; break; } else if (!list_empty(&cset->dying_tasks)) { it->cur_tasks_head = &cset->dying_tasks; break; } } if (!cset) { it->task_pos = NULL; return; } it->task_pos = it->cur_tasks_head->next; /* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters); } static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task) { lockdep_assert_held(&css_set_lock); if (it->task_pos == &task->cg_list) { it->task_pos = it->task_pos->next; it->flags |= CSS_TASK_ITER_SKIPPED; } } static void css_task_iter_advance(struct css_task_iter *it) { struct task_struct *task; lockdep_assert_held(&css_set_lock); repeat: if (it->task_pos) { /* * Advance iterator to find next entry. We go through cset * tasks, mg_tasks and dying_tasks, when consumed we move onto * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next; if (it->task_pos == &it->cur_cset->tasks) { it->cur_tasks_head = &it->cur_cset->mg_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->mg_tasks) { it->cur_tasks_head = &it->cur_cset->dying_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it); } if (!it->task_pos) return; task = list_entry(it->task_pos, struct task_struct, cg_list); if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ if (!thread_group_leader(task)) goto repeat; /* and dying leaders w/o live member threads */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; } } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { memset(it, 0, sizeof(*it)); spin_lock_irq(&css_set_lock); it->ss = css->ss; it->flags = flags; if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links; it->cset_head = it->cset_pos; css_task_iter_advance(it); spin_unlock_irq(&css_set_lock); } /** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } spin_lock_irq(&css_set_lock); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); } spin_unlock_irq(&css_set_lock); return it->cur_task; } /** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) { if (it->cur_cset) { spin_lock_irq(&css_set_lock); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irq(&css_set_lock); } if (it->cur_dcset) put_css_set(it->cur_dcset); if (it->cur_task) put_task_struct(it->cur_task); } static void cgroup_procs_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; if (ctx->procs.started) css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags) { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_file_ctx *ctx = of->priv; struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); css_task_iter_start(&cgrp->self, iter_flags, it); ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); } else return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { struct cgroup *cgrp = seq_css(s)->cgroup; /* * All processes of a threaded subtree belong to the domain cgroup * of the subtree. Only threads can be distributed across the * subtree. Reject reads on cgroup.procs in the subtree proper. * They're always empty anyway. */ if (cgroup_is_threaded(cgrp)) return ERR_PTR(-EOPNOTSUPP); return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED); } static int cgroup_procs_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", task_pid_vnr(v)); return 0; } static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) { int ret; struct inode *inode; lockdep_assert_held(&cgroup_mutex); inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (!inode) return -ENOMEM; ret = inode_permission(&init_user_ns, inode, MAY_WRITE); iput(inode); return ret; } static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns) { struct cgroup *com_cgrp = src_cgrp; int ret; lockdep_assert_held(&cgroup_mutex); /* find the common ancestor */ while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) com_cgrp = cgroup_parent(com_cgrp); /* %current should be authorized to migrate to the common ancestor */ ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret; /* * If namespaces are delegation boundaries, %current must be able * to see both source and destination cgroups from its namespace. */ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) return -ENOENT; return 0; } static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns) { int ret = 0; ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret; ret = cgroup_migrate_vet_dst(dst_cgrp); if (ret) return ret; if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) ret = -EOPNOTSUPP; return ret; } static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; ssize_t ret; bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked, dst_cgrp); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* find the source cgroup */ spin_lock_irq(&css_set_lock); src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); /* * Process and thread migrations follow same delegation rule. Check * permissions using the credentials from file open to protect against * inherited fd attacks. */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup, ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); return ret; } static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, true) ?: nbytes; } static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) { return __cgroup_procs_start(s, pos, 0); } static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, false) ?: nbytes; } /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { { .name = "cgroup.type", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_type_show, .write = cgroup_type_write, }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { .name = "cgroup.threads", .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_threads_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { .name = "cgroup.max.descendants", .seq_show = cgroup_max_descendants_show, .write = cgroup_max_descendants_write, }, { .name = "cgroup.max.depth", .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, { .name = "cgroup.freeze", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_freeze_show, .write = cgroup_freeze_write, }, { .name = "cgroup.kill", .flags = CFTYPE_NOT_ON_ROOT, .write = cgroup_kill_write, }, { .name = "cpu.stat", .seq_show = cpu_stat_show, }, { } /* terminate */ }; static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .open = cgroup_pressure_open, .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .open = cgroup_pressure_open, .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .open = cgroup_pressure_open, .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #ifdef CONFIG_IRQ_TIME_ACCOUNTING { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .open = cgroup_pressure_open, .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #endif { .name = "cgroup.pressure", .seq_show = cgroup_pressure_show, .write = cgroup_pressure_write, }, #endif /* CONFIG_PSI */ { } /* terminate */ }; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_work_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */ static void css_free_rwork_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); if (ss) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id; ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); psi_cgroup_free(cgrp); cgroup_rstat_exit(cgrp); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } } } static void css_release_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; cgroup_lock(); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); if (ss) { /* css release path */ if (!list_empty(&css->rstat_css_node)) { cgroup_rstat_flush(cgrp); list_del_rcu(&css->rstat_css_node); } cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); } else { struct cgroup *tcgrp; /* cgroup release path */ TRACE_CGROUP_PATH(release, cgrp); cgroup_rstat_flush(cgrp); spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); } cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { lockdep_assert_held(&cgroup_mutex); cgroup_get_live(cgrp); memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); INIT_LIST_HEAD(&css->rstat_css_node); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); } if (ss->css_rstat_flush) list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list); BUG_ON(cgroup_css(cgrp, ss)); } /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); if (css->parent) atomic_inc(&css->parent->online_cnt); } return ret; } /* if the CSS is online, invoke ->css_offline() on it and mark it offline */ static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) return; if (ss->css_offline) ss->css_offline(css); css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); } /** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err; lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); if (!css) css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css; init_and_link_css(css, ss, cgrp); err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); err = online_css(css); if (err) goto err_list_del; return css; err_list_del: list_del_rcu(&css->sibling); err_free_css: list_del_rcu(&css->rstat_css_node); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); return ERR_PTR(err); } /* * The returned cgroup is fully initialized including its control mask, but * it isn't associated with its kernfs_node and doesn't have the control * mask applied. */ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; struct kernfs_node *kn; int level = parent->level + 1; int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; ret = cgroup_rstat_init(cgrp); if (ret) goto out_cancel_ref; /* create the directory */ kn = kernfs_create_dir(parent->kn, name, mode, cgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_stat_exit; } cgrp->kn = kn; init_cgroup_housekeeping(cgrp); cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; ret = psi_cgroup_alloc(cgrp); if (ret) goto out_kernfs_remove; ret = cgroup_bpf_inherit(cgrp); if (ret) goto out_psi_free; /* * New cgroup inherits effective freeze counter, and * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be * attached to the child cgroup, it will become frozen. * At this point the new cgroup is unpopulated, so we can * consider it frozen immediately. */ set_bit(CGRP_FREEZE, &cgrp->flags); set_bit(CGRP_FROZEN, &cgrp->flags); } spin_lock_irq(&css_set_lock); for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestors[tcgrp->level] = tcgrp; if (tcgrp != cgrp) { tcgrp->nr_descendants++; /* * If the new cgroup is frozen, all ancestor cgroups * get a new frozen descendant, but their state can't * change because of this. */ if (cgrp->freezer.e_freeze) tcgrp->freezer.nr_frozen_descendants++; } } spin_unlock_irq(&css_set_lock); if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); cgrp->self.serial_nr = css_serial_nr_next++; /* allocation complete, commit to creation */ list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); cgroup_propagate_control(cgrp); return cgrp; out_psi_free: psi_cgroup_free(cgrp); out_kernfs_remove: kernfs_remove(cgrp->kn); out_stat_exit: cgroup_rstat_exit(cgrp); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); } static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { struct cgroup *cgroup; int ret = false; int level = 1; lockdep_assert_held(&cgroup_mutex); for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail; if (level > cgroup->max_depth) goto fail; level++; } ret = true; fail: return ret; } int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL; parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; if (!cgroup_check_hierarchy_limits(parent)) { ret = -EAGAIN; goto out_unlock; } cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } /* * This extra ref will be put in cgroup_free_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(cgrp->kn); ret = cgroup_kn_set_ugid(cgrp->kn); if (ret) goto out_destroy; ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; out_destroy: cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; } /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); cgroup_lock(); do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); cgroup_unlock(); } /* css kill confirmation processing requires process context, bounce */ static void css_killed_ref_fn(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } } /** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */ static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) return; css->flags |= CSS_DYING; /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive * until after ->css_offline(). */ css_get(css); /* * cgroup core guarantees that, by the time ->css_offline() is * invoked, no new css reference will be given out via * css_tryget_online(). We can't simply call percpu_ref_kill() and * proceed to offlining css's because percpu_ref_kill() doesn't * guarantee that the ref is seen as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } /** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_lock_live_group(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); cgroup_bpf_offline(cgrp); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; }; int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; ret = cgroup_destroy_locked(cgrp); if (!ret) TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { struct cgroup_subsys_state *css; pr_debug("Initializing cgroup subsys %s\n", ss->name); cgroup_lock(); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); /* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF; if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); BUG_ON(online_css(css)); cgroup_unlock(); } /** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */ int __init cgroup_init_early(void) { static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i; ctx.root = &cgrp_dfl_root; init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss, true); } return 0; } /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */ int __init cgroup_init(void) { struct cgroup_subsys *ss; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); cgroup_rstat_boot(); get_user_ns(init_cgroup_ns.user_ns); cgroup_lock(); /* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); cgroup_unlock(); for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id]; css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); } list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]); /* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (!cgroup_ssid_enabled(ssid)) continue; if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", ss->name); cgrp_dfl_root.subsys_mask |= 1 << ss->id; /* implicit controllers must be threaded too */ WARN_ON(ss->implicit_on_dfl && !ss->threaded); if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->threaded) cgrp_dfl_threaded_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } if (ss->bind) ss->bind(init_css_set.subsys[ssid]); cgroup_lock(); css_populate_dir(init_css_set.subsys[ssid]); cgroup_unlock(); } /* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); #ifdef CONFIG_CPUSETS WARN_ON(register_filesystem(&cpuset_fs_type)); #endif return 0; } static int __init cgroup_wq_init(void) { /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); return 0; } core_initcall(cgroup_wq_init); void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); kernfs_put(kn); } /* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */ struct cgroup *cgroup_get_from_id(u64 id) { struct kernfs_node *kn; struct cgroup *cgrp, *root_cgrp; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return ERR_PTR(-ENOENT); if (kernfs_type(kn) != KERNFS_DIR) { kernfs_put(kn); return ERR_PTR(-ENOENT); } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL; rcu_read_unlock(); kernfs_put(kn); if (!cgrp) return ERR_PTR(-ENOENT); root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_id); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; int retval; struct cgroup_root *root; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; cgroup_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); cgrp = task_cgroup_from_root(tsk, root); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock; seq_puts(m, buf); } else { seq_puts(m, "/"); } if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); } retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); cgroup_unlock(); kfree(buf); out: return retval; } /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); } /** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); return css->cgroup; } /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } /** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) { int ret; struct cgroup *dst_cgrp = NULL; struct css_set *cset; struct super_block *sb; struct file *f; if (kargs->flags & CLONE_INTO_CGROUP) cgroup_lock(); cgroup_threadgroup_change_begin(current); spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { kargs->cset = cset; return 0; } f = fget_raw(kargs->cgroup); if (!f) { ret = -EBADF; goto err; } sb = f->f_path.dentry->d_sb; dst_cgrp = cgroup_get_from_file(f); if (IS_ERR(dst_cgrp)) { ret = PTR_ERR(dst_cgrp); dst_cgrp = NULL; goto err; } if (cgroup_is_dead(dst_cgrp)) { ret = -ENODEV; goto err; } /* * Verify that we the target cgroup is writable for us. This is * usually done by the vfs layer but since we're not going through * the vfs layer here we need to do it "manually". */ ret = cgroup_may_write(dst_cgrp, sb); if (ret) goto err; /* * Spawning a task directly into a cgroup works by passing a file * descriptor to the target cgroup directory. This can even be an O_PATH * file descriptor. But it can never be a cgroup.procs file descriptor. * This was done on purpose so spawning into a cgroup could be * conceptualized as an atomic * * fd = openat(dfd_cgroup, "cgroup.procs", ...); * write(fd, <child-pid>, ...); * * sequence, i.e. it's a shorthand for the caller opening and writing * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us * to always use the caller's credentials. */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); if (ret) goto err; kargs->cset = find_css_set(cset, dst_cgrp); if (!kargs->cset) { ret = -ENOMEM; goto err; } put_css_set(cset); fput(f); kargs->cgrp = dst_cgrp; return ret; err: cgroup_threadgroup_change_end(current); cgroup_unlock(); if (f) fput(f); if (dst_cgrp) cgroup_put(dst_cgrp); put_css_set(cset); if (kargs->cset) put_css_set(kargs->cset); return ret; } /** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset; cgroup_threadgroup_change_end(current); if (cset) { put_css_set(cset); kargs->cset = NULL; } if (kargs->flags & CLONE_INTO_CGROUP) { cgroup_unlock(); if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; } } } /** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i, j, ret; ret = cgroup_css_set_fork(kargs); if (ret) return ret; do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask(); return 0; out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); } cgroup_css_set_put_fork(kargs); return ret; } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); cgroup_css_set_put_fork(kargs); } /** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; struct css_set *cset; int i; cset = kargs->cset; kargs->cset = NULL; spin_lock_irq(&css_set_lock); /* init tasks are special, only link regular threads */ if (likely(child->pid)) { if (kargs->cgrp) cgrp_flags = kargs->cgrp->flags; else cgrp_flags = cset->dfl_cgrp->flags; WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } else { put_css_set(cset); cset = NULL; } if (!(child->flags & PF_KTHREAD)) { if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { /* * If the cgroup has to be frozen, the new task has * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to * get the task into the frozen state. */ spin_lock(&child->sighand->siglock); WARN_ON_ONCE(child->frozen); child->jobctl |= JOBCTL_TRAP_FREEZE; spin_unlock(&child->sighand->siglock); /* * Calling cgroup_update_frozen() isn't required here, * because it will be called anyway a bit later from * do_freezer_trap(). So we avoid cgroup's transient * switch from the frozen state and back. */ } /* * If the cgroup is to be killed notice it now and take the * child down right after we finished preparing it for * userspace. */ kill = test_bit(CGRP_KILL, &cgrp_flags); } spin_unlock_irq(&css_set_lock); /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); /* Make the new cset the root_cset of the new cgroup namespace. */ if (kargs->flags & CLONE_NEWCGROUP) { struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; get_css_set(cset); child->nsproxy->cgroup_ns->root_cset = cset; put_css_set(rcset); } /* Cgroup has to be killed so take down child immediately. */ if (unlikely(kill)) do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID); cgroup_css_set_put_fork(kargs); } /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */ void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; int i; spin_lock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); list_add_tail(&tsk->cg_list, &cset->dying_tasks); cset->nr_tasks--; if (dl_task(tsk)) dec_dl_tasks_cs(tsk); WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) cgroup_update_frozen(task_dfl_cgroup(tsk)); spin_unlock_irq(&css_set_lock); /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask(); } void cgroup_release(struct task_struct *task) { struct cgroup_subsys *ss; int ssid; do_each_subsys_mask(ss, ssid, have_release_callback) { ss->release(task); } while_each_subsys_mask(); spin_lock_irq(&css_set_lock); css_set_skip_task_iters(task_css_set(task), task); list_del_init(&task->cg_list); spin_unlock_irq(&css_set_lock); } void cgroup_free(struct task_struct *task) { struct css_set *cset = task_css_set(task); put_css_set(cset); } static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; static_branch_disable(cgroup_subsys_enabled_key[i]); pr_info("Disabling %s control group subsystem\n", ss->name); } for (i = 0; i < OPT_FEATURE_COUNT; i++) { if (strcmp(token, cgroup_opt_feature_names[i])) continue; cgroup_feature_disable_mask |= 1 << i; pr_info("Disabling %s control group feature\n", cgroup_opt_feature_names[i]); break; } } return 1; } __setup("cgroup_disable=", cgroup_disable); void __init __weak enable_debug_cgroup(void) { } static int __init enable_cgroup_debug(char *str) { cgroup_debug = true; enable_debug_cgroup(); return 1; } __setup("cgroup_debug", enable_cgroup_debug); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); /* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT); rcu_read_unlock(); return css; } /** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); return idr_find(&ss->css_idr, id); } /** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); if (!kn) goto out; if (kernfs_type(kn) != KERNFS_DIR) { cgrp = ERR_PTR(-ENOTDIR); goto out_kernfs; } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); rcu_read_unlock(); out_kernfs: kernfs_put(kn); out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { struct cgroup *cgrp; struct file *f; f = fget_raw(fd); if (!f) return ERR_PTR(-EBADF); cgrp = cgroup_v1v2_get_from_file(f); fput(f); return cgrp; } /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) { u64 v = 1; while (power--) v *= 10; return v; } /** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) { s64 whole, frac = 0; int fstart = 0, fend = 0, flen; if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) return -EINVAL; if (frac < 0) return -EINVAL; flen = fend > fstart ? fend - fstart : 0; if (flen < dec_shift) frac *= power_of_ten(dec_shift - flen); else frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift)); *v = whole * power_of_ten(dec_shift) + frac; return 0; } /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { struct cgroup *cgroup; rcu_read_lock(); /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) { cgroup = &cgrp_dfl_root.cgrp; cgroup_get(cgroup); goto out; } while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { cgroup = cset->dfl_cgrp; break; } cpu_relax(); } out: skcd->cgroup = cgroup; cgroup_bpf_get(cgroup); rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); /* * We might be cloning a socket which is left in an empty * cgroup and the cgroup might have already been rmdir'd. * Don't use cgroup_get_live(). */ cgroup_get(cgrp); cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); cgroup_bpf_put(cgrp); cgroup_put(cgrp); } #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) { struct cftype *cft; ssize_t ret = 0; for (cft = files; cft && cft->name[0] != '\0'; cft++) { if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) continue; if (prefix) ret += snprintf(buf + ret, size - ret, "%s.", prefix); ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); if (WARN_ON(ret >= size)) break; } return ret; } static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct cgroup_subsys *ss; int ssid; ssize_t ret = 0; ret = show_delegatable_files(cgroup_base_files, buf + ret, PAGE_SIZE - ret, NULL); if (cgroup_psi_enabled()) ret += show_delegatable_files(cgroup_psi_files, buf + ret, PAGE_SIZE - ret, NULL); for_each_subsys(ss, ssid) ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, PAGE_SIZE - ret, cgroup_subsys_name[ssid]); return ret; } static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "nsdelegate\n" "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, &cgroup_features_attr.attr, NULL, }; static const struct attribute_group cgroup_sysfs_attr_group = { .attrs = cgroup_sysfs_attrs, .name = "cgroup", }; static int __init cgroup_sysfs_init(void) { return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); } subsys_initcall(cgroup_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 184 279 6 55 115 21 198 8 11 3 3 3 5 18 109 358 68 101 12 540 15 541 129 45 495 14 478 307 307 264 128 216 41 144 186 167 201 184 536 67 524 2 56 219 305 306 539 538 184 184 6 181 151 69 95 95 14 6 8 6 12 8 22 22 6 1 3 5 382 219 259 408 196 196 196 195 449 447 447 449 447 121 121 2136 2136 225 124 35 36 115 5 16 298 40 40 283 20 21 214 297 39 33 39 33 28 28 39 39 39 39 39 33 131 110 110 22 207 207 106 98 21 17 80 79 80 38 30 9 3 111 47 5 1 4 4 4 20 20 9 4 5 11 85 1 1 1 1 1 1 78 1 12 12 9 1 8 9 3 6 6 1 5 156 1 1 1 39 42 8 8 114 1 116 116 2 104 32 42 62 9 63 26 1 103 48 47 3 39 32 39 11 11 4 35 40 39 3 31 11 31 7 6 3 29 5 29 5 1 29 39 35 1 1 2 31 27 15 3 3 70 1 1 1 1 1 1 1 63 58 58 3 1 42 13 3 38 36 3 1 31 3 28 21 6 12 8 1 7 169 1 162 19 146 95 84 17 2 2 2 2 134 134 17 17 8 9 95 72 3 3 45 20 20 28 17 94 44 3 3 1 1 5 4 4 1 3 1 17 17 11 5 1 17 11 6 16 11 6 17 12 5 5 1 4 7 4 3 5 56 1 1 45 21 36 23 2 19 14 24 43 1 1 40 15 31 26 1 21 17 135 1 1 1 132 50 21 32 4 32 32 13 13 10 9 37 1 36 2 2 27 19 20 12 75 1 1 5 68 4 4 55 20 47 1 1 1 3 41 22 4 5 3 4 3 3 9 7 2 1 7 19 17 1 1 14 1 4 1 3 5 29 1 27 1 1 1 1 24 22 22 21 16 19 9 3 2 2 2 2 11 1 61 37 3 33 18 8 17 28 36 3 24 43 2 37 18 16 37 17 18 20 5 14 5 2 12 542 538 544 545 408 547 169 408 194 94 75 19 106 106 19 298 298 297 295 103 16 194 257 360 360 269 253 98 549 1 544 5 188 360 556 1 3 552 572 570 570 8 3 2 6 555 619 23 5 584 13 2 597 9 2 3 572 10 199 198 199 198 199 60 5 56 5 60 59 1 406 243 632 75 6 354 1 198 6 448 83 82 40 40 3 2 1 1 36 1 21 1 39 39 36 21 21 7 15 22 5 5 4 1 3 2 23 1 40 24 3 7 13 7 88 88 20 86 2 2 86 3 88 88 84 1 1 1 1 1 1 1 1 1 1 3662 3663 1 142 142 2 641 644 451 195 1 472 402 7 67 68 24 1 2 4 7 3 2 5 5 2 1 84 67 1 1 79 74 4 4 5 2 1 3 6 6 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018 Facebook */ #include <uapi/linux/btf.h> #include <uapi/linux/bpf.h> #include <uapi/linux/android_fuse.h> #include <uapi/linux/bpf_perf_event.h> #include <uapi/linux/types.h> #include <linux/seq_file.h> #include <linux/compiler.h> #include <linux/ctype.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/sort.h> #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/skmsg.h> #include <linux/perf_event.h> #include <linux/bsearch.h> #include <linux/kobject.h> #include <linux/sysfs.h> #include <net/sock.h> #include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes * the data types of BPF program/map. Hence, it basically focus * on the C programming language which the modern BPF is primary * using. * * ELF Section: * ~~~~~~~~~~~ * The BTF data is stored under the ".BTF" ELF section * * struct btf_type: * ~~~~~~~~~~~~~~~ * Each 'struct btf_type' object describes a C data type. * Depending on the type it is describing, a 'struct btf_type' * object may be followed by more data. F.e. * To describe an array, 'struct btf_type' is followed by * 'struct btf_array'. * * 'struct btf_type' and any extra data following it are * 4 bytes aligned. * * Type section: * ~~~~~~~~~~~~~ * The BTF type section contains a list of 'struct btf_type' objects. * Each one describes a C type. Recall from the above section * that a 'struct btf_type' object could be immediately followed by extra * data in order to describe some particular C types. * * type_id: * ~~~~~~~ * Each btf_type object is identified by a type_id. The type_id * is implicitly implied by the location of the btf_type object in * the BTF type section. The first one has type_id 1. The second * one has type_id 2...etc. Hence, an earlier btf_type has * a smaller type_id. * * A btf_type object may refer to another btf_type object by using * type_id (i.e. the "type" in the "struct btf_type"). * * NOTE that we cannot assume any reference-order. * A btf_type object can refer to an earlier btf_type object * but it can also refer to a later btf_type object. * * For example, to describe "const void *". A btf_type * object describing "const" may refer to another btf_type * object describing "void *". This type-reference is done * by specifying type_id: * * [1] CONST (anon) type_id=2 * [2] PTR (anon) type_id=0 * * The above is the btf_verifier debug log: * - Each line started with "[?]" is a btf_type object * - [?] is the type_id of the btf_type object. * - CONST/PTR is the BTF_KIND_XXX * - "(anon)" is the name of the type. It just * happens that CONST and PTR has no name. * - type_id=XXX is the 'u32 type' in btf_type * * NOTE: "void" has type_id 0 * * String section: * ~~~~~~~~~~~~~~ * The BTF string section contains the names used by the type section. * Each string is referred by an "offset" from the beginning of the * string section. * * Each string is '\0' terminated. * * The first character in the string section must be '\0' * which is used to mean 'anonymous'. Some btf_type may not * have a name. */ /* BTF verification: * * To verify BTF data, two passes are needed. * * Pass #1 * ~~~~~~~ * The first pass is to collect all btf_type objects to * an array: "btf->types". * * Depending on the C type that a btf_type is describing, * a btf_type may be followed by extra data. We don't know * how many btf_type is there, and more importantly we don't * know where each btf_type is located in the type section. * * Without knowing the location of each type_id, most verifications * cannot be done. e.g. an earlier btf_type may refer to a later * btf_type (recall the "const void *" above), so we cannot * check this type-reference in the first pass. * * In the first pass, it still does some verifications (e.g. * checking the name is a valid offset to the string section). * * Pass #2 * ~~~~~~~ * The main focus is to resolve a btf_type that is referring * to another type. * * We have to ensure the referring type: * 1) does exist in the BTF (i.e. in btf->types[]) * 2) does not cause a loop: * struct A { * struct B b; * }; * * struct B { * struct A a; * }; * * btf_type_needs_resolve() decides if a btf_type needs * to be resolved. * * The needs_resolve type implements the "resolve()" ops which * essentially does a DFS and detects backedge. * * During resolve (or DFS), different C types have different * "RESOLVED" conditions. * * When resolving a BTF_KIND_STRUCT, we need to resolve all its * members because a member is always referring to another * type. A struct's member can be treated as "RESOLVED" if * it is referring to a BTF_KIND_PTR. Otherwise, the * following valid C struct would be rejected: * * struct A { * int m; * struct A *a; * }; * * When resolving a BTF_KIND_PTR, it needs to keep resolving if * it is referring to another BTF_KIND_PTR. Otherwise, we cannot * detect a pointer loop, e.g.: * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR + * ^ | * +-----------------------------------------+ * */ #define BITS_PER_U128 (sizeof(u64) * BITS_PER_BYTE * 2) #define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) #define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) #define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) #define BITS_ROUNDUP_BYTES(bits) \ (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) #define BTF_INFO_MASK 0x9f00ffff #define BTF_INT_MASK 0x0fffffff #define BTF_TYPE_ID_VALID(type_id) ((type_id) <= BTF_MAX_TYPE) #define BTF_STR_OFFSET_VALID(name_off) ((name_off) <= BTF_MAX_NAME_OFFSET) /* 16MB for 64k structs and each has 16 members and * a few MB spaces for the string section. * The hard limit is S32_MAX. */ #define BTF_MAX_SIZE (16 * 1024 * 1024) #define for_each_member_from(i, from, struct_type, member) \ for (i = from, member = btf_type_member(struct_type) + from; \ i < btf_type_vlen(struct_type); \ i++, member++) #define for_each_vsi_from(i, from, struct_type, member) \ for (i = from, member = btf_type_var_secinfo(struct_type) + from; \ i < btf_type_vlen(struct_type); \ i++, member++) DEFINE_IDR(btf_idr); DEFINE_SPINLOCK(btf_idr_lock); enum btf_kfunc_hook { BTF_KFUNC_HOOK_XDP, BTF_KFUNC_HOOK_TC, BTF_KFUNC_HOOK_STRUCT_OPS, BTF_KFUNC_HOOK_TRACING, BTF_KFUNC_HOOK_SYSCALL, BTF_KFUNC_HOOK_MAX, }; enum { BTF_KFUNC_SET_MAX_CNT = 256, BTF_DTOR_KFUNC_MAX_CNT = 256, }; struct btf_kfunc_set_tab { struct btf_id_set8 *sets[BTF_KFUNC_HOOK_MAX]; }; struct btf_id_dtor_kfunc_tab { u32 cnt; struct btf_id_dtor_kfunc dtors[]; }; struct btf { void *data; struct btf_type **types; u32 *resolved_ids; u32 *resolved_sizes; const char *strings; void *nohdr_data; struct btf_header hdr; u32 nr_types; /* includes VOID for base BTF */ u32 types_size; u32 data_size; refcount_t refcnt; u32 id; struct rcu_head rcu; struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; /* split BTF support */ struct btf *base_btf; u32 start_id; /* first type ID in this BTF (0 for base BTF) */ u32 start_str_off; /* first string offset (0 for base BTF) */ char name[MODULE_NAME_LEN]; bool kernel_btf; }; enum verifier_phase { CHECK_META, CHECK_TYPE, }; struct resolve_vertex { const struct btf_type *t; u32 type_id; u16 next_member; }; enum visit_state { NOT_VISITED, VISITED, RESOLVED, }; enum resolve_mode { RESOLVE_TBD, /* To Be Determined */ RESOLVE_PTR, /* Resolving for Pointer */ RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union * or array */ }; #define MAX_RESOLVE_DEPTH 32 struct btf_sec_info { u32 off; u32 len; }; struct btf_verifier_env { struct btf *btf; u8 *visit_states; struct resolve_vertex stack[MAX_RESOLVE_DEPTH]; struct bpf_verifier_log log; u32 log_type_id; u32 top_stack; enum verifier_phase phase; enum resolve_mode resolve_mode; }; static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_UNKN] = "UNKNOWN", [BTF_KIND_INT] = "INT", [BTF_KIND_PTR] = "PTR", [BTF_KIND_ARRAY] = "ARRAY", [BTF_KIND_STRUCT] = "STRUCT", [BTF_KIND_UNION] = "UNION", [BTF_KIND_ENUM] = "ENUM", [BTF_KIND_FWD] = "FWD", [BTF_KIND_TYPEDEF] = "TYPEDEF", [BTF_KIND_VOLATILE] = "VOLATILE", [BTF_KIND_CONST] = "CONST", [BTF_KIND_RESTRICT] = "RESTRICT", [BTF_KIND_FUNC] = "FUNC", [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", [BTF_KIND_DECL_TAG] = "DECL_TAG", [BTF_KIND_TYPE_TAG] = "TYPE_TAG", [BTF_KIND_ENUM64] = "ENUM64", }; const char *btf_type_str(const struct btf_type *t) { return btf_kind_str[BTF_INFO_KIND(t->info)]; } /* Chunk size we use in safe copy of data to be shown. */ #define BTF_SHOW_OBJ_SAFE_SIZE 32 /* * This is the maximum size of a base type value (equivalent to a * 128-bit int); if we are at the end of our safe buffer and have * less than 16 bytes space we can't be assured of being able * to copy the next type safely, so in such cases we will initiate * a new copy. */ #define BTF_SHOW_OBJ_BASE_TYPE_SIZE 16 /* Type name size */ #define BTF_SHOW_NAME_SIZE 80 /* * Common data to all BTF show operations. Private show functions can add * their own data to a structure containing a struct btf_show and consult it * in the show callback. See btf_type_show() below. * * One challenge with showing nested data is we want to skip 0-valued * data, but in order to figure out whether a nested object is all zeros * we need to walk through it. As a result, we need to make two passes * when handling structs, unions and arrays; the first path simply looks * for nonzero data, while the second actually does the display. The first * pass is signalled by show->state.depth_check being set, and if we * encounter a non-zero value we set show->state.depth_to_show to * the depth at which we encountered it. When we have completed the * first pass, we will know if anything needs to be displayed if * depth_to_show > depth. See btf_[struct,array]_show() for the * implementation of this. * * Another problem is we want to ensure the data for display is safe to * access. To support this, the anonymous "struct {} obj" tracks the data * object and our safe copy of it. We copy portions of the data needed * to the object "copy" buffer, but because its size is limited to * BTF_SHOW_OBJ_COPY_LEN bytes, multiple copies may be required as we * traverse larger objects for display. * * The various data type show functions all start with a call to * btf_show_start_type() which returns a pointer to the safe copy * of the data needed (or if BTF_SHOW_UNSAFE is specified, to the * raw data itself). btf_show_obj_safe() is responsible for * using copy_from_kernel_nofault() to update the safe data if necessary * as we traverse the object's data. skbuff-like semantics are * used: * * - obj.head points to the start of the toplevel object for display * - obj.size is the size of the toplevel object * - obj.data points to the current point in the original data at * which our safe data starts. obj.data will advance as we copy * portions of the data. * * In most cases a single copy will suffice, but larger data structures * such as "struct task_struct" will require many copies. The logic in * btf_show_obj_safe() handles the logic that determines if a new * copy_from_kernel_nofault() is needed. */ struct btf_show { u64 flags; void *target; /* target of show operation (seq file, buffer) */ void (*showfn)(struct btf_show *show, const char *fmt, va_list args); const struct btf *btf; /* below are used during iteration */ struct { u8 depth; u8 depth_to_show; u8 depth_check; u8 array_member:1, array_terminated:1; u16 array_encoding; u32 type_id; int status; /* non-zero for error */ const struct btf_type *type; const struct btf_member *member; char name[BTF_SHOW_NAME_SIZE]; /* space for member name/type */ } state; struct { u32 size; void *head; void *data; u8 safe[BTF_SHOW_OBJ_SAFE_SIZE]; } obj; }; struct btf_kind_operations { s32 (*check_meta)(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left); int (*resolve)(struct btf_verifier_env *env, const struct resolve_vertex *v); int (*check_member)(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type); int (*check_kflag_member)(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type); void (*log_details)(struct btf_verifier_env *env, const struct btf_type *t); void (*show)(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offsets, struct btf_show *show); }; static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; static struct btf_type btf_void; static int btf_resolve(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id); static int btf_func_check(struct btf_verifier_env *env, const struct btf_type *t); static bool btf_type_is_modifier(const struct btf_type *t) { /* Some of them is not strictly a C modifier * but they are grouped into the same bucket * for BTF concern: * A type (t) that refers to another * type through t->type AND its size cannot * be determined without following the t->type. * * ptr does not fall into this bucket * because its size is always sizeof(void *). */ switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_TYPE_TAG: return true; } return false; } bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void; } static bool btf_type_is_fwd(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FWD; } static bool btf_type_nosize(const struct btf_type *t) { return btf_type_is_void(t) || btf_type_is_fwd(t) || btf_type_is_func(t) || btf_type_is_func_proto(t); } static bool btf_type_nosize_or_null(const struct btf_type *t) { return !t || btf_type_nosize(t); } static bool __btf_type_is_struct(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; } static bool btf_type_is_array(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; } static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } static bool btf_type_is_decl_tag(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; } static bool btf_type_is_decl_tag_target(const struct btf_type *t) { return btf_type_is_func(t) || btf_type_is_struct(t) || btf_type_is_var(t) || btf_type_is_typedef(t); } u32 btf_nr_types(const struct btf *btf) { u32 total = 0; while (btf) { total += btf->nr_types; btf = btf->base_btf; } return total; } s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) { const struct btf_type *t; const char *tname; u32 i, total; total = btf_nr_types(btf); for (i = 1; i < total; i++) { t = btf_type_by_id(btf, i); if (BTF_INFO_KIND(t->info) != kind) continue; tname = btf_name_by_offset(btf, t->name_off); if (!strcmp(tname, name)) return i; } return -ENOENT; } static s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p) { struct btf *btf; s32 ret; int id; btf = bpf_get_btf_vmlinux(); if (IS_ERR(btf)) return PTR_ERR(btf); if (!btf) return -EINVAL; ret = btf_find_by_name_kind(btf, name, kind); /* ret is never zero, since btf_find_by_name_kind returns * positive btf_id or negative error. */ if (ret > 0) { btf_get(btf); *btf_p = btf; return ret; } /* If name is not found in vmlinux's BTF then search in module's BTFs */ spin_lock_bh(&btf_idr_lock); idr_for_each_entry(&btf_idr, btf, id) { if (!btf_is_module(btf)) continue; /* linear search could be slow hence unlock/lock * the IDR to avoiding holding it for too long */ btf_get(btf); spin_unlock_bh(&btf_idr_lock); ret = btf_find_by_name_kind(btf, name, kind); if (ret > 0) { *btf_p = btf; return ret; } btf_put(btf); spin_lock_bh(&btf_idr_lock); } spin_unlock_bh(&btf_idr_lock); return ret; } const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, u32 id, u32 *res_id) { const struct btf_type *t = btf_type_by_id(btf, id); while (btf_type_is_modifier(t)) { id = t->type; t = btf_type_by_id(btf, t->type); } if (res_id) *res_id = id; return t; } const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, u32 id, u32 *res_id) { const struct btf_type *t; t = btf_type_skip_modifiers(btf, id, NULL); if (!btf_type_is_ptr(t)) return NULL; return btf_type_skip_modifiers(btf, t->type, res_id); } const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, u32 id, u32 *res_id) { const struct btf_type *ptype; ptype = btf_type_resolve_ptr(btf, id, res_id); if (ptype && btf_type_is_func_proto(ptype)) return ptype; return NULL; } /* Types that act only as a source, not sink or intermediate * type when resolving. */ static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } /* What types need to be resolved? * * btf_type_is_modifier() is an obvious one. * * btf_type_is_struct() because its member refers to * another type (through member->type). * * btf_type_is_var() because the variable refers to * another type. btf_type_is_datasec() holds multiple * btf_type_is_var() types that need resolving. * * btf_type_is_array() because its element (array->type) * refers to another type. Array can be thought of a * special case of struct while array just has the same * member-type repeated by array->nelems of times. */ static bool btf_type_needs_resolve(const struct btf_type *t) { return btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || btf_type_is_func(t) || btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } /* t->size can be used */ static bool btf_type_has_size(const struct btf_type *t) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_DATASEC: case BTF_KIND_FLOAT: case BTF_KIND_ENUM64: return true; } return false; } static const char *btf_int_encoding_str(u8 encoding) { if (encoding == 0) return "(none)"; else if (encoding == BTF_INT_SIGNED) return "SIGNED"; else if (encoding == BTF_INT_CHAR) return "CHAR"; else if (encoding == BTF_INT_BOOL) return "BOOL"; else return "UNKN"; } static u32 btf_type_int(const struct btf_type *t) { return *(u32 *)(t + 1); } static const struct btf_array *btf_type_array(const struct btf_type *t) { return (const struct btf_array *)(t + 1); } static const struct btf_enum *btf_type_enum(const struct btf_type *t) { return (const struct btf_enum *)(t + 1); } static const struct btf_var *btf_type_var(const struct btf_type *t) { return (const struct btf_var *)(t + 1); } static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) { return (const struct btf_decl_tag *)(t + 1); } static const struct btf_enum64 *btf_type_enum64(const struct btf_type *t) { return (const struct btf_enum64 *)(t + 1); } static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; } static bool btf_name_offset_valid(const struct btf *btf, u32 offset) { if (!BTF_STR_OFFSET_VALID(offset)) return false; while (offset < btf->start_str_off) btf = btf->base_btf; offset -= btf->start_str_off; return offset < btf->hdr.str_len; } static bool __btf_name_char_ok(char c, bool first) { if ((first ? !isalpha(c) : !isalnum(c)) && c != '_' && c != '.') return false; return true; } static const char *btf_str_by_offset(const struct btf *btf, u32 offset) { while (offset < btf->start_str_off) btf = btf->base_btf; offset -= btf->start_str_off; if (offset < btf->hdr.str_len) return &btf->strings[offset]; return NULL; } static bool __btf_name_valid(const struct btf *btf, u32 offset) { /* offset must be valid */ const char *src = btf_str_by_offset(btf, offset); const char *src_limit; if (!__btf_name_char_ok(*src, true)) return false; /* set a limit on identifier length */ src_limit = src + KSYM_NAME_LEN; src++; while (*src && src < src_limit) { if (!__btf_name_char_ok(*src, false)) return false; src++; } return !*src; } static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) { return __btf_name_valid(btf, offset); } static bool btf_name_valid_section(const struct btf *btf, u32 offset) { return __btf_name_valid(btf, offset); } static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) { const char *name; if (!offset) return "(anon)"; name = btf_str_by_offset(btf, offset); return name ?: "(invalid-name-offset)"; } const char *btf_name_by_offset(const struct btf *btf, u32 offset) { return btf_str_by_offset(btf, offset); } const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) { while (type_id < btf->start_id) btf = btf->base_btf; type_id -= btf->start_id; if (type_id >= btf->nr_types) return NULL; return btf->types[type_id]; } EXPORT_SYMBOL_GPL(btf_type_by_id); /* * Regular int is not a bit field and it must be either * u8/u16/u32/u64 or __int128. */ static bool btf_type_int_is_regular(const struct btf_type *t) { u8 nr_bits, nr_bytes; u32 int_data; int_data = btf_type_int(t); nr_bits = BTF_INT_BITS(int_data); nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); if (BITS_PER_BYTE_MASKED(nr_bits) || BTF_INT_OFFSET(int_data) || (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) && nr_bytes != (2 * sizeof(u64)))) { return false; } return true; } /* * Check that given struct member is a regular int with expected * offset and size. */ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size) { const struct btf_type *t; u32 id, int_data; u8 nr_bits; id = m->type; t = btf_type_id_size(btf, &id, NULL); if (!t || !btf_type_is_int(t)) return false; int_data = btf_type_int(t); nr_bits = BTF_INT_BITS(int_data); if (btf_type_kflag(s)) { u32 bitfield_size = BTF_MEMBER_BITFIELD_SIZE(m->offset); u32 bit_offset = BTF_MEMBER_BIT_OFFSET(m->offset); /* if kflag set, int should be a regular int and * bit offset should be at byte boundary. */ return !bitfield_size && BITS_ROUNDUP_BYTES(bit_offset) == expected_offset && BITS_ROUNDUP_BYTES(nr_bits) == expected_size; } if (BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(m->offset) || BITS_ROUNDUP_BYTES(m->offset) != expected_offset || BITS_PER_BYTE_MASKED(nr_bits) || BITS_ROUNDUP_BYTES(nr_bits) != expected_size) return false; return true; } /* Similar to btf_type_skip_modifiers() but does not skip typedefs. */ static const struct btf_type *btf_type_skip_qualifiers(const struct btf *btf, u32 id) { const struct btf_type *t = btf_type_by_id(btf, id); while (btf_type_is_modifier(t) && BTF_INFO_KIND(t->info) != BTF_KIND_TYPEDEF) { t = btf_type_by_id(btf, t->type); } return t; } #define BTF_SHOW_MAX_ITER 10 #define BTF_KIND_BIT(kind) (1ULL << kind) /* * Populate show->state.name with type name information. * Format of type name is * * [.member_name = ] (type_name) */ static const char *btf_show_name(struct btf_show *show) { /* BTF_MAX_ITER array suffixes "[]" */ const char *array_suffixes = "[][][][][][][][][][]"; const char *array_suffix = &array_suffixes[strlen(array_suffixes)]; /* BTF_MAX_ITER pointer suffixes "*" */ const char *ptr_suffixes = "**********"; const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)]; const char *name = NULL, *prefix = "", *parens = ""; const struct btf_member *m = show->state.member; const struct btf_type *t; const struct btf_array *array; u32 id = show->state.type_id; const char *member = NULL; bool show_member = false; u64 kinds = 0; int i; show->state.name[0] = '\0'; /* * Don't show type name if we're showing an array member; * in that case we show the array type so don't need to repeat * ourselves for each member. */ if (show->state.array_member) return ""; /* Retrieve member name, if any. */ if (m) { member = btf_name_by_offset(show->btf, m->name_off); show_member = strlen(member) > 0; id = m->type; } /* * Start with type_id, as we have resolved the struct btf_type * * via btf_modifier_show() past the parent typedef to the child * struct, int etc it is defined as. In such cases, the type_id * still represents the starting type while the struct btf_type * * in our show->state points at the resolved type of the typedef. */ t = btf_type_by_id(show->btf, id); if (!t) return ""; /* * The goal here is to build up the right number of pointer and * array suffixes while ensuring the type name for a typedef * is represented. Along the way we accumulate a list of * BTF kinds we have encountered, since these will inform later * display; for example, pointer types will not require an * opening "{" for struct, we will just display the pointer value. * * We also want to accumulate the right number of pointer or array * indices in the format string while iterating until we get to * the typedef/pointee/array member target type. * * We start by pointing at the end of pointer and array suffix * strings; as we accumulate pointers and arrays we move the pointer * or array string backwards so it will show the expected number of * '*' or '[]' for the type. BTF_SHOW_MAX_ITER of nesting of pointers * and/or arrays and typedefs are supported as a precaution. * * We also want to get typedef name while proceeding to resolve * type it points to so that we can add parentheses if it is a * "typedef struct" etc. */ for (i = 0; i < BTF_SHOW_MAX_ITER; i++) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_TYPEDEF: if (!name) name = btf_name_by_offset(show->btf, t->name_off); kinds |= BTF_KIND_BIT(BTF_KIND_TYPEDEF); id = t->type; break; case BTF_KIND_ARRAY: kinds |= BTF_KIND_BIT(BTF_KIND_ARRAY); parens = "["; if (!t) return ""; array = btf_type_array(t); if (array_suffix > array_suffixes) array_suffix -= 2; id = array->type; break; case BTF_KIND_PTR: kinds |= BTF_KIND_BIT(BTF_KIND_PTR); if (ptr_suffix > ptr_suffixes) ptr_suffix -= 1; id = t->type; break; default: id = 0; break; } if (!id) break; t = btf_type_skip_qualifiers(show->btf, id); } /* We may not be able to represent this type; bail to be safe */ if (i == BTF_SHOW_MAX_ITER) return ""; if (!name) name = btf_name_by_offset(show->btf, t->name_off); switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_STRUCT: case BTF_KIND_UNION: prefix = BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT ? "struct" : "union"; /* if it's an array of struct/union, parens is already set */ if (!(kinds & (BTF_KIND_BIT(BTF_KIND_ARRAY)))) parens = "{"; break; case BTF_KIND_ENUM: case BTF_KIND_ENUM64: prefix = "enum"; break; default: break; } /* pointer does not require parens */ if (kinds & BTF_KIND_BIT(BTF_KIND_PTR)) parens = ""; /* typedef does not require struct/union/enum prefix */ if (kinds & BTF_KIND_BIT(BTF_KIND_TYPEDEF)) prefix = ""; if (!name) name = ""; /* Even if we don't want type name info, we want parentheses etc */ if (show->flags & BTF_SHOW_NONAME) snprintf(show->state.name, sizeof(show->state.name), "%s", parens); else snprintf(show->state.name, sizeof(show->state.name), "%s%s%s(%s%s%s%s%s%s)%s", /* first 3 strings comprise ".member = " */ show_member ? "." : "", show_member ? member : "", show_member ? " = " : "", /* ...next is our prefix (struct, enum, etc) */ prefix, strlen(prefix) > 0 && strlen(name) > 0 ? " " : "", /* ...this is the type name itself */ name, /* ...suffixed by the appropriate '*', '[]' suffixes */ strlen(ptr_suffix) > 0 ? " " : "", ptr_suffix, array_suffix, parens); return show->state.name; } static const char *__btf_show_indent(struct btf_show *show) { const char *indents = " "; const char *indent = &indents[strlen(indents)]; if ((indent - show->state.depth) >= indents) return indent - show->state.depth; return indents; } static const char *btf_show_indent(struct btf_show *show) { return show->flags & BTF_SHOW_COMPACT ? "" : __btf_show_indent(show); } static const char *btf_show_newline(struct btf_show *show) { return show->flags & BTF_SHOW_COMPACT ? "" : "\n"; } static const char *btf_show_delim(struct btf_show *show) { if (show->state.depth == 0) return ""; if ((show->flags & BTF_SHOW_COMPACT) && show->state.type && BTF_INFO_KIND(show->state.type->info) == BTF_KIND_UNION) return "|"; return ","; } __printf(2, 3) static void btf_show(struct btf_show *show, const char *fmt, ...) { va_list args; if (!show->state.depth_check) { va_start(args, fmt); show->showfn(show, fmt, args); va_end(args); } } /* Macros are used here as btf_show_type_value[s]() prepends and appends * format specifiers to the format specifier passed in; these do the work of * adding indentation, delimiters etc while the caller simply has to specify * the type value(s) in the format specifier + value(s). */ #define btf_show_type_value(show, fmt, value) \ do { \ if ((value) != (__typeof__(value))0 || \ (show->flags & BTF_SHOW_ZERO) || \ show->state.depth == 0) { \ btf_show(show, "%s%s" fmt "%s%s", \ btf_show_indent(show), \ btf_show_name(show), \ value, btf_show_delim(show), \ btf_show_newline(show)); \ if (show->state.depth > show->state.depth_to_show) \ show->state.depth_to_show = show->state.depth; \ } \ } while (0) #define btf_show_type_values(show, fmt, ...) \ do { \ btf_show(show, "%s%s" fmt "%s%s", btf_show_indent(show), \ btf_show_name(show), \ __VA_ARGS__, btf_show_delim(show), \ btf_show_newline(show)); \ if (show->state.depth > show->state.depth_to_show) \ show->state.depth_to_show = show->state.depth; \ } while (0) /* How much is left to copy to safe buffer after @data? */ static int btf_show_obj_size_left(struct btf_show *show, void *data) { return show->obj.head + show->obj.size - data; } /* Is object pointed to by @data of @size already copied to our safe buffer? */ static bool btf_show_obj_is_safe(struct btf_show *show, void *data, int size) { return data >= show->obj.data && (data + size) < (show->obj.data + BTF_SHOW_OBJ_SAFE_SIZE); } /* * If object pointed to by @data of @size falls within our safe buffer, return * the equivalent pointer to the same safe data. Assumes * copy_from_kernel_nofault() has already happened and our safe buffer is * populated. */ static void *__btf_show_obj_safe(struct btf_show *show, void *data, int size) { if (btf_show_obj_is_safe(show, data, size)) return show->obj.safe + (data - show->obj.data); return NULL; } /* * Return a safe-to-access version of data pointed to by @data. * We do this by copying the relevant amount of information * to the struct btf_show obj.safe buffer using copy_from_kernel_nofault(). * * If BTF_SHOW_UNSAFE is specified, just return data as-is; no * safe copy is needed. * * Otherwise we need to determine if we have the required amount * of data (determined by the @data pointer and the size of the * largest base type we can encounter (represented by * BTF_SHOW_OBJ_BASE_TYPE_SIZE). Having that much data ensures * that we will be able to print some of the current object, * and if more is needed a copy will be triggered. * Some objects such as structs will not fit into the buffer; * in such cases additional copies when we iterate over their * members may be needed. * * btf_show_obj_safe() is used to return a safe buffer for * btf_show_start_type(); this ensures that as we recurse into * nested types we always have safe data for the given type. * This approach is somewhat wasteful; it's possible for example * that when iterating over a large union we'll end up copying the * same data repeatedly, but the goal is safety not performance. * We use stack data as opposed to per-CPU buffers because the * iteration over a type can take some time, and preemption handling * would greatly complicate use of the safe buffer. */ static void *btf_show_obj_safe(struct btf_show *show, const struct btf_type *t, void *data) { const struct btf_type *rt; int size_left, size; void *safe = NULL; if (show->flags & BTF_SHOW_UNSAFE) return data; rt = btf_resolve_size(show->btf, t, &size); if (IS_ERR(rt)) { show->state.status = PTR_ERR(rt); return NULL; } /* * Is this toplevel object? If so, set total object size and * initialize pointers. Otherwise check if we still fall within * our safe object data. */ if (show->state.depth == 0) { show->obj.size = size; show->obj.head = data; } else { /* * If the size of the current object is > our remaining * safe buffer we _may_ need to do a new copy. However * consider the case of a nested struct; it's size pushes * us over the safe buffer limit, but showing any individual * struct members does not. In such cases, we don't need * to initiate a fresh copy yet; however we definitely need * at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes left * in our buffer, regardless of the current object size. * The logic here is that as we resolve types we will * hit a base type at some point, and we need to be sure * the next chunk of data is safely available to display * that type info safely. We cannot rely on the size of * the current object here because it may be much larger * than our current buffer (e.g. task_struct is 8k). * All we want to do here is ensure that we can print the * next basic type, which we can if either * - the current type size is within the safe buffer; or * - at least BTF_SHOW_OBJ_BASE_TYPE_SIZE bytes are left in * the safe buffer. */ safe = __btf_show_obj_safe(show, data, min(size, BTF_SHOW_OBJ_BASE_TYPE_SIZE)); } /* * We need a new copy to our safe object, either because we haven't * yet copied and are initializing safe data, or because the data * we want falls outside the boundaries of the safe object. */ if (!safe) { size_left = btf_show_obj_size_left(show, data); if (size_left > BTF_SHOW_OBJ_SAFE_SIZE) size_left = BTF_SHOW_OBJ_SAFE_SIZE; show->state.status = copy_from_kernel_nofault(show->obj.safe, data, size_left); if (!show->state.status) { show->obj.data = data; safe = show->obj.safe; } } return safe; } /* * Set the type we are starting to show and return a safe data pointer * to be used for showing the associated data. */ static void *btf_show_start_type(struct btf_show *show, const struct btf_type *t, u32 type_id, void *data) { show->state.type = t; show->state.type_id = type_id; show->state.name[0] = '\0'; return btf_show_obj_safe(show, t, data); } static void btf_show_end_type(struct btf_show *show) { show->state.type = NULL; show->state.type_id = 0; show->state.name[0] = '\0'; } static void *btf_show_start_aggr_type(struct btf_show *show, const struct btf_type *t, u32 type_id, void *data) { void *safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return safe_data; btf_show(show, "%s%s%s", btf_show_indent(show), btf_show_name(show), btf_show_newline(show)); show->state.depth++; return safe_data; } static void btf_show_end_aggr_type(struct btf_show *show, const char *suffix) { show->state.depth--; btf_show(show, "%s%s%s%s", btf_show_indent(show), suffix, btf_show_delim(show), btf_show_newline(show)); btf_show_end_type(show); } static void btf_show_start_member(struct btf_show *show, const struct btf_member *m) { show->state.member = m; } static void btf_show_start_array_member(struct btf_show *show) { show->state.array_member = 1; btf_show_start_member(show, NULL); } static void btf_show_end_member(struct btf_show *show) { show->state.member = NULL; } static void btf_show_end_array_member(struct btf_show *show) { show->state.array_member = 0; btf_show_end_member(show); } static void *btf_show_start_array_type(struct btf_show *show, const struct btf_type *t, u32 type_id, u16 array_encoding, void *data) { show->state.array_encoding = array_encoding; show->state.array_terminated = 0; return btf_show_start_aggr_type(show, t, type_id, data); } static void btf_show_end_array_type(struct btf_show *show) { show->state.array_encoding = 0; show->state.array_terminated = 0; btf_show_end_aggr_type(show, "]"); } static void *btf_show_start_struct_type(struct btf_show *show, const struct btf_type *t, u32 type_id, void *data) { return btf_show_start_aggr_type(show, t, type_id, data); } static void btf_show_end_struct_type(struct btf_show *show) { btf_show_end_aggr_type(show, "}"); } __printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, const char *fmt, ...) { va_list args; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; va_list args; if (!bpf_verifier_log_needed(log)) return; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, const struct btf_type *t, bool log_details, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; struct btf *btf = env->btf; va_list args; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL) { /* btf verifier prints all types it is processing via * btf_verifier_log_type(..., fmt = NULL). * Skip those prints for in-kernel BTF verification. */ if (!fmt) return; /* Skip logging when loading module BTF with mismatches permitted */ if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) return; } __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), log_details ? " " : ""); if (log_details) btf_type_ops(t)->log_details(env, t); if (fmt && *fmt) { __btf_verifier_log(log, " "); va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __btf_verifier_log(log, "\n"); } #define btf_verifier_log_type(env, t, ...) \ __btf_verifier_log_type((env), (t), true, __VA_ARGS__) #define btf_verifier_log_basic(env, t, ...) \ __btf_verifier_log_type((env), (t), false, __VA_ARGS__) __printf(4, 5) static void btf_verifier_log_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; struct btf *btf = env->btf; va_list args; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL) { if (!fmt) return; /* Skip logging when loading module BTF with mismatches permitted */ if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) return; } /* The CHECK_META phase already did a btf dump. * * If member is logged again, it must hit an error in * parsing this member. It is useful to print out which * struct this member belongs to. */ if (env->phase != CHECK_META) btf_verifier_log_type(env, struct_type, NULL); if (btf_type_kflag(struct_type)) __btf_verifier_log(log, "\t%s type_id=%u bitfield_size=%u bits_offset=%u", __btf_name_by_offset(btf, member->name_off), member->type, BTF_MEMBER_BITFIELD_SIZE(member->offset), BTF_MEMBER_BIT_OFFSET(member->offset)); else __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", __btf_name_by_offset(btf, member->name_off), member->type, member->offset); if (fmt && *fmt) { __btf_verifier_log(log, " "); va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __btf_verifier_log(log, "\n"); } __printf(4, 5) static void btf_verifier_log_vsi(struct btf_verifier_env *env, const struct btf_type *datasec_type, const struct btf_var_secinfo *vsi, const char *fmt, ...) { struct bpf_verifier_log *log = &env->log; va_list args; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL && !fmt) return; if (env->phase != CHECK_META) btf_verifier_log_type(env, datasec_type, NULL); __btf_verifier_log(log, "\t type_id=%u offset=%u size=%u", vsi->type, vsi->offset, vsi->size); if (fmt && *fmt) { __btf_verifier_log(log, " "); va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } __btf_verifier_log(log, "\n"); } static void btf_verifier_log_hdr(struct btf_verifier_env *env, u32 btf_data_size) { struct bpf_verifier_log *log = &env->log; const struct btf *btf = env->btf; const struct btf_header *hdr; if (!bpf_verifier_log_needed(log)) return; if (log->level == BPF_LOG_KERNEL) return; hdr = &btf->hdr; __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); __btf_verifier_log(log, "version: %u\n", hdr->version); __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags); __btf_verifier_log(log, "hdr_len: %u\n", hdr->hdr_len); __btf_verifier_log(log, "type_off: %u\n", hdr->type_off); __btf_verifier_log(log, "type_len: %u\n", hdr->type_len); __btf_verifier_log(log, "str_off: %u\n", hdr->str_off); __btf_verifier_log(log, "str_len: %u\n", hdr->str_len); __btf_verifier_log(log, "btf_total_size: %u\n", btf_data_size); } static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) { struct btf *btf = env->btf; if (btf->types_size == btf->nr_types) { /* Expand 'types' array */ struct btf_type **new_types; u32 expand_by, new_size; if (btf->start_id + btf->types_size == BTF_MAX_TYPE) { btf_verifier_log(env, "Exceeded max num of types"); return -E2BIG; } expand_by = max_t(u32, btf->types_size >> 2, 16); new_size = min_t(u32, BTF_MAX_TYPE, btf->types_size + expand_by); new_types = kvcalloc(new_size, sizeof(*new_types), GFP_KERNEL | __GFP_NOWARN); if (!new_types) return -ENOMEM; if (btf->nr_types == 0) { if (!btf->base_btf) { /* lazily init VOID type */ new_types[0] = &btf_void; btf->nr_types++; } } else { memcpy(new_types, btf->types, sizeof(*btf->types) * btf->nr_types); } kvfree(btf->types); btf->types = new_types; btf->types_size = new_size; } btf->types[btf->nr_types++] = t; return 0; } static int btf_alloc_id(struct btf *btf) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&btf_idr_lock); id = idr_alloc_cyclic(&btf_idr, btf, 1, INT_MAX, GFP_ATOMIC); if (id > 0) btf->id = id; spin_unlock_bh(&btf_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } static void btf_free_id(struct btf *btf) { unsigned long flags; /* * In map-in-map, calling map_delete_elem() on outer * map will call bpf_map_put on the inner map. * It will then eventually call btf_free_id() * on the inner map. Some of the map_delete_elem() * implementation may have irq disabled, so * we need to use the _irqsave() version instead * of the _bh() version. */ spin_lock_irqsave(&btf_idr_lock, flags); idr_remove(&btf_idr, btf->id); spin_unlock_irqrestore(&btf_idr_lock, flags); } static void btf_free_kfunc_set_tab(struct btf *btf) { struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab; int hook; if (!tab) return; /* For module BTF, we directly assign the sets being registered, so * there is nothing to free except kfunc_set_tab. */ if (btf_is_module(btf)) goto free_tab; for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) kfree(tab->sets[hook]); free_tab: kfree(tab); btf->kfunc_set_tab = NULL; } static void btf_free_dtor_kfunc_tab(struct btf *btf) { struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; if (!tab) return; kfree(tab); btf->dtor_kfunc_tab = NULL; } static void btf_free(struct btf *btf) { btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); kvfree(btf->data); kfree(btf); } static void btf_free_rcu(struct rcu_head *rcu) { struct btf *btf = container_of(rcu, struct btf, rcu); btf_free(btf); } void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); } void btf_put(struct btf *btf) { if (btf && refcount_dec_and_test(&btf->refcnt)) { btf_free_id(btf); call_rcu(&btf->rcu, btf_free_rcu); } } static int env_resolve_init(struct btf_verifier_env *env) { struct btf *btf = env->btf; u32 nr_types = btf->nr_types; u32 *resolved_sizes = NULL; u32 *resolved_ids = NULL; u8 *visit_states = NULL; resolved_sizes = kvcalloc(nr_types, sizeof(*resolved_sizes), GFP_KERNEL | __GFP_NOWARN); if (!resolved_sizes) goto nomem; resolved_ids = kvcalloc(nr_types, sizeof(*resolved_ids), GFP_KERNEL | __GFP_NOWARN); if (!resolved_ids) goto nomem; visit_states = kvcalloc(nr_types, sizeof(*visit_states), GFP_KERNEL | __GFP_NOWARN); if (!visit_states) goto nomem; btf->resolved_sizes = resolved_sizes; btf->resolved_ids = resolved_ids; env->visit_states = visit_states; return 0; nomem: kvfree(resolved_sizes); kvfree(resolved_ids); kvfree(visit_states); return -ENOMEM; } static void btf_verifier_env_free(struct btf_verifier_env *env) { kvfree(env->visit_states); kfree(env); } static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, const struct btf_type *next_type) { switch (env->resolve_mode) { case RESOLVE_TBD: /* int, enum or void is a sink */ return !btf_type_needs_resolve(next_type); case RESOLVE_PTR: /* int, enum, void, struct, array, func or func_proto is a sink * for ptr */ return !btf_type_is_modifier(next_type) && !btf_type_is_ptr(next_type); case RESOLVE_STRUCT_OR_ARRAY: /* int, enum, void, ptr, func or func_proto is a sink * for struct and array */ return !btf_type_is_modifier(next_type) && !btf_type_is_array(next_type) && !btf_type_is_struct(next_type); default: BUG(); } } static bool env_type_is_resolved(const struct btf_verifier_env *env, u32 type_id) { /* base BTF types should be resolved by now */ if (type_id < env->btf->start_id) return true; return env->visit_states[type_id - env->btf->start_id] == RESOLVED; } static int env_stack_push(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { const struct btf *btf = env->btf; struct resolve_vertex *v; if (env->top_stack == MAX_RESOLVE_DEPTH) return -E2BIG; if (type_id < btf->start_id || env->visit_states[type_id - btf->start_id] != NOT_VISITED) return -EEXIST; env->visit_states[type_id - btf->start_id] = VISITED; v = &env->stack[env->top_stack++]; v->t = t; v->type_id = type_id; v->next_member = 0; if (env->resolve_mode == RESOLVE_TBD) { if (btf_type_is_ptr(t)) env->resolve_mode = RESOLVE_PTR; else if (btf_type_is_struct(t) || btf_type_is_array(t)) env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY; } return 0; } static void env_stack_set_next_member(struct btf_verifier_env *env, u16 next_member) { env->stack[env->top_stack - 1].next_member = next_member; } static void env_stack_pop_resolved(struct btf_verifier_env *env, u32 resolved_type_id, u32 resolved_size) { u32 type_id = env->stack[--(env->top_stack)].type_id; struct btf *btf = env->btf; type_id -= btf->start_id; /* adjust to local type id */ btf->resolved_sizes[type_id] = resolved_size; btf->resolved_ids[type_id] = resolved_type_id; env->visit_states[type_id] = RESOLVED; } static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) { return env->top_stack ? &env->stack[env->top_stack - 1] : NULL; } /* Resolve the size of a passed-in "type" * * type: is an array (e.g. u32 array[x][y]) * return type: type "u32[x][y]", i.e. BTF_KIND_ARRAY, * *type_size: (x * y * sizeof(u32)). Hence, *type_size always * corresponds to the return type. * *elem_type: u32 * *elem_id: id of u32 * *total_nelems: (x * y). Hence, individual elem size is * (*type_size / *total_nelems) * *type_id: id of type if it's changed within the function, 0 if not * * type: is not an array (e.g. const struct X) * return type: type "struct X" * *type_size: sizeof(struct X) * *elem_type: same as return type ("struct X") * *elem_id: 0 * *total_nelems: 1 * *type_id: id of type if it's changed within the function, 0 if not */ static const struct btf_type * __btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size, const struct btf_type **elem_type, u32 *elem_id, u32 *total_nelems, u32 *type_id) { const struct btf_type *array_type = NULL; const struct btf_array *array = NULL; u32 i, size, nelems = 1, id = 0; for (i = 0; i < MAX_RESOLVE_DEPTH; i++) { switch (BTF_INFO_KIND(type->info)) { /* type->size can be used */ case BTF_KIND_INT: case BTF_KIND_STRUCT: case BTF_KIND_UNION: case BTF_KIND_ENUM: case BTF_KIND_FLOAT: case BTF_KIND_ENUM64: size = type->size; goto resolved; case BTF_KIND_PTR: size = sizeof(void *); goto resolved; /* Modifiers */ case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_TYPE_TAG: id = type->type; type = btf_type_by_id(btf, type->type); break; case BTF_KIND_ARRAY: if (!array_type) array_type = type; array = btf_type_array(type); if (nelems && array->nelems > U32_MAX / nelems) return ERR_PTR(-EINVAL); nelems *= array->nelems; type = btf_type_by_id(btf, array->type); break; /* type without size */ default: return ERR_PTR(-EINVAL); } } return ERR_PTR(-EINVAL); resolved: if (nelems && size > U32_MAX / nelems) return ERR_PTR(-EINVAL); *type_size = nelems * size; if (total_nelems) *total_nelems = nelems; if (elem_type) *elem_type = type; if (elem_id) *elem_id = array ? array->type : 0; if (type_id && id) *type_id = id; return array_type ? : type; } const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size) { return __btf_resolve_size(btf, type, type_size, NULL, NULL, NULL, NULL); } static u32 btf_resolved_type_id(const struct btf *btf, u32 type_id) { while (type_id < btf->start_id) btf = btf->base_btf; return btf->resolved_ids[type_id - btf->start_id]; } /* The input param "type_id" must point to a needs_resolve type */ static const struct btf_type *btf_type_id_resolve(const struct btf *btf, u32 *type_id) { *type_id = btf_resolved_type_id(btf, *type_id); return btf_type_by_id(btf, *type_id); } static u32 btf_resolved_type_size(const struct btf *btf, u32 type_id) { while (type_id < btf->start_id) btf = btf->base_btf; return btf->resolved_sizes[type_id - btf->start_id]; } const struct btf_type *btf_type_id_size(const struct btf *btf, u32 *type_id, u32 *ret_size) { const struct btf_type *size_type; u32 size_type_id = *type_id; u32 size = 0; size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; if (btf_type_has_size(size_type)) { size = size_type->size; } else if (btf_type_is_array(size_type)) { size = btf_resolved_type_size(btf, size_type_id); } else if (btf_type_is_ptr(size_type)) { size = sizeof(void *); } else { if (WARN_ON_ONCE(!btf_type_is_modifier(size_type) && !btf_type_is_var(size_type))) return NULL; size_type_id = btf_resolved_type_id(btf, size_type_id); size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; else if (btf_type_has_size(size_type)) size = size_type->size; else if (btf_type_is_array(size_type)) size = btf_resolved_type_size(btf, size_type_id); else if (btf_type_is_ptr(size_type)) size = sizeof(void *); else return NULL; } *type_id = size_type_id; if (ret_size) *ret_size = size; return size_type; } static int btf_df_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { btf_verifier_log_basic(env, struct_type, "Unsupported check_member"); return -EINVAL; } static int btf_df_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { btf_verifier_log_basic(env, struct_type, "Unsupported check_kflag_member"); return -EINVAL; } /* Used for ptr, array struct/union and float type members. * int, enum and modifier types have their specific callback functions. */ static int btf_generic_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { if (BTF_MEMBER_BITFIELD_SIZE(member->offset)) { btf_verifier_log_member(env, struct_type, member, "Invalid member bitfield_size"); return -EINVAL; } /* bitfield size is 0, so member->offset represents bit offset only. * It is safe to call non kflag check_member variants. */ return btf_type_ops(member_type)->check_member(env, struct_type, member, member_type); } static int btf_df_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { btf_verifier_log_basic(env, v->t, "Unsupported resolve"); return -EINVAL; } static void btf_df_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offsets, struct btf_show *show) { btf_show(show, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); } static int btf_int_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 int_data = btf_type_int(member_type); u32 struct_bits_off = member->offset; u32 struct_size = struct_type->size; u32 nr_copy_bits; u32 bytes_offset; if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) { btf_verifier_log_member(env, struct_type, member, "bits_offset exceeds U32_MAX"); return -EINVAL; } struct_bits_off += BTF_INT_OFFSET(int_data); bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); nr_copy_bits = BTF_INT_BITS(int_data) + BITS_PER_BYTE_MASKED(struct_bits_off); if (nr_copy_bits > BITS_PER_U128) { btf_verifier_log_member(env, struct_type, member, "nr_copy_bits exceeds 128"); return -EINVAL; } if (struct_size < bytes_offset || struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static int btf_int_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off, nr_bits, nr_int_data_bits, bytes_offset; u32 int_data = btf_type_int(member_type); u32 struct_size = struct_type->size; u32 nr_copy_bits; /* a regular int type is required for the kflag int member */ if (!btf_type_int_is_regular(member_type)) { btf_verifier_log_member(env, struct_type, member, "Invalid member base type"); return -EINVAL; } /* check sanity of bitfield size */ nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset); struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset); nr_int_data_bits = BTF_INT_BITS(int_data); if (!nr_bits) { /* Not a bitfield member, member offset must be at byte * boundary. */ if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Invalid member offset"); return -EINVAL; } nr_bits = nr_int_data_bits; } else if (nr_bits > nr_int_data_bits) { btf_verifier_log_member(env, struct_type, member, "Invalid member bitfield_size"); return -EINVAL; } bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); nr_copy_bits = nr_bits + BITS_PER_BYTE_MASKED(struct_bits_off); if (nr_copy_bits > BITS_PER_U128) { btf_verifier_log_member(env, struct_type, member, "nr_copy_bits exceeds 128"); return -EINVAL; } if (struct_size < bytes_offset || struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_int_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { u32 int_data, nr_bits, meta_needed = sizeof(int_data); u16 encoding; if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } int_data = btf_type_int(t); if (int_data & ~BTF_INT_MASK) { btf_verifier_log_basic(env, t, "Invalid int_data:%x", int_data); return -EINVAL; } nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data); if (nr_bits > BITS_PER_U128) { btf_verifier_log_type(env, t, "nr_bits exceeds %zu", BITS_PER_U128); return -EINVAL; } if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) { btf_verifier_log_type(env, t, "nr_bits exceeds type_size"); return -EINVAL; } /* * Only one of the encoding bits is allowed and it * should be sufficient for the pretty print purpose (i.e. decoding). * Multiple bits can be allowed later if it is found * to be insufficient. */ encoding = BTF_INT_ENCODING(int_data); if (encoding && encoding != BTF_INT_SIGNED && encoding != BTF_INT_CHAR && encoding != BTF_INT_BOOL) { btf_verifier_log_type(env, t, "Unsupported encoding"); return -ENOTSUPP; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static void btf_int_log(struct btf_verifier_env *env, const struct btf_type *t) { int int_data = btf_type_int(t); btf_verifier_log(env, "size=%u bits_offset=%u nr_bits=%u encoding=%s", t->size, BTF_INT_OFFSET(int_data), BTF_INT_BITS(int_data), btf_int_encoding_str(BTF_INT_ENCODING(int_data))); } static void btf_int128_print(struct btf_show *show, void *data) { /* data points to a __int128 number. * Suppose * int128_num = *(__int128 *)data; * The below formulas shows what upper_num and lower_num represents: * upper_num = int128_num >> 64; * lower_num = int128_num & 0xffffffffFFFFFFFFULL; */ u64 upper_num, lower_num; #ifdef __BIG_ENDIAN_BITFIELD upper_num = *(u64 *)data; lower_num = *(u64 *)(data + 8); #else upper_num = *(u64 *)(data + 8); lower_num = *(u64 *)data; #endif if (upper_num == 0) btf_show_type_value(show, "0x%llx", lower_num); else btf_show_type_values(show, "0x%llx%016llx", upper_num, lower_num); } static void btf_int128_shift(u64 *print_num, u16 left_shift_bits, u16 right_shift_bits) { u64 upper_num, lower_num; #ifdef __BIG_ENDIAN_BITFIELD upper_num = print_num[0]; lower_num = print_num[1]; #else upper_num = print_num[1]; lower_num = print_num[0]; #endif /* shake out un-needed bits by shift/or operations */ if (left_shift_bits >= 64) { upper_num = lower_num << (left_shift_bits - 64); lower_num = 0; } else { upper_num = (upper_num << left_shift_bits) | (lower_num >> (64 - left_shift_bits)); lower_num = lower_num << left_shift_bits; } if (right_shift_bits >= 64) { lower_num = upper_num >> (right_shift_bits - 64); upper_num = 0; } else { lower_num = (lower_num >> right_shift_bits) | (upper_num << (64 - right_shift_bits)); upper_num = upper_num >> right_shift_bits; } #ifdef __BIG_ENDIAN_BITFIELD print_num[0] = upper_num; print_num[1] = lower_num; #else print_num[0] = lower_num; print_num[1] = upper_num; #endif } static void btf_bitfield_show(void *data, u8 bits_offset, u8 nr_bits, struct btf_show *show) { u16 left_shift_bits, right_shift_bits; u8 nr_copy_bytes; u8 nr_copy_bits; u64 print_num[2] = {}; nr_copy_bits = nr_bits + bits_offset; nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); memcpy(print_num, data, nr_copy_bytes); #ifdef __BIG_ENDIAN_BITFIELD left_shift_bits = bits_offset; #else left_shift_bits = BITS_PER_U128 - nr_copy_bits; #endif right_shift_bits = BITS_PER_U128 - nr_bits; btf_int128_shift(print_num, left_shift_bits, right_shift_bits); btf_int128_print(show, print_num); } static void btf_int_bits_show(const struct btf *btf, const struct btf_type *t, void *data, u8 bits_offset, struct btf_show *show) { u32 int_data = btf_type_int(t); u8 nr_bits = BTF_INT_BITS(int_data); u8 total_bits_offset; /* * bits_offset is at most 7. * BTF_INT_OFFSET() cannot exceed 128 bits. */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); btf_bitfield_show(data, bits_offset, nr_bits, show); } static void btf_int_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; u8 nr_bits = BTF_INT_BITS(int_data); void *safe_data; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { btf_int_bits_show(btf, t, safe_data, bits_offset, show); goto out; } switch (nr_bits) { case 128: btf_int128_print(show, safe_data); break; case 64: if (sign) btf_show_type_value(show, "%lld", *(s64 *)safe_data); else btf_show_type_value(show, "%llu", *(u64 *)safe_data); break; case 32: if (sign) btf_show_type_value(show, "%d", *(s32 *)safe_data); else btf_show_type_value(show, "%u", *(u32 *)safe_data); break; case 16: if (sign) btf_show_type_value(show, "%d", *(s16 *)safe_data); else btf_show_type_value(show, "%u", *(u16 *)safe_data); break; case 8: if (show->state.array_encoding == BTF_INT_CHAR) { /* check for null terminator */ if (show->state.array_terminated) break; if (*(char *)data == '\0') { show->state.array_terminated = 1; break; } if (isprint(*(char *)data)) { btf_show_type_value(show, "'%c'", *(char *)safe_data); break; } } if (sign) btf_show_type_value(show, "%d", *(s8 *)safe_data); else btf_show_type_value(show, "%u", *(u8 *)safe_data); break; default: btf_int_bits_show(btf, t, safe_data, bits_offset, show); break; } out: btf_show_end_type(show); } static const struct btf_kind_operations int_ops = { .check_meta = btf_int_check_meta, .resolve = btf_df_resolve, .check_member = btf_int_check_member, .check_kflag_member = btf_int_check_kflag_member, .log_details = btf_int_log, .show = btf_int_show, }; static int btf_modifier_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { const struct btf_type *resolved_type; u32 resolved_type_id = member->type; struct btf_member resolved_member; struct btf *btf = env->btf; resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); if (!resolved_type) { btf_verifier_log_member(env, struct_type, member, "Invalid member"); return -EINVAL; } resolved_member = *member; resolved_member.type = resolved_type_id; return btf_type_ops(resolved_type)->check_member(env, struct_type, &resolved_member, resolved_type); } static int btf_modifier_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { const struct btf_type *resolved_type; u32 resolved_type_id = member->type; struct btf_member resolved_member; struct btf *btf = env->btf; resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); if (!resolved_type) { btf_verifier_log_member(env, struct_type, member, "Invalid member"); return -EINVAL; } resolved_member = *member; resolved_member.type = resolved_type_id; return btf_type_ops(resolved_type)->check_kflag_member(env, struct_type, &resolved_member, resolved_type); } static int btf_ptr_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_size, struct_bits_off, bytes_offset; struct_size = struct_type->size; struct_bits_off = member->offset; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } if (struct_size - bytes_offset < sizeof(void *)) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static int btf_ref_type_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const char *value; if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (!BTF_TYPE_ID_VALID(t->type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } /* typedef/type_tag type must have a valid name, and other ref types, * volatile, const, restrict, should have a null name. */ if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) { if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } } else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) { value = btf_name_by_offset(env->btf, t->name_off); if (!value || !value[0]) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } } else { if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } } btf_verifier_log_type(env, t, NULL); return 0; } static int btf_modifier_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *t = v->t; const struct btf_type *next_type; u32 next_type_id = t->type; struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); /* Figure out the resolved next_type_id with size. * They will be stored in the current modifier's * resolved_ids and resolved_sizes such that it can * save us a few type-following when we use it later (e.g. in * pretty print). */ if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); /* "typedef void new_void", "const void"...etc */ if (!btf_type_is_void(next_type) && !btf_type_is_fwd(next_type) && !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static int btf_var_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); if (btf_type_is_modifier(next_type)) { const struct btf_type *resolved_type; u32 resolved_type_id; resolved_type_id = next_type_id; resolved_type = btf_type_id_resolve(btf, &resolved_type_id); if (btf_type_is_ptr(resolved_type) && !env_type_is_resolve_sink(env, resolved_type) && !env_type_is_resolved(env, resolved_type_id)) return env_stack_push(env, resolved_type, resolved_type_id); } /* We must resolve to something concrete at this point, no * forward types or similar that would resolve to size of * zero is allowed. */ if (!btf_type_id_size(btf, &next_type_id, NULL)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static int btf_ptr_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY, * the modifier may have stopped resolving when it was resolved * to a ptr (last-resolved-ptr). * * We now need to continue from the last-resolved-ptr to * ensure the last-resolved-ptr will not referring back to * the current ptr (t). */ if (btf_type_is_modifier(next_type)) { const struct btf_type *resolved_type; u32 resolved_type_id; resolved_type_id = next_type_id; resolved_type = btf_type_id_resolve(btf, &resolved_type_id); if (btf_type_is_ptr(resolved_type) && !env_type_is_resolve_sink(env, resolved_type) && !env_type_is_resolved(env, resolved_type_id)) return env_stack_push(env, resolved_type, resolved_type_id); } if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); if (!btf_type_is_void(next_type) && !btf_type_is_fwd(next_type) && !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static void btf_modifier_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { if (btf->resolved_ids) t = btf_type_id_resolve(btf, &type_id); else t = btf_type_skip_modifiers(btf, type_id, NULL); btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } static void btf_var_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { t = btf_type_id_resolve(btf, &type_id); btf_type_ops(t)->show(btf, t, type_id, data, bits_offset, show); } static void btf_ptr_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { void *safe_data; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; /* It is a hashed value unless BTF_SHOW_PTR_RAW is specified */ if (show->flags & BTF_SHOW_PTR_RAW) btf_show_type_value(show, "0x%px", *(void **)safe_data); else btf_show_type_value(show, "0x%p", *(void **)safe_data); btf_show_end_type(show); } static void btf_ref_type_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type_id=%u", t->type); } static struct btf_kind_operations modifier_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_modifier_resolve, .check_member = btf_modifier_check_member, .check_kflag_member = btf_modifier_check_kflag_member, .log_details = btf_ref_type_log, .show = btf_modifier_show, }; static struct btf_kind_operations ptr_ops = { .check_meta = btf_ref_type_check_meta, .resolve = btf_ptr_resolve, .check_member = btf_ptr_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_ref_type_log, .show = btf_ptr_show, }; static s32 btf_fwd_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (t->type) { btf_verifier_log_type(env, t, "type != 0"); return -EINVAL; } /* fwd type must have a valid name */ if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return 0; } static void btf_fwd_type_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "%s", btf_type_kflag(t) ? "union" : "struct"); } static struct btf_kind_operations fwd_ops = { .check_meta = btf_fwd_check_meta, .resolve = btf_df_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_fwd_type_log, .show = btf_df_show, }; static int btf_array_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off = member->offset; u32 struct_size, bytes_offset; u32 array_type_id, array_size; struct btf *btf = env->btf; if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } array_type_id = member->type; btf_type_id_size(btf, &array_type_id, &array_size); struct_size = struct_type->size; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (struct_size - bytes_offset < array_size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_array_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_array *array = btf_type_array(t); u32 meta_needed = sizeof(*array); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } /* array type should not have a name */ if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (t->size) { btf_verifier_log_type(env, t, "size != 0"); return -EINVAL; } /* Array elem type and index type cannot be in type void, * so !array->type and !array->index_type are not allowed. */ if (!array->type || !BTF_TYPE_ID_VALID(array->type)) { btf_verifier_log_type(env, t, "Invalid elem"); return -EINVAL; } if (!array->index_type || !BTF_TYPE_ID_VALID(array->index_type)) { btf_verifier_log_type(env, t, "Invalid index"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static int btf_array_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_array *array = btf_type_array(v->t); const struct btf_type *elem_type, *index_type; u32 elem_type_id, index_type_id; struct btf *btf = env->btf; u32 elem_size; /* Check array->index_type */ index_type_id = array->index_type; index_type = btf_type_by_id(btf, index_type_id); if (btf_type_nosize_or_null(index_type) || btf_type_is_resolve_source_only(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } if (!env_type_is_resolve_sink(env, index_type) && !env_type_is_resolved(env, index_type_id)) return env_stack_push(env, index_type, index_type_id); index_type = btf_type_id_size(btf, &index_type_id, NULL); if (!index_type || !btf_type_is_int(index_type) || !btf_type_int_is_regular(index_type)) { btf_verifier_log_type(env, v->t, "Invalid index"); return -EINVAL; } /* Check array->type */ elem_type_id = array->type; elem_type = btf_type_by_id(btf, elem_type_id); if (btf_type_nosize_or_null(elem_type) || btf_type_is_resolve_source_only(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; } if (!env_type_is_resolve_sink(env, elem_type) && !env_type_is_resolved(env, elem_type_id)) return env_stack_push(env, elem_type, elem_type_id); elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); if (!elem_type) { btf_verifier_log_type(env, v->t, "Invalid elem"); return -EINVAL; } if (btf_type_is_int(elem_type) && !btf_type_int_is_regular(elem_type)) { btf_verifier_log_type(env, v->t, "Invalid array of int"); return -EINVAL; } if (array->nelems && elem_size > U32_MAX / array->nelems) { btf_verifier_log_type(env, v->t, "Array size overflows U32_MAX"); return -EINVAL; } env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems); return 0; } static void btf_array_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_array *array = btf_type_array(t); btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u", array->type, array->index_type, array->nelems); } static void __btf_array_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_array *array = btf_type_array(t); const struct btf_kind_operations *elem_ops; const struct btf_type *elem_type; u32 i, elem_size = 0, elem_type_id; u16 encoding = 0; elem_type_id = array->type; elem_type = btf_type_skip_modifiers(btf, elem_type_id, NULL); if (elem_type && btf_type_has_size(elem_type)) elem_size = elem_type->size; if (elem_type && btf_type_is_int(elem_type)) { u32 int_type = btf_type_int(elem_type); encoding = BTF_INT_ENCODING(int_type); /* * BTF_INT_CHAR encoding never seems to be set for * char arrays, so if size is 1 and element is * printable as a char, we'll do that. */ if (elem_size == 1) encoding = BTF_INT_CHAR; } if (!btf_show_start_array_type(show, t, type_id, encoding, data)) return; if (!elem_type) goto out; elem_ops = btf_type_ops(elem_type); for (i = 0; i < array->nelems; i++) { btf_show_start_array_member(show); elem_ops->show(btf, elem_type, elem_type_id, data, bits_offset, show); data += elem_size; btf_show_end_array_member(show); if (show->state.array_terminated) break; } out: btf_show_end_array_type(show); } static void btf_array_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_member *m = show->state.member; /* * First check if any members would be shown (are non-zero). * See comments above "struct btf_show" definition for more * details on how this works at a high-level. */ if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) { if (!show->state.depth_check) { show->state.depth_check = show->state.depth + 1; show->state.depth_to_show = 0; } __btf_array_show(btf, t, type_id, data, bits_offset, show); show->state.member = m; if (show->state.depth_check != show->state.depth + 1) return; show->state.depth_check = 0; if (show->state.depth_to_show <= show->state.depth) return; /* * Reaching here indicates we have recursed and found * non-zero array member(s). */ } __btf_array_show(btf, t, type_id, data, bits_offset, show); } static struct btf_kind_operations array_ops = { .check_meta = btf_array_check_meta, .resolve = btf_array_resolve, .check_member = btf_array_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_array_log, .show = btf_array_show, }; static int btf_struct_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off = member->offset; u32 struct_size, bytes_offset; if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } struct_size = struct_type->size; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (struct_size - bytes_offset < member_type->size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_struct_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; const struct btf_member *member; u32 meta_needed, last_offset; struct btf *btf = env->btf; u32 struct_size = t->size; u32 offset; u16 i; meta_needed = btf_type_vlen(t) * sizeof(*member); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } /* struct type either no name or a valid one */ if (t->name_off && !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); last_offset = 0; for_each_member(i, t, member) { if (!btf_name_offset_valid(btf, member->name_off)) { btf_verifier_log_member(env, t, member, "Invalid member name_offset:%u", member->name_off); return -EINVAL; } /* struct member either no name or a valid one */ if (member->name_off && !btf_name_valid_identifier(btf, member->name_off)) { btf_verifier_log_member(env, t, member, "Invalid name"); return -EINVAL; } /* A member cannot be in type void */ if (!member->type || !BTF_TYPE_ID_VALID(member->type)) { btf_verifier_log_member(env, t, member, "Invalid type_id"); return -EINVAL; } offset = __btf_member_bit_offset(t, member); if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); return -EINVAL; } /* * ">" instead of ">=" because the last member could be * "char a[0];" */ if (last_offset > offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); return -EINVAL; } if (BITS_ROUNDUP_BYTES(offset) > struct_size) { btf_verifier_log_member(env, t, member, "Member bits_offset exceeds its struct size"); return -EINVAL; } btf_verifier_log_member(env, t, member, NULL); last_offset = offset; } return meta_needed; } static int btf_struct_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_member *member; int err; u16 i; /* Before continue resolving the next_member, * ensure the last member is indeed resolved to a * type with size info. */ if (v->next_member) { const struct btf_type *last_member_type; const struct btf_member *last_member; u32 last_member_type_id; last_member = btf_type_member(v->t) + v->next_member - 1; last_member_type_id = last_member->type; if (WARN_ON_ONCE(!env_type_is_resolved(env, last_member_type_id))) return -EINVAL; last_member_type = btf_type_by_id(env->btf, last_member_type_id); if (btf_type_kflag(v->t)) err = btf_type_ops(last_member_type)->check_kflag_member(env, v->t, last_member, last_member_type); else err = btf_type_ops(last_member_type)->check_member(env, v->t, last_member, last_member_type); if (err) return err; } for_each_member_from(i, v->next_member, v->t, member) { u32 member_type_id = member->type; const struct btf_type *member_type = btf_type_by_id(env->btf, member_type_id); if (btf_type_nosize_or_null(member_type) || btf_type_is_resolve_source_only(member_type)) { btf_verifier_log_member(env, v->t, member, "Invalid member"); return -EINVAL; } if (!env_type_is_resolve_sink(env, member_type) && !env_type_is_resolved(env, member_type_id)) { env_stack_set_next_member(env, i + 1); return env_stack_push(env, member_type, member_type_id); } if (btf_type_kflag(v->t)) err = btf_type_ops(member_type)->check_kflag_member(env, v->t, member, member_type); else err = btf_type_ops(member_type)->check_member(env, v->t, member, member_type); if (err) return err; } env_stack_pop_resolved(env, 0, 0); return 0; } static void btf_struct_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } enum btf_field_type { BTF_FIELD_SPIN_LOCK, BTF_FIELD_TIMER, BTF_FIELD_KPTR, }; enum { BTF_FIELD_IGNORE = 0, BTF_FIELD_FOUND = 1, }; struct btf_field_info { u32 type_id; u32 off; enum bpf_kptr_type type; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, u32 off, int sz, struct btf_field_info *info) { if (!__btf_type_is_struct(t)) return BTF_FIELD_IGNORE; if (t->size != sz) return BTF_FIELD_IGNORE; info->off = off; return BTF_FIELD_FOUND; } static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, u32 off, int sz, struct btf_field_info *info) { enum bpf_kptr_type type; u32 res_id; /* For PTR, sz is always == 8 */ if (!btf_type_is_ptr(t)) return BTF_FIELD_IGNORE; t = btf_type_by_id(btf, t->type); if (!btf_type_is_type_tag(t)) return BTF_FIELD_IGNORE; /* Reject extra tags */ if (btf_type_is_type_tag(btf_type_by_id(btf, t->type))) return -EINVAL; if (!strcmp("kptr", __btf_name_by_offset(btf, t->name_off))) type = BPF_KPTR_UNREF; else if (!strcmp("kptr_ref", __btf_name_by_offset(btf, t->name_off))) type = BPF_KPTR_REF; else return -EINVAL; /* Get the base type */ t = btf_type_skip_modifiers(btf, t->type, &res_id); /* Only pointer to struct is allowed */ if (!__btf_type_is_struct(t)) return -EINVAL; info->type_id = res_id; info->off = off; info->type = type; return BTF_FIELD_FOUND; } static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, const char *name, int sz, int align, enum btf_field_type field_type, struct btf_field_info *info, int info_cnt) { const struct btf_member *member; struct btf_field_info tmp; int ret, idx = 0; u32 i, off; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) continue; off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; off /= 8; if (off % align) return -EINVAL; switch (field_type) { case BTF_FIELD_SPIN_LOCK: case BTF_FIELD_TIMER: ret = btf_find_struct(btf, member_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; case BTF_FIELD_KPTR: ret = btf_find_kptr(btf, member_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; default: return -EFAULT; } if (ret == BTF_FIELD_IGNORE) continue; if (idx >= info_cnt) return -E2BIG; ++idx; } return idx; } static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, const char *name, int sz, int align, enum btf_field_type field_type, struct btf_field_info *info, int info_cnt) { const struct btf_var_secinfo *vsi; struct btf_field_info tmp; int ret, idx = 0; u32 i, off; for_each_vsi(i, t, vsi) { const struct btf_type *var = btf_type_by_id(btf, vsi->type); const struct btf_type *var_type = btf_type_by_id(btf, var->type); off = vsi->offset; if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) continue; if (vsi->size != sz) continue; if (off % align) return -EINVAL; switch (field_type) { case BTF_FIELD_SPIN_LOCK: case BTF_FIELD_TIMER: ret = btf_find_struct(btf, var_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; case BTF_FIELD_KPTR: ret = btf_find_kptr(btf, var_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; default: return -EFAULT; } if (ret == BTF_FIELD_IGNORE) continue; if (idx >= info_cnt) return -E2BIG; ++idx; } return idx; } static int btf_find_field(const struct btf *btf, const struct btf_type *t, enum btf_field_type field_type, struct btf_field_info *info, int info_cnt) { const char *name; int sz, align; switch (field_type) { case BTF_FIELD_SPIN_LOCK: name = "bpf_spin_lock"; sz = sizeof(struct bpf_spin_lock); align = __alignof__(struct bpf_spin_lock); break; case BTF_FIELD_TIMER: name = "bpf_timer"; sz = sizeof(struct bpf_timer); align = __alignof__(struct bpf_timer); break; case BTF_FIELD_KPTR: name = NULL; sz = sizeof(u64); align = 8; break; default: return -EFAULT; } if (__btf_type_is_struct(t)) return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt); else if (btf_type_is_datasec(t)) return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt); return -EINVAL; } /* find 'struct bpf_spin_lock' in map value. * return >= 0 offset if found * and < 0 in case of error */ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) { struct btf_field_info info; int ret; ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1); if (ret < 0) return ret; if (!ret) return -ENOENT; return info.off; } int btf_find_timer(const struct btf *btf, const struct btf_type *t) { struct btf_field_info info; int ret; ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1); if (ret < 0) return ret; if (!ret) return -ENOENT; return info.off; } struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, const struct btf_type *t) { struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX]; struct bpf_map_value_off *tab; struct btf *kernel_btf = NULL; struct module *mod = NULL; int ret, i, nr_off; ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr)); if (ret < 0) return ERR_PTR(ret); if (!ret) return NULL; nr_off = ret; tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN); if (!tab) return ERR_PTR(-ENOMEM); for (i = 0; i < nr_off; i++) { const struct btf_type *t; s32 id; /* Find type in map BTF, and use it to look up the matching type * in vmlinux or module BTFs, by name and kind. */ t = btf_type_by_id(btf, info_arr[i].type_id); id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), &kernel_btf); if (id < 0) { ret = id; goto end; } /* Find and stash the function pointer for the destruction function that * needs to be eventually invoked from the map free path. */ if (info_arr[i].type == BPF_KPTR_REF) { const struct btf_type *dtor_func; const char *dtor_func_name; unsigned long addr; s32 dtor_btf_id; /* This call also serves as a whitelist of allowed objects that * can be used as a referenced pointer and be stored in a map at * the same time. */ dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); if (dtor_btf_id < 0) { ret = dtor_btf_id; goto end_btf; } dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); if (!dtor_func) { ret = -ENOENT; goto end_btf; } if (btf_is_module(kernel_btf)) { mod = btf_try_get_module(kernel_btf); if (!mod) { ret = -ENXIO; goto end_btf; } } /* We already verified dtor_func to be btf_type_is_func * in register_btf_id_dtor_kfuncs. */ dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); addr = kallsyms_lookup_name(dtor_func_name); if (!addr) { ret = -EINVAL; goto end_mod; } tab->off[i].kptr.dtor = (void *)addr; } tab->off[i].offset = info_arr[i].off; tab->off[i].type = info_arr[i].type; tab->off[i].kptr.btf_id = id; tab->off[i].kptr.btf = kernel_btf; tab->off[i].kptr.module = mod; } tab->nr_off = nr_off; return tab; end_mod: module_put(mod); end_btf: btf_put(kernel_btf); end: while (i--) { btf_put(tab->off[i].kptr.btf); if (tab->off[i].kptr.module) module_put(tab->off[i].kptr.module); } kfree(tab); return ERR_PTR(ret); } static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_member *member; void *safe_data; u32 i; safe_data = btf_show_start_struct_type(show, t, type_id, data); if (!safe_data) return; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); const struct btf_kind_operations *ops; u32 member_offset, bitfield_size; u32 bytes_offset; u8 bits8_offset; btf_show_start_member(show, member); member_offset = __btf_member_bit_offset(t, member); bitfield_size = __btf_member_bitfield_size(t, member); bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); bits8_offset = BITS_PER_BYTE_MASKED(member_offset); if (bitfield_size) { safe_data = btf_show_start_type(show, member_type, member->type, data + bytes_offset); if (safe_data) btf_bitfield_show(safe_data, bits8_offset, bitfield_size, show); btf_show_end_type(show); } else { ops = btf_type_ops(member_type); ops->show(btf, member_type, member->type, data + bytes_offset, bits8_offset, show); } btf_show_end_member(show); } btf_show_end_struct_type(show); } static void btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_member *m = show->state.member; /* * First check if any members would be shown (are non-zero). * See comments above "struct btf_show" definition for more * details on how this works at a high-level. */ if (show->state.depth > 0 && !(show->flags & BTF_SHOW_ZERO)) { if (!show->state.depth_check) { show->state.depth_check = show->state.depth + 1; show->state.depth_to_show = 0; } __btf_struct_show(btf, t, type_id, data, bits_offset, show); /* Restore saved member data here */ show->state.member = m; if (show->state.depth_check != show->state.depth + 1) return; show->state.depth_check = 0; if (show->state.depth_to_show <= show->state.depth) return; /* * Reaching here indicates we have recursed and found * non-zero child values. */ } __btf_struct_show(btf, t, type_id, data, bits_offset, show); } static struct btf_kind_operations struct_ops = { .check_meta = btf_struct_check_meta, .resolve = btf_struct_resolve, .check_member = btf_struct_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_struct_log, .show = btf_struct_show, }; static int btf_enum_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off = member->offset; u32 struct_size, bytes_offset; if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } struct_size = struct_type->size; bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); if (struct_size - bytes_offset < member_type->size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static int btf_enum_check_kflag_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u32 struct_bits_off, nr_bits, bytes_end, struct_size; u32 int_bitsize = sizeof(int) * BITS_PER_BYTE; struct_bits_off = BTF_MEMBER_BIT_OFFSET(member->offset); nr_bits = BTF_MEMBER_BITFIELD_SIZE(member->offset); if (!nr_bits) { if (BITS_PER_BYTE_MASKED(struct_bits_off)) { btf_verifier_log_member(env, struct_type, member, "Member is not byte aligned"); return -EINVAL; } nr_bits = int_bitsize; } else if (nr_bits > int_bitsize) { btf_verifier_log_member(env, struct_type, member, "Invalid member bitfield_size"); return -EINVAL; } struct_size = struct_type->size; bytes_end = BITS_ROUNDUP_BYTES(struct_bits_off + nr_bits); if (struct_size < bytes_end) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static s32 btf_enum_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_enum *enums = btf_type_enum(t); struct btf *btf = env->btf; const char *fmt_str; u16 i, nr_enums; u32 meta_needed; nr_enums = btf_type_vlen(t); meta_needed = nr_enums * sizeof(*enums); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (t->size > 8 || !is_power_of_2(t->size)) { btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; } /* enum type either no name or a valid one */ if (t->name_off && !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); for (i = 0; i < nr_enums; i++) { if (!btf_name_offset_valid(btf, enums[i].name_off)) { btf_verifier_log(env, "\tInvalid name_offset:%u", enums[i].name_off); return -EINVAL; } /* enum member must have a valid name */ if (!enums[i].name_off || !btf_name_valid_identifier(btf, enums[i].name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (env->log.level == BPF_LOG_KERNEL) continue; fmt_str = btf_type_kflag(t) ? "\t%s val=%d\n" : "\t%s val=%u\n"; btf_verifier_log(env, fmt_str, __btf_name_by_offset(btf, enums[i].name_off), enums[i].val); } return meta_needed; } static void btf_enum_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } static void btf_enum_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_enum *enums = btf_type_enum(t); u32 i, nr_enums = btf_type_vlen(t); void *safe_data; int v; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; v = *(int *)safe_data; for (i = 0; i < nr_enums; i++) { if (v != enums[i].val) continue; btf_show_type_value(show, "%s", __btf_name_by_offset(btf, enums[i].name_off)); btf_show_end_type(show); return; } if (btf_type_kflag(t)) btf_show_type_value(show, "%d", v); else btf_show_type_value(show, "%u", v); btf_show_end_type(show); } static struct btf_kind_operations enum_ops = { .check_meta = btf_enum_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, .check_kflag_member = btf_enum_check_kflag_member, .log_details = btf_enum_log, .show = btf_enum_show, }; static s32 btf_enum64_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_enum64 *enums = btf_type_enum64(t); struct btf *btf = env->btf; const char *fmt_str; u16 i, nr_enums; u32 meta_needed; nr_enums = btf_type_vlen(t); meta_needed = nr_enums * sizeof(*enums); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (t->size > 8 || !is_power_of_2(t->size)) { btf_verifier_log_type(env, t, "Unexpected size"); return -EINVAL; } /* enum type either no name or a valid one */ if (t->name_off && !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); for (i = 0; i < nr_enums; i++) { if (!btf_name_offset_valid(btf, enums[i].name_off)) { btf_verifier_log(env, "\tInvalid name_offset:%u", enums[i].name_off); return -EINVAL; } /* enum member must have a valid name */ if (!enums[i].name_off || !btf_name_valid_identifier(btf, enums[i].name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (env->log.level == BPF_LOG_KERNEL) continue; fmt_str = btf_type_kflag(t) ? "\t%s val=%lld\n" : "\t%s val=%llu\n"; btf_verifier_log(env, fmt_str, __btf_name_by_offset(btf, enums[i].name_off), btf_enum64_value(enums + i)); } return meta_needed; } static void btf_enum64_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_enum64 *enums = btf_type_enum64(t); u32 i, nr_enums = btf_type_vlen(t); void *safe_data; s64 v; safe_data = btf_show_start_type(show, t, type_id, data); if (!safe_data) return; v = *(u64 *)safe_data; for (i = 0; i < nr_enums; i++) { if (v != btf_enum64_value(enums + i)) continue; btf_show_type_value(show, "%s", __btf_name_by_offset(btf, enums[i].name_off)); btf_show_end_type(show); return; } if (btf_type_kflag(t)) btf_show_type_value(show, "%lld", v); else btf_show_type_value(show, "%llu", v); btf_show_end_type(show); } static struct btf_kind_operations enum64_ops = { .check_meta = btf_enum64_check_meta, .resolve = btf_df_resolve, .check_member = btf_enum_check_member, .check_kflag_member = btf_enum_check_kflag_member, .log_details = btf_enum_log, .show = btf_enum64_show, }; static s32 btf_func_proto_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { u32 meta_needed = btf_type_vlen(t) * sizeof(struct btf_param); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (t->name_off) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static void btf_func_proto_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_param *args = (const struct btf_param *)(t + 1); u16 nr_args = btf_type_vlen(t), i; btf_verifier_log(env, "return=%u args=(", t->type); if (!nr_args) { btf_verifier_log(env, "void"); goto done; } if (nr_args == 1 && !args[0].type) { /* Only one vararg */ btf_verifier_log(env, "vararg"); goto done; } btf_verifier_log(env, "%u %s", args[0].type, __btf_name_by_offset(env->btf, args[0].name_off)); for (i = 1; i < nr_args - 1; i++) btf_verifier_log(env, ", %u %s", args[i].type, __btf_name_by_offset(env->btf, args[i].name_off)); if (nr_args > 1) { const struct btf_param *last_arg = &args[nr_args - 1]; if (last_arg->type) btf_verifier_log(env, ", %u %s", last_arg->type, __btf_name_by_offset(env->btf, last_arg->name_off)); else btf_verifier_log(env, ", vararg"); } done: btf_verifier_log(env, ")"); } static struct btf_kind_operations func_proto_ops = { .check_meta = btf_func_proto_check_meta, .resolve = btf_df_resolve, /* * BTF_KIND_FUNC_PROTO cannot be directly referred by * a struct's member. * * It should be a function pointer instead. * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) * * Hence, there is no btf_func_check_member(). */ .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_func_proto_log, .show = btf_df_show, }; static s32 btf_func_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { if (!t->name_off || !btf_name_valid_identifier(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } if (btf_type_vlen(t) > BTF_FUNC_GLOBAL) { btf_verifier_log_type(env, t, "Invalid func linkage"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return 0; } static int btf_func_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *t = v->t; u32 next_type_id = t->type; int err; err = btf_func_check(env, t); if (err) return err; env_stack_pop_resolved(env, next_type_id, 0); return 0; } static struct btf_kind_operations func_ops = { .check_meta = btf_func_check_meta, .resolve = btf_func_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_ref_type_log, .show = btf_df_show, }; static s32 btf_var_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_var *var; u32 meta_needed = sizeof(*var); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (!t->name_off || !__btf_name_valid(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } /* A var cannot be in type void */ if (!t->type || !BTF_TYPE_ID_VALID(t->type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } var = btf_type_var(t); if (var->linkage != BTF_VAR_STATIC && var->linkage != BTF_VAR_GLOBAL_ALLOCATED) { btf_verifier_log_type(env, t, "Linkage not supported"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static void btf_var_log(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_var *var = btf_type_var(t); btf_verifier_log(env, "type_id=%u linkage=%u", t->type, var->linkage); } static const struct btf_kind_operations var_ops = { .check_meta = btf_var_check_meta, .resolve = btf_var_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_var_log, .show = btf_var_show, }; static s32 btf_datasec_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_var_secinfo *vsi; u64 last_vsi_end_off = 0, sum = 0; u32 i, meta_needed; meta_needed = btf_type_vlen(t) * sizeof(*vsi); if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } if (!t->size) { btf_verifier_log_type(env, t, "size == 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (!t->name_off || !btf_name_valid_section(env->btf, t->name_off)) { btf_verifier_log_type(env, t, "Invalid name"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); for_each_vsi(i, t, vsi) { /* A var cannot be in type void */ if (!vsi->type || !BTF_TYPE_ID_VALID(vsi->type)) { btf_verifier_log_vsi(env, t, vsi, "Invalid type_id"); return -EINVAL; } if (vsi->offset < last_vsi_end_off || vsi->offset >= t->size) { btf_verifier_log_vsi(env, t, vsi, "Invalid offset"); return -EINVAL; } if (!vsi->size || vsi->size > t->size) { btf_verifier_log_vsi(env, t, vsi, "Invalid size"); return -EINVAL; } last_vsi_end_off = vsi->offset + vsi->size; if (last_vsi_end_off > t->size) { btf_verifier_log_vsi(env, t, vsi, "Invalid offset+size"); return -EINVAL; } btf_verifier_log_vsi(env, t, vsi, NULL); sum += vsi->size; } if (t->size < sum) { btf_verifier_log_type(env, t, "Invalid btf_info size"); return -EINVAL; } return meta_needed; } static int btf_datasec_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_var_secinfo *vsi; struct btf *btf = env->btf; u16 i; env->resolve_mode = RESOLVE_TBD; for_each_vsi_from(i, v->next_member, v->t, vsi) { u32 var_type_id = vsi->type, type_id, type_size = 0; const struct btf_type *var_type = btf_type_by_id(env->btf, var_type_id); if (!var_type || !btf_type_is_var(var_type)) { btf_verifier_log_vsi(env, v->t, vsi, "Not a VAR kind member"); return -EINVAL; } if (!env_type_is_resolve_sink(env, var_type) && !env_type_is_resolved(env, var_type_id)) { env_stack_set_next_member(env, i + 1); return env_stack_push(env, var_type, var_type_id); } type_id = var_type->type; if (!btf_type_id_size(btf, &type_id, &type_size)) { btf_verifier_log_vsi(env, v->t, vsi, "Invalid type"); return -EINVAL; } if (vsi->size < type_size) { btf_verifier_log_vsi(env, v->t, vsi, "Invalid size"); return -EINVAL; } } env_stack_pop_resolved(env, 0, 0); return 0; } static void btf_datasec_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } static void btf_datasec_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) { const struct btf_var_secinfo *vsi; const struct btf_type *var; u32 i; if (!btf_show_start_type(show, t, type_id, data)) return; btf_show_type_value(show, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off)); for_each_vsi(i, t, vsi) { var = btf_type_by_id(btf, vsi->type); if (i) btf_show(show, ","); btf_type_ops(var)->show(btf, var, vsi->type, data + vsi->offset, bits_offset, show); } btf_show_end_type(show); } static const struct btf_kind_operations datasec_ops = { .check_meta = btf_datasec_check_meta, .resolve = btf_datasec_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_datasec_log, .show = btf_datasec_show, }; static s32 btf_float_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } if (t->size != 2 && t->size != 4 && t->size != 8 && t->size != 12 && t->size != 16) { btf_verifier_log_type(env, t, "Invalid type_size"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return 0; } static int btf_float_check_member(struct btf_verifier_env *env, const struct btf_type *struct_type, const struct btf_member *member, const struct btf_type *member_type) { u64 start_offset_bytes; u64 end_offset_bytes; u64 misalign_bits; u64 align_bytes; u64 align_bits; /* Different architectures have different alignment requirements, so * here we check only for the reasonable minimum. This way we ensure * that types after CO-RE can pass the kernel BTF verifier. */ align_bytes = min_t(u64, sizeof(void *), member_type->size); align_bits = align_bytes * BITS_PER_BYTE; div64_u64_rem(member->offset, align_bits, &misalign_bits); if (misalign_bits) { btf_verifier_log_member(env, struct_type, member, "Member is not properly aligned"); return -EINVAL; } start_offset_bytes = member->offset / BITS_PER_BYTE; end_offset_bytes = start_offset_bytes + member_type->size; if (end_offset_bytes > struct_type->size) { btf_verifier_log_member(env, struct_type, member, "Member exceeds struct_size"); return -EINVAL; } return 0; } static void btf_float_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "size=%u", t->size); } static const struct btf_kind_operations float_ops = { .check_meta = btf_float_check_meta, .resolve = btf_df_resolve, .check_member = btf_float_check_member, .check_kflag_member = btf_generic_check_kflag_member, .log_details = btf_float_log, .show = btf_df_show, }; static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { const struct btf_decl_tag *tag; u32 meta_needed = sizeof(*tag); s32 component_idx; const char *value; if (meta_left < meta_needed) { btf_verifier_log_basic(env, t, "meta_left:%u meta_needed:%u", meta_left, meta_needed); return -EINVAL; } value = btf_name_by_offset(env->btf, t->name_off); if (!value || !value[0]) { btf_verifier_log_type(env, t, "Invalid value"); return -EINVAL; } if (btf_type_vlen(t)) { btf_verifier_log_type(env, t, "vlen != 0"); return -EINVAL; } if (btf_type_kflag(t)) { btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); return -EINVAL; } component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); return -EINVAL; } btf_verifier_log_type(env, t, NULL); return meta_needed; } static int btf_decl_tag_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; s32 component_idx; u32 vlen; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || !btf_type_is_decl_tag_target(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } if (!env_type_is_resolve_sink(env, next_type) && !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx != -1) { if (btf_type_is_var(next_type) || btf_type_is_typedef(next_type)) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); return -EINVAL; } if (btf_type_is_struct(next_type)) { vlen = btf_type_vlen(next_type); } else { /* next_type should be a function */ next_type = btf_type_by_id(btf, next_type->type); vlen = btf_type_vlen(next_type); } if ((u32)component_idx >= vlen) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); return -EINVAL; } } env_stack_pop_resolved(env, next_type_id, 0); return 0; } static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type=%u component_idx=%d", t->type, btf_type_decl_tag(t)->component_idx); } static const struct btf_kind_operations decl_tag_ops = { .check_meta = btf_decl_tag_check_meta, .resolve = btf_decl_tag_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, .log_details = btf_decl_tag_log, .show = btf_df_show, }; static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_type *ret_type; const struct btf_param *args; const struct btf *btf; u16 nr_args, i; int err; btf = env->btf; args = (const struct btf_param *)(t + 1); nr_args = btf_type_vlen(t); /* Check func return type which could be "void" (t->type == 0) */ if (t->type) { u32 ret_type_id = t->type; ret_type = btf_type_by_id(btf, ret_type_id); if (!ret_type) { btf_verifier_log_type(env, t, "Invalid return type"); return -EINVAL; } if (btf_type_is_resolve_source_only(ret_type)) { btf_verifier_log_type(env, t, "Invalid return type"); return -EINVAL; } if (btf_type_needs_resolve(ret_type) && !env_type_is_resolved(env, ret_type_id)) { err = btf_resolve(env, ret_type, ret_type_id); if (err) return err; } /* Ensure the return type is a type that has a size */ if (!btf_type_id_size(btf, &ret_type_id, NULL)) { btf_verifier_log_type(env, t, "Invalid return type"); return -EINVAL; } } if (!nr_args) return 0; /* Last func arg type_id could be 0 if it is a vararg */ if (!args[nr_args - 1].type) { if (args[nr_args - 1].name_off) { btf_verifier_log_type(env, t, "Invalid arg#%u", nr_args); return -EINVAL; } nr_args--; } err = 0; for (i = 0; i < nr_args; i++) { const struct btf_type *arg_type; u32 arg_type_id; arg_type_id = args[i].type; arg_type = btf_type_by_id(btf, arg_type_id); if (!arg_type) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); err = -EINVAL; break; } if (btf_type_is_resolve_source_only(arg_type)) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } if (args[i].name_off && (!btf_name_offset_valid(btf, args[i].name_off) || !btf_name_valid_identifier(btf, args[i].name_off))) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); err = -EINVAL; break; } if (btf_type_needs_resolve(arg_type) && !env_type_is_resolved(env, arg_type_id)) { err = btf_resolve(env, arg_type, arg_type_id); if (err) break; } if (!btf_type_id_size(btf, &arg_type_id, NULL)) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); err = -EINVAL; break; } } return err; } static int btf_func_check(struct btf_verifier_env *env, const struct btf_type *t) { const struct btf_type *proto_type; const struct btf_param *args; const struct btf *btf; u16 nr_args, i; btf = env->btf; proto_type = btf_type_by_id(btf, t->type); if (!proto_type || !btf_type_is_func_proto(proto_type)) { btf_verifier_log_type(env, t, "Invalid type_id"); return -EINVAL; } args = (const struct btf_param *)(proto_type + 1); nr_args = btf_type_vlen(proto_type); for (i = 0; i < nr_args; i++) { if (!args[i].name_off && args[i].type) { btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); return -EINVAL; } } return 0; } static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_INT] = &int_ops, [BTF_KIND_PTR] = &ptr_ops, [BTF_KIND_ARRAY] = &array_ops, [BTF_KIND_STRUCT] = &struct_ops, [BTF_KIND_UNION] = &struct_ops, [BTF_KIND_ENUM] = &enum_ops, [BTF_KIND_FWD] = &fwd_ops, [BTF_KIND_TYPEDEF] = &modifier_ops, [BTF_KIND_VOLATILE] = &modifier_ops, [BTF_KIND_CONST] = &modifier_ops, [BTF_KIND_RESTRICT] = &modifier_ops, [BTF_KIND_FUNC] = &func_ops, [BTF_KIND_FUNC_PROTO] = &func_proto_ops, [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, [BTF_KIND_DECL_TAG] = &decl_tag_ops, [BTF_KIND_TYPE_TAG] = &modifier_ops, [BTF_KIND_ENUM64] = &enum64_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { u32 saved_meta_left = meta_left; s32 var_meta_size; if (meta_left < sizeof(*t)) { btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu", env->log_type_id, meta_left, sizeof(*t)); return -EINVAL; } meta_left -= sizeof(*t); if (t->info & ~BTF_INFO_MASK) { btf_verifier_log(env, "[%u] Invalid btf_info:%x", env->log_type_id, t->info); return -EINVAL; } if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { btf_verifier_log(env, "[%u] Invalid kind:%u", env->log_type_id, BTF_INFO_KIND(t->info)); return -EINVAL; } if (!btf_name_offset_valid(env->btf, t->name_off)) { btf_verifier_log(env, "[%u] Invalid name_offset:%u", env->log_type_id, t->name_off); return -EINVAL; } var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left); if (var_meta_size < 0) return var_meta_size; meta_left -= var_meta_size; return saved_meta_left - meta_left; } static int btf_check_all_metas(struct btf_verifier_env *env) { struct btf *btf = env->btf; struct btf_header *hdr; void *cur, *end; hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; end = cur + hdr->type_len; env->log_type_id = btf->base_btf ? btf->start_id : 1; while (cur < end) { struct btf_type *t = cur; s32 meta_size; meta_size = btf_check_meta(env, t, end - cur); if (meta_size < 0) return meta_size; btf_add_type(env, t); cur += meta_size; env->log_type_id++; } return 0; } static bool btf_resolve_valid(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { struct btf *btf = env->btf; if (!env_type_is_resolved(env, type_id)) return false; if (btf_type_is_struct(t) || btf_type_is_datasec(t)) return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); if (btf_type_is_decl_tag(t) || btf_type_is_func(t)) return btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); return t && !btf_type_is_modifier(t) && !btf_type_is_var(t) && !btf_type_is_datasec(t); } if (btf_type_is_array(t)) { const struct btf_array *array = btf_type_array(t); const struct btf_type *elem_type; u32 elem_type_id = array->type; u32 elem_size; elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); return elem_type && !btf_type_is_modifier(elem_type) && (array->nelems * elem_size == btf_resolved_type_size(btf, type_id)); } return false; } static int btf_resolve(struct btf_verifier_env *env, const struct btf_type *t, u32 type_id) { u32 save_log_type_id = env->log_type_id; const struct resolve_vertex *v; int err = 0; env->resolve_mode = RESOLVE_TBD; env_stack_push(env, t, type_id); while (!err && (v = env_stack_peak(env))) { env->log_type_id = v->type_id; err = btf_type_ops(v->t)->resolve(env, v); } env->log_type_id = type_id; if (err == -E2BIG) { btf_verifier_log_type(env, t, "Exceeded max resolving depth:%u", MAX_RESOLVE_DEPTH); } else if (err == -EEXIST) { btf_verifier_log_type(env, t, "Loop detected"); } /* Final sanity check */ if (!err && !btf_resolve_valid(env, t, type_id)) { btf_verifier_log_type(env, t, "Invalid resolve state"); err = -EINVAL; } env->log_type_id = save_log_type_id; return err; } static int btf_check_all_types(struct btf_verifier_env *env) { struct btf *btf = env->btf; const struct btf_type *t; u32 type_id, i; int err; err = env_resolve_init(env); if (err) return err; env->phase++; for (i = btf->base_btf ? 0 : 1; i < btf->nr_types; i++) { type_id = btf->start_id + i; t = btf_type_by_id(btf, type_id); env->log_type_id = type_id; if (btf_type_needs_resolve(t) && !env_type_is_resolved(env, type_id)) { err = btf_resolve(env, t, type_id); if (err) return err; } if (btf_type_is_func_proto(t)) { err = btf_func_proto_check(env, t); if (err) return err; } } return 0; } static int btf_parse_type_sec(struct btf_verifier_env *env) { const struct btf_header *hdr = &env->btf->hdr; int err; /* Type section must align to 4 bytes */ if (hdr->type_off & (sizeof(u32) - 1)) { btf_verifier_log(env, "Unaligned type_off"); return -EINVAL; } if (!env->btf->base_btf && !hdr->type_len) { btf_verifier_log(env, "No type found"); return -EINVAL; } err = btf_check_all_metas(env); if (err) return err; return btf_check_all_types(env); } static int btf_parse_str_sec(struct btf_verifier_env *env) { const struct btf_header *hdr; struct btf *btf = env->btf; const char *start, *end; hdr = &btf->hdr; start = btf->nohdr_data + hdr->str_off; end = start + hdr->str_len; if (end != btf->data + btf->data_size) { btf_verifier_log(env, "String section is not at the end"); return -EINVAL; } btf->strings = start; if (btf->base_btf && !hdr->str_len) return 0; if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || end[-1]) { btf_verifier_log(env, "Invalid string section"); return -EINVAL; } if (!btf->base_btf && start[0]) { btf_verifier_log(env, "Invalid string section"); return -EINVAL; } return 0; } static const size_t btf_sec_info_offset[] = { offsetof(struct btf_header, type_off), offsetof(struct btf_header, str_off), }; static int btf_sec_info_cmp(const void *a, const void *b) { const struct btf_sec_info *x = a; const struct btf_sec_info *y = b; return (int)(x->off - y->off) ? : (int)(x->len - y->len); } static int btf_check_sec_info(struct btf_verifier_env *env, u32 btf_data_size) { struct btf_sec_info secs[ARRAY_SIZE(btf_sec_info_offset)]; u32 total, expected_total, i; const struct btf_header *hdr; const struct btf *btf; btf = env->btf; hdr = &btf->hdr; /* Populate the secs from hdr */ for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) secs[i] = *(struct btf_sec_info *)((void *)hdr + btf_sec_info_offset[i]); sort(secs, ARRAY_SIZE(btf_sec_info_offset), sizeof(struct btf_sec_info), btf_sec_info_cmp, NULL); /* Check for gaps and overlap among sections */ total = 0; expected_total = btf_data_size - hdr->hdr_len; for (i = 0; i < ARRAY_SIZE(btf_sec_info_offset); i++) { if (expected_total < secs[i].off) { btf_verifier_log(env, "Invalid section offset"); return -EINVAL; } if (total < secs[i].off) { /* gap */ btf_verifier_log(env, "Unsupported section found"); return -EINVAL; } if (total > secs[i].off) { btf_verifier_log(env, "Section overlap found"); return -EINVAL; } if (expected_total - total < secs[i].len) { btf_verifier_log(env, "Total section length too long"); return -EINVAL; } total += secs[i].len; } /* There is data other than hdr and known sections */ if (expected_total != total) { btf_verifier_log(env, "Unsupported section found"); return -EINVAL; } return 0; } static int btf_parse_hdr(struct btf_verifier_env *env) { u32 hdr_len, hdr_copy, btf_data_size; const struct btf_header *hdr; struct btf *btf; btf = env->btf; btf_data_size = btf->data_size; if (btf_data_size < offsetofend(struct btf_header, hdr_len)) { btf_verifier_log(env, "hdr_len not found"); return -EINVAL; } hdr = btf->data; hdr_len = hdr->hdr_len; if (btf_data_size < hdr_len) { btf_verifier_log(env, "btf_header not found"); return -EINVAL; } /* Ensure the unsupported header fields are zero */ if (hdr_len > sizeof(btf->hdr)) { u8 *expected_zero = btf->data + sizeof(btf->hdr); u8 *end = btf->data + hdr_len; for (; expected_zero < end; expected_zero++) { if (*expected_zero) { btf_verifier_log(env, "Unsupported btf_header"); return -E2BIG; } } } hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); memcpy(&btf->hdr, btf->data, hdr_copy); hdr = &btf->hdr; btf_verifier_log_hdr(env, btf_data_size); if (hdr->magic != BTF_MAGIC) { btf_verifier_log(env, "Invalid magic"); return -EINVAL; } if (hdr->version != BTF_VERSION) { btf_verifier_log(env, "Unsupported version"); return -ENOTSUPP; } if (hdr->flags) { btf_verifier_log(env, "Unsupported flags"); return -ENOTSUPP; } if (!btf->base_btf && btf_data_size == hdr->hdr_len) { btf_verifier_log(env, "No data"); return -EINVAL; } return btf_check_sec_info(env, btf_data_size); } static int btf_check_type_tags(struct btf_verifier_env *env, struct btf *btf, int start_id) { int i, n, good_id = start_id - 1; bool in_tags; n = btf_nr_types(btf); for (i = start_id; i < n; i++) { const struct btf_type *t; int chain_limit = 32; u32 cur_id = i; t = btf_type_by_id(btf, i); if (!t) return -EINVAL; if (!btf_type_is_modifier(t)) continue; cond_resched(); in_tags = btf_type_is_type_tag(t); while (btf_type_is_modifier(t)) { if (!chain_limit--) { btf_verifier_log(env, "Max chain length or cycle detected"); return -ELOOP; } if (btf_type_is_type_tag(t)) { if (!in_tags) { btf_verifier_log(env, "Type tags don't precede modifiers"); return -EINVAL; } } else if (in_tags) { in_tags = false; } if (cur_id <= good_id) break; /* Move to next type */ cur_id = t->type; t = btf_type_by_id(btf, cur_id); if (!t) return -EINVAL; } good_id = i; } return 0; } static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, u32 log_level, char __user *log_ubuf, u32 log_size) { struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL; u8 *data; int err; if (btf_data_size > BTF_MAX_SIZE) return ERR_PTR(-E2BIG); env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); log = &env->log; if (log_level || log_ubuf || log_size) { /* user requested verbose verifier output * and supplied buffer to store the verification trace */ log->level = log_level; log->ubuf = log_ubuf; log->len_total = log_size; /* log attributes have to be sane */ if (!bpf_verifier_log_attr_valid(log)) { err = -EINVAL; goto errout; } } btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; goto errout; } env->btf = btf; data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; goto errout; } btf->data = data; btf->data_size = btf_data_size; if (copy_from_bpfptr(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } err = btf_parse_hdr(env); if (err) goto errout; btf->nohdr_data = btf->data + btf->hdr.hdr_len; err = btf_parse_str_sec(env); if (err) goto errout; err = btf_parse_type_sec(env); if (err) goto errout; err = btf_check_type_tags(env, btf, 1); if (err) goto errout; if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; goto errout; } btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; errout: btf_verifier_env_free(env); if (btf) btf_free(btf); return ERR_PTR(err); } extern char __weak __start_BTF[]; extern char __weak __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) static union { struct bpf_ctx_convert { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ prog_ctx_type _id##_prog; \ kern_ctx_type _id##_kern; #include <linux/bpf_types.h> #undef BPF_PROG_TYPE } *__t; /* 't' is written once under lock. Read many times. */ const struct btf_type *t; } bpf_ctx_convert; enum { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ __ctx_convert##_id, #include <linux/bpf_types.h> #undef BPF_PROG_TYPE __ctx_convert_unused, /* to avoid empty enum in extreme .config */ }; static u8 bpf_ctx_convert_map[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = __ctx_convert##_id, #include <linux/bpf_types.h> #undef BPF_PROG_TYPE 0, /* avoid empty array */ }; #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { const struct btf_type *conv_struct; const struct btf_type *ctx_struct; const struct btf_member *ctx_type; const char *tname, *ctx_tname; conv_struct = bpf_ctx_convert.t; if (!conv_struct) { bpf_log(log, "btf_vmlinux is malformed\n"); return NULL; } t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_struct(t)) { /* Only pointer to struct is supported for now. * That means that BPF_PROG_TYPE_TRACEPOINT with BTF * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ return NULL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "arg#%d struct doesn't have a name\n", arg); return NULL; } /* prog_type is valid bpf program type. No need for bounds check. */ ctx_type = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2; /* ctx_struct is a pointer to prog_ctx_type in vmlinux. * Like 'struct __sk_buff' */ ctx_struct = btf_type_by_id(btf_vmlinux, ctx_type->type); if (!ctx_struct) /* should not happen */ return NULL; again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); return NULL; } /* only compare that prog's ctx type name is the same as * kernel expects. No need to compare field by field. * It's ok for bpf prog to do: * struct __sk_buff {}; * int socket_filter_bpf_prog(struct __sk_buff *skb) * { // no fields of skb are ever used } */ if (strcmp(ctx_tname, tname)) { /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ if (!btf_type_is_modifier(ctx_struct)) return NULL; while (btf_type_is_modifier(ctx_struct)) ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type); goto again; } return ctx_type; } static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) { const struct btf_member *prog_ctx_type, *kern_ctx_type; prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); if (!prog_ctx_type) return -ENOENT; kern_ctx_type = prog_ctx_type + 1; return kern_ctx_type->type; } BTF_ID_LIST(bpf_ctx_convert_btf_id) BTF_ID(struct, bpf_ctx_convert) struct btf *btf_parse_vmlinux(void) { struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL; int err; env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); log = &env->log; log->level = BPF_LOG_KERNEL; btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; goto errout; } env->btf = btf; btf->data = __start_BTF; btf->data_size = __stop_BTF - __start_BTF; btf->kernel_btf = true; snprintf(btf->name, sizeof(btf->name), "vmlinux"); err = btf_parse_hdr(env); if (err) goto errout; btf->nohdr_data = btf->data + btf->hdr.hdr_len; err = btf_parse_str_sec(env); if (err) goto errout; err = btf_check_all_metas(env); if (err) goto errout; err = btf_check_type_tags(env, btf, 1); if (err) goto errout; /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); bpf_struct_ops_init(btf, log); refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); if (err) goto errout; btf_verifier_env_free(env); return btf; errout: btf_verifier_env_free(env); if (btf) { kvfree(btf->types); kfree(btf); } return ERR_PTR(err); } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES static struct btf *btf_parse_module(const char *module_name, const void *data, unsigned int data_size) { struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL, *base_btf; int err; base_btf = bpf_get_btf_vmlinux(); if (IS_ERR(base_btf)) return base_btf; if (!base_btf) return ERR_PTR(-EINVAL); env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); if (!env) return ERR_PTR(-ENOMEM); log = &env->log; log->level = BPF_LOG_KERNEL; btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); if (!btf) { err = -ENOMEM; goto errout; } env->btf = btf; btf->base_btf = base_btf; btf->start_id = base_btf->nr_types; btf->start_str_off = base_btf->hdr.str_len; btf->kernel_btf = true; snprintf(btf->name, sizeof(btf->name), "%s", module_name); btf->data = kvmalloc(data_size, GFP_KERNEL | __GFP_NOWARN); if (!btf->data) { err = -ENOMEM; goto errout; } memcpy(btf->data, data, data_size); btf->data_size = data_size; err = btf_parse_hdr(env); if (err) goto errout; btf->nohdr_data = btf->data + btf->hdr.hdr_len; err = btf_parse_str_sec(env); if (err) goto errout; err = btf_check_all_metas(env); if (err) goto errout; err = btf_check_type_tags(env, btf, btf_nr_types(base_btf)); if (err) goto errout; btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; errout: btf_verifier_env_free(env); if (btf) { kvfree(btf->data); kvfree(btf->types); kfree(btf); } return ERR_PTR(err); } #endif /* CONFIG_DEBUG_INFO_BTF_MODULES */ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) { struct bpf_prog *tgt_prog = prog->aux->dst_prog; if (tgt_prog) return tgt_prog->aux->btf; else return prog->aux->attach_btf; } static bool is_int_ptr(struct btf *btf, const struct btf_type *t) { /* skip modifiers */ t = btf_type_skip_modifiers(btf, t->type, NULL); return btf_type_is_int(t); } static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off) { const struct btf_param *args; const struct btf_type *t; u32 offset = 0, nr_args; int i; if (!func_proto) return off / 8; nr_args = btf_type_vlen(func_proto); args = (const struct btf_param *)(func_proto + 1); for (i = 0; i < nr_args; i++) { t = btf_type_skip_modifiers(btf, args[i].type, NULL); offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8); if (off < offset) return i; } t = btf_type_skip_modifiers(btf, func_proto->type, NULL); offset += btf_type_is_ptr(t) ? 8 : roundup(t->size, 8); if (off < offset) return nr_args; return nr_args + 1; } bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const struct btf_type *t = prog->aux->attach_func_proto; struct bpf_prog *tgt_prog = prog->aux->dst_prog; struct btf *btf = bpf_prog_get_target_btf(prog); const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; const char *tag_value; u32 nr_args, arg; int i, ret; if (off % 8) { bpf_log(log, "func '%s' offset %d is not multiple of 8\n", tname, off); return false; } arg = get_ctx_arg_idx(btf, t, off); args = (const struct btf_param *)(t + 1); /* if (t == NULL) Fall back to default BPF prog with * MAX_BPF_FUNC_REG_ARGS u64 arguments. */ nr_args = t ? btf_type_vlen(t) : MAX_BPF_FUNC_REG_ARGS; if (prog->aux->attach_btf_trace) { /* skip first 'void *__data' argument in btf_trace_##name typedef */ args++; nr_args--; } if (arg > nr_args) { bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); return false; } if (arg == nr_args) { switch (prog->expected_attach_type) { case BPF_LSM_CGROUP: case BPF_LSM_MAC: case BPF_TRACE_FEXIT: /* When LSM programs are attached to void LSM hooks * they use FEXIT trampolines and when attached to * int LSM hooks, they use MODIFY_RETURN trampolines. * * While the LSM programs are BPF_MODIFY_RETURN-like * the check: * * if (ret_type != 'int') * return -EINVAL; * * is _not_ done here. This is still safe as LSM hooks * have only void and int return types. */ if (!t) return true; t = btf_type_by_id(btf, t->type); break; case BPF_MODIFY_RETURN: /* For now the BPF_MODIFY_RETURN can only be attached to * functions that return an int. */ if (!t) return false; t = btf_type_skip_modifiers(btf, t->type, NULL); if (!btf_type_is_small_int(t)) { bpf_log(log, "ret type %s not allowed for fmod_ret\n", btf_type_str(t)); return false; } break; default: bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); return false; } } else { if (!t) /* Default prog with MAX_BPF_FUNC_REG_ARGS args */ return true; t = btf_type_by_id(btf, args[arg].type); } /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (btf_type_is_small_int(t) || btf_is_any_enum(t) || __btf_type_is_struct(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { bpf_log(log, "func '%s' arg%d '%s' has type %s. Only pointer access is allowed\n", tname, arg, __btf_name_by_offset(btf, t->name_off), btf_type_str(t)); return false; } /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; u32 type, flag; type = base_type(ctx_arg_info->reg_type); flag = type_flag(ctx_arg_info->reg_type); if (ctx_arg_info->offset == off && type == PTR_TO_BUF && (flag & PTR_MAYBE_NULL)) { info->reg_type = ctx_arg_info->reg_type; return true; } } if (t->type == 0) /* This is a pointer to void. * It is the same as scalar from the verifier safety pov. * No further pointer walking is allowed. */ return true; if (is_int_ptr(btf, t)) return true; /* this is a pointer to another type */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; if (ctx_arg_info->offset == off) { if (!ctx_arg_info->btf_id) { bpf_log(log,"invalid btf_id for context argument offset %u\n", off); return false; } info->reg_type = ctx_arg_info->reg_type; info->btf = btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } } info->reg_type = PTR_TO_BTF_ID; if (tgt_prog) { enum bpf_prog_type tgt_type; if (tgt_prog->type == BPF_PROG_TYPE_EXT) tgt_type = tgt_prog->aux->saved_dst_prog_type; else tgt_type = tgt_prog->type; ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg); if (ret > 0) { info->btf = btf_vmlinux; info->btf_id = ret; return true; } else { return false; } } info->btf = btf; info->btf_id = t->type; t = btf_type_by_id(btf, t->type); if (btf_type_is_type_tag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); if (strcmp(tag_value, "user") == 0) info->reg_type |= MEM_USER; if (strcmp(tag_value, "percpu") == 0) info->reg_type |= MEM_PERCPU; } /* skip modifiers */ while (btf_type_is_modifier(t)) { info->btf_id = t->type; t = btf_type_by_id(btf, t->type); } if (!btf_type_is_struct(t)) { bpf_log(log, "func '%s' arg%d type %s is not a struct\n", tname, arg, btf_type_str(t)); return false; } bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); return true; } enum bpf_struct_walk_result { /* < 0 error */ WALK_SCALAR = 0, WALK_PTR, WALK_STRUCT, }; static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, u32 *next_btf_id, enum bpf_type_flag *flag) { u32 i, moff, mtrue_end, msize = 0, total_nelems = 0; const struct btf_type *mtype, *elem_type = NULL; const struct btf_member *member; const char *tname, *mname, *tag_value; u32 vlen, elem_id, mid; again: tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { bpf_log(log, "Type '%s' is not a struct\n", tname); return -EINVAL; } vlen = btf_type_vlen(t); if (off + size > t->size) { /* If the last element is a variable size array, we may * need to relax the rule. */ struct btf_array *array_elem; if (vlen == 0) goto error; member = btf_type_member(t) + vlen - 1; mtype = btf_type_skip_modifiers(btf, member->type, NULL); if (!btf_type_is_array(mtype)) goto error; array_elem = (struct btf_array *)(mtype + 1); if (array_elem->nelems != 0) goto error; moff = __btf_member_bit_offset(t, member) / 8; if (off < moff) goto error; /* Only allow structure for now, can be relaxed for * other types later. */ t = btf_type_skip_modifiers(btf, array_elem->type, NULL); if (!btf_type_is_struct(t)) goto error; off = (off - moff) % t->size; goto again; error: bpf_log(log, "access beyond struct %s at off %u size %u\n", tname, off, size); return -EACCES; } for_each_member(i, t, member) { /* offset of the field in bytes */ moff = __btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; if (__btf_member_bitfield_size(t, member)) { u32 end_bit = __btf_member_bit_offset(t, member) + __btf_member_bitfield_size(t, member); /* off <= moff instead of off == moff because clang * does not generate a BTF member for anonymous * bitfield like the ":16" here: * struct { * int :16; * int x:8; * }; */ if (off <= moff && BITS_ROUNDUP_BYTES(end_bit) <= off + size) return WALK_SCALAR; /* off may be accessing a following member * * or * * Doing partial access at either end of this * bitfield. Continue on this case also to * treat it as not accessing this bitfield * and eventually error out as field not * found to keep it simple. * It could be relaxed if there was a legit * partial access case later. */ continue; } /* In case of "off" is pointing to holes of a struct */ if (off < moff) break; /* type of the field */ mid = member->type; mtype = btf_type_by_id(btf, member->type); mname = __btf_name_by_offset(btf, member->name_off); mtype = __btf_resolve_size(btf, mtype, &msize, &elem_type, &elem_id, &total_nelems, &mid); if (IS_ERR(mtype)) { bpf_log(log, "field %s doesn't have size\n", mname); return -EFAULT; } mtrue_end = moff + msize; if (off >= mtrue_end) /* no overlap with member, keep iterating */ continue; if (btf_type_is_array(mtype)) { u32 elem_idx; /* __btf_resolve_size() above helps to * linearize a multi-dimensional array. * * The logic here is treating an array * in a struct as the following way: * * struct outer { * struct inner array[2][2]; * }; * * looks like: * * struct outer { * struct inner array_elem0; * struct inner array_elem1; * struct inner array_elem2; * struct inner array_elem3; * }; * * When accessing outer->array[1][0], it moves * moff to "array_elem2", set mtype to * "struct inner", and msize also becomes * sizeof(struct inner). Then most of the * remaining logic will fall through without * caring the current member is an array or * not. * * Unlike mtype/msize/moff, mtrue_end does not * change. The naming difference ("_true") tells * that it is not always corresponding to * the current mtype/msize/moff. * It is the true end of the current * member (i.e. array in this case). That * will allow an int array to be accessed like * a scratch space, * i.e. allow access beyond the size of * the array's element as long as it is * within the mtrue_end boundary. */ /* skip empty array */ if (moff == mtrue_end) continue; msize /= total_nelems; elem_idx = (off - moff) / msize; moff += elem_idx * msize; mtype = elem_type; mid = elem_id; } /* the 'off' we're looking for is either equal to start * of this field or inside of this struct */ if (btf_type_is_struct(mtype)) { /* our field must be inside that union or struct */ t = mtype; /* return if the offset matches the member offset */ if (off == moff) { *next_btf_id = mid; return WALK_STRUCT; } /* adjust offset we're looking for */ off -= moff; goto again; } if (btf_type_is_ptr(mtype)) { const struct btf_type *stype, *t; enum bpf_type_flag tmp_flag = 0; u32 id; if (msize != size || off != moff) { bpf_log(log, "cannot access ptr member %s with moff %u in struct %s with off %u size %u\n", mname, moff, tname, off, size); return -EACCES; } /* check type tag */ t = btf_type_by_id(btf, mtype->type); if (btf_type_is_type_tag(t)) { tag_value = __btf_name_by_offset(btf, t->name_off); /* check __user tag */ if (strcmp(tag_value, "user") == 0) tmp_flag = MEM_USER; /* check __percpu tag */ if (strcmp(tag_value, "percpu") == 0) tmp_flag = MEM_PERCPU; } stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; *flag = tmp_flag; return WALK_PTR; } } /* Allow more flexible access within an int as long as * it is within mtrue_end. * Since mtrue_end could be the end of an array, * that also allows using an array of int as a scratch * space. e.g. skb->cb[]. */ if (off + size > mtrue_end && !(*flag & PTR_UNTRUSTED)) { bpf_log(log, "access beyond the end of member %s (mend:%u) in struct %s with off %u size %u\n", mname, mtrue_end, tname, off, size); return -EACCES; } return WALK_SCALAR; } bpf_log(log, "struct %s doesn't have field at offset %d\n", tname, off); return -EINVAL; } int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype __maybe_unused, u32 *next_btf_id, enum bpf_type_flag *flag) { enum bpf_type_flag tmp_flag = 0; int err; u32 id; do { err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); switch (err) { case WALK_PTR: /* If we found the pointer or scalar on t+off, * we're done. */ *next_btf_id = id; *flag = tmp_flag; return PTR_TO_BTF_ID; case WALK_SCALAR: return SCALAR_VALUE; case WALK_STRUCT: /* We found nested struct, so continue the search * by diving in it. At this point the offset is * aligned with the new type, so set it to 0. */ t = btf_type_by_id(btf, id); off = 0; break; default: /* It's either error or unknown return value.. * scream and leave. */ if (WARN_ONCE(err > 0, "unknown btf_struct_walk return value")) return -EINVAL; return err; } } while (t); return -EINVAL; } /* Check that two BTF types, each specified as an BTF object + id, are exactly * the same. Trivial ID check is not enough due to module BTFs, because we can * end up with two different module BTFs, but IDs point to the common type in * vmlinux BTF. */ static bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2) { if (id1 != id2) return false; if (btf1 == btf2) return true; return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2); } bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, bool strict) { const struct btf_type *type; enum bpf_type_flag flag; int err; /* Are we already done? */ if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id)) return true; /* In case of strict type match, we do not walk struct, the top level * type match must succeed. When strict is true, off should have already * been 0. */ if (strict) return false; again: type = btf_type_by_id(btf, id); if (!type) return false; err = btf_struct_walk(log, btf, type, off, 1, &id, &flag); if (err != WALK_STRUCT) return false; /* We found nested struct object. If it matches * the requested ID, we're done. Otherwise let's * continue the search with offset 0 in the new * type. */ if (!btf_types_are_same(btf, id, need_btf, need_type_id)) { off = 0; goto again; } return true; } static int __get_type_size(struct btf *btf, u32 btf_id, const struct btf_type **ret_type) { const struct btf_type *t; *ret_type = btf_type_by_id(btf, 0); if (!btf_id) /* void */ return 0; t = btf_type_by_id(btf, btf_id); while (t && btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!t) return -EINVAL; *ret_type = t; if (btf_type_is_ptr(t)) /* kernel size of pointer. Not BPF's size of pointer*/ return sizeof(void *); if (btf_type_is_int(t) || btf_is_any_enum(t) || __btf_type_is_struct(t)) return t->size; return -EINVAL; } int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func, const char *tname, struct btf_func_model *m) { const struct btf_param *args; const struct btf_type *t; u32 i, nargs; int ret; if (!func) { /* BTF function prototype doesn't match the verifier types. * Fall back to MAX_BPF_FUNC_REG_ARGS u64 args. */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { m->arg_size[i] = 8; m->arg_flags[i] = 0; } m->ret_size = 8; m->nr_args = MAX_BPF_FUNC_REG_ARGS; return 0; } args = (const struct btf_param *)(func + 1); nargs = btf_type_vlen(func); if (nargs > MAX_BPF_FUNC_ARGS) { bpf_log(log, "The function %s has %d arguments. Too many.\n", tname, nargs); return -EINVAL; } ret = __get_type_size(btf, func->type, &t); if (ret < 0 || __btf_type_is_struct(t)) { bpf_log(log, "The function %s return type %s is unsupported.\n", tname, btf_type_str(t)); return -EINVAL; } m->ret_size = ret; for (i = 0; i < nargs; i++) { if (i == nargs - 1 && args[i].type == 0) { bpf_log(log, "The function %s with variable args is unsupported.\n", tname); return -EINVAL; } ret = __get_type_size(btf, args[i].type, &t); /* No support of struct argument size greater than 16 bytes */ if (ret < 0 || ret > 16) { bpf_log(log, "The function %s arg%d type %s is unsupported.\n", tname, i, btf_type_str(t)); return -EINVAL; } if (ret == 0) { bpf_log(log, "The function %s has malformed void argument.\n", tname); return -EINVAL; } m->arg_size[i] = ret; m->arg_flags[i] = __btf_type_is_struct(t) ? BTF_FMODEL_STRUCT_ARG : 0; } m->nr_args = nargs; return 0; } /* Compare BTFs of two functions assuming only scalars and pointers to context. * t1 points to BTF_KIND_FUNC in btf1 * t2 points to BTF_KIND_FUNC in btf2 * Returns: * EINVAL - function prototype mismatch * EFAULT - verifier bug * 0 - 99% match. The last 1% is validated by the verifier. */ static int btf_check_func_type_match(struct bpf_verifier_log *log, struct btf *btf1, const struct btf_type *t1, struct btf *btf2, const struct btf_type *t2) { const struct btf_param *args1, *args2; const char *fn1, *fn2, *s1, *s2; u32 nargs1, nargs2, i; fn1 = btf_name_by_offset(btf1, t1->name_off); fn2 = btf_name_by_offset(btf2, t2->name_off); if (btf_func_linkage(t1) != BTF_FUNC_GLOBAL) { bpf_log(log, "%s() is not a global function\n", fn1); return -EINVAL; } if (btf_func_linkage(t2) != BTF_FUNC_GLOBAL) { bpf_log(log, "%s() is not a global function\n", fn2); return -EINVAL; } t1 = btf_type_by_id(btf1, t1->type); if (!t1 || !btf_type_is_func_proto(t1)) return -EFAULT; t2 = btf_type_by_id(btf2, t2->type); if (!t2 || !btf_type_is_func_proto(t2)) return -EFAULT; args1 = (const struct btf_param *)(t1 + 1); nargs1 = btf_type_vlen(t1); args2 = (const struct btf_param *)(t2 + 1); nargs2 = btf_type_vlen(t2); if (nargs1 != nargs2) { bpf_log(log, "%s() has %d args while %s() has %d args\n", fn1, nargs1, fn2, nargs2); return -EINVAL; } t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); if (t1->info != t2->info) { bpf_log(log, "Return type %s of %s() doesn't match type %s of %s()\n", btf_type_str(t1), fn1, btf_type_str(t2), fn2); return -EINVAL; } for (i = 0; i < nargs1; i++) { t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL); t2 = btf_type_skip_modifiers(btf2, args2[i].type, NULL); if (t1->info != t2->info) { bpf_log(log, "arg%d in %s() is %s while %s() has %s\n", i, fn1, btf_type_str(t1), fn2, btf_type_str(t2)); return -EINVAL; } if (btf_type_has_size(t1) && t1->size != t2->size) { bpf_log(log, "arg%d in %s() has size %d while %s() has %d\n", i, fn1, t1->size, fn2, t2->size); return -EINVAL; } /* global functions are validated with scalars and pointers * to context only. And only global functions can be replaced. * Hence type check only those types. */ if (btf_type_is_int(t1) || btf_is_any_enum(t1)) continue; if (!btf_type_is_ptr(t1)) { bpf_log(log, "arg%d in %s() has unrecognized type\n", i, fn1); return -EINVAL; } t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); if (!btf_type_is_struct(t1)) { bpf_log(log, "arg%d in %s() is not a pointer to context\n", i, fn1); return -EINVAL; } if (!btf_type_is_struct(t2)) { bpf_log(log, "arg%d in %s() is not a pointer to context\n", i, fn2); return -EINVAL; } /* This is an optional check to make program writing easier. * Compare names of structs and report an error to the user. * btf_prepare_func_args() already checked that t2 struct * is a context type. btf_prepare_func_args() will check * later that t1 struct is a context type as well. */ s1 = btf_name_by_offset(btf1, t1->name_off); s2 = btf_name_by_offset(btf2, t2->name_off); if (strcmp(s1, s2)) { bpf_log(log, "arg%d %s(struct %s *) doesn't match %s(struct %s *)\n", i, fn1, s1, fn2, s2); return -EINVAL; } } return 0; } /* Compare BTFs of given program with BTF of target program */ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf2, const struct btf_type *t2) { struct btf *btf1 = prog->aux->btf; const struct btf_type *t1; u32 btf_id = 0; if (!prog->aux->func_info) { bpf_log(log, "Program extension requires BTF\n"); return -EINVAL; } btf_id = prog->aux->func_info[0].type_id; if (!btf_id) return -EFAULT; t1 = btf_type_by_id(btf1, btf_id); if (!t1 || !btf_type_is_func(t1)) return -EFAULT; return btf_check_func_type_match(log, btf1, t1, btf2, t2); } static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { #ifdef CONFIG_NET [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], #endif }; /* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int rec) { const struct btf_type *member_type; const struct btf_member *member; u32 i; if (!btf_type_is_struct(t)) return false; for_each_member(i, t, member) { const struct btf_array *array; member_type = btf_type_skip_modifiers(btf, member->type, NULL); if (btf_type_is_struct(member_type)) { if (rec >= 3) { bpf_log(log, "max struct nesting depth exceeded\n"); return false; } if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1)) return false; continue; } if (btf_type_is_array(member_type)) { array = btf_type_array(member_type); if (!array->nelems) return false; member_type = btf_type_skip_modifiers(btf, array->type, NULL); if (!btf_type_is_scalar(member_type)) return false; continue; } if (!btf_type_is_scalar(member_type)) return false; } return true; } static bool is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) { int len, sfx_len = sizeof("__sz") - 1; const struct btf_type *t; const char *param_name; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; /* In the future, this can be ported to use BTF tagging */ param_name = btf_name_by_offset(btf, arg->name_off); if (str_is_empty(param_name)) return false; len = strlen(param_name); if (len < sfx_len) return false; param_name += len - sfx_len; if (strncmp(param_name, "__sz", sfx_len)) return false; return true; } static bool btf_is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg, const char *name) { int len, target_len = strlen(name); const struct btf_type *t; const char *param_name; t = btf_type_skip_modifiers(btf, arg->type, NULL); if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; param_name = btf_name_by_offset(btf, arg->name_off); if (str_is_empty(param_name)) return false; len = strlen(param_name); if (len != target_len) return false; if (strcmp(param_name, name)) return false; return true; } static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok, struct bpf_kfunc_arg_meta *kfunc_meta, bool processing_call) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); bool rel = false, kptr_get = false, trusted_args = false; bool sleepable = false; struct bpf_verifier_log *log = &env->log; u32 i, nargs, ref_id, ref_obj_id = 0; bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; int ref_regno = 0, ret; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info or in add_kfunc_call(). */ bpf_log(log, "BTF of func_id %u doesn't point to KIND_FUNC\n", func_id); return -EFAULT; } func_name = btf_name_by_offset(btf, t->name_off); t = btf_type_by_id(btf, t->type); if (!t || !btf_type_is_func_proto(t)) { bpf_log(log, "Invalid BTF of func %s\n", func_name); return -EFAULT; } args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { bpf_log(log, "Function %s has %d > %d args\n", func_name, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } if (is_kfunc && kfunc_meta) { /* Only kfunc can be release func */ rel = kfunc_meta->flags & KF_RELEASE; kptr_get = kfunc_meta->flags & KF_KPTR_GET; trusted_args = kfunc_meta->flags & KF_TRUSTED_ARGS; sleepable = kfunc_meta->flags & KF_SLEEPABLE; } /* check that BTF function arguments match actual types that the * verifier sees. */ for (i = 0; i < nargs; i++) { enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; bool obj_ptr = false; t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (btf_type_is_scalar(t)) { if (is_kfunc && kfunc_meta) { bool is_buf_size = false; /* check for any const scalar parameter of name "rdonly_buf_size" * or "rdwr_buf_size" */ if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, "rdonly_buf_size")) { kfunc_meta->r0_rdonly = true; is_buf_size = true; } else if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, "rdwr_buf_size")) is_buf_size = true; if (is_buf_size) { if (kfunc_meta->r0_size) { bpf_log(log, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); return -EINVAL; } if (!tnum_is_const(reg->var_off)) { bpf_log(log, "R%d is not a const\n", regno); return -EINVAL; } kfunc_meta->r0_size = reg->var_off.value; ret = mark_chain_precision(env, regno); if (ret) return ret; } } if (reg->type == SCALAR_VALUE) continue; bpf_log(log, "R%d is not a scalar\n", regno); return -EINVAL; } if (!btf_type_is_ptr(t)) { bpf_log(log, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); return -EINVAL; } /* These register types have special constraints wrt ref_obj_id * and offset checks. The rest of trusted args don't. */ obj_ptr = reg->type == PTR_TO_CTX || reg->type == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)]; /* Check if argument must be a referenced pointer, args + i has * been verified to be a pointer (after skipping modifiers). * PTR_TO_CTX is ok without having non-zero ref_obj_id. */ if (is_kfunc && trusted_args && (obj_ptr && reg->type != PTR_TO_CTX) && !reg->ref_obj_id) { bpf_log(log, "R%d must be referenced\n", regno); return -EINVAL; } ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); /* Trusted args have the same offset checks as release arguments */ if ((trusted_args && obj_ptr) || (rel && reg->ref_obj_id)) arg_type |= OBJ_RELEASE; ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; if (is_kfunc && reg->ref_obj_id) { /* Ensure only one argument is referenced PTR_TO_BTF_ID */ if (ref_obj_id) { bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", regno, reg->ref_obj_id, ref_obj_id); return -EFAULT; } ref_regno = regno; ref_obj_id = reg->ref_obj_id; } /* kptr_get is only true for kfunc */ if (i == 0 && kptr_get) { struct bpf_map_value_off_desc *off_desc; if (reg->type != PTR_TO_MAP_VALUE) { bpf_log(log, "arg#0 expected pointer to map value\n"); return -EINVAL; } /* check_func_arg_reg_off allows var_off for * PTR_TO_MAP_VALUE, but we need fixed offset to find * off_desc. */ if (!tnum_is_const(reg->var_off)) { bpf_log(log, "arg#0 must have constant offset\n"); return -EINVAL; } off_desc = bpf_map_kptr_off_contains(reg->map_ptr, reg->off + reg->var_off.value); if (!off_desc || off_desc->type != BPF_KPTR_REF) { bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n", reg->off + reg->var_off.value); return -EINVAL; } if (!btf_type_is_ptr(ref_t)) { bpf_log(log, "arg#0 BTF type must be a double pointer\n"); return -EINVAL; } ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); if (!btf_type_is_struct(ref_t)) { bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", func_name, i, btf_type_str(ref_t), ref_tname); return -EINVAL; } if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf, off_desc->kptr.btf_id, true)) { bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n", func_name, i, btf_type_str(ref_t), ref_tname); return -EINVAL; } /* rest of the arguments can be anything, like normal kfunc */ } else if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ if (reg->type != PTR_TO_CTX) { bpf_log(log, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); return -EINVAL; } } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) { const struct btf_type *reg_ref_t; const struct btf *reg_btf; const char *reg_ref_tname; u32 reg_ref_id; if (!btf_type_is_struct(ref_t)) { bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", func_name, i, btf_type_str(ref_t), ref_tname); return -EINVAL; } if (reg->type == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; } else { reg_btf = btf_vmlinux; reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); if (!btf_struct_ids_match(log, reg_btf, reg_ref_id, reg->off, btf, ref_id, trusted_args || (rel && reg->ref_obj_id))) { bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", func_name, i, btf_type_str(ref_t), ref_tname, regno, btf_type_str(reg_ref_t), reg_ref_tname); return -EINVAL; } } else if (ptr_to_mem_ok && processing_call) { const struct btf_type *resolve_ret; u32 type_size; if (is_kfunc) { bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]); bool arg_dynptr = btf_type_is_struct(ref_t) && !strcmp(ref_tname, stringify_struct(bpf_dynptr_kern)); /* Permit pointer to mem, but only when argument * type is pointer to scalar, or struct composed * (recursively) of scalars. * When arg_mem_size is true, the pointer can be * void *. * Also permit initialized local dynamic pointers. */ if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(log, btf, ref_t, 0) && !arg_dynptr && (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { bpf_log(log, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); return -EINVAL; } if (arg_dynptr) { if (reg->type != PTR_TO_STACK) { bpf_log(log, "arg#%d pointer type %s %s not to stack\n", i, btf_type_str(ref_t), ref_tname); return -EINVAL; } if (!is_dynptr_reg_valid_init(env, reg)) { bpf_log(log, "arg#%d pointer type %s %s must be valid and initialized\n", i, btf_type_str(ref_t), ref_tname); return -EINVAL; } if (!is_dynptr_type_expected(env, reg, ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { bpf_log(log, "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", i, btf_type_str(ref_t), ref_tname); return -EINVAL; } continue; } /* Check for mem, len pair */ if (arg_mem_size) { if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) { bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); return -EINVAL; } i++; continue; } } resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", i, btf_type_str(ref_t), ref_tname, PTR_ERR(resolve_ret)); return -EINVAL; } if (check_mem_reg(env, reg, regno, type_size)) return -EINVAL; } else { bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i, is_kfunc ? "kernel " : "", func_name, func_id); return -EINVAL; } } /* Either both are set, or neither */ WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno)); /* We already made sure ref_obj_id is set only for one argument. We do * allow (!rel && ref_obj_id), so that passing such referenced * PTR_TO_BTF_ID to other kfuncs works. Note that rel is only true when * is_kfunc is true. */ if (rel && !ref_obj_id) { bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", func_name); return -EINVAL; } if (sleepable && !env->prog->aux->sleepable) { bpf_log(log, "kernel function %s is sleepable but the program is not\n", func_name); return -EINVAL; } if (kfunc_meta && ref_obj_id) kfunc_meta->ref_obj_id = ref_obj_id; /* returns argument register number > 0 in case of reference release kfunc */ return rel ? ref_regno : 0; } /* Compare BTF of a function declaration with given bpf_reg_state. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - there is a type mismatch or BTF is not available. * 0 - BTF matches with what bpf_reg_state expects. * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. */ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs) { struct bpf_prog *prog = env->prog; struct btf *btf = prog->aux->btf; bool is_global; u32 btf_id; int err; if (!prog->aux->func_info) return -EINVAL; btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) return -EFAULT; if (prog->aux->func_info_aux[subprog].unreliable) return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, false); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. * In such cases mark the function as unreliable from BTF point of view. */ if (err) prog->aux->func_info_aux[subprog].unreliable = true; return err; } /* Compare BTF of a function call with given bpf_reg_state. * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - there is a type mismatch or BTF is not available. * 0 - BTF matches with what bpf_reg_state expects. * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. * * NOTE: the code is duplicated from btf_check_subprog_arg_match() * because btf_check_func_arg_match() is still doing both. Once that * function is split in 2, we can call from here btf_check_subprog_arg_match() * first, and then treat the calling part in a new code path. */ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs) { struct bpf_prog *prog = env->prog; struct btf *btf = prog->aux->btf; bool is_global; u32 btf_id; int err; if (!prog->aux->func_info) return -EINVAL; btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) return -EFAULT; if (prog->aux->func_info_aux[subprog].unreliable) return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, true); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. * In such cases mark the function as unreliable from BTF point of view. */ if (err) prog->aux->func_info_aux[subprog].unreliable = true; return err; } int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, struct bpf_kfunc_arg_meta *meta) { return btf_check_func_arg_match(env, btf, func_id, regs, true, meta, true); } /* Convert BTF of a function into bpf_reg_state if possible * Returns: * EFAULT - there is a verifier bug. Abort verification. * EINVAL - cannot convert BTF. * 0 - Successfully converted BTF into bpf_reg_state * (either PTR_TO_CTX or SCALAR_VALUE). */ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs) { struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; enum bpf_prog_type prog_type = prog->type; struct btf *btf = prog->aux->btf; const struct btf_param *args; const struct btf_type *t, *ref_t; u32 i, nargs, btf_id; const char *tname; if (!prog->aux->func_info || prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { bpf_log(log, "Verifier bug\n"); return -EFAULT; } btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) { bpf_log(log, "Global functions need valid BTF\n"); return -EFAULT; } t = btf_type_by_id(btf, btf_id); if (!t || !btf_type_is_func(t)) { /* These checks were already done by the verifier while loading * struct bpf_func_info */ bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", subprog); return -EFAULT; } tname = btf_name_by_offset(btf, t->name_off); if (log->level & BPF_LOG_LEVEL) bpf_log(log, "Validating %s() func#%d...\n", tname, subprog); if (prog->aux->func_info_aux[subprog].unreliable) { bpf_log(log, "Verifier bug in function %s()\n", tname); return -EFAULT; } if (prog_type == BPF_PROG_TYPE_EXT) prog_type = prog->aux->dst_prog->type; t = btf_type_by_id(btf, t->type); if (!t || !btf_type_is_func_proto(t)) { bpf_log(log, "Invalid type of function %s()\n", tname); return -EFAULT; } args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } /* check that function returns int */ t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); return -EINVAL; } /* Convert BTF function arguments into verifier types. * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { struct bpf_reg_state *reg = ®s[i + 1]; t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (btf_type_is_int(t) || btf_is_any_enum(t)) { reg->type = SCALAR_VALUE; continue; } if (btf_type_is_ptr(t)) { if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { reg->type = PTR_TO_CTX; continue; } t = btf_type_skip_modifiers(btf, t->type, NULL); ref_t = btf_resolve_size(btf, t, ®->mem_size); if (IS_ERR(ref_t)) { bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", i, btf_type_str(t), btf_name_by_offset(btf, t->name_off), PTR_ERR(ref_t)); return -EINVAL; } reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; reg->id = ++env->id_gen; continue; } bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } return 0; } static void btf_type_show(const struct btf *btf, u32 type_id, void *obj, struct btf_show *show) { const struct btf_type *t = btf_type_by_id(btf, type_id); show->btf = btf; memset(&show->state, 0, sizeof(show->state)); memset(&show->obj, 0, sizeof(show->obj)); btf_type_ops(t)->show(btf, t, type_id, obj, 0, show); } static void btf_seq_show(struct btf_show *show, const char *fmt, va_list args) { seq_vprintf((struct seq_file *)show->target, fmt, args); } int btf_type_seq_show_flags(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m, u64 flags) { struct btf_show sseq; sseq.target = m; sseq.showfn = btf_seq_show; sseq.flags = flags; btf_type_show(btf, type_id, obj, &sseq); return sseq.state.status; } void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, struct seq_file *m) { (void) btf_type_seq_show_flags(btf, type_id, obj, m, BTF_SHOW_NONAME | BTF_SHOW_COMPACT | BTF_SHOW_ZERO | BTF_SHOW_UNSAFE); } struct btf_show_snprintf { struct btf_show show; int len_left; /* space left in string */ int len; /* length we would have written */ }; static void btf_snprintf_show(struct btf_show *show, const char *fmt, va_list args) { struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show; int len; len = vsnprintf(show->target, ssnprintf->len_left, fmt, args); if (len < 0) { ssnprintf->len_left = 0; ssnprintf->len = len; } else if (len >= ssnprintf->len_left) { /* no space, drive on to get length we would have written */ ssnprintf->len_left = 0; ssnprintf->len += len; } else { ssnprintf->len_left -= len; ssnprintf->len += len; show->target += len; } } int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, char *buf, int len, u64 flags) { struct btf_show_snprintf ssnprintf; ssnprintf.show.target = buf; ssnprintf.show.flags = flags; ssnprintf.show.showfn = btf_snprintf_show; ssnprintf.len_left = len; ssnprintf.len = 0; btf_type_show(btf, type_id, obj, (struct btf_show *)&ssnprintf); /* If we encountered an error, return it. */ if (ssnprintf.show.state.status) return ssnprintf.show.state.status; /* Otherwise return length we would have written */ return ssnprintf.len; } #ifdef CONFIG_PROC_FS static void bpf_btf_show_fdinfo(struct seq_file *m, struct file *filp) { const struct btf *btf = filp->private_data; seq_printf(m, "btf_id:\t%u\n", btf->id); } #endif static int btf_release(struct inode *inode, struct file *filp) { btf_put(filp->private_data); return 0; } const struct file_operations btf_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_btf_show_fdinfo, #endif .release = btf_release, }; static int __btf_new_fd(struct btf *btf) { return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); } int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr) { struct btf *btf; int ret; btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel), attr->btf_size, attr->btf_log_level, u64_to_user_ptr(attr->btf_log_buf), attr->btf_log_size); if (IS_ERR(btf)) return PTR_ERR(btf); ret = btf_alloc_id(btf); if (ret) { btf_free(btf); return ret; } /* * The BTF ID is published to the userspace. * All BTF free must go through call_rcu() from * now on (i.e. free by calling btf_put()). */ ret = __btf_new_fd(btf); if (ret < 0) btf_put(btf); return ret; } struct btf *btf_get_by_fd(int fd) { struct btf *btf; struct fd f; f = fdget(fd); if (!f.file) return ERR_PTR(-EBADF); if (f.file->f_op != &btf_fops) { fdput(f); return ERR_PTR(-EINVAL); } btf = f.file->private_data; refcount_inc(&btf->refcnt); fdput(f); return btf; } int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo; struct bpf_btf_info info; u32 info_copy, btf_copy; void __user *ubtf; char __user *uname; u32 uinfo_len, uname_len, name_len; int ret = 0; uinfo = u64_to_user_ptr(attr->info.info); uinfo_len = attr->info.info_len; info_copy = min_t(u32, uinfo_len, sizeof(info)); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_copy)) return -EFAULT; info.id = btf->id; ubtf = u64_to_user_ptr(info.btf); btf_copy = min_t(u32, btf->data_size, info.btf_size); if (copy_to_user(ubtf, btf->data, btf_copy)) return -EFAULT; info.btf_size = btf->data_size; info.kernel_btf = btf->kernel_btf; uname = u64_to_user_ptr(info.name); uname_len = info.name_len; if (!uname ^ !uname_len) return -EINVAL; name_len = strlen(btf->name); info.name_len = name_len; if (uname) { if (uname_len >= name_len + 1) { if (copy_to_user(uname, btf->name, name_len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(uname, btf->name, uname_len - 1)) return -EFAULT; if (put_user(zero, uname + uname_len - 1)) return -EFAULT; /* let user-space know about too short buffer */ ret = -ENOSPC; } } if (copy_to_user(uinfo, &info, info_copy) || put_user(info_copy, &uattr->info.info_len)) return -EFAULT; return ret; } int btf_get_fd_by_id(u32 id) { struct btf *btf; int fd; rcu_read_lock(); btf = idr_find(&btf_idr, id); if (!btf || !refcount_inc_not_zero(&btf->refcnt)) btf = ERR_PTR(-ENOENT); rcu_read_unlock(); if (IS_ERR(btf)) return PTR_ERR(btf); fd = __btf_new_fd(btf); if (fd < 0) btf_put(btf); return fd; } u32 btf_obj_id(const struct btf *btf) { return btf->id; } bool btf_is_kernel(const struct btf *btf) { return btf->kernel_btf; } bool btf_is_module(const struct btf *btf) { return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0; } static int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; return *pa - *pb; } bool btf_id_set_contains(const struct btf_id_set *set, u32 id) { return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; } static void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) { return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } enum { BTF_MODULE_F_LIVE = (1 << 0), }; #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module { struct list_head list; struct module *module; struct btf *btf; struct bin_attribute *sysfs_attr; int flags; }; static LIST_HEAD(btf_modules); static DEFINE_MUTEX(btf_module_mutex); static ssize_t btf_module_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { const struct btf *btf = bin_attr->private; memcpy(buf, btf->data + off, len); return len; } static void purge_cand_cache(struct btf *btf); static int btf_module_notify(struct notifier_block *nb, unsigned long op, void *module) { struct btf_module *btf_mod, *tmp; struct module *mod = module; struct btf *btf; int err = 0; if (mod->btf_data_size == 0 || (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE && op != MODULE_STATE_GOING)) goto out; switch (op) { case MODULE_STATE_COMING: btf_mod = kzalloc(sizeof(*btf_mod), GFP_KERNEL); if (!btf_mod) { err = -ENOMEM; goto out; } btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size); if (IS_ERR(btf)) { kfree(btf_mod); if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) { pr_warn("failed to validate module [%s] BTF: %ld\n", mod->name, PTR_ERR(btf)); err = PTR_ERR(btf); } else { pr_warn_once("Kernel module BTF mismatch detected, BTF debug info may be unavailable for some modules\n"); } goto out; } err = btf_alloc_id(btf); if (err) { btf_free(btf); kfree(btf_mod); goto out; } purge_cand_cache(NULL); mutex_lock(&btf_module_mutex); btf_mod->module = module; btf_mod->btf = btf; list_add(&btf_mod->list, &btf_modules); mutex_unlock(&btf_module_mutex); if (IS_ENABLED(CONFIG_SYSFS)) { struct bin_attribute *attr; attr = kzalloc(sizeof(*attr), GFP_KERNEL); if (!attr) goto out; sysfs_bin_attr_init(attr); attr->attr.name = btf->name; attr->attr.mode = 0444; attr->size = btf->data_size; attr->private = btf; attr->read = btf_module_read; err = sysfs_create_bin_file(btf_kobj, attr); if (err) { pr_warn("failed to register module [%s] BTF in sysfs: %d\n", mod->name, err); kfree(attr); err = 0; goto out; } btf_mod->sysfs_attr = attr; } break; case MODULE_STATE_LIVE: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->module != module) continue; btf_mod->flags |= BTF_MODULE_F_LIVE; break; } mutex_unlock(&btf_module_mutex); break; case MODULE_STATE_GOING: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->module != module) continue; list_del(&btf_mod->list); if (btf_mod->sysfs_attr) sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr); purge_cand_cache(btf_mod->btf); btf_put(btf_mod->btf); kfree(btf_mod->sysfs_attr); kfree(btf_mod); break; } mutex_unlock(&btf_module_mutex); break; } out: return notifier_from_errno(err); } static struct notifier_block btf_module_nb = { .notifier_call = btf_module_notify, }; static int __init btf_module_init(void) { register_module_notifier(&btf_module_nb); return 0; } fs_initcall(btf_module_init); #endif /* CONFIG_DEBUG_INFO_BTF_MODULES */ struct module *btf_try_get_module(const struct btf *btf) { struct module *res = NULL; #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module *btf_mod, *tmp; mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->btf != btf) continue; /* We must only consider module whose __init routine has * finished, hence we must check for BTF_MODULE_F_LIVE flag, * which is set from the notifier callback for * MODULE_STATE_LIVE. */ if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module)) res = btf_mod->module; break; } mutex_unlock(&btf_module_mutex); #endif return res; } /* Returns struct btf corresponding to the struct module. * This function can return NULL or ERR_PTR. */ static struct btf *btf_get_module_btf(const struct module *module) { #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module *btf_mod, *tmp; #endif struct btf *btf = NULL; if (!module) { btf = bpf_get_btf_vmlinux(); if (!IS_ERR_OR_NULL(btf)) btf_get(btf); return btf; } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { if (btf_mod->module != module) continue; btf_get(btf_mod->btf); btf = btf_mod->btf; break; } mutex_unlock(&btf_module_mutex); #endif return btf; } BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf = NULL; int btf_obj_fd = 0; long ret; if (flags) return -EINVAL; if (name_sz <= 1 || name[name_sz - 1]) return -EINVAL; ret = bpf_find_btf_id(name, kind, &btf); if (ret > 0 && btf_is_module(btf)) { btf_obj_fd = __btf_new_fd(btf); if (btf_obj_fd < 0) { btf_put(btf); return btf_obj_fd; } return ret | (((u64)btf_obj_fd) << 32); } if (ret > 0) btf_put(btf); return ret; } const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .func = bpf_btf_find_by_name_kind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) #define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE /* Kernel Function (kfunc) BTF ID set registration API */ static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, struct btf_id_set8 *add_set) { bool vmlinux_set = !btf_is_module(btf); struct btf_kfunc_set_tab *tab; struct btf_id_set8 *set; u32 set_cnt; int ret; if (hook >= BTF_KFUNC_HOOK_MAX) { ret = -EINVAL; goto end; } if (!add_set->cnt) return 0; tab = btf->kfunc_set_tab; if (!tab) { tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN); if (!tab) return -ENOMEM; btf->kfunc_set_tab = tab; } set = tab->sets[hook]; /* Warn when register_btf_kfunc_id_set is called twice for the same hook * for module sets. */ if (WARN_ON_ONCE(set && !vmlinux_set)) { ret = -EINVAL; goto end; } /* We don't need to allocate, concatenate, and sort module sets, because * only one is allowed per hook. Hence, we can directly assign the * pointer and return. */ if (!vmlinux_set) { tab->sets[hook] = add_set; return 0; } /* In case of vmlinux sets, there may be more than one set being * registered per hook. To create a unified set, we allocate a new set * and concatenate all individual sets being registered. While each set * is individually sorted, they may become unsorted when concatenated, * hence re-sorting the final set again is required to make binary * searching the set using btf_id_set8_contains function work. */ set_cnt = set ? set->cnt : 0; if (set_cnt > U32_MAX - add_set->cnt) { ret = -EOVERFLOW; goto end; } if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) { ret = -E2BIG; goto end; } /* Grow set */ set = krealloc(tab->sets[hook], offsetof(struct btf_id_set8, pairs[set_cnt + add_set->cnt]), GFP_KERNEL | __GFP_NOWARN); if (!set) { ret = -ENOMEM; goto end; } /* For newly allocated set, initialize set->cnt to 0 */ if (!tab->sets[hook]) set->cnt = 0; tab->sets[hook] = set; /* Concatenate the two sets */ memcpy(set->pairs + set->cnt, add_set->pairs, add_set->cnt * sizeof(set->pairs[0])); set->cnt += add_set->cnt; sort(set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func, NULL); return 0; end: btf_free_kfunc_set_tab(btf); return ret; } static u32 *__btf_kfunc_id_set_contains(const struct btf *btf, enum btf_kfunc_hook hook, u32 kfunc_btf_id) { struct btf_id_set8 *set; u32 *id; if (hook >= BTF_KFUNC_HOOK_MAX) return NULL; if (!btf->kfunc_set_tab) return NULL; set = btf->kfunc_set_tab->sets[hook]; if (!set) return NULL; id = btf_id_set8_contains(set, kfunc_btf_id); if (!id) return NULL; /* The flags for BTF ID are located next to it */ return id + 1; } static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_XDP: return BTF_KFUNC_HOOK_XDP; case BPF_PROG_TYPE_SCHED_CLS: return BTF_KFUNC_HOOK_TC; case BPF_PROG_TYPE_STRUCT_OPS: return BTF_KFUNC_HOOK_STRUCT_OPS; case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: return BTF_KFUNC_HOOK_TRACING; case BPF_PROG_TYPE_SYSCALL: return BTF_KFUNC_HOOK_SYSCALL; default: return BTF_KFUNC_HOOK_MAX; } } /* Caution: * Reference to the module (obtained using btf_try_get_module) corresponding to * the struct btf *MUST* be held when calling this function from verifier * context. This is usually true as we stash references in prog's kfunc_btf_tab; * keeping the reference for the duration of the call provides the necessary * protection for looking up a well-formed btf->kfunc_set_tab. */ u32 *btf_kfunc_id_set_contains(const struct btf *btf, enum bpf_prog_type prog_type, u32 kfunc_btf_id) { enum btf_kfunc_hook hook; hook = bpf_prog_type_to_kfunc_hook(prog_type); return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); } /* This function must be invoked only from initcalls/module init functions */ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *kset) { enum btf_kfunc_hook hook; struct btf *btf; int ret; btf = btf_get_module_btf(kset->owner); if (!btf) { if (!kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { pr_err("missing vmlinux BTF, cannot register kfuncs\n"); return -ENOENT; } if (kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) pr_warn("missing module BTF, cannot register kfuncs\n"); return 0; } if (IS_ERR(btf)) return PTR_ERR(btf); hook = bpf_prog_type_to_kfunc_hook(prog_type); ret = btf_populate_kfunc_set(btf, hook, kset->set); btf_put(btf); return ret; } EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) { struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; struct btf_id_dtor_kfunc *dtor; if (!tab) return -ENOENT; /* Even though the size of tab->dtors[0] is > sizeof(u32), we only need * to compare the first u32 with btf_id, so we can reuse btf_id_cmp_func. */ BUILD_BUG_ON(offsetof(struct btf_id_dtor_kfunc, btf_id) != 0); dtor = bsearch(&btf_id, tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func); if (!dtor) return -ENOENT; return dtor->kfunc_btf_id; } static int btf_check_dtor_kfuncs(struct btf *btf, const struct btf_id_dtor_kfunc *dtors, u32 cnt) { const struct btf_type *dtor_func, *dtor_func_proto, *t; const struct btf_param *args; s32 dtor_btf_id; u32 nr_args, i; for (i = 0; i < cnt; i++) { dtor_btf_id = dtors[i].kfunc_btf_id; dtor_func = btf_type_by_id(btf, dtor_btf_id); if (!dtor_func || !btf_type_is_func(dtor_func)) return -EINVAL; dtor_func_proto = btf_type_by_id(btf, dtor_func->type); if (!dtor_func_proto || !btf_type_is_func_proto(dtor_func_proto)) return -EINVAL; /* Make sure the prototype of the destructor kfunc is 'void func(type *)' */ t = btf_type_by_id(btf, dtor_func_proto->type); if (!t || !btf_type_is_void(t)) return -EINVAL; nr_args = btf_type_vlen(dtor_func_proto); if (nr_args != 1) return -EINVAL; args = btf_params(dtor_func_proto); t = btf_type_by_id(btf, args[0].type); /* Allow any pointer type, as width on targets Linux supports * will be same for all pointer types (i.e. sizeof(void *)) */ if (!t || !btf_type_is_ptr(t)) return -EINVAL; } return 0; } /* This function must be invoked only from initcalls/module init functions */ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner) { struct btf_id_dtor_kfunc_tab *tab; struct btf *btf; u32 tab_cnt; int ret; btf = btf_get_module_btf(owner); if (!btf) { if (!owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { pr_err("missing vmlinux BTF, cannot register dtor kfuncs\n"); return -ENOENT; } if (owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { pr_err("missing module BTF, cannot register dtor kfuncs\n"); return -ENOENT; } return 0; } if (IS_ERR(btf)) return PTR_ERR(btf); if (add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); ret = -E2BIG; goto end; } /* Ensure that the prototype of dtor kfuncs being registered is sane */ ret = btf_check_dtor_kfuncs(btf, dtors, add_cnt); if (ret < 0) goto end; tab = btf->dtor_kfunc_tab; /* Only one call allowed for modules */ if (WARN_ON_ONCE(tab && btf_is_module(btf))) { ret = -EINVAL; goto end; } tab_cnt = tab ? tab->cnt : 0; if (tab_cnt > U32_MAX - add_cnt) { ret = -EOVERFLOW; goto end; } if (tab_cnt + add_cnt >= BTF_DTOR_KFUNC_MAX_CNT) { pr_err("cannot register more than %d kfunc destructors\n", BTF_DTOR_KFUNC_MAX_CNT); ret = -E2BIG; goto end; } tab = krealloc(btf->dtor_kfunc_tab, offsetof(struct btf_id_dtor_kfunc_tab, dtors[tab_cnt + add_cnt]), GFP_KERNEL | __GFP_NOWARN); if (!tab) { ret = -ENOMEM; goto end; } if (!btf->dtor_kfunc_tab) tab->cnt = 0; btf->dtor_kfunc_tab = tab; memcpy(tab->dtors + tab->cnt, dtors, add_cnt * sizeof(tab->dtors[0])); tab->cnt += add_cnt; sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); end: if (ret) btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } EXPORT_SYMBOL_GPL(register_btf_id_dtor_kfuncs); #define MAX_TYPES_ARE_COMPAT_DEPTH 2 /* Check local and target types for compatibility. This check is used for * type-based CO-RE relocations and follow slightly different rules than * field-based relocations. This function assumes that root types were already * checked for name match. Beyond that initial root-level name check, names * are completely ignored. Compatibility rules are as follows: * - any two STRUCTs/UNIONs/FWDs/ENUMs/INTs/ENUM64s are considered compatible, but * kind should match for local and target types (i.e., STRUCT is not * compatible with UNION); * - for ENUMs/ENUM64s, the size is ignored; * - for INT, size and signedness are ignored; * - for ARRAY, dimensionality is ignored, element types are checked for * compatibility recursively; * - CONST/VOLATILE/RESTRICT modifiers are ignored; * - TYPEDEFs/PTRs are compatible if types they pointing to are compatible; * - FUNC_PROTOs are compatible if they have compatible signature: same * number of input args and compatible return and argument types. * These rules are not set in stone and probably will be adjusted as we get * more experience with using BPF CO-RE relocations. */ int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id) { return __bpf_core_types_are_compat(local_btf, local_id, targ_btf, targ_id, MAX_TYPES_ARE_COMPAT_DEPTH); } #define MAX_TYPES_MATCH_DEPTH 2 int bpf_core_types_match(const struct btf *local_btf, u32 local_id, const struct btf *targ_btf, u32 targ_id) { return __bpf_core_types_match(local_btf, local_id, targ_btf, targ_id, false, MAX_TYPES_MATCH_DEPTH); } static bool bpf_core_is_flavor_sep(const char *s) { /* check X___Y name pattern, where X and Y are not underscores */ return s[0] != '_' && /* X */ s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ s[4] != '_'; /* Y */ } size_t bpf_core_essential_name_len(const char *name) { size_t n = strlen(name); int i; for (i = n - 5; i >= 0; i--) { if (bpf_core_is_flavor_sep(name + i)) return i + 1; } return n; } struct bpf_cand_cache { const char *name; u32 name_len; u16 kind; u16 cnt; struct { const struct btf *btf; u32 id; } cands[]; }; static void bpf_free_cands(struct bpf_cand_cache *cands) { if (!cands->cnt) /* empty candidate array was allocated on stack */ return; kfree(cands); } static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands) { kfree(cands->name); kfree(cands); } #define VMLINUX_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; #define MODULE_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; static DEFINE_MUTEX(cand_cache_mutex); static void __print_cand_cache(struct bpf_verifier_log *log, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache *cc; int i, j; for (i = 0; i < cache_size; i++) { cc = cache[i]; if (!cc) continue; bpf_log(log, "[%d]%s(", i, cc->name); for (j = 0; j < cc->cnt; j++) { bpf_log(log, "%d", cc->cands[j].id); if (j < cc->cnt - 1) bpf_log(log, " "); } bpf_log(log, "), "); } } static void print_cand_cache(struct bpf_verifier_log *log) { mutex_lock(&cand_cache_mutex); bpf_log(log, "vmlinux_cand_cache:"); __print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); bpf_log(log, "\nmodule_cand_cache:"); __print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE); bpf_log(log, "\n"); mutex_unlock(&cand_cache_mutex); } static u32 hash_cands(struct bpf_cand_cache *cands) { return jhash(cands->name, cands->name_len, 0); } static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size]; if (cc && cc->name_len == cands->name_len && !strncmp(cc->name, cands->name, cands->name_len)) return cc; return NULL; } static size_t sizeof_cands(int cnt) { return offsetof(struct bpf_cand_cache, cands[cnt]); } static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands; if (*cc) { bpf_free_cands_from_cache(*cc); *cc = NULL; } new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL); if (!new_cands) { bpf_free_cands(cands); return ERR_PTR(-ENOMEM); } /* strdup the name, since it will stay in cache. * the cands->name points to strings in prog's BTF and the prog can be unloaded. */ new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL); bpf_free_cands(cands); if (!new_cands->name) { kfree(new_cands); return ERR_PTR(-ENOMEM); } *cc = new_cands; return new_cands; } #ifdef CONFIG_DEBUG_INFO_BTF_MODULES static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache, int cache_size) { struct bpf_cand_cache *cc; int i, j; for (i = 0; i < cache_size; i++) { cc = cache[i]; if (!cc) continue; if (!btf) { /* when new module is loaded purge all of module_cand_cache, * since new module might have candidates with the name * that matches cached cands. */ bpf_free_cands_from_cache(cc); cache[i] = NULL; continue; } /* when module is unloaded purge cache entries * that match module's btf */ for (j = 0; j < cc->cnt; j++) if (cc->cands[j].btf == btf) { bpf_free_cands_from_cache(cc); cache[i] = NULL; break; } } } static void purge_cand_cache(struct btf *btf) { mutex_lock(&cand_cache_mutex); __purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE); mutex_unlock(&cand_cache_mutex); } #endif static struct bpf_cand_cache * bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf, int targ_start_id) { struct bpf_cand_cache *new_cands; const struct btf_type *t; const char *targ_name; size_t targ_essent_len; int n, i; n = btf_nr_types(targ_btf); for (i = targ_start_id; i < n; i++) { t = btf_type_by_id(targ_btf, i); if (btf_kind(t) != cands->kind) continue; targ_name = btf_name_by_offset(targ_btf, t->name_off); if (!targ_name) continue; /* the resched point is before strncmp to make sure that search * for non-existing name will have a chance to schedule(). */ cond_resched(); if (strncmp(cands->name, targ_name, cands->name_len) != 0) continue; targ_essent_len = bpf_core_essential_name_len(targ_name); if (targ_essent_len != cands->name_len) continue; /* most of the time there is only one candidate for a given kind+name pair */ new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL); if (!new_cands) { bpf_free_cands(cands); return ERR_PTR(-ENOMEM); } memcpy(new_cands, cands, sizeof_cands(cands->cnt)); bpf_free_cands(cands); cands = new_cands; cands->cands[cands->cnt].btf = targ_btf; cands->cands[cands->cnt].id = i; cands->cnt++; } return cands; } static struct bpf_cand_cache * bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id) { struct bpf_cand_cache *cands, *cc, local_cand = {}; const struct btf *local_btf = ctx->btf; const struct btf_type *local_type; const struct btf *main_btf; size_t local_essent_len; struct btf *mod_btf; const char *name; int id; main_btf = bpf_get_btf_vmlinux(); if (IS_ERR(main_btf)) return ERR_CAST(main_btf); if (!main_btf) return ERR_PTR(-EINVAL); local_type = btf_type_by_id(local_btf, local_type_id); if (!local_type) return ERR_PTR(-EINVAL); name = btf_name_by_offset(local_btf, local_type->name_off); if (str_is_empty(name)) return ERR_PTR(-EINVAL); local_essent_len = bpf_core_essential_name_len(name); cands = &local_cand; cands->name = name; cands->kind = btf_kind(local_type); cands->name_len = local_essent_len; cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); /* cands is a pointer to stack here */ if (cc) { if (cc->cnt) return cc; goto check_modules; } /* Attempt to find target candidates in vmlinux BTF first */ cands = bpf_core_add_cands(cands, main_btf, 1); if (IS_ERR(cands)) return ERR_CAST(cands); /* cands is a pointer to kmalloced memory here if cands->cnt > 0 */ /* populate cache even when cands->cnt == 0 */ cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); if (IS_ERR(cc)) return ERR_CAST(cc); /* if vmlinux BTF has any candidate, don't go for module BTFs */ if (cc->cnt) return cc; check_modules: /* cands is a pointer to stack here and cands->cnt == 0 */ cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); if (cc) /* if cache has it return it even if cc->cnt == 0 */ return cc; /* If candidate is not found in vmlinux's BTF then search in module's BTFs */ spin_lock_bh(&btf_idr_lock); idr_for_each_entry(&btf_idr, mod_btf, id) { if (!btf_is_module(mod_btf)) continue; /* linear search could be slow hence unlock/lock * the IDR to avoiding holding it for too long */ btf_get(mod_btf); spin_unlock_bh(&btf_idr_lock); cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf)); btf_put(mod_btf); if (IS_ERR(cands)) return ERR_CAST(cands); spin_lock_bh(&btf_idr_lock); } spin_unlock_bh(&btf_idr_lock); /* cands is a pointer to kmalloced memory here if cands->cnt > 0 * or pointer to stack if cands->cnd == 0. * Copy it into the cache even when cands->cnt == 0 and * return the result. */ return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); } int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn) { bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL; struct bpf_core_cand_list cands = {}; struct bpf_core_relo_res targ_res; struct bpf_core_spec *specs; int err; /* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5" * into arrays of btf_ids of struct fields and array indices. */ specs = kcalloc(3, sizeof(*specs), GFP_KERNEL); if (!specs) return -ENOMEM; if (need_cands) { struct bpf_cand_cache *cc; int i; mutex_lock(&cand_cache_mutex); cc = bpf_core_find_cands(ctx, relo->type_id); if (IS_ERR(cc)) { bpf_log(ctx->log, "target candidate search failed for %d\n", relo->type_id); err = PTR_ERR(cc); goto out; } if (cc->cnt) { cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL); if (!cands.cands) { err = -ENOMEM; goto out; } } for (i = 0; i < cc->cnt; i++) { bpf_log(ctx->log, "CO-RE relocating %s %s: found target candidate [%d]\n", btf_kind_str[cc->kind], cc->name, cc->cands[i].id); cands.cands[i].btf = cc->cands[i].btf; cands.cands[i].id = cc->cands[i].id; } cands.len = cc->cnt; /* cand_cache_mutex needs to span the cache lookup and * copy of btf pointer into bpf_core_cand_list, * since module can be unloaded while bpf_core_calc_relo_insn * is working with module's btf. */ } err = bpf_core_calc_relo_insn((void *)ctx->log, relo, relo_idx, ctx->btf, &cands, specs, &targ_res); if (err) goto out; err = bpf_core_patch_insn((void *)ctx->log, insn, relo->insn_off / 8, relo, relo_idx, &targ_res); out: kfree(specs); if (need_cands) { kfree(cands.cands); mutex_unlock(&cand_cache_mutex); if (ctx->log->level & BPF_LOG_LEVEL2) print_cand_cache(ctx->log); } return err; } |
| 11565 8 11560 11537 4674 37 4660 92 4 5 79 10 32 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/uaccess.h> #include <linux/nospec.h> /* out-of-line parts */ #ifndef INLINE_COPY_FROM_USER unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } EXPORT_SYMBOL(_copy_from_user); #endif #ifndef INLINE_COPY_TO_USER unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (likely(access_ok(to, n))) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } EXPORT_SYMBOL(_copy_to_user); #endif /** * check_zeroed_user: check if a userspace buffer only contains zero bytes * @from: Source address, in userspace. * @size: Size of buffer. * * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for * userspace addresses (and is more efficient because we don't care where the * first non-zero byte is). * * Returns: * * 0: There were non-zero bytes present in the buffer. * * 1: The buffer was full of zero bytes. * * -EFAULT: access to userspace failed. */ int check_zeroed_user(const void __user *from, size_t size) { unsigned long val; uintptr_t align = (uintptr_t) from % sizeof(unsigned long); if (unlikely(size == 0)) return 1; from -= align; size += align; if (!user_read_access_begin(from, size)) return -EFAULT; unsafe_get_user(val, (unsigned long __user *) from, err_fault); if (align) val &= ~aligned_byte_mask(align); while (size > sizeof(unsigned long)) { if (unlikely(val)) goto done; from += sizeof(unsigned long); size -= sizeof(unsigned long); unsafe_get_user(val, (unsigned long __user *) from, err_fault); } if (size < sizeof(unsigned long)) val &= aligned_byte_mask(size); done: user_read_access_end(); return (val == 0); err_fault: user_read_access_end(); return -EFAULT; } EXPORT_SYMBOL(check_zeroed_user); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_PGTABLE_INVERT_H #define _ASM_PGTABLE_INVERT_H 1 #ifndef __ASSEMBLY__ /* * 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 /* __ASSEMBLY__ */ #endif |
| 1305 1305 412 412 1093 412 412 412 412 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/runtime.c - Helper functions for device runtime PM * * Copyright (c) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * Copyright (C) 2010 Alan Stern <stern@rowland.harvard.edu> */ #include <linux/sched/mm.h> #include <linux/ktime.h> #include <linux/hrtimer.h> #include <linux/export.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeirq.h> #include <trace/events/rpm.h> #include "../base.h" #include "power.h" typedef int (*pm_callback_t)(struct device *); static pm_callback_t __rpm_get_callback(struct device *dev, size_t cb_offset) { pm_callback_t cb; const struct dev_pm_ops *ops; if (dev->pm_domain) ops = &dev->pm_domain->ops; else if (dev->type && dev->type->pm) ops = dev->type->pm; else if (dev->class && dev->class->pm) ops = dev->class->pm; else if (dev->bus && dev->bus->pm) ops = dev->bus->pm; else ops = NULL; if (ops) cb = *(pm_callback_t *)((void *)ops + cb_offset); else cb = NULL; if (!cb && dev->driver && dev->driver->pm) cb = *(pm_callback_t *)((void *)dev->driver->pm + cb_offset); return cb; } #define RPM_GET_CALLBACK(dev, callback) \ __rpm_get_callback(dev, offsetof(struct dev_pm_ops, callback)) static int rpm_resume(struct device *dev, int rpmflags); static int rpm_suspend(struct device *dev, int rpmflags); /** * update_pm_runtime_accounting - Update the time accounting of power states * @dev: Device to update the accounting for * * In order to be able to have time accounting of the various power states * (as used by programs such as PowerTOP to show the effectiveness of runtime * PM), we need to track the time spent in each state. * update_pm_runtime_accounting must be called each time before the * runtime_status field is updated, to account the time in the old state * correctly. */ static void update_pm_runtime_accounting(struct device *dev) { u64 now, last, delta; if (dev->power.disable_depth > 0) return; last = dev->power.accounting_timestamp; now = ktime_get_mono_fast_ns(); dev->power.accounting_timestamp = now; /* * Because ktime_get_mono_fast_ns() is not monotonic during * timekeeping updates, ensure that 'now' is after the last saved * timesptamp. */ if (now < last) return; delta = now - last; if (dev->power.runtime_status == RPM_SUSPENDED) dev->power.suspended_time += delta; else dev->power.active_time += delta; } static void __update_runtime_status(struct device *dev, enum rpm_status status) { update_pm_runtime_accounting(dev); trace_rpm_status(dev, status); dev->power.runtime_status = status; } static u64 rpm_get_accounted_time(struct device *dev, bool suspended) { u64 time; unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); update_pm_runtime_accounting(dev); time = suspended ? dev->power.suspended_time : dev->power.active_time; spin_unlock_irqrestore(&dev->power.lock, flags); return time; } u64 pm_runtime_active_time(struct device *dev) { return rpm_get_accounted_time(dev, false); } u64 pm_runtime_suspended_time(struct device *dev) { return rpm_get_accounted_time(dev, true); } EXPORT_SYMBOL_GPL(pm_runtime_suspended_time); /** * pm_runtime_deactivate_timer - Deactivate given device's suspend timer. * @dev: Device to handle. */ static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } /** * pm_runtime_cancel_pending - Deactivate suspend timer and cancel requests. * @dev: Device to handle. */ static void pm_runtime_cancel_pending(struct device *dev) { pm_runtime_deactivate_timer(dev); /* * In case there's a request pending, make sure its work function will * return without doing anything. */ dev->power.request = RPM_REQ_NONE; } /* * pm_runtime_autosuspend_expiration - Get a device's autosuspend-delay expiration time. * @dev: Device to handle. * * Compute the autosuspend-delay expiration time based on the device's * power.last_busy time. If the delay has already expired or is disabled * (negative) or the power.use_autosuspend flag isn't set, return 0. * Otherwise return the expiration time in nanoseconds (adjusted to be nonzero). * * This function may be called either with or without dev->power.lock held. * Either way it can be racy, since power.last_busy may be updated at any time. */ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 expires; if (!dev->power.use_autosuspend) return 0; autosuspend_delay = READ_ONCE(dev->power.autosuspend_delay); if (autosuspend_delay < 0) return 0; expires = READ_ONCE(dev->power.last_busy); expires += (u64)autosuspend_delay * NSEC_PER_MSEC; if (expires > ktime_get_mono_fast_ns()) return expires; /* Expires in the future */ return 0; } EXPORT_SYMBOL_GPL(pm_runtime_autosuspend_expiration); static int dev_memalloc_noio(struct device *dev, void *data) { return dev->power.memalloc_noio; } /* * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag. * @dev: Device to handle. * @enable: True for setting the flag and False for clearing the flag. * * Set the flag for all devices in the path from the device to the * root device in the device tree if @enable is true, otherwise clear * the flag for devices in the path whose siblings don't set the flag. * * The function should only be called by block device, or network * device driver for solving the deadlock problem during runtime * resume/suspend: * * If memory allocation with GFP_KERNEL is called inside runtime * resume/suspend callback of any one of its ancestors(or the * block device itself), the deadlock may be triggered inside the * memory allocation since it might not complete until the block * device becomes active and the involed page I/O finishes. The * situation is pointed out first by Alan Stern. Network device * are involved in iSCSI kind of situation. * * The lock of dev_hotplug_mutex is held in the function for handling * hotplug race because pm_runtime_set_memalloc_noio() may be called * in async probe(). * * The function should be called between device_add() and device_del() * on the affected device(block/network device). */ void pm_runtime_set_memalloc_noio(struct device *dev, bool enable) { static DEFINE_MUTEX(dev_hotplug_mutex); mutex_lock(&dev_hotplug_mutex); for (;;) { bool enabled; /* hold power lock since bitfield is not SMP-safe. */ spin_lock_irq(&dev->power.lock); enabled = dev->power.memalloc_noio; dev->power.memalloc_noio = enable; spin_unlock_irq(&dev->power.lock); /* * not need to enable ancestors any more if the device * has been enabled. */ if (enabled && enable) break; dev = dev->parent; /* * clear flag of the parent device only if all the * children don't set the flag because ancestor's * flag was set by any one of the descendants. */ if (!dev || (!enable && device_for_each_child(dev, NULL, dev_memalloc_noio))) break; } mutex_unlock(&dev_hotplug_mutex); } EXPORT_SYMBOL_GPL(pm_runtime_set_memalloc_noio); /** * rpm_check_suspend_allowed - Test whether a device may be suspended. * @dev: Device to test. */ static int rpm_check_suspend_allowed(struct device *dev) { int retval = 0; if (dev->power.runtime_error) retval = -EINVAL; else if (dev->power.disable_depth > 0) retval = -EACCES; else if (atomic_read(&dev->power.usage_count)) retval = -EAGAIN; else if (!dev->power.ignore_children && atomic_read(&dev->power.child_count)) retval = -EBUSY; /* Pending resume requests take precedence over suspends. */ else if ((dev->power.deferred_resume && dev->power.runtime_status == RPM_SUSPENDING) || (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME)) retval = -EAGAIN; else if (__dev_pm_qos_resume_latency(dev) == 0) retval = -EPERM; else if (dev->power.runtime_status == RPM_SUSPENDED) retval = 1; return retval; } static int rpm_get_suppliers(struct device *dev) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { int retval; if (!(link->flags & DL_FLAG_PM_RUNTIME)) continue; retval = pm_runtime_get_sync(link->supplier); /* Ignore suppliers with disabled runtime PM. */ if (retval < 0 && retval != -EACCES) { pm_runtime_put_noidle(link->supplier); return retval; } refcount_inc(&link->rpm_active); } return 0; } /** * pm_runtime_release_supplier - Drop references to device link's supplier. * @link: Target device link. * * Drop all runtime PM references associated with @link to its supplier device. */ void pm_runtime_release_supplier(struct device_link *link) { struct device *supplier = link->supplier; /* * The additional power.usage_count check is a safety net in case * the rpm_active refcount becomes saturated, in which case * refcount_dec_not_one() would return true forever, but it is not * strictly necessary. */ while (refcount_dec_not_one(&link->rpm_active) && atomic_read(&supplier->power.usage_count) > 0) pm_runtime_put_noidle(supplier); } static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) { pm_runtime_release_supplier(link); if (try_to_suspend) pm_request_idle(link->supplier); } } static void rpm_put_suppliers(struct device *dev) { __rpm_put_suppliers(dev, true); } static void rpm_suspend_suppliers(struct device *dev) { struct device_link *link; int idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) pm_request_idle(link->supplier); device_links_read_unlock(idx); } /** * __rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int retval = 0, idx; bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); } else { spin_unlock_irq(&dev->power.lock); /* * Resume suppliers if necessary. * * The device's runtime PM status cannot change until this * routine returns, so it is safe to read the status outside of * the lock. */ if (use_links && dev->power.runtime_status == RPM_RESUMING) { idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); if (retval) { rpm_put_suppliers(dev); goto fail; } device_links_read_unlock(idx); } } if (cb) retval = cb(dev); if (dev->power.irq_safe) { spin_lock(&dev->power.lock); } else { /* * If the device is suspending and the callback has returned * success, drop the usage counters of the suppliers that have * been reference counted on its resume. * * Do that if resume fails too. */ if (use_links && ((dev->power.runtime_status == RPM_SUSPENDING && !retval) || (dev->power.runtime_status == RPM_RESUMING && retval))) { idx = device_links_read_lock(); __rpm_put_suppliers(dev, false); fail: device_links_read_unlock(idx); } spin_lock_irq(&dev->power.lock); } return retval; } /** * rpm_idle - Notify device bus type if the device can be suspended. * @dev: Device to notify the bus type about. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. If * another idle notification has been started earlier, return immediately. If * the RPM_ASYNC flag is set then queue an idle-notification request; otherwise * run the ->runtime_idle() callback directly. If the ->runtime_idle callback * doesn't exist or if it returns 0, call rpm_suspend with the RPM_AUTO flag. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_idle(struct device *dev, int rpmflags) { int (*callback)(struct device *); int retval; trace_rpm_idle_rcuidle(dev, rpmflags); retval = rpm_check_suspend_allowed(dev); if (retval < 0) ; /* Conditions are wrong. */ /* Idle notifications are allowed only in the RPM_ACTIVE state. */ else if (dev->power.runtime_status != RPM_ACTIVE) retval = -EAGAIN; /* * Any pending request other than an idle notification takes * precedence over us, except that the timer may be running. */ else if (dev->power.request_pending && dev->power.request > RPM_REQ_IDLE) retval = -EAGAIN; /* Act as though RPM_NOWAIT is always set. */ else if (dev->power.idle_notification) retval = -EINPROGRESS; if (retval) goto out; /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; callback = RPM_GET_CALLBACK(dev, runtime_idle); /* If no callback assume success. */ if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_IDLE; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } trace_rpm_return_int_rcuidle(dev, _THIS_IP_, 0); return 0; } dev->power.idle_notification = true; if (dev->power.irq_safe) spin_unlock(&dev->power.lock); else spin_unlock_irq(&dev->power.lock); retval = callback(dev); if (dev->power.irq_safe) spin_lock(&dev->power.lock); else spin_lock_irq(&dev->power.lock); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); out: trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO); } /** * rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. * @dev: Device to run the callback for. */ static int rpm_callback(int (*cb)(struct device *), struct device *dev) { int retval; if (dev->power.memalloc_noio) { unsigned int noio_flag; /* * Deadlock might be caused if memory allocation with * GFP_KERNEL happens inside runtime_suspend and * runtime_resume callbacks of one block device's * ancestor or the block device itself. Network * device might be thought as part of iSCSI block * device, so network device and its ancestor should * be marked as memalloc_noio too. */ noio_flag = memalloc_noio_save(); retval = __rpm_callback(cb, dev); memalloc_noio_restore(noio_flag); } else { retval = __rpm_callback(cb, dev); } dev->power.runtime_error = retval; return retval != -EACCES ? retval : -EIO; } /** * rpm_suspend - Carry out runtime suspend of given device. * @dev: Device to suspend. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be suspended. * Cancel a pending idle notification, autosuspend or suspend. If * another suspend has been started earlier, either return immediately * or wait for it to finish, depending on the RPM_NOWAIT and RPM_ASYNC * flags. If the RPM_ASYNC flag is set then queue a suspend request; * otherwise run the ->runtime_suspend() callback directly. When * ->runtime_suspend succeeded, if a deferred resume was requested while * the callback was running then carry it out, otherwise send an idle * notification for its parent (if the suspend succeeded and both * ignore_children of parent->power and irq_safe of dev->power are not set). * If ->runtime_suspend failed with -EAGAIN or -EBUSY, and if the RPM_AUTO * flag is set and the next autosuspend-delay expiration time is in the * future, schedule another autosuspend attempt. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_suspend(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval; trace_rpm_suspend_rcuidle(dev, rpmflags); repeat: retval = rpm_check_suspend_allowed(dev); if (retval < 0) goto out; /* Conditions are wrong. */ /* Synchronous suspends are not allowed in the RPM_RESUMING state. */ if (dev->power.runtime_status == RPM_RESUMING && !(rpmflags & RPM_ASYNC)) retval = -EAGAIN; if (retval) goto out; /* If the autosuspend_delay time hasn't expired yet, reschedule. */ if ((rpmflags & RPM_AUTO) && dev->power.runtime_status != RPM_SUSPENDING) { u64 expires = pm_runtime_autosuspend_expiration(dev); if (expires != 0) { /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; /* * Optimization: If the timer is already running and is * set to expire at or before the autosuspend delay, * avoid the overhead of resetting it. Just let it * expire; pm_suspend_timer_fn() will take care of the * rest. */ if (!(dev->power.timer_expires && dev->power.timer_expires <= expires)) { /* * We add a slack of 25% to gather wakeups * without sacrificing the granularity. */ u64 slack = (u64)READ_ONCE(dev->power.autosuspend_delay) * (NSEC_PER_MSEC >> 2); dev->power.timer_expires = expires; hrtimer_start_range_ns(&dev->power.suspend_timer, ns_to_ktime(expires), slack, HRTIMER_MODE_ABS); } dev->power.timer_autosuspends = 1; goto out; } } /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); if (dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { retval = -EINPROGRESS; goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the other suspend running in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ /* Carry out an asynchronous or a synchronous suspend. */ if (rpmflags & RPM_ASYNC) { dev->power.request = (rpmflags & RPM_AUTO) ? RPM_REQ_AUTOSUSPEND : RPM_REQ_SUSPEND; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } goto out; } __update_runtime_status(dev, RPM_SUSPENDING); callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); retval = rpm_callback(callback, dev); if (retval) goto fail; dev_pm_enable_wake_irq_complete(dev); no_callback: __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_deactivate_timer(dev); if (dev->parent) { parent = dev->parent; atomic_add_unless(&parent->power.child_count, -1, 0); } wake_up_all(&dev->power.wait_queue); if (dev->power.deferred_resume) { dev->power.deferred_resume = false; rpm_resume(dev, 0); retval = -EAGAIN; goto out; } if (dev->power.irq_safe) goto out; /* Maybe the parent is now able to suspend. */ if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); rpm_idle(parent, RPM_ASYNC); spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); } /* Maybe the suppliers are now able to suspend. */ if (dev->power.links_count > 0) { spin_unlock_irq(&dev->power.lock); rpm_suspend_suppliers(dev); spin_lock_irq(&dev->power.lock); } out: trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); return retval; fail: dev_pm_disable_wake_irq_check(dev, true); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); if (retval == -EAGAIN || retval == -EBUSY) { dev->power.runtime_error = 0; /* * If the callback routine failed an autosuspend, and * if the last_busy time has been updated so that there * is a new autosuspend expiration time, automatically * reschedule another autosuspend. */ if ((rpmflags & RPM_AUTO) && pm_runtime_autosuspend_expiration(dev) != 0) goto repeat; } else { pm_runtime_cancel_pending(dev); } goto out; } /** * rpm_resume - Carry out runtime resume of given device. * @dev: Device to resume. * @rpmflags: Flag bits. * * Check if the device's runtime PM status allows it to be resumed. Cancel * any scheduled or pending requests. If another resume has been started * earlier, either return immediately or wait for it to finish, depending on the * RPM_NOWAIT and RPM_ASYNC flags. Similarly, if there's a suspend running in * parallel with this function, either tell the other process to resume after * suspending (deferred_resume) or wait for it to finish. If the RPM_ASYNC * flag is set then queue a resume request; otherwise run the * ->runtime_resume() callback directly. Queue an idle notification for the * device if the resume succeeded. * * This function must be called under dev->power.lock with interrupts disabled. */ static int rpm_resume(struct device *dev, int rpmflags) __releases(&dev->power.lock) __acquires(&dev->power.lock) { int (*callback)(struct device *); struct device *parent = NULL; int retval = 0; trace_rpm_resume_rcuidle(dev, rpmflags); repeat: if (dev->power.runtime_error) { retval = -EINVAL; } else if (dev->power.disable_depth > 0) { if (dev->power.runtime_status == RPM_ACTIVE && dev->power.last_status == RPM_ACTIVE) retval = 1; else retval = -EACCES; } if (retval) goto out; /* * Other scheduled or pending requests need to be canceled. Small * optimization: If an autosuspend timer is running, leave it running * rather than cancelling it now only to restart it again in the near * future. */ dev->power.request = RPM_REQ_NONE; if (!dev->power.timer_autosuspends) pm_runtime_deactivate_timer(dev); if (dev->power.runtime_status == RPM_ACTIVE) { retval = 1; goto out; } if (dev->power.runtime_status == RPM_RESUMING || dev->power.runtime_status == RPM_SUSPENDING) { DEFINE_WAIT(wait); if (rpmflags & (RPM_ASYNC | RPM_NOWAIT)) { if (dev->power.runtime_status == RPM_SUSPENDING) { dev->power.deferred_resume = true; if (rpmflags & RPM_NOWAIT) retval = -EINPROGRESS; } else { retval = -EINPROGRESS; } goto out; } if (dev->power.irq_safe) { spin_unlock(&dev->power.lock); cpu_relax(); spin_lock(&dev->power.lock); goto repeat; } /* Wait for the operation carried out in parallel with us. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_RESUMING && dev->power.runtime_status != RPM_SUSPENDING) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); goto repeat; } /* * See if we can skip waking up the parent. This is safe only if * power.no_callbacks is set, because otherwise we don't know whether * the resume will actually succeed. */ if (dev->power.no_callbacks && !parent && dev->parent) { spin_lock_nested(&dev->parent->power.lock, SINGLE_DEPTH_NESTING); if (dev->parent->power.disable_depth > 0 || dev->parent->power.ignore_children || dev->parent->power.runtime_status == RPM_ACTIVE) { atomic_inc(&dev->parent->power.child_count); spin_unlock(&dev->parent->power.lock); retval = 1; goto no_callback; /* Assume success. */ } spin_unlock(&dev->parent->power.lock); } /* Carry out an asynchronous or a synchronous resume. */ if (rpmflags & RPM_ASYNC) { dev->power.request = RPM_REQ_RESUME; if (!dev->power.request_pending) { dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } retval = 0; goto out; } if (!parent && dev->parent) { /* * Increment the parent's usage counter and resume it if * necessary. Not needed if dev is irq-safe; then the * parent is permanently resumed. */ parent = dev->parent; if (dev->power.irq_safe) goto skip_parent; spin_unlock(&dev->power.lock); pm_runtime_get_noresume(parent); spin_lock(&parent->power.lock); /* * Resume the parent if it has runtime PM enabled and not been * set to ignore its children. */ if (!parent->power.disable_depth && !parent->power.ignore_children) { rpm_resume(parent, 0); if (parent->power.runtime_status != RPM_ACTIVE) retval = -EBUSY; } spin_unlock(&parent->power.lock); spin_lock(&dev->power.lock); if (retval) goto out; goto repeat; } skip_parent: if (dev->power.no_callbacks) goto no_callback; /* Assume success. */ __update_runtime_status(dev, RPM_RESUMING); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_cancel_pending(dev); dev_pm_enable_wake_irq_check(dev, false); } else { no_callback: __update_runtime_status(dev, RPM_ACTIVE); pm_runtime_mark_last_busy(dev); if (parent) atomic_inc(&parent->power.child_count); } wake_up_all(&dev->power.wait_queue); if (retval >= 0) rpm_idle(dev, RPM_ASYNC); out: if (parent && !dev->power.irq_safe) { spin_unlock_irq(&dev->power.lock); pm_runtime_put(parent); spin_lock_irq(&dev->power.lock); } trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); return retval; } /** * pm_runtime_work - Universal runtime PM work function. * @work: Work structure used for scheduling the execution of this function. * * Use @work to get the device object the work is to be done for, determine what * is to be done and execute the appropriate runtime PM function. */ static void pm_runtime_work(struct work_struct *work) { struct device *dev = container_of(work, struct device, power.work); enum rpm_request req; spin_lock_irq(&dev->power.lock); if (!dev->power.request_pending) goto out; req = dev->power.request; dev->power.request = RPM_REQ_NONE; dev->power.request_pending = false; switch (req) { case RPM_REQ_NONE: break; case RPM_REQ_IDLE: rpm_idle(dev, RPM_NOWAIT); break; case RPM_REQ_SUSPEND: rpm_suspend(dev, RPM_NOWAIT); break; case RPM_REQ_AUTOSUSPEND: rpm_suspend(dev, RPM_NOWAIT | RPM_AUTO); break; case RPM_REQ_RESUME: rpm_resume(dev, RPM_NOWAIT); break; } out: spin_unlock_irq(&dev->power.lock); } /** * pm_suspend_timer_fn - Timer function for pm_schedule_suspend(). * @timer: hrtimer used by pm_schedule_suspend(). * * Check if the time is right and queue a suspend request. */ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) { struct device *dev = container_of(timer, struct device, power.suspend_timer); unsigned long flags; u64 expires; spin_lock_irqsave(&dev->power.lock, flags); expires = dev->power.timer_expires; /* * If 'expires' is after the current time, we've been called * too early. */ if (expires > 0 && expires < ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); } spin_unlock_irqrestore(&dev->power.lock, flags); return HRTIMER_NORESTART; } /** * pm_schedule_suspend - Set up a timer to submit a suspend request in future. * @dev: Device to suspend. * @delay: Time to wait before submitting a suspend request, in milliseconds. */ int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (!delay) { retval = rpm_suspend(dev, RPM_ASYNC); goto out; } retval = rpm_check_suspend_allowed(dev); if (retval) goto out; /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); out: spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(pm_schedule_suspend); static int rpm_drop_usage_count(struct device *dev) { int ret; ret = atomic_sub_return(1, &dev->power.usage_count); if (ret >= 0) return ret; /* * Because rpm_resume() does not check the usage counter, it will resume * the device even if the usage counter is 0 or negative, so it is * sufficient to increment the usage counter here to reverse the change * made above. */ atomic_inc(&dev->power.usage_count); dev_warn(dev, "Runtime PM usage count underflow!\n"); return -EINVAL; } /** * __pm_runtime_idle - Entry point for runtime idle operations. * @dev: Device to send idle notification for. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out an idle * notification, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_idle(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage_rcuidle(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_idle); /** * __pm_runtime_suspend - Entry point for runtime put/suspend operations. * @dev: Device to suspend. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, decrement the device's usage count and * return immediately if it is larger than zero (if it becomes negative, log a * warning, increment it, and return an error). Then carry out a suspend, * either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_suspend(struct device *dev, int rpmflags) { unsigned long flags; int retval; if (rpmflags & RPM_GET_PUT) { retval = rpm_drop_usage_count(dev); if (retval < 0) { return retval; } else if (retval > 0) { trace_rpm_usage_rcuidle(dev, rpmflags); return 0; } } might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_suspend); /** * __pm_runtime_resume - Entry point for runtime resume operations. * @dev: Device to resume. * @rpmflags: Flag bits. * * If the RPM_GET_PUT flag is set, increment the device's usage count. Then * carry out a resume, either synchronous or asynchronous. * * This routine may be called in atomic context if the RPM_ASYNC flag is set, * or if pm_runtime_irq_safe() has been called. */ int __pm_runtime_resume(struct device *dev, int rpmflags) { unsigned long flags; int retval; might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_resume(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(__pm_runtime_resume); /** * pm_runtime_get_if_active - Conditionally bump up device usage counter. * @dev: Device to handle. * @ign_usage_count: Whether or not to look at the current usage counter value. * * Return -EINVAL if runtime PM is disabled for @dev. * * Otherwise, if the runtime PM status of @dev is %RPM_ACTIVE and either * @ign_usage_count is %true or the runtime PM usage counter of @dev is not * zero, increment the usage counter of @dev and return 1. Otherwise, return 0 * without changing the usage counter. * * If @ign_usage_count is %true, this function can be used to prevent suspending * the device when its runtime PM status is %RPM_ACTIVE. * * If @ign_usage_count is %false, this function can be used to prevent * suspending the device when both its runtime PM status is %RPM_ACTIVE and its * runtime PM usage counter is not zero. * * The caller is responsible for decrementing the runtime PM usage counter of * @dev after this function has returned a positive value for it. */ int pm_runtime_get_if_active(struct device *dev, bool ign_usage_count) { unsigned long flags; int retval; spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.disable_depth > 0) { retval = -EINVAL; } else if (dev->power.runtime_status != RPM_ACTIVE) { retval = 0; } else if (ign_usage_count) { retval = 1; atomic_inc(&dev->power.usage_count); } else { retval = atomic_inc_not_zero(&dev->power.usage_count); } trace_rpm_usage_rcuidle(dev, 0); spin_unlock_irqrestore(&dev->power.lock, flags); return retval; } EXPORT_SYMBOL_GPL(pm_runtime_get_if_active); /** * __pm_runtime_set_status - Set runtime PM status of a device. * @dev: Device to handle. * @status: New runtime PM status of the device. * * If runtime PM of the device is disabled or its power.runtime_error field is * different from zero, the status may be changed either to RPM_ACTIVE, or to * RPM_SUSPENDED, as long as that reflects the actual state of the device. * However, if the device has a parent and the parent is not active, and the * parent's power.ignore_children flag is unset, the device's status cannot be * set to RPM_ACTIVE, so -EBUSY is returned in that case. * * If successful, __pm_runtime_set_status() clears the power.runtime_error field * and the device parent's counter of unsuspended children is modified to * reflect the new status. If the new status is RPM_SUSPENDED, an idle * notification request for the parent is submitted. * * If @dev has any suppliers (as reflected by device links to them), and @status * is RPM_ACTIVE, they will be activated upfront and if the activation of one * of them fails, the status of @dev will be changed to RPM_SUSPENDED (instead * of the @status value) and the suppliers will be deacticated on exit. The * error returned by the failing supplier activation will be returned in that * case. */ int __pm_runtime_set_status(struct device *dev, unsigned int status) { struct device *parent = dev->parent; bool notify_parent = false; unsigned long flags; int error = 0; if (status != RPM_ACTIVE && status != RPM_SUSPENDED) return -EINVAL; spin_lock_irqsave(&dev->power.lock, flags); /* * Prevent PM-runtime from being enabled for the device or return an * error if it is enabled already and working. */ if (dev->power.runtime_error || dev->power.disable_depth) dev->power.disable_depth++; else error = -EAGAIN; spin_unlock_irqrestore(&dev->power.lock, flags); if (error) return error; /* * If the new status is RPM_ACTIVE, the suppliers can be activated * upfront regardless of the current status, because next time * rpm_put_suppliers() runs, the rpm_active refcounts of the links * involved will be dropped down to one anyway. */ if (status == RPM_ACTIVE) { int idx = device_links_read_lock(); error = rpm_get_suppliers(dev); if (error) status = RPM_SUSPENDED; device_links_read_unlock(idx); } spin_lock_irqsave(&dev->power.lock, flags); if (dev->power.runtime_status == status || !parent) goto out_set; if (status == RPM_SUSPENDED) { atomic_add_unless(&parent->power.child_count, -1, 0); notify_parent = !parent->power.ignore_children; } else { spin_lock_nested(&parent->power.lock, SINGLE_DEPTH_NESTING); /* * It is invalid to put an active child under a parent that is * not active, has runtime PM enabled and the * 'power.ignore_children' flag unset. */ if (!parent->power.disable_depth && !parent->power.ignore_children && parent->power.runtime_status != RPM_ACTIVE) { dev_err(dev, "runtime PM trying to activate child device %s but parent (%s) is not active\n", dev_name(dev), dev_name(parent)); error = -EBUSY; } else if (dev->power.runtime_status == RPM_SUSPENDED) { atomic_inc(&parent->power.child_count); } spin_unlock(&parent->power.lock); if (error) { status = RPM_SUSPENDED; goto out; } } out_set: __update_runtime_status(dev, status); if (!error) dev->power.runtime_error = 0; out: spin_unlock_irqrestore(&dev->power.lock, flags); if (notify_parent) pm_request_idle(parent); if (status == RPM_SUSPENDED) { int idx = device_links_read_lock(); rpm_put_suppliers(dev); device_links_read_unlock(idx); } pm_runtime_enable(dev); return error; } EXPORT_SYMBOL_GPL(__pm_runtime_set_status); /** * __pm_runtime_barrier - Cancel pending requests and wait for completions. * @dev: Device to handle. * * Flush all pending requests for the device from pm_wq and wait for all * runtime PM operations involving the device in progress to complete. * * Should be called under dev->power.lock with interrupts disabled. */ static void __pm_runtime_barrier(struct device *dev) { pm_runtime_deactivate_timer(dev); if (dev->power.request_pending) { dev->power.request = RPM_REQ_NONE; spin_unlock_irq(&dev->power.lock); cancel_work_sync(&dev->power.work); spin_lock_irq(&dev->power.lock); dev->power.request_pending = false; } if (dev->power.runtime_status == RPM_SUSPENDING || dev->power.runtime_status == RPM_RESUMING || dev->power.idle_notification) { DEFINE_WAIT(wait); /* Suspend, wake-up or idle notification in progress. */ for (;;) { prepare_to_wait(&dev->power.wait_queue, &wait, TASK_UNINTERRUPTIBLE); if (dev->power.runtime_status != RPM_SUSPENDING && dev->power.runtime_status != RPM_RESUMING && !dev->power.idle_notification) break; spin_unlock_irq(&dev->power.lock); schedule(); spin_lock_irq(&dev->power.lock); } finish_wait(&dev->power.wait_queue, &wait); } } /** * pm_runtime_barrier - Flush pending requests and wait for completions. * @dev: Device to handle. * * Prevent the device from being suspended by incrementing its usage counter and * if there's a pending resume request for the device, wake the device up. * Next, make sure that all pending requests for the device have been flushed * from pm_wq and wait for all runtime PM operations involving the device in * progress to complete. * * Return value: * 1, if there was a resume request pending and the device had to be woken up, * 0, otherwise */ int pm_runtime_barrier(struct device *dev) { int retval = 0; pm_runtime_get_noresume(dev); spin_lock_irq(&dev->power.lock); if (dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { rpm_resume(dev, 0); retval = 1; } __pm_runtime_barrier(dev); spin_unlock_irq(&dev->power.lock); pm_runtime_put_noidle(dev); return retval; } EXPORT_SYMBOL_GPL(pm_runtime_barrier); /** * __pm_runtime_disable - Disable runtime PM of a device. * @dev: Device to handle. * @check_resume: If set, check if there's a resume request for the device. * * Increment power.disable_depth for the device and if it was zero previously, * cancel all pending runtime PM requests for the device and wait for all * operations in progress to complete. The device can be either active or * suspended after its runtime PM has been disabled. * * If @check_resume is set and there's a resume request pending when * __pm_runtime_disable() is called and power.disable_depth is zero, the * function will wake up the device before disabling its runtime PM. */ void __pm_runtime_disable(struct device *dev, bool check_resume) { spin_lock_irq(&dev->power.lock); if (dev->power.disable_depth > 0) { dev->power.disable_depth++; goto out; } /* * Wake up the device if there's a resume request pending, because that * means there probably is some I/O to process and disabling runtime PM * shouldn't prevent the device from processing the I/O. */ if (check_resume && dev->power.request_pending && dev->power.request == RPM_REQ_RESUME) { /* * Prevent suspends and idle notifications from being carried * out after we have woken up the device. */ pm_runtime_get_noresume(dev); rpm_resume(dev, 0); pm_runtime_put_noidle(dev); } /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); dev->power.last_status = dev->power.runtime_status; } out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_disable); /** * pm_runtime_enable - Enable runtime PM of a device. * @dev: Device to handle. */ void pm_runtime_enable(struct device *dev) { unsigned long flags; spin_lock_irqsave(&dev->power.lock, flags); if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); goto out; } if (--dev->power.disable_depth > 0) goto out; dev->power.last_status = RPM_INVALID; dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); if (dev->power.runtime_status == RPM_SUSPENDED && !dev->power.ignore_children && atomic_read(&dev->power.child_count) > 0) dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); static void pm_runtime_disable_action(void *data) { pm_runtime_dont_use_autosuspend(data); pm_runtime_disable(data); } /** * devm_pm_runtime_enable - devres-enabled version of pm_runtime_enable. * * NOTE: this will also handle calling pm_runtime_dont_use_autosuspend() for * you at driver exit time if needed. * * @dev: Device to handle. */ int devm_pm_runtime_enable(struct device *dev) { pm_runtime_enable(dev); return devm_add_action_or_reset(dev, pm_runtime_disable_action, dev); } EXPORT_SYMBOL_GPL(devm_pm_runtime_enable); /** * pm_runtime_forbid - Block runtime PM of a device. * @dev: Device to handle. * * Increase the device's usage count and clear its power.runtime_auto flag, * so that it cannot be suspended at run time until pm_runtime_allow() is called * for it. */ void pm_runtime_forbid(struct device *dev) { spin_lock_irq(&dev->power.lock); if (!dev->power.runtime_auto) goto out; dev->power.runtime_auto = false; atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_forbid); /** * pm_runtime_allow - Unblock runtime PM of a device. * @dev: Device to handle. * * Decrease the device's usage count and set its power.runtime_auto flag. */ void pm_runtime_allow(struct device *dev) { int ret; spin_lock_irq(&dev->power.lock); if (dev->power.runtime_auto) goto out; dev->power.runtime_auto = true; ret = rpm_drop_usage_count(dev); if (ret == 0) rpm_idle(dev, RPM_AUTO | RPM_ASYNC); else if (ret > 0) trace_rpm_usage_rcuidle(dev, RPM_AUTO | RPM_ASYNC); out: spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_allow); /** * pm_runtime_no_callbacks - Ignore runtime PM callbacks for a device. * @dev: Device to handle. * * Set the power.no_callbacks flag, which tells the PM core that this * device is power-managed through its parent and has no runtime PM * callbacks of its own. The runtime sysfs attributes will be removed. */ void pm_runtime_no_callbacks(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.no_callbacks = 1; spin_unlock_irq(&dev->power.lock); if (device_is_registered(dev)) rpm_sysfs_remove(dev); } EXPORT_SYMBOL_GPL(pm_runtime_no_callbacks); /** * pm_runtime_irq_safe - Leave interrupts disabled during callbacks. * @dev: Device to handle * * Set the power.irq_safe flag, which tells the PM core that the * ->runtime_suspend() and ->runtime_resume() callbacks for this device should * always be invoked with the spinlock held and interrupts disabled. It also * causes the parent's usage counter to be permanently incremented, preventing * the parent from runtime suspending -- otherwise an irq-safe child might have * to wait for a non-irq-safe parent. */ void pm_runtime_irq_safe(struct device *dev) { if (dev->parent) pm_runtime_get_sync(dev->parent); spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 1; spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_irq_safe); /** * update_autosuspend - Handle a change to a device's autosuspend settings. * @dev: Device to handle. * @old_delay: The former autosuspend_delay value. * @old_use: The former use_autosuspend value. * * Prevent runtime suspend if the new delay is negative and use_autosuspend is * set; otherwise allow it. Send an idle notification if suspends are allowed. * * This function must be called under dev->power.lock with interrupts disabled. */ static void update_autosuspend(struct device *dev, int old_delay, int old_use) { int delay = dev->power.autosuspend_delay; /* Should runtime suspend be prevented now? */ if (dev->power.use_autosuspend && delay < 0) { /* If it used to be allowed then prevent it. */ if (!old_use || old_delay >= 0) { atomic_inc(&dev->power.usage_count); rpm_resume(dev, 0); } else { trace_rpm_usage_rcuidle(dev, 0); } } /* Runtime suspend should be allowed now. */ else { /* If it used to be prevented then allow it. */ if (old_use && old_delay < 0) atomic_dec(&dev->power.usage_count); /* Maybe we can autosuspend now. */ rpm_idle(dev, RPM_AUTO); } } /** * pm_runtime_set_autosuspend_delay - Set a device's autosuspend_delay value. * @dev: Device to handle. * @delay: Value of the new delay in milliseconds. * * Set the device's power.autosuspend_delay value. If it changes to negative * and the power.use_autosuspend flag is set, prevent runtime suspends. If it * changes the other way, allow runtime suspends. */ void pm_runtime_set_autosuspend_delay(struct device *dev, int delay) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.autosuspend_delay = delay; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(pm_runtime_set_autosuspend_delay); /** * __pm_runtime_use_autosuspend - Set a device's use_autosuspend flag. * @dev: Device to handle. * @use: New value for use_autosuspend. * * Set the device's power.use_autosuspend flag, and allow or prevent runtime * suspends as needed. */ void __pm_runtime_use_autosuspend(struct device *dev, bool use) { int old_delay, old_use; spin_lock_irq(&dev->power.lock); old_delay = dev->power.autosuspend_delay; old_use = dev->power.use_autosuspend; dev->power.use_autosuspend = use; update_autosuspend(dev, old_delay, old_use); spin_unlock_irq(&dev->power.lock); } EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); /** * pm_runtime_init - Initialize runtime PM fields in given device object. * @dev: Device object to initialize. */ void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; atomic_set(&dev->power.usage_count, 0); dev->power.runtime_error = 0; atomic_set(&dev->power.child_count, 0); pm_suspend_ignore_children(dev, false); dev->power.runtime_auto = true; dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; dev->power.needs_force_resume = 0; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; hrtimer_init(&dev->power.suspend_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); dev->power.suspend_timer.function = pm_suspend_timer_fn; init_waitqueue_head(&dev->power.wait_queue); } /** * pm_runtime_reinit - Re-initialize runtime PM fields in given device object. * @dev: Device object to re-initialize. */ void pm_runtime_reinit(struct device *dev) { if (!pm_runtime_enabled(dev)) { if (dev->power.runtime_status == RPM_ACTIVE) pm_runtime_set_suspended(dev); if (dev->power.irq_safe) { spin_lock_irq(&dev->power.lock); dev->power.irq_safe = 0; spin_unlock_irq(&dev->power.lock); if (dev->parent) pm_runtime_put(dev->parent); } } } /** * pm_runtime_remove - Prepare for removing a device from device hierarchy. * @dev: Device object being removed from device hierarchy. */ void pm_runtime_remove(struct device *dev) { __pm_runtime_disable(dev, false); pm_runtime_reinit(dev); } /** * pm_runtime_get_suppliers - Resume and reference-count supplier devices. * @dev: Consumer device. */ void pm_runtime_get_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; pm_runtime_get_sync(link->supplier); } device_links_read_unlock(idx); } /** * pm_runtime_put_suppliers - Drop references to supplier devices. * @dev: Consumer device. */ void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; int idx; idx = device_links_read_lock(); list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; pm_runtime_put(link->supplier); } device_links_read_unlock(idx); } void pm_runtime_new_link(struct device *dev) { spin_lock_irq(&dev->power.lock); dev->power.links_count++; spin_unlock_irq(&dev->power.lock); } static void pm_runtime_drop_link_count(struct device *dev) { spin_lock_irq(&dev->power.lock); WARN_ON(dev->power.links_count == 0); dev->power.links_count--; spin_unlock_irq(&dev->power.lock); } /** * pm_runtime_drop_link - Prepare for device link removal. * @link: Device link going away. * * Drop the link count of the consumer end of @link and decrement the supplier * device's runtime PM usage counter as many times as needed to drop all of the * PM runtime reference to it from the consumer. */ void pm_runtime_drop_link(struct device_link *link) { if (!(link->flags & DL_FLAG_PM_RUNTIME)) return; pm_runtime_drop_link_count(link->consumer); pm_runtime_release_supplier(link); pm_request_idle(link->supplier); } static bool pm_runtime_need_not_resume(struct device *dev) { return atomic_read(&dev->power.usage_count) <= 1 && (atomic_read(&dev->power.child_count) == 0 || dev->power.ignore_children); } /** * pm_runtime_force_suspend - Force a device into suspend state if needed. * @dev: Device to suspend. * * Disable runtime PM so we safely can check the device's runtime PM status and * if it is active, invoke its ->runtime_suspend callback to suspend it and * change its runtime PM status field to RPM_SUSPENDED. Also, if the device's * usage and children counters don't indicate that the device was in use before * the system-wide transition under way, decrement its parent's children counter * (if there is a parent). Keep runtime PM disabled to preserve the state * unless we encounter errors. * * Typically this function may be invoked from a system suspend callback to make * sure the device is put into low power state and it should only be used during * system-wide PM transitions to sleep states. It assumes that the analogous * pm_runtime_force_resume() will be used to resume the device. */ int pm_runtime_force_suspend(struct device *dev) { int (*callback)(struct device *); int ret; pm_runtime_disable(dev); if (pm_runtime_status_suspended(dev)) return 0; callback = RPM_GET_CALLBACK(dev, runtime_suspend); dev_pm_enable_wake_irq_check(dev, true); ret = callback ? callback(dev) : 0; if (ret) goto err; dev_pm_enable_wake_irq_complete(dev); /* * If the device can stay in suspend after the system-wide transition * to the working state that will follow, drop the children counter of * its parent, but set its status to RPM_SUSPENDED anyway in case this * function will be called again for it in the meantime. */ if (pm_runtime_need_not_resume(dev)) { pm_runtime_set_suspended(dev); } else { __update_runtime_status(dev, RPM_SUSPENDED); dev->power.needs_force_resume = 1; } return 0; err: dev_pm_disable_wake_irq_check(dev, true); pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_suspend); /** * pm_runtime_force_resume - Force a device into resume state if needed. * @dev: Device to resume. * * Prior invoking this function we expect the user to have brought the device * into low power state by a call to pm_runtime_force_suspend(). Here we reverse * those actions and bring the device into full power, if it is expected to be * used on system resume. In the other case, we defer the resume to be managed * via runtime PM. * * Typically this function may be invoked from a system resume callback. */ int pm_runtime_force_resume(struct device *dev) { int (*callback)(struct device *); int ret = 0; if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume) goto out; /* * The value of the parent's children counter is correct already, so * just update the status of the device. */ __update_runtime_status(dev, RPM_ACTIVE); callback = RPM_GET_CALLBACK(dev, runtime_resume); dev_pm_disable_wake_irq_check(dev, false); ret = callback ? callback(dev) : 0; if (ret) { pm_runtime_set_suspended(dev); dev_pm_enable_wake_irq_check(dev, false); goto out; } pm_runtime_mark_last_busy(dev); out: dev->power.needs_force_resume = 0; pm_runtime_enable(dev); return ret; } EXPORT_SYMBOL_GPL(pm_runtime_force_resume); |
| 1620 1615 23 23 23 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(sk_cache); static struct bpf_local_storage_data * bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_map *smap; sk_storage = rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held()); if (!sk_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = bpf_sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; bpf_selem_unlink(SELEM(sdata), true); return 0; } /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { struct bpf_local_storage_elem *selem; struct bpf_local_storage *sk_storage; bool free_sk_storage = false; struct hlist_node *n; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) { rcu_read_unlock(); return; } /* Netiher the bpf_prog nor the bpf-map's syscall * could be modifying the sk_storage->list now. * Thus, no elem can be added-to or deleted-from the * sk_storage->list by the bpf_prog or by the bpf-map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the sk_storage->list and * the map's bucket->list. */ raw_spin_lock_bh(&sk_storage->lock); hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { /* Always unlink from map before unlinking from * sk_storage. */ bpf_selem_unlink_map(selem); free_sk_storage = bpf_selem_unlink_storage_nolock( sk_storage, selem, true, false); } raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); if (free_sk_storage) kfree_rcu(sk_storage, rcu); } static void bpf_sk_storage_map_free(struct bpf_map *map) { struct bpf_local_storage_map *smap; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); bpf_local_storage_map_free(smap, NULL); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; smap = bpf_local_storage_map_alloc(attr); if (IS_ERR(smap)) return ERR_CAST(smap); smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); return &smap->map; } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_sk_storage_lookup(sock->sk, map, true); sockfd_put(sock); return sdata ? sdata->data : NULL; } return ERR_PTR(err); } static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_local_storage_update( sock->sk, (struct bpf_local_storage_map *)map, value, map_flags, GFP_ATOMIC); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } return err; } static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) { struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { err = bpf_sk_storage_del(sock->sk, map); sockfd_put(sock); return err; } return err; } static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_elem *copy_selem; copy_selem = bpf_selem_alloc(smap, newsk, NULL, true, GFP_ATOMIC); if (!copy_selem) return NULL; if (map_value_has_spin_lock(&smap->map)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else copy_map_value(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data); return copy_selem; } int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { struct bpf_local_storage *new_sk_storage = NULL; struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { struct bpf_local_storage_elem *copy_selem; struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); if (!(smap->map.map_flags & BPF_F_CLONE)) continue; /* Note that for lockless listeners adding new element * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ map = bpf_map_inc_not_zero(&smap->map); if (IS_ERR(map)) continue; copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem); if (!copy_selem) { ret = -ENOMEM; bpf_map_put(map); goto out; } if (new_sk_storage) { bpf_selem_link_map(smap, copy_selem); bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { ret = bpf_local_storage_alloc(newsk, smap, copy_selem, GFP_ATOMIC); if (ret) { kfree(copy_selem); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); goto out; } new_sk_storage = rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } out: rcu_read_unlock(); /* In case of an error, don't free anything explicitly here, the * caller is responsible to call bpf_sk_storage_free. */ return ret; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags, gfp_t, gfp_flags) { struct bpf_local_storage_data *sdata; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = bpf_sk_storage_lookup(sk, map, true); if (sdata) return (unsigned long)sdata->data; if (flags == BPF_SK_STORAGE_GET_F_CREATE && /* Cannot add new elem to a going away sk. * Otherwise, the new elem may become a leak * (and also other memory issues during map * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { sdata = bpf_local_storage_update( sk, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, gfp_flags); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ sock_put(sk); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } return (unsigned long)NULL; } BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk)) return -EINVAL; if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; err = bpf_sk_storage_del(sk, map); sock_put(sk); return err; } return -ENOENT; } static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { int optmem_max = READ_ONCE(sysctl_optmem_max); struct sock *sk = (struct sock *)owner; /* same check as in sock_kmalloc() */ if (size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { atomic_add(size, &sk->sk_omem_alloc); return 0; } return -ENOMEM; } static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct sock *sk = owner; atomic_sub(size, &sk->sk_omem_alloc); } static struct bpf_local_storage __rcu ** bpf_sk_storage_ptr(void *owner) { struct sock *sk = owner; return &sk->sk_bpf_storage; } BTF_ID_LIST_SINGLE(sk_storage_map_btf_ids, struct, bpf_local_storage_map) const struct bpf_map_ops sk_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = bpf_sk_storage_map_alloc, .map_free = bpf_sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_id = &sk_storage_map_btf_ids[0], .map_local_storage_charge = bpf_sk_storage_charge, .map_local_storage_uncharge = bpf_sk_storage_uncharge, .map_owner_storage_ptr = bpf_sk_storage_ptr, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_CTX, /* context is 'struct sock' */ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_delete_proto = { .func = bpf_sk_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { const struct btf *btf_vmlinux; const struct btf_type *t; const char *tname; u32 btf_id; if (prog->aux->dst_prog) return false; /* Ensure the tracing program is not tracing * any bpf_sk_storage*() function and also * use the bpf_sk_storage_(get|delete) helper. */ switch (prog->expected_attach_type) { case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: /* bpf_sk_storage has no trace point */ return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: btf_vmlinux = bpf_get_btf_vmlinux(); if (IS_ERR_OR_NULL(btf_vmlinux)) return false; btf_id = prog->aux->attach_btf_id; t = btf_type_by_id(btf_vmlinux, btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); return !!strncmp(tname, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; } return false; } /* *gfp_flags* is a hidden argument provided by the verifier */ BPF_CALL_5(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags, gfp_t, gfp_flags) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags, gfp_flags); } BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); } const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = { .func = bpf_sk_storage_get_tracing, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, .allowed = bpf_sk_storage_tracing_allowed, }; const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = { .func = bpf_sk_storage_delete_tracing, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .allowed = bpf_sk_storage_tracing_allowed, }; struct bpf_sk_storage_diag { u32 nr_maps; struct bpf_map *maps[]; }; /* The reply will be like: * INET_DIAG_BPF_SK_STORAGES (nla_nest) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * .... */ static int nla_value_size(u32 value_size) { /* SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) */ return nla_total_size(0) + nla_total_size(sizeof(u32)) + nla_total_size_64bit(value_size); } void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) { u32 i; if (!diag) return; for (i = 0; i < diag->nr_maps; i++) bpf_map_put(diag->maps[i]); kfree(diag); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free); static bool diag_check_dup(const struct bpf_sk_storage_diag *diag, const struct bpf_map *map) { u32 i; for (i = 0; i < diag->nr_maps; i++) { if (diag->maps[i] == map) return true; } return false; } struct bpf_sk_storage_diag * bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) { struct bpf_sk_storage_diag *diag; struct nlattr *nla; u32 nr_maps = 0; int rem, err; /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) return ERR_PTR(-EPERM); nla_for_each_nested(nla, nla_stgs, rem) { if (nla_type(nla) == SK_DIAG_BPF_STORAGE_REQ_MAP_FD) { if (nla_len(nla) != sizeof(u32)) return ERR_PTR(-EINVAL); nr_maps++; } } diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); if (!diag) return ERR_PTR(-ENOMEM); nla_for_each_nested(nla, nla_stgs, rem) { struct bpf_map *map; int map_fd; if (nla_type(nla) != SK_DIAG_BPF_STORAGE_REQ_MAP_FD) continue; map_fd = nla_get_u32(nla); map = bpf_map_get(map_fd); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_free; } if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) { bpf_map_put(map); err = -EINVAL; goto err_free; } if (diag_check_dup(diag, map)) { bpf_map_put(map); err = -EEXIST; goto err_free; } diag->maps[diag->nr_maps++] = map; } return diag; err_free: bpf_sk_storage_diag_free(diag); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) return -EMSGSIZE; smap = rcu_dereference(sdata->smap); if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) goto errout; nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE, smap->map.value_size, SK_DIAG_BPF_STORAGE_PAD); if (!nla_value) goto errout; if (map_value_has_spin_lock(&smap->map)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else copy_map_value(&smap->map, nla_data(nla_value), sdata->data); nla_nest_end(skb, nla_stg); return 0; errout: nla_nest_cancel(skb, nla_stg); return -EMSGSIZE; } static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { smap = rcu_dereference(SDATA(selem)->smap); diag_size += nla_value_size(smap->map.value_size); if (nla_stgs && diag_get(SDATA(selem), skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; u32 i; *res_diag_size = 0; /* No map has been specified. Dump all. */ if (!diag->nr_maps) return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type, res_diag_size); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { sdata = bpf_local_storage_lookup(sk_storage, (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) continue; diag_size += nla_value_size(diag->maps[i]->value_size); if (nla_stgs && diag_get(sdata, skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); struct bpf_iter_seq_sk_storage_map_info { struct bpf_map *map; unsigned int bucket_id; unsigned skip_elems; }; static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, struct bpf_local_storage_elem *prev_selem) __acquires(RCU) __releases(RCU) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; struct bpf_local_storage_map_bucket *b; smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; /* try to find next selem in the same bucket */ selem = prev_selem; count = 0; while (selem) { selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; rcu_read_unlock(); skip_elems = 0; break; } sk_storage = rcu_dereference(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; } count++; } for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); count = 0; hlist_for_each_entry_rcu(selem, &b->list, map_node) { sk_storage = rcu_dereference(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; return selem; } count++; } rcu_read_unlock(); skip_elems = 0; } info->bucket_id = i; info->skip_elems = 0; return NULL; } static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) return NULL; if (*pos == 0) ++*pos; return selem; } static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; ++*pos; ++info->skip_elems; return bpf_sk_storage_map_seq_find_next(seq->private, v); } struct bpf_iter__bpf_sk_storage_map { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(struct sock *, sk); __bpf_md_ptr(void *, value); }; DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, struct bpf_map *map, struct sock *sk, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; meta.seq = seq; prog = bpf_iter_get_info(&meta, selem == NULL); if (prog) { ctx.meta = &meta; ctx.map = info->map; if (selem) { sk_storage = rcu_dereference(selem->local_storage); ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); } return ret; } static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) { return __bpf_sk_storage_map_seq_show(seq, v); } static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { if (!v) (void)__bpf_sk_storage_map_seq_show(seq, v); else rcu_read_unlock(); } static int bpf_iter_init_sk_storage_map(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_inc_with_uref(aux->map); seq_info->map = aux->map; return 0; } static void bpf_iter_fini_sk_storage_map(void *priv_data) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_put_with_uref(seq_info->map); } static int bpf_iter_attach_map(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) { struct bpf_map *map; int err = -EINVAL; if (!linfo->map.map_fd) return -EBADF; map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto put_map; if (prog->aux->max_rdwr_access > map->value_size) { err = -EACCES; goto put_map; } aux->map = map; return 0; put_map: bpf_map_put_with_uref(map); return err; } static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) { bpf_map_put_with_uref(aux->map); } static const struct seq_operations bpf_sk_storage_map_seq_ops = { .start = bpf_sk_storage_map_seq_start, .next = bpf_sk_storage_map_seq_next, .stop = bpf_sk_storage_map_seq_stop, .show = bpf_sk_storage_map_seq_show, }; static const struct bpf_iter_seq_info iter_seq_info = { .seq_ops = &bpf_sk_storage_map_seq_ops, .init_seq_private = bpf_iter_init_sk_storage_map, .fini_seq_private = bpf_iter_fini_sk_storage_map, .seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info), }; static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), PTR_TO_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; static int __init bpf_sk_storage_map_iter_init(void) { bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info); } late_initcall(bpf_sk_storage_map_iter_init); |
| 4 4 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 | // 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) { unsigned int size = sizeof(struct sock_reuseport) + sizeof(struct sock *) * max_socks; struct sock_reuseport *reuse = kzalloc(size, 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); |
| 471 396 5 76 15 1 12 12 386 66 392 3 6 62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VIRTIO_NET_H #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> #include <uapi/linux/tcp.h> #include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) { switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: return protocol == cpu_to_be16(ETH_P_IP); case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: return false; } } static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { if (skb->protocol) return 0; switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: skb->protocol = cpu_to_be16(ETH_P_IPV6); break; default: return -EINVAL; } return 0; } static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, const struct virtio_net_hdr *hdr, bool little_endian) { unsigned int gso_type = 0; unsigned int thlen = 0; unsigned int p_off = 0; unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; ip_proto = IPPROTO_TCP; thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; default: return -EINVAL; } if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN) gso_type |= SKB_GSO_TCP_ECN; if (hdr->gso_size == 0) return -EINVAL; } skb_reset_mac_header(skb); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); if (!pskb_may_pull(skb, needed)) return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; p_off = skb_transport_offset(skb) + thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { struct flow_keys_basic keys; if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); if (!protocol) virtio_net_hdr_set_proto(skb, hdr); else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; else skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { skb->protocol = htons(ETH_P_IPV6); goto retry; } return -EINVAL; } p_off = keys.control.thoff + thlen; if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = thlen; if (!pskb_may_pull(skb, p_off)) return -EINVAL; } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); /* UFO may not include transport header in gso_size. */ if (gso_type & SKB_GSO_UDP) nh_off -= thlen; /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) return -EINVAL; /* Too small packets are not really GSO ones. */ if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; /* Header must be checked, and gso_segs computed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } } return 0; } static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, struct virtio_net_hdr *hdr, bool little_endian, bool has_data_valid, int vlan_hlen) { memset(hdr, 0, sizeof(*hdr)); /* no info leak */ if (skb_is_gso(skb)) { struct skb_shared_info *sinfo = skb_shinfo(skb); /* This is a hint as to how much should be linear. */ hdr->hdr_len = __cpu_to_virtio16(little_endian, skb_headlen(skb)); hdr->gso_size = __cpu_to_virtio16(little_endian, sinfo->gso_size); if (sinfo->gso_type & SKB_GSO_TCPV4) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; } else hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; hdr->csum_start = __cpu_to_virtio16(little_endian, skb_checksum_start_offset(skb) + vlan_hlen); hdr->csum_offset = __cpu_to_virtio16(little_endian, skb->csum_offset); } else if (has_data_valid && skb->ip_summed == CHECKSUM_UNNECESSARY) { hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ return 0; } #endif /* _LINUX_VIRTIO_NET_H */ |
| 2846 927 927 893 893 811 3097 2419 902 903 243 243 927 927 267 268 3533 3533 3 3533 7 7 7 7 7 903 903 903 903 902 903 903 903 903 902 901 902 903 903 903 903 903 903 903 903 903 1832 1832 1832 1832 1832 1832 1832 1832 242 247 247 3 4 7 7 7 7 7 7 7 926 927 927 927 927 337 903 902 902 902 337 337 243 243 243 243 463 128 337 243 51 51 20 20 42 42 903 903 903 903 902 28 878 903 128 778 903 902 243 243 903 902 538 539 539 123 539 538 930 1 1 928 928 928 1 927 926 927 927 927 25 903 902 902 116 755 1 755 541 1 220 546 545 545 7 27 512 538 522 17 539 538 539 535 4 7 223 224 337 243 243 243 268 931 930 37 119 778 271 539 513 494 46 539 538 494 42 42 931 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/cpufreq_times.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/sched.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK EXPORT_TRACEPOINT_SYMBOL_GPL(task_newtask); EXPORT_TRACEPOINT_SYMBOL_GPL(task_rename); /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ EXPORT_SYMBOL_GPL(tasklist_lock); #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #endif #ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) # ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL) continue; return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_stack); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm) { int i; int ret; BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) goto err; } return 0; err: /* * If memcg_kmem_charge_page() fails, page's memory cgroup pointer is * NULL, and memcg_kmem_uncharge_page() in free_thread_stack() will * ignore this page. */ for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Reset stack metadata. */ kasan_unpoison_range(s->addr, THREAD_SIZE); stack = kasan_reset_tag(s->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(s)) { vfree(s->addr); return -ENOMEM; } tsk->stack_vm_area = s; tsk->stack = stack; return 0; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm = find_vm_area(stack); if (memcg_charge_kernel_stack(vm)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } # else /* !CONFIG_VMAP_STACK */ static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } # endif /* CONFIG_VMAP_STACK */ # else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ #else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = arch_alloc_thread_stack_node(tsk, node); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { arch_free_thread_stack(tsk); tsk->stack = NULL; } #endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; #ifdef CONFIG_PER_VMA_LOCK /* SLAB cache for vm_area_struct.lock */ static struct kmem_cache *vma_lock_cachep; static bool vma_lock_alloc(struct vm_area_struct *vma) { vma->vm_lock = kmem_cache_alloc(vma_lock_cachep, GFP_KERNEL); if (!vma->vm_lock) return false; init_rwsem(&vma->vm_lock->lock); vma->vm_lock_seq = -1; return true; } static inline void vma_lock_free(struct vm_area_struct *vma) { kmem_cache_free(vma_lock_cachep, vma->vm_lock); } #else /* CONFIG_PER_VMA_LOCK */ static inline bool vma_lock_alloc(struct vm_area_struct *vma) { return true; } static inline void vma_lock_free(struct vm_area_struct *vma) {} #endif /* CONFIG_PER_VMA_LOCK */ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!vma) return NULL; vma_init(vma, mm); if (!vma_lock_alloc(vma)) { kmem_cache_free(vm_area_cachep, vma); return NULL; } return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) return NULL; ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); /* * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ data_race(memcpy(new, orig, sizeof(*new))); if (!vma_lock_alloc(new)) { kmem_cache_free(vm_area_cachep, new); return NULL; } INIT_LIST_HEAD(&new->anon_vma_chain); dup_anon_vma_name(orig, new); return new; } void __vm_area_free(struct vm_area_struct *vma) { free_anon_vma_name(vma); vma_lock_free(vma); kmem_cache_free(vm_area_cachep, vma); } #ifdef CONFIG_PER_VMA_LOCK static void vm_area_free_rcu_cb(struct rcu_head *head) { struct vm_area_struct *vma = container_of(head, struct vm_area_struct, vm_rcu); /* The vma should not be locked while being destroyed. */ VM_BUG_ON_VMA(rwsem_is_locked(&vma->vm_lock->lock), vma); __vm_area_free(vma); } #endif void vm_area_free(struct vm_area_struct *vma) { #ifdef CONFIG_PER_VMA_LOCK call_rcu(&vma->vm_rcu, vm_area_free_rcu_cb); #else __vm_area_free(vma); #endif } static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm; int i; vm = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif cpufreq_task_times_exit(tsk); release_user_cpus_ptr(tsk); scs_release(tsk); trace_android_vh_free_task(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && deny_write_access(exe_file)) pr_warn_once("deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp; int retval; unsigned long charge = 0; LIST_HEAD(uf); MA_STATE(mas, &mm->mm_mt, 0, 0); uprobe_start_dup_mmap(); if (mmap_write_lock_killable(oldmm)) { retval = -EINTR; goto fail_uprobe_end; } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; retval = ksm_fork(mm, oldmm); if (retval) goto out; khugepaged_fork(mm, oldmm); /* Use __mt_dup() to efficiently build an identical maple tree. */ retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL); if (unlikely(retval)) goto out; mt_clear_in_rcu(mas.tree); mas_for_each(&mas, mpnt, ULONG_MAX) { struct file *file; vma_start_write(mpnt); if (mpnt->vm_flags & VM_DONTCOPY) { __mas_set_range(&mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store_gfp(&mas, NULL, GFP_KERNEL); if (unlikely(mas_is_err(&mas))) { retval = -ENOMEM; goto loop_out; } vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; vm_flags_clear(tmp, VM_LOCKED_MASK); /* * Copy/update hugetlb private vma information. */ if (is_vm_hugetlb_page(tmp)) hugetlb_dup_vma_private(tmp); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (tmp->vm_flags & VM_SHARED) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } /* * Link the vma into the MT. After using __mt_dup(), memory * allocation is not necessary here, so it cannot fail. */ mas.index = tmp->vm_start; mas.last = tmp->vm_end - 1; mas_store(&mas, tmp); mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (retval) { mpnt = mas_find(&mas, ULONG_MAX); goto loop_out; } } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: mas_destroy(&mas); if (!retval) { mt_set_in_rcu(mas.tree); } else if (mpnt) { /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with * XA_ZERO_ENTRY. In exit_mmap(), if this marker is encountered, * stop releasing VMAs that have not been duplicated after this * point. */ mas_set_range(&mas, mpnt->vm_start, mpnt->vm_end - 1); mas_store(&mas, XA_ZERO_ENTRY); } out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); dup_userfaultfd_complete(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = atomic_long_read(&mm->rss_stat.count[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = totalram_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } #endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */ void __init fork_init(void) { int i; #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); #endif /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_queue = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_IOMMU_SVA tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_CPU_SUP_INTEL tsk->reported_split_lock = 0; #endif android_init_vendor_data(tsk, 1); android_init_oem_data(tsk, 1); trace_android_vh_dup_task_struct(tsk, orig); return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); #ifdef CONFIG_PER_VMA_LOCK mm->mm_lock_seq = 0; #endif mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (init_new_context(p, mm)) goto fail_nocontext; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_nocontext: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_page(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) { trace_android_vh_mmput(mm); __mmput(mm); } } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve task is single * threaded. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe), * dealing with concurrent invocation and without grabbing the mmap lock in * write mode. * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } /* set the new file, lockless */ ret = deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); old_exe_file = xchg(&mm->exe_file, new_exe_file); if (old_exe_file) { /* * Don't race with dup_mmap() getting the file and disallowing * write access while someone might open the file writable. */ mmap_read_lock(mm); allow_write_access(old_exe_file); fput(old_exe_file); mmap_read_unlock(mm); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = rcu_dereference(mm->exe_file); if (exe_file && !get_file_rcu(exe_file)) exe_file = NULL; rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (!(task->flags & PF_KTHREAD)) exe_file = get_mm_exe_file(mm); } task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (task->flags & PF_KTHREAD) mm = NULL; else mmget(mm); } task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (mm && mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_UNINTERRUPTIBLE|TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); if (err) goto free_pt; mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) goto out; if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); goto out; } newf = dup_fd(oldf, NR_OPEN_MAX, &error); if (!newf) goto out; tsk->files = newf; error = 0; out: return error; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } struct pid *pidfd_pid(const struct file *file) { if (file->f_op == &pidfd_fops) return file->private_data; return ERR_PTR(-EBADF); } static int pidfd_release(struct inode *inode, struct file *file) { struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); return 0; } #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = f->private_data; struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Inform pollers only when the whole thread group exits. * If the thread group leader exits before all other threads in the * group, then poll(2) should block, similar to the wait(2) family. */ if (thread_group_exited(pid)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } const struct file_operations pidfd_fops = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { int i; for (i = 0; i < RV_PER_TASK_MONITORS; i++) p->rv[i].da_mon.monitoring = false; } #else #define rv_task_fork(p) do {} while (0) #endif /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } /* * If the new process will be in a different time namespace * do not allow it to share VM or a thread group with the forking task. */ if (clone_flags & (CLONE_THREAD | CLONE_VM)) { if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. * - CLONE_THREAD is blocked until someone really needs it. */ if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->io_thread) { /* * Mark us an IO worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_IO_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } cpufreq_task_times_init(p); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, O_RDWR | O_CLOEXEC); if (IS_ERR(pidfile)) { put_unused_fd(pidfd); retval = PTR_ERR(pidfile); goto bad_fork_free_pid; } get_pid(pid); /* held by pidfile now */ retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ sched_cgroup_fork(p, args); /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_cancel_cgroup; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_cancel_cgroup; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } trace_android_vh_copy_process(current, nr_threads, current->signal->nr_threads); total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_cancel_cgroup: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .io_thread = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((args->flags & CLONE_PIDFD) && (args->flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); cpufreq_task_times_alloc(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } #endif void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); #ifdef CONFIG_PER_VMA_LOCK vma_lock_cachep = KMEM_CACHE(vma_lock, SLAB_PANIC|SLAB_ACCOUNT); #endif mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp) { struct files_struct *fd = current->files; int error = 0; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { *new_fdp = dup_fd(fd, max_fds, &error); if (!*new_fdp) return error; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 1271 1272 1179 46 1103 1126 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | // SPDX-License-Identifier: GPL-2.0 /* * linux/lib/kasprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/stdarg.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> /* Simplified asprintf. */ char *kvasprintf(gfp_t gfp, const char *fmt, va_list ap) { unsigned int first, second; char *p; va_list aq; va_copy(aq, ap); first = vsnprintf(NULL, 0, fmt, aq); va_end(aq); p = kmalloc_track_caller(first+1, gfp); if (!p) return NULL; second = vsnprintf(p, first+1, fmt, ap); WARN(first != second, "different return values (%u and %u) from vsnprintf(\"%s\", ...)", first, second, fmt); return p; } EXPORT_SYMBOL(kvasprintf); /* * If fmt contains no % (or is exactly %s), use kstrdup_const. If fmt * (or the sole vararg) points to rodata, we will then save a memory * allocation and string copy. In any case, the return value should be * freed using kfree_const(). */ const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list ap) { if (!strchr(fmt, '%')) return kstrdup_const(fmt, gfp); if (!strcmp(fmt, "%s")) return kstrdup_const(va_arg(ap, const char*), gfp); return kvasprintf(gfp, fmt, ap); } EXPORT_SYMBOL(kvasprintf_const); char *kasprintf(gfp_t gfp, const char *fmt, ...) { va_list ap; char *p; va_start(ap, fmt); p = kvasprintf(gfp, fmt, ap); va_end(ap); return p; } EXPORT_SYMBOL(kasprintf); |
| 69 69 69 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/tcp.h> #include <linux/rcupdate.h> #include <net/tcp.h> void tcp_fastopen_init_key_once(struct net *net) { u8 key[TCP_FASTOPEN_KEY_LENGTH]; struct tcp_fastopen_context *ctxt; rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) { rcu_read_unlock(); return; } rcu_read_unlock(); /* tcp_fastopen_reset_cipher publishes the new context * atomically, so we allow this race happening here. * * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ get_random_bytes(key, sizeof(key)); tcp_fastopen_reset_cipher(net, NULL, key, NULL); } static void tcp_fastopen_ctx_free(struct rcu_head *head) { struct tcp_fastopen_context *ctx = container_of(head, struct tcp_fastopen_context, rcu); kfree_sensitive(ctx); } void tcp_fastopen_destroy_cipher(struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference_protected( inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1); if (ctx) call_rcu(&ctx->rcu, tcp_fastopen_ctx_free); } void tcp_fastopen_ctx_destroy(struct net *net) { struct tcp_fastopen_context *ctxt; ctxt = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, NULL); if (ctxt) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); } int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key) { struct tcp_fastopen_context *ctx, *octx; struct fastopen_queue *q; int err = 0; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto out; } ctx->key[0].key[0] = get_unaligned_le64(primary_key); ctx->key[0].key[1] = get_unaligned_le64(primary_key + 8); if (backup_key) { ctx->key[1].key[0] = get_unaligned_le64(backup_key); ctx->key[1].key[1] = get_unaligned_le64(backup_key + 8); ctx->num = 2; } else { ctx->num = 1; } if (sk) { q = &inet_csk(sk)->icsk_accept_queue.fastopenq; octx = xchg((__force struct tcp_fastopen_context **)&q->ctx, ctx); } else { octx = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, ctx); } if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); out: return err; } int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key) { struct tcp_fastopen_context *ctx; int n_keys = 0, i; rcu_read_lock(); if (icsk) ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); else ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctx) { n_keys = tcp_fastopen_context_len(ctx); for (i = 0; i < n_keys; i++) { put_unaligned_le64(ctx->key[i].key[0], key + (i * 2)); put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1); } } rcu_read_unlock(); return n_keys; } static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req, struct sk_buff *syn, const siphash_key_t *key, struct tcp_fastopen_cookie *foc) { BUILD_BUG_ON(TCP_FASTOPEN_COOKIE_SIZE != sizeof(u64)); if (req->rsk_ops->family == AF_INET) { const struct iphdr *iph = ip_hdr(syn); foc->val[0] = cpu_to_le64(siphash(&iph->saddr, sizeof(iph->saddr) + sizeof(iph->daddr), key)); foc->len = TCP_FASTOPEN_COOKIE_SIZE; return true; } #if IS_ENABLED(CONFIG_IPV6) if (req->rsk_ops->family == AF_INET6) { const struct ipv6hdr *ip6h = ipv6_hdr(syn); foc->val[0] = cpu_to_le64(siphash(&ip6h->saddr, sizeof(ip6h->saddr) + sizeof(ip6h->daddr), key)); foc->len = TCP_FASTOPEN_COOKIE_SIZE; return true; } #endif return false; } /* Generate the fastopen cookie by applying SipHash to both the source and * destination addresses. */ static void tcp_fastopen_cookie_gen(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; rcu_read_lock(); ctx = tcp_fastopen_get_ctx(sk); if (ctx) __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[0], foc); rcu_read_unlock(); } /* If an incoming SYN or SYNACK frame contains a payload and/or FIN, * queue this additional data / FIN. */ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt) return; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; skb_dst_drop(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects * skb->len to include the tcp_hdrlen. Hence, it should * be called before __skb_pull(). */ tp->segs_in = 0; tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); sk_forced_mem_schedule(sk, skb->truesize); skb_set_owner_r(skb, sk); TCP_SKB_CB(skb)->seq++; TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; __skb_queue_tail(&sk->sk_receive_queue, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, * as we certainly are not changing upper 32bit value (0) */ tp->bytes_received = skb->len; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); } /* returns 0 - no key match, 1 for primary, 2 for backup */ static int tcp_fastopen_cookie_gen_check(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *orig, struct tcp_fastopen_cookie *valid_foc) { struct tcp_fastopen_cookie search_foc = { .len = -1 }; struct tcp_fastopen_cookie *foc = valid_foc; struct tcp_fastopen_context *ctx; int i, ret = 0; rcu_read_lock(); ctx = tcp_fastopen_get_ctx(sk); if (!ctx) goto out; for (i = 0; i < tcp_fastopen_context_len(ctx); i++) { __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[i], foc); if (tcp_fastopen_cookie_match(foc, orig)) { ret = i + 1; goto out; } foc = &search_foc; } out: rcu_read_unlock(); return ret; } static struct sock *tcp_fastopen_create_child(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; struct sock *child; bool own_req; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, NULL, &own_req); if (!child) return NULL; spin_lock(&queue->fastopenq.lock); queue->fastopenq.qlen++; spin_unlock(&queue->fastopenq.lock); /* Initialize the child socket. Have to fix some values to take * into account the child is a Fast Open socket and is created * only out of the bits carried in the SYN packet. */ tp = tcp_sk(child); rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash * because it's been added to the accept queue directly. */ req->timeout = tcp_timeout_init(child); inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, req->timeout, TCP_RTO_MAX); refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tcp_fastopen_add_skb(child, skb); tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; tp->rcv_wup = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ return child; } static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying * to validating the cookie in order to avoid burning CPU cycles * unnecessarily. * * XXX (TFO) - The implication of checking the max_qlen before * processing a cookie request is that clients can't differentiate * between qlen overflow causing Fast Open to be disabled * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; max_qlen = READ_ONCE(fastopenq->max_qlen); if (max_qlen == 0) return false; if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); spin_unlock(&fastopenq->lock); return false; } fastopenq->rskq_rst_head = req1->dl_next; fastopenq->qlen--; spin_unlock(&fastopenq->lock); reqsk_put(req1); } return true; } static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } /* Returns true if we should perform Fast Open on the SYN. The cookie (foc) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; int ret = 0; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len == 0) { /* Client requests a cookie. */ tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc); } else if (foc->len > 0) { ret = tcp_fastopen_cookie_gen_check(sk, req, skb, foc, &valid_foc); if (!ret) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } else { /* Cookie is valid. Create a (full) child socket to * accept the data in SYN before returning a SYN-ACK to * ack the data. If we fail to create the socket, fall * back and ack the ISN only but includes the same * cookie. * * Note: Data-less SYN with valid cookie is allowed to * send data in SYN_RECV state. */ fastopen: child = tcp_fastopen_create_child(sk, skb, req); if (child) { if (ret == 2) { valid_foc.exp = foc->exp; *foc = valid_foc; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEALTKEY); } else { foc->len = -1; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); return child; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } } valid_foc.exp = foc->exp; *foc = valid_foc; return NULL; } bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { const struct dst_entry *dst; tcp_fastopen_cache_get(sk, mss, cookie); /* Firewall blackhole issue check */ if (tcp_fastopen_active_should_disable(sk)) { cookie->len = -1; return false; } dst = __sk_dst_get(sk); if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) { cookie->len = -1; return true; } if (cookie->len > 0) return true; tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE; return false; } /* This function checks if we want to defer sending SYN until the first * write(). We defer under the following conditions: * 1. fastopen_connect sockopt is set * 2. we have a valid cookie * Return value: return true if we want to defer until application writes data * return false if we want to send out SYN immediately */ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) { struct tcp_fastopen_cookie cookie = { .len = 0 }; struct tcp_sock *tp = tcp_sk(sk); u16 mss; if (tp->fastopen_connect && !tp->fastopen_req) { if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) { inet_sk(sk)->defer_connect = 1; return true; } /* Alloc fastopen_req in order for FO option to be included * in SYN */ tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req), sk->sk_allocation); if (tp->fastopen_req) tp->fastopen_req->cookie = cookie; else *err = -ENOBUFS; } return false; } EXPORT_SYMBOL(tcp_fastopen_defer_connect); /* * The following code block is to deal with middle box issues with TFO: * Middlebox firewall issues can potentially cause server's data being * blackholed after a successful 3WHS using TFO. * The proposed solution is to disable active TFO globally under the * following circumstances: * 1. client side TFO socket receives out of order FIN * 2. client side TFO socket receives out of order RST * 3. client side TFO socket has timed out three times consecutively during * or after handshake * We disable active side TFO globally for 1hr at first. Then if it * happens again, we disable it for 2h, then 4h, 8h, ... * And we reset the timeout back to 1hr when we see a successful active * TFO connection with data exchanges. */ /* Disable active TFO and record current jiffies and * tfo_active_disable_times */ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)) return; /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). * We want net->ipv4.tfo_active_disable_stamp to be updated first. */ smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } /* Calculate timeout for tfo active disable * Return true if we are still in the active TFO disable period * Return false if timeout already expired and we should use active TFO */ bool tcp_fastopen_active_should_disable(struct sock *sk) { unsigned int tfo_bh_timeout = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout); unsigned long timeout; int tfo_da_times; int multiplier; if (!tfo_bh_timeout) return false; tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); if (!tfo_da_times) return false; /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ smp_rmb(); /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + multiplier * tfo_bh_timeout * HZ; if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO * condition and reset tfo_active_disable_times */ tcp_sk(sk)->syn_fastopen_ch = 1; return false; } /* Disable active TFO if FIN is the only packet in the ofo queue * and no data is received. * Also check if we can reset tfo_active_disable_times if data is * received successfully on a marked active TFO sockets opened on * a non-loopback interface */ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst; struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { skb = skb_rb_first(&tp->out_of_order_queue); if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; } } } else if (tp->syn_fastopen_ch && atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } } void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired) { u32 timeouts = inet_csk(sk)->icsk_retransmits; struct tcp_sock *tp = tcp_sk(sk); /* Broken middle-boxes may black-hole Fast Open connection during or * even after the handshake. Be extremely conservative and pause * Fast Open globally after hitting the third consecutive timeout or * exceeding the configured timeout limit. */ if ((tp->syn_fastopen || tp->syn_data || tp->syn_data_acked) && (timeouts == 2 || (timeouts < 2 && expired))) { tcp_fastopen_active_disable(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); } } |
| 5 5 5 1 7 1 5 4 2 2 8 1 1 1 12 11 1 7 7 7 66 59 7 7 2 5 22 22 22 29 7 22 12 12 89 77 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned long arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_user_ns(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { security_file_set_fowner(filp); f_modown(filp, pid, type, force); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; struct pid *pid = NULL; int who = arg, ret = 0; type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { f_modown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&filp->f_owner.lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; switch (cmd) { case F_GET_RW_HINT: hint = inode->i_write_hint; if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; inode_lock(inode); inode->i_write_hint = hint; inode_unlock(inode); return 0; default: return -EINVAL; } } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(arg, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(arg, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, arg & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, arg, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(arg)) { break; } err = 0; filp->f_owner.signum = arg; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, arg); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, arg); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, arg); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, arg); break; case F_GET_RW_HINT: case F_SET_RW_HINT: err = fcntl_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); struct flock64 flock; long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(f.file, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; long err = -EBADF; if (!f.file) return err; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out_put; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out_put: fdput(f); return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __read_mostly; static void fasync_free_rcu(struct rcu_head *head) { kmem_cache_free(fasync_cache, container_of(head, struct fasync_struct, fa_rcu)); } /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; call_rcu(&fa->fa_rcu, fasync_free_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 9082 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_INTERNAL_H #define __X86_KERNEL_FPU_INTERNAL_H extern struct fpstate init_fpstate; /* CPU feature check wrappers */ static __always_inline __pure bool use_xsave(void) { return cpu_feature_enabled(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return cpu_feature_enabled(X86_FEATURE_FXSR); } #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ (void)(x); 0; }) #endif /* Used in init.c */ extern void fpstate_init_user(struct fpstate *fpstate); extern void fpstate_reset(struct fpu *fpu); #endif |
| 336 613 306 619 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _IP6_FIB_H #define _IP6_FIB_H #include <linux/ipv6_route.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/notifier.h> #include <linux/android_kabi.h> #include <net/dst.h> #include <net/flow.h> #include <net/ip_fib.h> #include <net/netlink.h> #include <net/inetpeer.h> #include <net/fib_notifier.h> #include <linux/indirect_call_wrapper.h> #include <uapi/linux/bpf.h> #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 #else #define FIB6_TABLE_HASHSZ 1 #endif #define RT6_DEBUG 2 #if RT6_DEBUG >= 3 #define RT6_TRACE(x...) pr_debug(x) #else #define RT6_TRACE(x...) do { ; } while (0) #endif struct rt6_info; struct fib6_info; struct fib6_config { u32 fc_table; u32 fc_metric; int fc_dst_len; int fc_src_len; int fc_ifindex; u32 fc_flags; u32 fc_protocol; u16 fc_type; /* only 8 bits are used */ u16 fc_delete_all_nh : 1, fc_ignore_dev_down:1, __unused : 14; u32 fc_nh_id; struct in6_addr fc_dst; struct in6_addr fc_src; struct in6_addr fc_prefsrc; struct in6_addr fc_gateway; unsigned long fc_expires; struct nlattr *fc_mx; int fc_mx_len; int fc_mp_len; struct nlattr *fc_mp; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; bool fc_is_fdb; ANDROID_KABI_RESERVE(1); }; struct fib6_node { struct fib6_node __rcu *parent; struct fib6_node __rcu *left; struct fib6_node __rcu *right; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node __rcu *subtree; #endif struct fib6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; struct fib6_info __rcu *rr_ptr; struct rcu_head rcu; ANDROID_KABI_RESERVE(1); }; struct fib6_gc_args { int timeout; int more; }; #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL static inline bool fib6_routes_require_src(const struct net *net) { return false; } static inline void fib6_routes_require_src_inc(struct net *net) {} static inline void fib6_routes_require_src_dec(struct net *net) {} #else static inline bool fib6_routes_require_src(const struct net *net) { return net->ipv6.fib6_routes_require_src > 0; } static inline void fib6_routes_require_src_inc(struct net *net) { net->ipv6.fib6_routes_require_src++; } static inline void fib6_routes_require_src_dec(struct net *net) { net->ipv6.fib6_routes_require_src--; } #define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif /* * routing information * */ struct rt6key { struct in6_addr addr; int plen; }; struct fib6_table; struct rt6_exception_bucket { struct hlist_head chain; int depth; }; struct rt6_exception { struct hlist_node hlist; struct rt6_info *rt6i; unsigned long stamp; struct rcu_head rcu; }; #define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 #define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) #define FIB6_MAX_DEPTH 5 struct fib6_nh { struct fib_nh_common nh_common; #ifdef CONFIG_IPV6_ROUTER_PREF unsigned long last_probe; #endif struct rt6_info * __percpu *rt6i_pcpu; struct rt6_exception_bucket __rcu *rt6i_exception_bucket; }; struct fib6_info { struct fib6_table *fib6_table; struct fib6_info __rcu *fib6_next; struct fib6_node __rcu *fib6_node; /* Multipath routes: * siblings is a list of fib6_info that have the same metric/weight, * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ union { struct list_head fib6_siblings; struct list_head nh_list; }; unsigned int fib6_nsiblings; refcount_t fib6_ref; unsigned long expires; struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] struct rt6key fib6_dst; u32 fib6_flags; struct rt6key fib6_src; struct rt6key fib6_prefsrc; u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; u8 offload; u8 trap; u8 offload_failed; u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, fib6_destroying:1, unused:4; struct rcu_head rcu; struct nexthop *nh; ANDROID_KABI_RESERVE(1); struct fib6_nh fib6_nh[]; }; struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; struct list_head rt6i_uncached; struct uncached_list *rt6i_uncached_list; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; ANDROID_KABI_RESERVE(1); }; struct fib6_result { struct fib6_nh *nh; struct fib6_info *f6i; u32 fib6_flags; u8 fib6_type; struct rt6_info *rt6; }; #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ rt = rcu_dereference(rt->fib6_next)) #define for_each_fib6_walker_rt(w) \ for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) { return rt->fib6_src.plen > 0; } static inline void fib6_clean_expires(struct fib6_info *f6i) { f6i->fib6_flags &= ~RTF_EXPIRES; f6i->expires = 0; } static inline void fib6_set_expires(struct fib6_info *f6i, unsigned long expires) { f6i->expires = expires; f6i->fib6_flags |= RTF_EXPIRES; } static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) return time_after(jiffies, f6i->expires); return false; } /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely * Return false if not */ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, u32 *cookie) { struct fib6_node *fn; bool status = false; fn = rcu_dereference(f6i->fib6_node); if (fn) { *cookie = READ_ONCE(fn->fn_sernum); /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ smp_rmb(); status = true; } return status; } static inline u32 rt6_get_cookie(const struct rt6_info *rt) { struct fib6_info *from; u32 cookie = 0; if (rt->sernum) return rt->sernum; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) fib6_get_cookie_safe(from, &cookie); rcu_read_unlock(); return cookie; } static inline void ip6_rt_put(struct rt6_info *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rt6_info */ BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0); dst_release(&rt->dst); } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) { refcount_inc(&f6i->fib6_ref); } static inline bool fib6_info_hold_safe(struct fib6_info *f6i) { return refcount_inc_not_zero(&f6i->fib6_ref); } static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) call_rcu(&f6i->rcu, fib6_info_destroy_rcu); } enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif FWS_L, FWS_R, FWS_C, FWS_U }; struct fib6_walker { struct list_head lh; struct fib6_node *root, *node; struct fib6_info *leaf; enum fib6_walk_state state; unsigned int skip; unsigned int count; unsigned int skip_in_node; int (*func)(struct fib6_walker *); void *args; }; struct rt6_statistics { __u32 fib_nodes; /* all fib6 nodes */ __u32 fib_route_nodes; /* intermediate nodes */ __u32 fib_rt_entries; /* rt entries in fib table */ __u32 fib_rt_cache; /* cached rt entries in exception table */ __u32 fib_discarded_routes; /* total number of routes delete */ /* The following stat is not protected by any lock */ atomic_t fib_rt_alloc; /* total number of routes alloced */ }; #define RTN_TL_ROOT 0x0001 #define RTN_ROOT 0x0002 /* tree root node */ #define RTN_RTINFO 0x0004 /* node with valid routing info */ /* * priority levels (or metrics) * */ struct fib6_table { struct hlist_node tb6_hlist; u32 tb6_id; spinlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; #define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC #define RT6_TABLE_MAIN RT_TABLE_MAIN #define RT6_TABLE_DFLT RT6_TABLE_MAIN #define RT6_TABLE_INFO RT6_TABLE_MAIN #define RT6_TABLE_PREFIX RT6_TABLE_MAIN #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_MIN 1 #define FIB6_TABLE_MAX RT_TABLE_MAX #define RT6_TABLE_LOCAL RT_TABLE_LOCAL #else #define FIB6_TABLE_MIN RT_TABLE_MAIN #define FIB6_TABLE_MAX FIB6_TABLE_MIN #define RT6_TABLE_LOCAL RT6_TABLE_MAIN #endif typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, struct flowi6 *, const struct sk_buff *, int); struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; unsigned int nsiblings; }; /* * exported functions */ struct fib6_table *fib6_get_table(struct net *net, u32 id); struct fib6_table *fib6_new_table(struct net *net, u32 id); struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup); /* called with rcu lock held; can return error pointer * caller needs to select path */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags); /* called with rcu lock held; caller needs to select path */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict); void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict); struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr); struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match); void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); static inline void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) { const struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) *addr = from->fib6_prefsrc.addr; else *addr = in6addr_any; rcu_read_unlock(); } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack); int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack); int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt); void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); void fib6_run_gc(unsigned long expires, struct net *net, bool force); void fib6_gc_cleanup(void); int fib6_init(void); struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; loff_t skip; struct fib6_table *tbl; int sernum; }; extern const struct seq_operations ipv6_route_seq_ops; int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i); void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) { return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed); #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct fib6_info *, rt); }; #endif INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup, struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return INDIRECT_CALL_4(lookup, ip6_pol_route_output, ip6_pol_route_input, ip6_pol_route_lookup, __ip6_route_redirect, net, table, fl6, skb, flags); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static inline bool fib6_has_custom_rules(const struct net *net) { return net->ipv6.fib6_has_custom_rules; } int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv6.fib6_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; fl6->flowi6_proto = flkeys->basic.ip_proto; return true; } #else static inline bool fib6_has_custom_rules(const struct net *net) { return false; } static inline int fib6_rules_init(void) { return 0; } static inline void fib6_rules_cleanup(void) { return ; } static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib6_rules_seq_read(struct net *net) { return 0; } static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { return false; } #endif #endif |
| 1706 5023 6290 5024 5023 869 5022 153 6299 6299 153 2633 1571 1417 2633 4985 4985 4984 4986 1227 6288 1146 1146 1146 140 140 140 1347 337 200 11 11 11 11 5339 5340 5159 1622 589 285 766 285 869 3519 168 1681 3430 870 870 2469 2471 869 5341 5023 5024 5023 5019 5024 5024 5022 1077 1038 314 5019 1209 5023 5024 5024 5024 869 869 868 870 870 5022 47 46 47 47 16 33 41 16 9 34 9 26 26 26 33 33 33 1075 1077 1077 1077 1077 1077 4984 4983 5023 5024 5003 5024 1214 2484 4988 5022 5011 153 153 153 153 5021 5022 68 68 364 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, Intel Corporation. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/dsfield.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_skbedit.h> #include <net/tc_act/tc_skbedit.h> static struct tc_action_ops act_skbedit_ops; static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params, struct sk_buff *skb) { u16 queue_mapping = params->queue_mapping; if (params->flags & SKBEDIT_F_TXQ_SKBHASH) { u32 hash = skb_get_hash(skb); queue_mapping += hash % params->mapping_mod; } return netdev_cap_txqueue(skb->dev, queue_mapping); } static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_skbedit_params *params; int action; tcf_lastuse_update(&d->tcf_tm); bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); params = rcu_dereference_bh(d->params); action = READ_ONCE(d->tcf_action); if (params->flags & SKBEDIT_F_PRIORITY) skb->priority = params->priority; if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto err; skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2; break; case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto err; skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; break; } } if (params->flags & SKBEDIT_F_QUEUE_MAPPING && skb->dev->real_num_tx_queues > params->queue_mapping) { #ifdef CONFIG_NET_EGRESS netdev_xmit_skip_txqueue(true); #endif skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb)); } if (params->flags & SKBEDIT_F_MARK) { skb->mark &= ~params->mask; skb->mark |= params->mark & params->mask; } if (params->flags & SKBEDIT_F_PTYPE) skb->pkt_type = params->ptype; return action; err: qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats)); return TC_ACT_SHOT; } static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_t *tm = &d->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_PARMS] = { .len = sizeof(struct tc_skbedit) }, [TCA_SKBEDIT_PRIORITY] = { .len = sizeof(u32) }, [TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MASK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) }, [TCA_SKBEDIT_QUEUE_MAPPING_MAX] = { .len = sizeof(u16) }, }; static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id); bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_skbedit *parm; struct tcf_skbedit *d; u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL; u16 *queue_mapping = NULL, *ptype = NULL; u16 mapping_mod = 1; bool exists = false; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL); if (err < 0) return err; if (tb[TCA_SKBEDIT_PARMS] == NULL) return -EINVAL; if (tb[TCA_SKBEDIT_PRIORITY] != NULL) { flags |= SKBEDIT_F_PRIORITY; priority = nla_data(tb[TCA_SKBEDIT_PRIORITY]); } if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) { flags |= SKBEDIT_F_QUEUE_MAPPING; queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]); } if (tb[TCA_SKBEDIT_PTYPE] != NULL) { ptype = nla_data(tb[TCA_SKBEDIT_PTYPE]); if (!skb_pkt_type_ok(*ptype)) return -EINVAL; flags |= SKBEDIT_F_PTYPE; } if (tb[TCA_SKBEDIT_MARK] != NULL) { flags |= SKBEDIT_F_MARK; mark = nla_data(tb[TCA_SKBEDIT_MARK]); } if (tb[TCA_SKBEDIT_MASK] != NULL) { flags |= SKBEDIT_F_MASK; mask = nla_data(tb[TCA_SKBEDIT_MASK]); } if (tb[TCA_SKBEDIT_FLAGS] != NULL) { u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]); if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) { u16 *queue_mapping_max; if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] || !tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) { NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping."); return -EINVAL; } queue_mapping_max = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]); if (*queue_mapping_max < *queue_mapping) { NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min."); return -EINVAL; } mapping_mod = *queue_mapping_max - *queue_mapping + 1; flags |= SKBEDIT_F_TXQ_SKBHASH; } if (*pure_flags & SKBEDIT_F_INHERITDSFIELD) flags |= SKBEDIT_F_INHERITDSFIELD; } parm = nla_data(tb[TCA_SKBEDIT_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; if (!flags) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_skbedit_ops, bind, true, act_flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } d = to_skbedit(*a); ret = ACT_P_CREATED; } else { d = to_skbedit(*a); if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { err = -ENOMEM; goto put_chain; } params_new->flags = flags; if (flags & SKBEDIT_F_PRIORITY) params_new->priority = *priority; if (flags & SKBEDIT_F_QUEUE_MAPPING) { params_new->queue_mapping = *queue_mapping; params_new->mapping_mod = mapping_mod; } if (flags & SKBEDIT_F_MARK) params_new->mark = *mark; if (flags & SKBEDIT_F_PTYPE) params_new->ptype = *ptype; /* default behaviour is to use all the bits */ params_new->mask = 0xffffffff; if (flags & SKBEDIT_F_MASK) params_new->mask = *mask; spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(d->params, params_new, lockdep_is_held(&d->tcf_lock)); spin_unlock_bh(&d->tcf_lock); if (params_new) kfree_rcu(params_new, rcu); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_skbedit *d = to_skbedit(a); struct tcf_skbedit_params *params; struct tc_skbedit opt = { .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; u64 pure_flags = 0; struct tcf_t t; spin_lock_bh(&d->tcf_lock); params = rcu_dereference_protected(d->params, lockdep_is_held(&d->tcf_lock)); opt.action = d->tcf_action; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_PRIORITY) && nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) && nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_MARK) && nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_PTYPE) && nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_MASK) && nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask)) goto nla_put_failure; if (params->flags & SKBEDIT_F_INHERITDSFIELD) pure_flags |= SKBEDIT_F_INHERITDSFIELD; if (params->flags & SKBEDIT_F_TXQ_SKBHASH) { if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX, params->queue_mapping + params->mapping_mod - 1)) goto nla_put_failure; pure_flags |= SKBEDIT_F_TXQ_SKBHASH; } if (pure_flags != 0 && nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags)) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; spin_unlock_bh(&d->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_skbedit_cleanup(struct tc_action *a) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_skbedit_params *params; params = rcu_dereference_protected(d->params, 1); if (params) kfree_rcu(params, rcu); } static size_t tcf_skbedit_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_skbedit)) + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */ + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */ } static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; if (is_tcf_skbedit_mark(act)) { entry->id = FLOW_ACTION_MARK; entry->mark = tcf_skbedit_mark(act); } else if (is_tcf_skbedit_ptype(act)) { entry->id = FLOW_ACTION_PTYPE; entry->ptype = tcf_skbedit_ptype(act); } else if (is_tcf_skbedit_priority(act)) { entry->id = FLOW_ACTION_PRIORITY; entry->priority = tcf_skbedit_priority(act); } else if (is_tcf_skbedit_queue_mapping(act)) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used"); return -EOPNOTSUPP; } else if (is_tcf_skbedit_inheritdsfield(act)) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used"); return -EOPNOTSUPP; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported skbedit option offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; if (is_tcf_skbedit_mark(act)) fl_action->id = FLOW_ACTION_MARK; else if (is_tcf_skbedit_ptype(act)) fl_action->id = FLOW_ACTION_PTYPE; else if (is_tcf_skbedit_priority(act)) fl_action->id = FLOW_ACTION_PRIORITY; else return -EOPNOTSUPP; } return 0; } static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .id = TCA_ID_SKBEDIT, .owner = THIS_MODULE, .act = tcf_skbedit_act, .stats_update = tcf_skbedit_stats_update, .dump = tcf_skbedit_dump, .init = tcf_skbedit_init, .cleanup = tcf_skbedit_cleanup, .get_fill_size = tcf_skbedit_get_fill_size, .offload_act_setup = tcf_skbedit_offload_act_setup, .size = sizeof(struct tcf_skbedit), }; static __net_init int skbedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id); return tc_action_net_init(net, tn, &act_skbedit_ops); } static void __net_exit skbedit_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_skbedit_ops.net_id); } static struct pernet_operations skbedit_net_ops = { .init = skbedit_init_net, .exit_batch = skbedit_exit_net, .id = &act_skbedit_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>"); MODULE_DESCRIPTION("SKB Editing"); MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { return tcf_register_action(&act_skbedit_ops, &skbedit_net_ops); } static void __exit skbedit_cleanup_module(void) { tcf_unregister_action(&act_skbedit_ops, &skbedit_net_ops); } module_init(skbedit_init_module); module_exit(skbedit_cleanup_module); |
| 630 630 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 | // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */ #include <linux/jump_label.h> #include <linux/uaccess.h> #include <linux/export.h> #include <linux/string.h> #include <linux/types.h> #include <asm/mce.h> #ifdef CONFIG_X86_MCE static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key); void enable_copy_mc_fragile(void) { static_branch_inc(©_mc_fragile_key); } #define copy_mc_fragile_enabled (static_branch_unlikely(©_mc_fragile_key)) /* * Similar to copy_user_handle_tail, probe for the write fault point, or * source exception point. */ __visible notrace unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len) { for (; len; --len, to++, from++) if (copy_mc_fragile(to, from, 1)) break; return len; } #else /* * No point in doing careful copying, or consulting a static key when * there is no #MC handler in the CONFIG_X86_MCE=n case. */ void enable_copy_mc_fragile(void) { } #define copy_mc_fragile_enabled (0) #endif unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned len); /** * copy_mc_to_kernel - memory copy that handles source exceptions * * @dst: destination address * @src: source address * @len: number of bytes to copy * * Call into the 'fragile' version on systems that benefit from avoiding * corner case poison consumption scenarios, For example, accessing * poison across 2 cachelines with a single instruction. Almost all * other uses case can use copy_mc_enhanced_fast_string() for a fast * recoverable copy, or fallback to plain memcpy. * * Return 0 for success, or number of bytes not copied if there was an * exception. */ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len) { if (copy_mc_fragile_enabled) return copy_mc_fragile(dst, src, len); if (static_cpu_has(X86_FEATURE_ERMS)) return copy_mc_enhanced_fast_string(dst, src, len); memcpy(dst, src, len); return 0; } EXPORT_SYMBOL_GPL(copy_mc_to_kernel); unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len) { unsigned long ret; if (copy_mc_fragile_enabled) { __uaccess_begin(); ret = copy_mc_fragile((__force void *)dst, src, len); __uaccess_end(); return ret; } if (static_cpu_has(X86_FEATURE_ERMS)) { __uaccess_begin(); ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len); __uaccess_end(); return ret; } return copy_user_generic((__force void *)dst, src, len); } |
| 9 9 9 3 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XFRM_HASH_H #define _XFRM_HASH_H #include <linux/xfrm.h> #include <linux/socket.h> #include <linux/jhash.h> static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr) { return ntohl(addr->a4); } static inline unsigned int __xfrm6_addr_hash(const xfrm_address_t *addr) { return jhash2((__force u32 *)addr->a6, 4, 0); } static inline unsigned int __xfrm4_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4; return ntohl((__force __be32)sum); } static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { return __xfrm6_addr_hash(daddr) ^ __xfrm6_addr_hash(saddr); } static inline u32 __bits2mask32(__u8 bits) { u32 mask32 = 0xffffffff; if (bits == 0) mask32 = 0; else if (bits < 32) mask32 <<= (32 - bits); return mask32; } static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return jhash_2words(ntohl(daddr->a4) & __bits2mask32(dbits), ntohl(saddr->a4) & __bits2mask32(sbits), 0); } static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr, __u8 prefixlen) { unsigned int pdw; unsigned int pbi; u32 initval = 0; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); initval = (__force u32)(addr->a6[pdw] & mask); } return jhash2((__force u32 *)addr->a6, pdw, initval); } static inline unsigned int __xfrm6_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return __xfrm6_pref_hash(daddr, dbits) ^ __xfrm6_pref_hash(saddr, sbits); } static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family, unsigned int hmask) { unsigned int h = family ^ reqid; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_src_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask) { unsigned int h = family; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, unsigned int hmask) { unsigned int h = (__force u32)spi ^ proto; switch (family) { case AF_INET: h ^= __xfrm4_addr_hash(daddr); break; case AF_INET6: h ^= __xfrm6_addr_hash(daddr); break; } return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __xfrm_seq_hash(u32 seq, unsigned int hmask) { unsigned int h = seq; return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __idx_hash(u32 index, unsigned int hmask) { return (index ^ (index >> 8)) & hmask; } static inline unsigned int __sel_hash(const struct xfrm_selector *sel, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { const xfrm_address_t *daddr = &sel->daddr; const xfrm_address_t *saddr = &sel->saddr; unsigned int h = 0; switch (family) { case AF_INET: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } static inline unsigned int __addr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { unsigned int h = 0; switch (family) { case AF_INET: h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } struct hlist_head *xfrm_hash_alloc(unsigned int sz); void xfrm_hash_free(struct hlist_head *n, unsigned int sz); #endif /* _XFRM_HASH_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NETFILTER_NETDEV_H_ #define _NETFILTER_NETDEV_H_ #include <linux/netfilter.h> #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) return false; #endif return rcu_access_pointer(skb->dev->nf_hooks_ingress); } /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; /* Must recheck the ingress hook head, in the event it became NULL * after the check in nf_hook_ingress_active evaluated to true. */ if (unlikely(!e)) return 0; nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; return ret; } #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) { return 0; } static inline int nf_hook_ingress(struct sk_buff *skb) { return 0; } #endif /* CONFIG_NETFILTER_INGRESS */ #ifdef CONFIG_NETFILTER_EGRESS static inline bool nf_hook_egress_active(void) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) return false; #endif return true; } /** * nf_hook_egress - classify packets before transmission * @skb: packet to be classified * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * * Returns @skb on success or %NULL if the packet was consumed or filtered. * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. * On egress, the order is reversed for symmetry. Conceptually, tc and * netfilter can be thought of as layers, with netfilter layered above tc: * When tc redirects a packet to another interface, netfilter is not applied * because the packet is on the tc layer. * * The nf_skip_egress flag controls whether netfilter is applied on egress. * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the * packet passes through tc and netfilter. Because __dev_queue_xmit() may be * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { struct nf_hook_entries *e; struct nf_hook_state state; int ret; #ifdef CONFIG_NETFILTER_SKIP_EGRESS if (skb->nf_skip_egress) return skb; #endif e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); /* nf assumes rcu_read_lock, not just read_lock_bh */ rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); rcu_read_unlock(); if (ret == 1) { return skb; } else if (ret < 0) { *rc = NET_XMIT_DROP; return NULL; } else { /* ret == 0 */ *rc = NET_XMIT_SUCCESS; return NULL; } } #else /* CONFIG_NETFILTER_EGRESS */ static inline bool nf_hook_egress_active(void) { return false; } static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { return skb; } #endif /* CONFIG_NETFILTER_EGRESS */ static inline void nf_skip_egress(struct sk_buff *skb, bool skip) { #ifdef CONFIG_NETFILTER_SKIP_EGRESS skb->nf_skip_egress = skip; #endif } static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif #ifdef CONFIG_NETFILTER_EGRESS RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); #endif } #endif /* _NETFILTER_NETDEV_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #ifndef _WG_PEER_H #define _WG_PEER_H #include "device.h" #include "noise.h" #include "cookie.h" #include <linux/types.h> #include <linux/netfilter.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <net/dst_cache.h> struct wg_device; struct endpoint { union { struct sockaddr addr; struct sockaddr_in addr4; struct sockaddr_in6 addr6; }; union { struct { struct in_addr src4; /* Essentially the same as addr6->scope_id */ int src_if4; }; struct in6_addr src6; }; }; struct wg_peer { struct wg_device *device; struct prev_queue tx_queue, rx_queue; struct sk_buff_head staged_packet_queue; int serial_work_cpu; bool is_dead; struct noise_keypairs keypairs; struct endpoint endpoint; struct dst_cache endpoint_cache; rwlock_t endpoint_lock; struct noise_handshake handshake; atomic64_t last_sent_handshake; struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work; struct cookie latest_cookie; struct hlist_node pubkey_hash; u64 rx_bytes, tx_bytes; struct timer_list timer_retransmit_handshake, timer_send_keepalive; struct timer_list timer_new_handshake, timer_zero_key_material; struct timer_list timer_persistent_keepalive; unsigned int timer_handshake_attempts; u16 persistent_keepalive_interval; bool timer_need_another_keepalive; bool sent_lastminute_handshake; struct timespec64 walltime_last_handshake; struct kref refcount; struct rcu_head rcu; struct list_head peer_list; struct list_head allowedips_list; struct napi_struct napi; u64 internal_id; }; struct wg_peer *wg_peer_create(struct wg_device *wg, const u8 public_key[NOISE_PUBLIC_KEY_LEN], const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]); struct wg_peer *__must_check wg_peer_get_maybe_zero(struct wg_peer *peer); static inline struct wg_peer *wg_peer_get(struct wg_peer *peer) { kref_get(&peer->refcount); return peer; } void wg_peer_put(struct wg_peer *peer); void wg_peer_remove(struct wg_peer *peer); void wg_peer_remove_all(struct wg_device *wg); int wg_peer_init(void); void wg_peer_uninit(void); #endif /* _WG_PEER_H */ |
| 804 804 803 244 244 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/swap_state.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie * * Rewritten to use page cache, (C) 1998 Stephen Tweedie */ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/init.h> #include <linux/pagemap.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/migrate.h> #include <linux/vmalloc.h> #include <linux/swap_slots.h> #include <linux/huge_mm.h> #include <linux/shmem_fs.h> #include "internal.h" #include "swap.h" /* * swapper_space is a fiction, retained to simplify the path through * vmscan's shrink_page_list. */ static const struct address_space_operations swap_aops = { .writepage = swap_writepage, .dirty_folio = noop_dirty_folio, #ifdef CONFIG_MIGRATION .migrate_folio = migrate_folio, #endif }; struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly; static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly; static bool enable_vma_readahead __read_mostly = true; #define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) #define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) #define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK #define SWAP_RA_WIN_MASK (~PAGE_MASK & ~SWAP_RA_HITS_MASK) #define SWAP_RA_HITS(v) ((v) & SWAP_RA_HITS_MASK) #define SWAP_RA_WIN(v) (((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT) #define SWAP_RA_ADDR(v) ((v) & PAGE_MASK) #define SWAP_RA_VAL(addr, win, hits) \ (((addr) & PAGE_MASK) | \ (((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) | \ ((hits) & SWAP_RA_HITS_MASK)) /* Initial readahead hits is 4 to start up with a small window */ #define GET_SWAP_RA_VAL(vma) \ (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) static atomic_t swapin_readahead_hits = ATOMIC_INIT(4); void show_swap_cache_info(void) { printk("%lu pages in swap cache\n", total_swapcache_pages()); printk("Free swap = %ldkB\n", get_nr_swap_pages() << (PAGE_SHIFT - 10)); printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); } void *get_shadow_from_swap_cache(swp_entry_t entry) { struct address_space *address_space = swap_address_space(entry); pgoff_t idx = swp_offset(entry); struct page *page; page = xa_load(&address_space->i_pages, idx); if (xa_is_value(page)) return page; return NULL; } EXPORT_SYMBOL_GPL(get_shadow_from_swap_cache); /* * add_to_swap_cache resembles filemap_add_folio on swapper_space, * but sets SwapCache flag and private instead of mapping and index. */ int add_to_swap_cache(struct folio *folio, swp_entry_t entry, gfp_t gfp, void **shadowp) { struct address_space *address_space = swap_address_space(entry); pgoff_t idx = swp_offset(entry); XA_STATE_ORDER(xas, &address_space->i_pages, idx, folio_order(folio)); unsigned long i, nr = folio_nr_pages(folio); void *old; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio); folio_ref_add(folio, nr); folio_set_swapcache(folio); do { xas_lock_irq(&xas); xas_create_range(&xas); if (xas_error(&xas)) goto unlock; for (i = 0; i < nr; i++) { VM_BUG_ON_FOLIO(xas.xa_index != idx + i, folio); old = xas_load(&xas); if (xa_is_value(old)) { if (shadowp) *shadowp = old; } set_page_private(folio_page(folio, i), entry.val + i); xas_store(&xas, folio); xas_next(&xas); } address_space->nrpages += nr; __node_stat_mod_folio(folio, NR_FILE_PAGES, nr); __lruvec_stat_mod_folio(folio, NR_SWAPCACHE, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (!xas_error(&xas)) return 0; folio_clear_swapcache(folio); folio_ref_sub(folio, nr); return xas_error(&xas); } /* * This must be called only on folios that have * been verified to be in the swap cache. */ void __delete_from_swap_cache(struct folio *folio, swp_entry_t entry, void *shadow) { struct address_space *address_space = swap_address_space(entry); int i; long nr = folio_nr_pages(folio); pgoff_t idx = swp_offset(entry); XA_STATE(xas, &address_space->i_pages, idx); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio); VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); for (i = 0; i < nr; i++) { void *entry = xas_store(&xas, shadow); VM_BUG_ON_PAGE(entry != folio, entry); set_page_private(folio_page(folio, i), 0); xas_next(&xas); } folio_clear_swapcache(folio); address_space->nrpages -= nr; __node_stat_mod_folio(folio, NR_FILE_PAGES, -nr); __lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr); } /** * add_to_swap - allocate swap space for a folio * @folio: folio we want to move to swap * * Allocate swap space for the folio and add the folio to the * swap cache. * * Context: Caller needs to hold the folio lock. * Return: Whether the folio was added to the swap cache. */ bool add_to_swap(struct folio *folio) { swp_entry_t entry; int err; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); entry = folio_alloc_swap(folio); if (!entry.val) return false; /* * XArray node allocations from PF_MEMALLOC contexts could * completely exhaust the page allocator. __GFP_NOMEMALLOC * stops emergency reserves from being allocated. * * TODO: this could cause a theoretical memory reclaim * deadlock in the swap out path. */ /* * Add it to the swap cache. */ err = add_to_swap_cache(folio, entry, __GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN, NULL); if (err) /* * add_to_swap_cache() doesn't return -EEXIST, so we can safely * clear SWAP_HAS_CACHE flag. */ goto fail; /* * Normally the folio will be dirtied in unmap because its * pte should be dirty. A special case is MADV_FREE page. The * page's pte could have dirty bit cleared but the folio's * SwapBacked flag is still set because clearing the dirty bit * and SwapBacked flag has no lock protected. For such folio, * unmap will not set dirty bit for it, so folio reclaim will * not write the folio out. This can cause data corruption when * the folio is swapped in later. Always setting the dirty flag * for the folio solves the problem. */ folio_mark_dirty(folio); return true; fail: put_swap_folio(folio, entry); return false; } /* * This must be called only on folios that have * been verified to be in the swap cache and locked. * It will never put the folio into the free list, * the caller has a reference on the folio. */ void delete_from_swap_cache(struct folio *folio) { swp_entry_t entry = folio_swap_entry(folio); struct address_space *address_space = swap_address_space(entry); xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(folio, entry, NULL); xa_unlock_irq(&address_space->i_pages); put_swap_folio(folio, entry); folio_ref_sub(folio, folio_nr_pages(folio)); } void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end) { unsigned long curr = begin; void *old; for (;;) { swp_entry_t entry = swp_entry(type, curr); struct address_space *address_space = swap_address_space(entry); XA_STATE(xas, &address_space->i_pages, curr); xa_lock_irq(&address_space->i_pages); xas_for_each(&xas, old, end) { if (!xa_is_value(old)) continue; xas_store(&xas, NULL); } xa_unlock_irq(&address_space->i_pages); /* search the next swapcache until we meet end */ curr >>= SWAP_ADDRESS_SPACE_SHIFT; curr++; curr <<= SWAP_ADDRESS_SPACE_SHIFT; if (curr > end) break; } } /* * If we are the only user, then try to free up the swap cache. * * Its ok to check the swapcache flag without the folio lock * here because we are going to recheck again inside * folio_free_swap() _with_ the lock. * - Marcelo */ void free_swap_cache(struct page *page) { struct folio *folio = page_folio(page); if (folio_test_swapcache(folio) && !folio_mapped(folio) && folio_trylock(folio)) { folio_free_swap(folio); folio_unlock(folio); } } /* * Perform a free_page(), also freeing any swap cache associated with * this page if it is the last user of the page. */ void free_page_and_swap_cache(struct page *page) { free_swap_cache(page); if (!is_huge_zero_page(page)) put_page(page); } /* * Passed an array of pages, drop them all from swapcache and then release * them. They are removed from the LRU and freed if this is their last use. */ void free_pages_and_swap_cache(struct page **pages, int nr) { struct page **pagep = pages; int i; lru_add_drain(); for (i = 0; i < nr; i++) free_swap_cache(pagep[i]); release_pages(pagep, nr); } static inline bool swap_use_vma_readahead(void) { return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap); } /* * Lookup a swap entry in the swap cache. A found folio will be returned * unlocked and with its refcount incremented - we rely on the kernel * lock getting page table operations atomic even if we drop the folio * lock before returning. */ struct folio *swap_cache_get_folio(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio; struct swap_info_struct *si; si = get_swap_device(entry); if (!si) return NULL; folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry)); put_swap_device(si); if (folio) { bool vma_ra = swap_use_vma_readahead(); bool readahead; /* * At the moment, we don't support PG_readahead for anon THP * so let's bail out rather than confusing the readahead stat. */ if (unlikely(folio_test_large(folio))) return folio; readahead = folio_test_clear_readahead(folio); if (vma && vma_ra) { unsigned long ra_val; int win, hits; ra_val = GET_SWAP_RA_VAL(vma); win = SWAP_RA_WIN(ra_val); hits = SWAP_RA_HITS(ra_val); if (readahead) hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX); atomic_long_set(&vma->swap_readahead_info, SWAP_RA_VAL(addr, win, hits)); } if (readahead) { count_vm_event(SWAP_RA_HIT); if (!vma || !vma_ra) atomic_inc(&swapin_readahead_hits); } } return folio; } /** * find_get_incore_page - Find and get a page from the page or swap caches. * @mapping: The address_space to search. * @index: The page cache index. * * This differs from find_get_page() in that it will also look for the * page in the swap cache. * * Return: The found page or %NULL. */ struct page *find_get_incore_page(struct address_space *mapping, pgoff_t index) { swp_entry_t swp; struct swap_info_struct *si; struct page *page = pagecache_get_page(mapping, index, FGP_ENTRY | FGP_HEAD, 0); if (!page) return page; if (!xa_is_value(page)) return find_subpage(page, index); if (!shmem_mapping(mapping)) return NULL; swp = radix_to_swp_entry(page); /* There might be swapin error entries in shmem mapping. */ if (non_swap_entry(swp)) return NULL; /* Prevent swapoff from happening to us */ si = get_swap_device(swp); if (!si) return NULL; page = find_get_page(swap_address_space(swp), swp_offset(swp)); put_swap_device(si); return page; } struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated) { struct swap_info_struct *si; struct folio *folio; void *shadow = NULL; *new_page_allocated = false; for (;;) { int err; /* * First check the swap cache. Since this is normally * called after swap_cache_get_folio() failed, re-calling * that would confuse statistics. */ si = get_swap_device(entry); if (!si) return NULL; folio = filemap_get_folio(swap_address_space(entry), swp_offset(entry)); put_swap_device(si); if (folio) return folio_file_page(folio, swp_offset(entry)); /* * Just skip read ahead for unused swap slot. * During swap_off when swap_slot_cache is disabled, * we have to handle the race between putting * swap entry in swap cache and marking swap slot * as SWAP_HAS_CACHE. That's done in later part of code or * else swap_off will be aborted if we return NULL. */ if (!__swp_swapcount(entry) && swap_slot_cache_enabled) return NULL; /* * Get a new page to read into from swap. Allocate it now, * before marking swap_map SWAP_HAS_CACHE, when -EEXIST will * cause any racers to loop around until we add it to cache. */ folio = vma_alloc_folio(gfp_mask, 0, vma, addr, false); if (!folio) return NULL; /* * Swap entry may have been freed since our caller observed it. */ err = swapcache_prepare(entry); if (!err) break; folio_put(folio); if (err != -EEXIST) return NULL; /* * We might race against __delete_from_swap_cache(), and * stumble across a swap_map entry whose SWAP_HAS_CACHE * has not yet been cleared. Or race against another * __read_swap_cache_async(), which has set SWAP_HAS_CACHE * in swap_map, but not yet added its page to swap cache. */ schedule_timeout_uninterruptible(1); } /* * The swap entry is ours to swap in. Prepare the new page. */ __folio_set_locked(folio); __folio_set_swapbacked(folio); if (mem_cgroup_swapin_charge_folio(folio, NULL, gfp_mask, entry)) goto fail_unlock; /* May fail (-ENOMEM) if XArray node allocation failed. */ if (add_to_swap_cache(folio, entry, gfp_mask & GFP_RECLAIM_MASK, &shadow)) goto fail_unlock; mem_cgroup_swapin_uncharge_swap(entry); if (shadow) workingset_refault(folio, shadow); /* Caller will initiate read into locked folio */ folio_add_lru(folio); *new_page_allocated = true; return &folio->page; fail_unlock: put_swap_folio(folio, entry); folio_unlock(folio); folio_put(folio); return NULL; } /* * Locate a page of swap in physical memory, reserving swap cache space * and reading the disk if it is not already cached. * A failure return means that either the page allocation failed or that * the swap entry is no longer in use. */ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr, struct swap_iocb **plug) { bool page_was_allocated; struct page *retpage = __read_swap_cache_async(entry, gfp_mask, vma, addr, &page_was_allocated); if (page_was_allocated) swap_readpage(retpage, false, plug); return retpage; } static unsigned int __swapin_nr_pages(unsigned long prev_offset, unsigned long offset, int hits, int max_pages, int prev_win) { unsigned int pages, last_ra; /* * This heuristic has been found to work well on both sequential and * random loads, swapping to hard disk or to SSD: please don't ask * what the "+ 2" means, it just happens to work well, that's all. */ pages = hits + 2; if (pages == 2) { /* * We can have no readahead hits to judge by: but must not get * stuck here forever, so check for an adjacent offset instead * (and don't even bother to check whether swap type is same). */ if (offset != prev_offset + 1 && offset != prev_offset - 1) pages = 1; } else { unsigned int roundup = 4; while (roundup < pages) roundup <<= 1; pages = roundup; } if (pages > max_pages) pages = max_pages; /* Don't shrink readahead too fast */ last_ra = prev_win / 2; if (pages < last_ra) pages = last_ra; return pages; } static unsigned long swapin_nr_pages(unsigned long offset) { static unsigned long prev_offset; unsigned int hits, pages, max_pages; static atomic_t last_readahead_pages; max_pages = 1 << READ_ONCE(page_cluster); if (max_pages <= 1) return 1; hits = atomic_xchg(&swapin_readahead_hits, 0); pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits, max_pages, atomic_read(&last_readahead_pages)); if (!hits) WRITE_ONCE(prev_offset, offset); atomic_set(&last_readahead_pages, pages); return pages; } /** * swap_cluster_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen * because it doesn't cost us any seek time. We also make sure to queue * the 'original' request together with the readahead ones... * * This has been extended to use the NUMA policies from the mm triggering * the readahead. * * Caller must hold read mmap_lock if vmf->vma is not NULL. */ struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { struct page *page; unsigned long entry_offset = swp_offset(entry); unsigned long offset = entry_offset; unsigned long start_offset, end_offset; unsigned long mask; struct swap_info_struct *si = swp_swap_info(entry); struct blk_plug plug; struct swap_iocb *splug = NULL; bool page_allocated; struct vm_area_struct *vma = vmf->vma; unsigned long addr = vmf->address; mask = swapin_nr_pages(offset) - 1; if (!mask) goto skip; /* Read a page_cluster sized and aligned cluster around offset. */ start_offset = offset & ~mask; end_offset = offset | mask; if (!start_offset) /* First page is swap header. */ start_offset++; if (end_offset >= si->max) end_offset = si->max - 1; blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = __read_swap_cache_async( swp_entry(swp_type(entry), offset), gfp_mask, vma, addr, &page_allocated); if (!page) continue; if (page_allocated) { swap_readpage(page, false, &splug); if (offset != entry_offset) { SetPageReadahead(page); count_vm_event(SWAP_RA); } } put_page(page); } blk_finish_plug(&plug); swap_read_unplug(splug); lru_add_drain(); /* Push any new pages onto the LRU now */ skip: /* The page was likely read above, so no need for plugging here */ return read_swap_cache_async(entry, gfp_mask, vma, addr, NULL); } int init_swap_address_space(unsigned int type, unsigned long nr_pages) { struct address_space *spaces, *space; unsigned int i, nr; nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); spaces = kvcalloc(nr, sizeof(struct address_space), GFP_KERNEL); if (!spaces) return -ENOMEM; for (i = 0; i < nr; i++) { space = spaces + i; xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ); atomic_set(&space->i_mmap_writable, 0); space->a_ops = &swap_aops; /* swap cache doesn't use writeback related tags */ mapping_set_no_writeback_tags(space); } nr_swapper_spaces[type] = nr; swapper_spaces[type] = spaces; return 0; } void exit_swap_address_space(unsigned int type) { int i; struct address_space *spaces = swapper_spaces[type]; for (i = 0; i < nr_swapper_spaces[type]; i++) VM_WARN_ON_ONCE(!mapping_empty(&spaces[i])); kvfree(spaces); nr_swapper_spaces[type] = 0; swapper_spaces[type] = NULL; } static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, unsigned long faddr, unsigned long lpfn, unsigned long rpfn, unsigned long *start, unsigned long *end) { *start = max3(lpfn, PFN_DOWN(vma->vm_start), PFN_DOWN(faddr & PMD_MASK)); *end = min3(rpfn, PFN_DOWN(vma->vm_end), PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE)); } static void swap_ra_info(struct vm_fault *vmf, struct vma_swap_readahead *ra_info) { struct vm_area_struct *vma = vmf->vma; unsigned long ra_val; unsigned long faddr, pfn, fpfn; unsigned long start, end; pte_t *pte, *orig_pte; unsigned int max_win, hits, prev_win, win, left; #ifndef CONFIG_64BIT pte_t *tpte; #endif max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster), SWAP_RA_ORDER_CEILING); if (max_win == 1) { ra_info->win = 1; return; } faddr = vmf->address; orig_pte = pte = pte_offset_map(vmf->pmd, faddr); fpfn = PFN_DOWN(faddr); ra_val = GET_SWAP_RA_VAL(vma); pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val)); prev_win = SWAP_RA_WIN(ra_val); hits = SWAP_RA_HITS(ra_val); ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits, max_win, prev_win); atomic_long_set(&vma->swap_readahead_info, SWAP_RA_VAL(faddr, win, 0)); if (win == 1) { pte_unmap(orig_pte); return; } /* Copy the PTEs because the page table may be unmapped */ if (fpfn == pfn + 1) swap_ra_clamp_pfn(vma, faddr, fpfn, fpfn + win, &start, &end); else if (pfn == fpfn + 1) swap_ra_clamp_pfn(vma, faddr, fpfn - win + 1, fpfn + 1, &start, &end); else { left = (win - 1) / 2; swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left, &start, &end); } ra_info->nr_pte = end - start; ra_info->offset = fpfn - start; pte -= ra_info->offset; #ifdef CONFIG_64BIT ra_info->ptes = pte; #else tpte = ra_info->ptes; for (pfn = start; pfn != end; pfn++) *tpte++ = *pte++; #endif pte_unmap(orig_pte); } /** * swap_vma_readahead - swap in pages in hope we need them soon * @fentry: swap entry of this memory * @gfp_mask: memory allocation flags * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read in a few pages whose * virtual addresses are around the fault address in the same vma. * * Caller must hold read mmap_lock if vmf->vma is not NULL. * */ static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask, struct vm_fault *vmf) { struct blk_plug plug; struct swap_iocb *splug = NULL; struct vm_area_struct *vma = vmf->vma; struct page *page; pte_t *pte, pentry; swp_entry_t entry; unsigned int i; bool page_allocated; struct vma_swap_readahead ra_info = { .win = 1, }; swap_ra_info(vmf, &ra_info); if (ra_info.win == 1) goto skip; blk_start_plug(&plug); for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte; i++, pte++) { pentry = *pte; if (!is_swap_pte(pentry)) continue; entry = pte_to_swp_entry(pentry); if (unlikely(non_swap_entry(entry))) continue; page = __read_swap_cache_async(entry, gfp_mask, vma, vmf->address, &page_allocated); if (!page) continue; if (page_allocated) { swap_readpage(page, false, &splug); if (i != ra_info.offset) { SetPageReadahead(page); count_vm_event(SWAP_RA); } } put_page(page); } blk_finish_plug(&plug); swap_read_unplug(splug); lru_add_drain(); skip: /* The page was likely read above, so no need for plugging here */ return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, NULL); } /** * swapin_readahead - swap in pages in hope we need them soon * @entry: swap entry of this memory * @gfp_mask: memory allocation flags * @vmf: fault information * * Returns the struct page for entry and addr, after queueing swapin. * * It's a main entry function for swap readahead. By the configuration, * it will read ahead blocks by cluster-based(ie, physical disk based) * or vma-based(ie, virtual address based on faulty address) readahead. */ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_fault *vmf) { return swap_use_vma_readahead() ? swap_vma_readahead(entry, gfp_mask, vmf) : swap_cluster_readahead(entry, gfp_mask, vmf); } #ifdef CONFIG_SYSFS static ssize_t vma_ra_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", enable_vma_readahead ? "true" : "false"); } static ssize_t vma_ra_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { ssize_t ret; ret = kstrtobool(buf, &enable_vma_readahead); if (ret) return ret; return count; } static struct kobj_attribute vma_ra_enabled_attr = __ATTR_RW(vma_ra_enabled); static struct attribute *swap_attrs[] = { &vma_ra_enabled_attr.attr, NULL, }; static const struct attribute_group swap_attr_group = { .attrs = swap_attrs, }; static int __init swap_init_sysfs(void) { int err; struct kobject *swap_kobj; swap_kobj = kobject_create_and_add("swap", mm_kobj); if (!swap_kobj) { pr_err("failed to create swap kobject\n"); return -ENOMEM; } err = sysfs_create_group(swap_kobj, &swap_attr_group); if (err) { pr_err("failed to register swap group\n"); goto delete_obj; } return 0; delete_obj: kobject_put(swap_kobj); return err; } subsys_initcall(swap_init_sysfs); #endif |
| 2 89 6686 6686 6686 1019 337 3094 3095 6 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H #include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> /* * Macro to mark a page protection value as UC- */ #define pgprot_noncached(prot) \ ((boot_cpu_data.x86 > 3) \ ? (__pgprot(pgprot_val(prot) | \ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) #ifndef __ASSEMBLY__ #include <linux/spinlock.h> #include <asm/x86_init.h> #include <asm/pkru.h> #include <asm/fpu/api.h> #include <asm/coco.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); void ptdump_walk_pgd_level_checkwx(void); void ptdump_walk_user_pgd_level_checkwx(void); /* * Macros to add or remove encryption attribute */ #define pgprot_encrypted(prot) __pgprot(cc_mkenc(pgprot_val(prot))) #define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot))) #ifdef CONFIG_DEBUG_WX #define debug_checkwx() ptdump_walk_pgd_level_checkwx() #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else #define debug_checkwx() do { } while (0) #define debug_checkwx_user() do { } while (0) #endif /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; #define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d # define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) #endif #ifndef __PAGETABLE_PUD_FOLDED #define p4d_clear(p4d) native_p4d_clear(p4d) #endif #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif #define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) #define pmd_clear(pmd) native_pmd_clear(pmd) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) #ifndef __PAGETABLE_P4D_FOLDED #define p4d_val(x) native_p4d_val(x) #define __p4d(x) native_make_p4d(x) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) #endif #ifndef __PAGETABLE_PMD_FOLDED #define pmd_val(x) native_pmd_val(x) #define __pmd(x) native_make_pmd(x) #endif #define pte_val(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) #endif /* CONFIG_PARAVIRT_XXL */ /* * The following only work if pte_present() is true. * Undefined behaviour if not.. */ static inline int pte_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; } static inline int pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY; } #define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; } static inline int pud_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_DIRTY; } static inline int pud_young(pud_t pud) { return pud_flags(pud) & _PAGE_ACCESSED; } static inline int pte_write(pte_t pte) { return pte_flags(pte) & _PAGE_RW; } static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) { return pte_flags(pte) & _PAGE_SPECIAL; } /* Entries that were set to PROT_NONE are inverted */ static inline u64 protnone_mask(u64 val); static inline unsigned long pte_pfn(pte_t pte) { phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) { return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } static inline unsigned long pgd_pfn(pgd_t pgd) { return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } #define p4d_leaf p4d_large static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ return 0; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #endif #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { return boot_cpu_has(X86_FEATURE_PSE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_devmap(pud_t pud) { return !!(pud_val(pud) & _PAGE_DEVMAP); } #else static inline int pud_devmap(pud_t pud) { return 0; } #endif static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); return native_make_pte(v | set); } static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) { pteval_t v = native_pte_val(pte); return native_make_pte(v & ~clear); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_UFFD_WP); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pte_t pte_mkclean(pte_t pte) { return pte_clear_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkold(pte_t pte) { return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_wrprotect(pte_t pte) { return pte_clear_flags(pte, _PAGE_RW); } static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL); } static inline pte_t pte_mkdevmap(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); } static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v & ~clear); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_UFFD_WP; } static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_UFFD_WP); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pmd_t pmd_mkold(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkclean(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DEVMAP); } static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkwrite(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkclean(pud_t pud) { return pud_clear_flags(pud, _PAGE_DIRTY); } static inline pud_t pud_wrprotect(pud_t pud) { return pud_clear_flags(pud, _PAGE_RW); } static inline pud_t pud_mkdirty(pud_t pud) { return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pud_t pud_mkdevmap(pud_t pud) { return pud_set_flags(pud, _PAGE_DEVMAP); } static inline pud_t pud_mkhuge(pud_t pud) { return pud_set_flags(pud, _PAGE_PSE); } static inline pud_t pud_mkyoung(pud_t pud) { return pud_set_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkwrite(pud_t pud) { return pud_set_flags(pud, _PAGE_RW); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; } static inline int pmd_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } static inline int pud_soft_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_SOFT_DIRTY; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_mksoft_dirty(pud_t pud) { return pud_set_flags(pud, _PAGE_SOFT_DIRTY); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_clear_soft_dirty(pud_t pud) { return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. */ static inline pgprotval_t massage_pgprot(pgprot_t pgprot) { pgprotval_t protval = pgprot_val(pgprot); if (protval & _PAGE_PRESENT) protval &= __supported_pte_mask; return protval; } static inline pgprotval_t check_pgprot(pgprot_t pgprot) { pgprotval_t massaged_val = massage_pgprot(pgprot); /* mmdebug.h can not be included here because of dependencies */ #ifdef CONFIG_DEBUG_VM WARN_ONCE(pgprot_val(pgprot) != massaged_val, "attempted to set unsupported pgprot: %016llx " "bits: %016llx supported: %016llx\n", (u64)pgprot_val(pgprot), (u64)pgprot_val(pgprot) ^ massaged_val, (u64)__supported_pte_mask); #endif return massaged_val; } static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PUD_PAGE_MASK; return __pud(pfn | check_pgprot(pgprot)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; /* * Chop off the NX bit (if present), and add the NX portion of * the newprot (if present): */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); } /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) #define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. */ if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* * Certain new memtypes are not allowed with certain * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back * - request is write-through, return cannot be write-back * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } return 1; } pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); #ifdef CONFIG_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* * Take a PGD location (pgdp) and a pgd value that needs to be set there. * Populates the user and returns the resulting PGD that must be set in * the kernel copy of the page tables. */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { if (!static_cpu_has(X86_FEATURE_PTI)) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } #else /* CONFIG_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } #endif /* CONFIG_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else # include <asm/pgtable_64.h> #endif #ifndef __ASSEMBLY__ #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> #include <asm/fixmap.h> static inline int pte_none(pte_t pte) { return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) { return a.pte == b.pte; } static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t a) { return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; } #endif #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { if (pte_flags(a) & _PAGE_PRESENT) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && atomic_read(&mm->tlb_flush_pending)) return true; return false; } static inline int pmd_present(pmd_t pmd) { /* * Checking for _PAGE_PSE is needed too because * split_huge_page will temporarily clear the present bit (but * the _PAGE_PSE flag will remain set at all times while the * _PAGE_PRESENT bit is clear). */ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } #ifdef CONFIG_NUMA_BALANCING /* * These work without NUMA balancing but the kernel does not care. See the * comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } static inline int pmd_protnone(pmd_t pmd) { return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } #endif /* CONFIG_NUMA_BALANCING */ static inline int pmd_none(pmd_t pmd) { /* Only check low word on 32-bit platforms, since it might be out of sync with upper half. */ unsigned long val = native_pmd_val(pmd); return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * * (Currently stuck as a macro because of indirect forward reference * to linux/mm.h:page_to_nid()) */ #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != (_KERNPG_TABLE & ~_PAGE_ACCESSED); } static inline unsigned long pages_to_mb(unsigned long npg) { return npg >> (20 - PAGE_SHIFT); } #if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int pud_present(pud_t pud) { return pud_flags(pud) & _PAGE_PRESENT; } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) #define pud_leaf pud_large static inline int pud_large(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == (_PAGE_PSE | _PAGE_PRESENT); } static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #else #define pud_leaf pud_large static inline int pud_large(pud_t pud) { return 0; } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline int p4d_none(p4d_t p4d) { return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int p4d_present(p4d_t p4d) { return p4d_flags(p4d) & _PAGE_PRESENT; } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ static inline unsigned long p4d_index(unsigned long address) { return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); } #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { if (!pgtable_l5_enabled()) return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } static inline unsigned long pgd_page_vaddr(pgd_t pgd) { return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; if (!pgtable_l5_enabled()) return 0; if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) { if (!pgtable_l5_enabled()) return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables * except on 32-bit non-PAE which is not supported on * KNL. */ return !native_pgd_val(pgd); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) #ifndef __ASSEMBLY__ extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); extern void memblock_find_dma_reserve(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); #ifdef CONFIG_X86_64 extern pgd_t trampoline_pgd_entry; #endif /* local pte updates need not use xchg for locking */ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) { pte_t res = *ptep; /* Pure native function needs no input for mm, addr */ native_pte_clear(NULL, 0, ptep); return res; } static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) { pmd_t res = *pmdp; native_pmd_clear(pmdp); return res; } static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) { pud_t res = *pudp; native_pud_clear(pudp); return res; } static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { page_table_check_pte_set(mm, addr, ptep, pte); set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, addr, pmdp, pmd); set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, addr, pudp, pud); native_set_pud(pudp, pud); } /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to * race with other CPU's that might be updating the dirty * bit at the same time. */ struct vm_area_struct; #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH extern int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, addr, pte); return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; if (full) { /* * Full address destruction in progress; paravirt does not * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, addr, pte); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte); } #define flush_tlb_fix_spurious_fault(vma, address) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_RW; } #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { pmd_t pmd = native_pmdp_get_and_clear(pmdp); page_table_check_pmd_clear(mm, addr, pmd); return pmd; } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { pud_t pud = native_pudp_get_and_clear(pudp); page_table_check_pud_clear(mm, addr, pud); return pud; } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); } #define pud_write pud_write static inline int pud_write(pud_t pud) { return pud_flags(pud) & _PAGE_RW; } #ifndef pmdp_establish #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; WRITE_ONCE(*pmdp, pmd); return old; } } #endif #define __HAVE_ARCH_PMDP_INVALIDATE_AD extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. * * Returns true for parts of the PGD that map userspace and * false for the parts that map the kernel. */ static inline bool pgdp_maps_userspace(void *__ptr) { unsigned long ptr = (unsigned long)__ptr; return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } #define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } #ifdef CONFIG_PAGE_TABLE_ISOLATION /* * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. */ #define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT /* * This generates better code than the inline assembly in * __set_bit(). */ static inline void *ptr_set_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr |= BIT(bit); return (void *)__ptr; } static inline void *ptr_clear_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr &= ~BIT(bit); return (void *)__ptr; } static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) { return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) { return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) { return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } #endif /* CONFIG_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * * dst - pointer to pgd range anywhere on a pgd page * src - "" * count - the number of pgds to copy. * * dst and src can be on the same page, but the range must not overlap, * and must not cross a page boundary. */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), count * sizeof(pgd_t)); #endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) static inline int page_level_shift(enum pg_level level) { return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; } static inline unsigned long page_level_size(enum pg_level level) { return 1UL << page_level_shift(level); } static inline unsigned long page_level_mask(enum pg_level level) { return ~(page_level_size(level) - 1); } /* * The x86 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } #ifdef _PAGE_SWP_EXCLUSIVE #define __HAVE_ARCH_PTE_SWP_EXCLUSIVE static inline pte_t pte_swp_mkexclusive(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); } static inline int pte_swp_exclusive(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); } #endif /* _PAGE_SWP_EXCLUSIVE */ #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } #endif #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_UFFD_WP); } static inline int pte_swp_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_UFFD_WP; } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP); } static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP); } static inline int pmd_swp_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP; } static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* ifdef to avoid doing 59-bit shift on 32-bit values */ return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; #else return 0; #endif } static inline bool __pkru_allows_pkey(u16 pkey, bool write) { u32 pkru = read_pkru(); if (!__pkru_allows_read(pkru, pkey)) return false; if (write && !__pkru_allows_write(pkru, pkey)) return false; return true; } /* * 'pteval' can come from a PTE, PMD or PUD. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the * same value on all 3 types. */ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; if (write) need_pte_bits |= _PAGE_RW; if ((pteval & need_pte_bits) != need_pte_bits) return 0; return __pkru_allows_pkey(pte_flags_pkey(pteval), write); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { return __pte_access_permitted(pte_val(pte), write); } #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { return __pte_access_permitted(pmd_val(pmd), write); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return __pte_access_permitted(pud_val(pud), write); } #define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); static inline bool arch_has_pfn_modify_check(void) { return boot_cpu_has_bug(X86_BUG_L1TF); } #define arch_has_hw_pte_young arch_has_hw_pte_young static inline bool arch_has_hw_pte_young(void) { return true; } #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) { return !cpu_feature_enabled(X86_FEATURE_XENPV); } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER); } #endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ |
| 285 285 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem. * * Changes: * YOSHIFUJI Hideaki @USAGI: added icmp sysctl table. */ #include <linux/mm.h> #include <linux/sysctl.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ndisc.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> #include <net/netevent.h> #include <net/ip_fib.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif #include <linux/ioam6.h> static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static u32 rt6_multipath_hash_fields_all_mask = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static u32 ioam6_id_max = IOAM6_DEFAULT_ID; static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_policy); ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static int proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_fields); ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "anycast_src_echo_reply", .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_consistency", .data = &init_net.ipv6.sysctl.flowlabel_consistency, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "auto_flowlabels", .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "idgen_retries", .data = &init_net.ipv6.sysctl.idgen_retries, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "idgen_delay", .data = &init_net.ipv6.sysctl.idgen_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "flowlabel_state_ranges", .data = &init_net.ipv6.sysctl.flowlabel_state_ranges, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_reflect", .data = &init_net.ipv6.sysctl.flowlabel_reflect, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &flowlabel_reflect_max, }, { .procname = "max_dst_opts_number", .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_opts_number", .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_dst_opts_length", .data = &init_net.ipv6.sysctl.max_dst_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_length", .data = &init_net.ipv6.sysctl.max_hbh_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv6.sysctl.multipath_hash_policy, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "fib_multipath_hash_fields", .data = &init_net.ipv6.sysctl.multipath_hash_fields, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_fields, .extra1 = SYSCTL_ONE, .extra2 = &rt6_multipath_hash_fields_all_mask, }, { .procname = "seg6_flowlabel", .data = &init_net.ipv6.sysctl.seg6_flowlabel, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_notify_on_flag_change", .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "ioam6_id", .data = &init_net.ipv6.sysctl.ioam6_id, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra2 = &ioam6_id_max, }, { .procname = "ioam6_id_wide", .data = &init_net.ipv6.sysctl.ioam6_id_wide, .maxlen = sizeof(u64), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra2 = &ioam6_id_wide_max, }, { } }; static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "mld_qrv", .data = &sysctl_mld_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #ifdef CONFIG_NETLABEL { .procname = "calipso_cache_enable", .data = &calipso_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "calipso_cache_bucket_size", .data = &calipso_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ { } }; static int __net_init ipv6_sysctl_net_init(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; int err, i; err = -ENOMEM; ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), GFP_KERNEL); if (!ipv6_table) goto out; /* Update the variables to point into the current struct net */ for (i = 0; i < ARRAY_SIZE(ipv6_table_template) - 1; i++) ipv6_table[i].data += (void *)net - (void *)&init_net; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) goto out_ipv6_table; ipv6_icmp_table = ipv6_icmp_sysctl_init(net); if (!ipv6_icmp_table) goto out_ipv6_route_table; net->ipv6.sysctl.hdr = register_net_sysctl(net, "net/ipv6", ipv6_table); if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; net->ipv6.sysctl.route_hdr = register_net_sysctl(net, "net/ipv6/route", ipv6_route_table); if (!net->ipv6.sysctl.route_hdr) goto out_unregister_ipv6_table; net->ipv6.sysctl.icmp_hdr = register_net_sysctl(net, "net/ipv6/icmp", ipv6_icmp_table); if (!net->ipv6.sysctl.icmp_hdr) goto out_unregister_route_table; err = 0; out: return err; out_unregister_route_table: unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); out_unregister_ipv6_table: unregister_net_sysctl_table(net->ipv6.sysctl.hdr); out_ipv6_icmp_table: kfree(ipv6_icmp_table); out_ipv6_route_table: kfree(ipv6_route_table); out_ipv6_table: kfree(ipv6_table); goto out; } static void __net_exit ipv6_sysctl_net_exit(struct net *net) { struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.hdr); kfree(ipv6_table); kfree(ipv6_route_table); kfree(ipv6_icmp_table); } static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, }; static struct ctl_table_header *ip6_header; int ipv6_sysctl_register(void) { int err = -ENOMEM; ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); if (!ip6_header) goto out; err = register_pernet_subsys(&ipv6_sysctl_net_ops); if (err) goto err_pernet; out: return err; err_pernet: unregister_net_sysctl_table(ip6_header); goto out; } void ipv6_sysctl_unregister(void) { unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); } |
| 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | #ifndef __LINUX_ERSPAN_H #define __LINUX_ERSPAN_H /* * GRE header for ERSPAN type I encapsulation (4 octets [34:37]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |0|0|0|0|0|00000|000000000|00000| Protocol Type for ERSPAN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * The Type I ERSPAN frame format is based on the barebones IP + GRE * encapsulation (as described above) on top of the raw mirrored frame. * There is no extra ERSPAN header. * * * GRE header for ERSPAN type II and II encapsulation (8 octets [34:41]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |0|0|0|1|0|00000|000000000|00000| Protocol Type for ERSPAN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Sequence Number (increments per packet per session) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Note that in the above GRE header [RFC1701] out of the C, R, K, S, * s, Recur, Flags, Version fields only S (bit 03) is set to 1. The * other fields are set to zero, so only a sequence number follows. * * ERSPAN Version 1 (Type II) header (8 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ver | VLAN | COS | En|T| Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Reserved | Index | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * * ERSPAN Version 2 (Type III) header (12 octets [42:49]) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ver | VLAN | COS |BSO|T| Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Timestamp | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | SGT |P| FT | Hw ID |D|Gra|O| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Platform Specific SubHeader (8 octets, optional) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Platf ID | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Platform Specific Info | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * GRE proto ERSPAN type I/II = 0x88BE, type III = 0x22EB */ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/skbuff.h> #include <uapi/linux/erspan.h> #define ERSPAN_VERSION 0x1 /* ERSPAN type II */ #define VER_MASK 0xf000 #define VLAN_MASK 0x0fff #define COS_MASK 0xe000 #define EN_MASK 0x1800 #define T_MASK 0x0400 #define ID_MASK 0x03ff #define INDEX_MASK 0xfffff #define ERSPAN_VERSION2 0x2 /* ERSPAN type III*/ #define BSO_MASK EN_MASK #define SGT_MASK 0xffff0000 #define P_MASK 0x8000 #define FT_MASK 0x7c00 #define HWID_MASK 0x03f0 #define DIR_MASK 0x0008 #define GRA_MASK 0x0006 #define O_MASK 0x0001 #define HWID_OFFSET 4 #define DIR_OFFSET 3 enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 #define ERSPAN_V2_MDSIZE 8 struct erspan_base_hdr { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 vlan_upper:4, ver:4; __u8 vlan:8; __u8 session_id_upper:2, t:1, en:2, cos:3; __u8 session_id:8; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 ver: 4, vlan_upper:4; __u8 vlan:8; __u8 cos:3, en:2, t:1, session_id_upper:2; __u8 session_id:8; #else #error "Please fix <asm/byteorder.h>" #endif }; static inline void set_session_id(struct erspan_base_hdr *ershdr, u16 id) { ershdr->session_id = id & 0xff; ershdr->session_id_upper = (id >> 8) & 0x3; } static inline u16 get_session_id(const struct erspan_base_hdr *ershdr) { return (ershdr->session_id_upper << 8) + ershdr->session_id; } static inline void set_vlan(struct erspan_base_hdr *ershdr, u16 vlan) { ershdr->vlan = vlan & 0xff; ershdr->vlan_upper = (vlan >> 8) & 0xf; } static inline u16 get_vlan(const struct erspan_base_hdr *ershdr) { return (ershdr->vlan_upper << 8) + ershdr->vlan; } static inline void set_hwid(struct erspan_md2 *md2, u8 hwid) { md2->hwid = hwid & 0xf; md2->hwid_upper = (hwid >> 4) & 0x3; } static inline u8 get_hwid(const struct erspan_md2 *md2) { return (md2->hwid_upper << 4) + md2->hwid; } static inline int erspan_hdr_len(int version) { if (version == 0) return 0; return sizeof(struct erspan_base_hdr) + (version == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); } static inline u8 tos_to_cos(u8 tos) { u8 dscp, cos; dscp = tos >> 2; cos = dscp >> 3; return cos; } static inline void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4) { struct ethhdr *eth = (struct ethhdr *)skb->data; enum erspan_encap_type enc_type; struct erspan_base_hdr *ershdr; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 tos; __be32 *idx; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + (ipv6_hdr(skb)->flow_lbl[0] >> 4); enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and * perserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); vlan_tci = ntohs(qp->tci); enc_type = ERSPAN_ENCAP_INFRAME; } skb_push(skb, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); ershdr = (struct erspan_base_hdr *)skb->data; memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V1_MDSIZE); /* Build base header */ ershdr->ver = ERSPAN_VERSION; ershdr->cos = tos_to_cos(tos); ershdr->en = enc_type; ershdr->t = truncate; set_vlan(ershdr, vlan_tci); set_session_id(ershdr, id); /* Build metadata */ idx = (__be32 *)(ershdr + 1); *idx = htonl(index & INDEX_MASK); } /* ERSPAN GRA: timestamp granularity * 00b --> granularity = 100 microseconds * 01b --> granularity = 100 nanoseconds * 10b --> granularity = IEEE 1588 * Here we only support 100 microseconds. */ static inline __be32 erspan_get_timestamp(void) { u64 h_usecs; ktime_t kt; kt = ktime_get_real(); h_usecs = ktime_divns(kt, 100 * NSEC_PER_USEC); /* ERSPAN base header only has 32-bit, * so it wraps around 4 days. */ return htonl((u32)h_usecs); } /* ERSPAN BSO (Bad/Short/Oversized), see RFC1757 * 00b --> Good frame with no error, or unknown integrity * 01b --> Payload is a Short Frame * 10b --> Payload is an Oversized Frame * 11b --> Payload is a Bad Frame with CRC or Alignment Error */ enum erspan_bso { BSO_NOERROR = 0x0, BSO_SHORT = 0x1, BSO_OVERSIZED = 0x2, BSO_BAD = 0x3, }; static inline u8 erspan_detect_bso(struct sk_buff *skb) { /* BSO_BAD is not handled because the frame CRC * or alignment error information is in FCS. */ if (skb->len < ETH_ZLEN) return BSO_SHORT; if (skb->len > ETH_FRAME_LEN) return BSO_OVERSIZED; return BSO_NOERROR; } static inline void erspan_build_header_v2(struct sk_buff *skb, u32 id, u8 direction, u16 hwid, bool truncate, bool is_ipv4) { struct ethhdr *eth = (struct ethhdr *)skb->data; struct erspan_base_hdr *ershdr; struct erspan_md2 *md2; struct qtag_prefix { __be16 eth_type; __be16 tci; } *qp; u16 vlan_tci = 0; u8 gra = 0; /* 100 usec */ u8 bso = 0; /* Bad/Short/Oversized */ u8 sgt = 0; u8 tos; tos = is_ipv4 ? ip_hdr(skb)->tos : (ipv6_hdr(skb)->priority << 4) + (ipv6_hdr(skb)->flow_lbl[0] >> 4); /* Unlike v1, v2 does not have En field, * so only extract vlan tci field. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); vlan_tci = ntohs(qp->tci); } bso = erspan_detect_bso(skb); skb_push(skb, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); ershdr = (struct erspan_base_hdr *)skb->data; memset(ershdr, 0, sizeof(*ershdr) + ERSPAN_V2_MDSIZE); /* Build base header */ ershdr->ver = ERSPAN_VERSION2; ershdr->cos = tos_to_cos(tos); ershdr->en = bso; ershdr->t = truncate; set_vlan(ershdr, vlan_tci); set_session_id(ershdr, id); /* Build metadata */ md2 = (struct erspan_md2 *)(ershdr + 1); md2->timestamp = erspan_get_timestamp(); md2->sgt = htons(sgt); md2->p = 1; md2->ft = 0; md2->dir = direction; md2->gra = gra; md2->o = 0; set_hwid(md2, hwid); } #endif |
| 285 285 285 285 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 | // SPDX-License-Identifier: GPL-2.0-only /* * x_tables core - Backend for {ip,ip6,arp}_tables * * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org> * Copyright (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on existing ip_tables code which is * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/audit.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define XT_PCPU_BLOCK_SIZE 4096 #define XT_MAX_TABLE_SIZE (512 * 1024 * 1024) struct xt_template { struct list_head list; /* called when table is needed in the given netns */ int (*table_init)(struct net *net); struct module *me; /* A unique name... */ char name[XT_TABLE_MAXNAMELEN]; }; static struct list_head xt_templates[NFPROTO_NUMPROTO]; struct xt_pernet { struct list_head tables[NFPROTO_NUMPROTO]; }; struct compat_delta { unsigned int offset; /* offset in kernel */ int delta; /* delta in 32bit user land */ }; struct xt_af { struct mutex mutex; struct list_head match; struct list_head target; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT struct mutex compat_mutex; struct compat_delta *compat_tab; unsigned int number; /* number of slots in compat_tab[] */ unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; static unsigned int xt_pernet_id __read_mostly; static struct xt_af *xt __read_mostly; static const char *const xt_prefix[NFPROTO_NUMPROTO] = { [NFPROTO_UNSPEC] = "x", [NFPROTO_IPV4] = "ip", [NFPROTO_ARP] = "arp", [NFPROTO_BRIDGE] = "eb", [NFPROTO_IPV6] = "ip6", }; /* Registration hooks for targets. */ int xt_register_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_add(&target->list, &xt[af].target); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_target); void xt_unregister_target(struct xt_target *target) { u_int8_t af = target->family; mutex_lock(&xt[af].mutex); list_del(&target->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_target); int xt_register_targets(struct xt_target *target, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_target(&target[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_targets(target, i); return err; } EXPORT_SYMBOL(xt_register_targets); void xt_unregister_targets(struct xt_target *target, unsigned int n) { while (n-- > 0) xt_unregister_target(&target[n]); } EXPORT_SYMBOL(xt_unregister_targets); int xt_register_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_add(&match->list, &xt[af].match); mutex_unlock(&xt[af].mutex); return 0; } EXPORT_SYMBOL(xt_register_match); void xt_unregister_match(struct xt_match *match) { u_int8_t af = match->family; mutex_lock(&xt[af].mutex); list_del(&match->list); mutex_unlock(&xt[af].mutex); } EXPORT_SYMBOL(xt_unregister_match); int xt_register_matches(struct xt_match *match, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = xt_register_match(&match[i]); if (err) goto err; } return err; err: if (i > 0) xt_unregister_matches(match, i); return err; } EXPORT_SYMBOL(xt_register_matches); void xt_unregister_matches(struct xt_match *match, unsigned int n) { while (n-- > 0) xt_unregister_match(&match[n]); } EXPORT_SYMBOL(xt_unregister_matches); /* * These are weird, but module loading must not be done with mutex * held (since they will register), and we have to have a single * function to use. */ /* Find match, grabs ref. Returns ERR_PTR() on error. */ struct xt_match *xt_find_match(u8 af, const char *name, u8 revision) { struct xt_match *m; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision == revision) { if (try_module_get(m->me)) { mutex_unlock(&xt[af].mutex); return m; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_match(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } EXPORT_SYMBOL(xt_find_match); struct xt_match * xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision) { struct xt_match *match; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); match = xt_find_match(nfproto, name, revision); if (IS_ERR(match)) { request_module("%st_%s", xt_prefix[nfproto], name); match = xt_find_match(nfproto, name, revision); } return match; } EXPORT_SYMBOL_GPL(xt_request_find_match); /* Find target, grabs ref. Returns ERR_PTR() on error. */ static struct xt_target *xt_find_target(u8 af, const char *name, u8 revision) { struct xt_target *t; int err = -ENOENT; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision == revision) { if (try_module_get(t->me)) { mutex_unlock(&xt[af].mutex); return t; } } else err = -EPROTOTYPE; /* Found something. */ } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC) /* Try searching again in the family-independent list */ return xt_find_target(NFPROTO_UNSPEC, name, revision); return ERR_PTR(err); } struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision) { struct xt_target *target; if (strnlen(name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) return ERR_PTR(-EINVAL); target = xt_find_target(af, name, revision); if (IS_ERR(target)) { request_module("%st_%s", xt_prefix[af], name); target = xt_find_target(af, name, revision); } return target; } EXPORT_SYMBOL_GPL(xt_request_find_target); static int xt_obj_to_user(u16 __user *psize, u16 size, void __user *pname, const char *name, u8 __user *prev, u8 rev) { if (put_user(size, psize)) return -EFAULT; if (copy_to_user(pname, name, strlen(name) + 1)) return -EFAULT; if (put_user(rev, prev)) return -EFAULT; return 0; } #define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE) \ xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size, \ U->u.user.name, K->u.kernel.TYPE->name, \ &U->u.user.revision, K->u.kernel.TYPE->revision) int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size) { usersize = usersize ? : size; if (copy_to_user(dst, src, usersize)) return -EFAULT; if (usersize != aligned_size && clear_user(dst + usersize, aligned_size - usersize)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(xt_data_to_user); #define XT_DATA_TO_USER(U, K, TYPE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ K->u.kernel.TYPE->TYPE##size, \ XT_ALIGN(K->u.kernel.TYPE->TYPE##size)) int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u) { return XT_OBJ_TO_USER(u, m, match, 0) || XT_DATA_TO_USER(u, m, match); } EXPORT_SYMBOL_GPL(xt_match_to_user); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u) { return XT_OBJ_TO_USER(u, t, target, 0) || XT_DATA_TO_USER(u, t, target); } EXPORT_SYMBOL_GPL(xt_target_to_user); static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_match *m; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) *bestp = m->revision; if (m->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) { const struct xt_target *t; int have_rev = 0; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) *bestp = t->revision; if (t->revision == revision) have_rev = 1; } } mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); return have_rev; } /* Returns true or false (if no such extension at all) */ int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err) { int have_rev, best = -1; if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { *err = -ENOENT; return 0; } *err = best; if (!have_rev) *err = -EPROTONOSUPPORT; return 1; } EXPORT_SYMBOL_GPL(xt_find_revision); static char * textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; static const char *const arp_names[] = { "INPUT", "FORWARD", "OUTPUT", }; const char *const *names; unsigned int i, max; char *p = buf; bool np = false; int res; names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : ARRAY_SIZE(inetbr_names); *p = '\0'; for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); if (res > 0) { size -= res; p += res; } np = true; } return buf; } /** * xt_check_proc_name - check that name is suitable for /proc file creation * * @name: file name candidate * @size: length of buffer * * some x_tables modules wish to create a file in /proc. * This function makes sure that the name is suitable for this * purpose, it checks that name is NUL terminated and isn't a 'special' * name, like "..". * * returns negative number on error or 0 if name is useable. */ int xt_check_proc_name(const char *name, unsigned int size) { if (name[0] == '\0') return -EINVAL; if (strnlen(name, size) == size) return -ENAMETOOLONG; if (strcmp(name, ".") == 0 || strcmp(name, "..") == 0 || strchr(name, '/')) return -EINVAL; return 0; } EXPORT_SYMBOL(xt_check_proc_name); int xt_check_match(struct xt_mtchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; if (XT_ALIGN(par->match->matchsize) != size && par->match->matchsize != -1) { /* * ebt_among is exempt from centralized matchsize checking * because it uses a dynamic-size data set. */ pr_err_ratelimited("%s_tables: %s.%u match: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->match->name, par->match->revision, XT_ALIGN(par->match->matchsize), size); return -EINVAL; } if (par->match->table != NULL && strcmp(par->match->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s match: only valid in %s table, not %s\n", xt_prefix[par->family], par->match->name, par->match->table, par->table); return -EINVAL; } if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s match: used from hooks %s, but only valid from %s\n", xt_prefix[par->family], par->match->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->match->hooks, par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s match: only valid for protocol %u\n", xt_prefix[par->family], par->match->name, par->match->proto); return -EINVAL; } if (par->match->checkentry != NULL) { ret = par->match->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } EXPORT_SYMBOL_GPL(xt_check_match); /** xt_check_entry_match - check that matches end before start of target * * @match: beginning of xt_entry_match * @target: beginning of this rules target (alleged end of matches) * @alignment: alignment requirement of match structures * * Validates that all matches add up to the beginning of the target, * and that each match covers at least the base structure size. * * Return: 0 on success, negative errno on failure. */ static int xt_check_entry_match(const char *match, const char *target, const size_t alignment) { const struct xt_entry_match *pos; int length = target - match; if (length == 0) /* no matches */ return 0; pos = (struct xt_entry_match *)match; do { if ((unsigned long)pos % alignment) return -EINVAL; if (length < (int)sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size < sizeof(struct xt_entry_match)) return -EINVAL; if (pos->u.match_size > length) return -EINVAL; length -= pos->u.match_size; pos = ((void *)((char *)(pos) + (pos)->u.match_size)); } while (length > 0); return 0; } /** xt_check_table_hooks - check hook entry points are sane * * @info xt_table_info to check * @valid_hooks - hook entry points that we can enter from * * Validates that the hook entry and underflows points are set up. * * Return: 0 on success, negative errno on failure. */ int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks) { const char *err = "unsorted underflow"; unsigned int i, max_uflow, max_entry; bool check_hooks = false; BUILD_BUG_ON(ARRAY_SIZE(info->hook_entry) != ARRAY_SIZE(info->underflow)); max_entry = 0; max_uflow = 0; for (i = 0; i < ARRAY_SIZE(info->hook_entry); i++) { if (!(valid_hooks & (1 << i))) continue; if (info->hook_entry[i] == 0xFFFFFFFF) return -EINVAL; if (info->underflow[i] == 0xFFFFFFFF) return -EINVAL; if (check_hooks) { if (max_uflow > info->underflow[i]) goto error; if (max_uflow == info->underflow[i]) { err = "duplicate underflow"; goto error; } if (max_entry > info->hook_entry[i]) { err = "unsorted entry"; goto error; } if (max_entry == info->hook_entry[i]) { err = "duplicate entry"; goto error; } } max_entry = info->hook_entry[i]; max_uflow = info->underflow[i]; check_hooks = true; } return 0; error: pr_err_ratelimited("%s at hook %d\n", err, i); return -EINVAL; } EXPORT_SYMBOL(xt_check_table_hooks); static bool verdict_ok(int verdict) { if (verdict > 0) return true; if (verdict < 0) { int v = -verdict - 1; if (verdict == XT_RETURN) return true; switch (v) { case NF_ACCEPT: return true; case NF_DROP: return true; case NF_QUEUE: return true; default: break; } return false; } return false; } static bool error_tg_ok(unsigned int usersize, unsigned int kernsize, const char *msg, unsigned int msglen) { return usersize == kernsize && strnlen(msg, msglen) < msglen; } #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { struct xt_af *xp = &xt[af]; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (WARN_ON(!xp->compat_tab)) return -ENOMEM; if (xp->cur >= xp->number) return -EINVAL; if (xp->cur) delta += xp->compat_tab[xp->cur - 1].delta; xp->compat_tab[xp->cur].offset = offset; xp->compat_tab[xp->cur].delta = delta; xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); void xt_compat_flush_offsets(u_int8_t af) { WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (xt[af].compat_tab) { vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { struct compat_delta *tmp = xt[af].compat_tab; int mid, left = 0, right = xt[af].cur - 1; while (left <= right) { mid = (left + right) >> 1; if (offset > tmp[mid].offset) left = mid + 1; else if (offset < tmp[mid].offset) right = mid - 1; else return mid ? tmp[mid - 1].delta : 0; } return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); int xt_compat_init_offsets(u8 af, unsigned int number) { size_t mem; WARN_ON(!mutex_is_locked(&xt[af].compat_mutex)); if (!number || number > (INT_MAX / sizeof(struct compat_delta))) return -EINVAL; if (WARN_ON(xt[af].compat_tab)) return -EINVAL; mem = sizeof(struct compat_delta) * number; if (mem > XT_MAX_TABLE_SIZE) return -ENOMEM; xt[af].compat_tab = vmalloc(mem); if (!xt[af].compat_tab) return -ENOMEM; xt[af].number = number; xt[af].cur = 0; return 0; } EXPORT_SYMBOL(xt_compat_init_offsets); int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_match_offset); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; m = *dstptr; memcpy(m, cm, sizeof(*cm)); if (match->compat_from_user) match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); msize += off; m->u.user.match_size = msize; strscpy(name, match->name, sizeof(name)); module_put(match->me); strncpy(m->u.user.name, name, sizeof(m->u.user.name)); *size += off; *dstptr += msize; } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); #define COMPAT_XT_DATA_TO_USER(U, K, TYPE, C_SIZE) \ xt_data_to_user(U->data, K->data, \ K->u.kernel.TYPE->usersize, \ C_SIZE, \ COMPAT_XT_ALIGN(C_SIZE)) int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match __user *cm = *dstptr; int off = xt_compat_match_offset(match); u_int16_t msize = m->u.user.match_size - off; if (XT_OBJ_TO_USER(cm, m, match, msize)) return -EFAULT; if (match->compat_to_user) { if (match->compat_to_user((void __user *)cm->data, m->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm))) return -EFAULT; } *size -= off; *dstptr += msize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_match_to_user); /* non-compat version may have padding after verdict */ struct compat_xt_standard_target { struct compat_xt_entry_target t; compat_uint_t verdict; }; struct compat_xt_error_target { struct compat_xt_entry_target t; char errorname[XT_FUNCTION_MAXNAMELEN]; }; int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct compat_xt_entry_target *t; const char *e = base; if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct compat_xt_standard_target *st = (const void *)t; if (COMPAT_XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct compat_xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } /* compat_xt_entry match has less strict alignment requirements, * otherwise they are identical. In case of padding differences * we need to add compat version of xt_check_entry_match. */ BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match)); return xt_check_entry_match(elems, base + target_offset, __alignof__(struct compat_xt_entry_match)); } EXPORT_SYMBOL(xt_compat_check_entry_offsets); #endif /* CONFIG_NETFILTER_XTABLES_COMPAT */ /** * xt_check_entry_offsets - validate arp/ip/ip6t_entry * * @base: pointer to arp/ip/ip6t_entry * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems * @target_offset: the arp/ip/ip6_t->target_offset * @next_offset: the arp/ip/ip6_t->next_offset * * validates that target_offset and next_offset are sane and that all * match sizes (if any) align with the target offset. * * This function does not validate the targets or matches themselves, it * only tests that all the offsets and sizes are correct, that all * match structures are aligned, and that the last structure ends where * the target structure begins. * * Also see xt_compat_check_entry_offsets for CONFIG_NETFILTER_XTABLES_COMPAT version. * * The arp/ip/ip6t_entry structure @base must have passed following tests: * - it must point to a valid memory location * - base to base + next_offset must be accessible, i.e. not exceed allocated * length. * * A well-formed entry looks like this: * * ip(6)t_entry match [mtdata] match [mtdata] target [tgdata] ip(6)t_entry * e->elems[]-----' | | * matchsize | | * matchsize | | * | | * target_offset---------------------------------' | * next_offset---------------------------------------------------' * * elems[]: flexible array member at end of ip(6)/arpt_entry struct. * This is where matches (if any) and the target reside. * target_offset: beginning of target. * next_offset: start of the next rule; also: size of this rule. * Since targets have a minimum size, target_offset + minlen <= next_offset. * * Every match stores its size, sum of sizes must not exceed target_offset. * * Return: 0 on success, negative errno on failure. */ int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset) { long size_of_base_struct = elems - (const char *)base; const struct xt_entry_target *t; const char *e = base; /* target start is within the ip/ip6/arpt_entry struct */ if (target_offset < size_of_base_struct) return -EINVAL; if (target_offset + sizeof(*t) > next_offset) return -EINVAL; t = (void *)(e + target_offset); if (t->u.target_size < sizeof(*t)) return -EINVAL; if (target_offset + t->u.target_size > next_offset) return -EINVAL; if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0) { const struct xt_standard_target *st = (const void *)t; if (XT_ALIGN(target_offset + sizeof(*st)) != next_offset) return -EINVAL; if (!verdict_ok(st->verdict)) return -EINVAL; } else if (strcmp(t->u.user.name, XT_ERROR_TARGET) == 0) { const struct xt_error_target *et = (const void *)t; if (!error_tg_ok(t->u.target_size, sizeof(*et), et->errorname, sizeof(et->errorname))) return -EINVAL; } return xt_check_entry_match(elems, base + target_offset, __alignof__(struct xt_entry_match)); } EXPORT_SYMBOL(xt_check_entry_offsets); /** * xt_alloc_entry_offsets - allocate array to store rule head offsets * * @size: number of entries * * Return: NULL or zeroed kmalloc'd or vmalloc'd array */ unsigned int *xt_alloc_entry_offsets(unsigned int size) { if (size > XT_MAX_TABLE_SIZE / sizeof(unsigned int)) return NULL; return kvcalloc(size, sizeof(unsigned int), GFP_KERNEL); } EXPORT_SYMBOL(xt_alloc_entry_offsets); /** * xt_find_jump_offset - check if target is a valid jump offset * * @offsets: array containing all valid rule start offsets of a rule blob * @target: the jump target to search for * @size: entries in @offset */ bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size) { int m, low = 0, hi = size; while (hi > low) { m = (low + hi) / 2u; if (offsets[m] > target) hi = m; else if (offsets[m] < target) low = m + 1; else return true; } return false; } EXPORT_SYMBOL(xt_find_jump_offset); int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u16 proto, bool inv_proto) { int ret; if (XT_ALIGN(par->target->targetsize) != size) { pr_err_ratelimited("%s_tables: %s.%u target: invalid size %u (kernel) != (user) %u\n", xt_prefix[par->family], par->target->name, par->target->revision, XT_ALIGN(par->target->targetsize), size); return -EINVAL; } if (par->target->table != NULL && strcmp(par->target->table, par->table) != 0) { pr_info_ratelimited("%s_tables: %s target: only valid in %s table, not %s\n", xt_prefix[par->family], par->target->name, par->target->table, par->table); return -EINVAL; } if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) { char used[64], allow[64]; pr_info_ratelimited("%s_tables: %s target: used from hooks %s, but only usable from %s\n", xt_prefix[par->family], par->target->name, textify_hooks(used, sizeof(used), par->hook_mask, par->family), textify_hooks(allow, sizeof(allow), par->target->hooks, par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { pr_info_ratelimited("%s_tables: %s target: only valid for protocol %u\n", xt_prefix[par->family], par->target->name, par->target->proto); return -EINVAL; } if (par->target->checkentry != NULL) { ret = par->target->checkentry(par); if (ret < 0) return ret; else if (ret > 0) /* Flag up potential errors. */ return -EIO; } return 0; } EXPORT_SYMBOL_GPL(xt_check_target); /** * xt_copy_counters - copy counters and metadata from a sockptr_t * * @arg: src sockptr * @len: alleged size of userspace memory * @info: where to store the xt_counters_info metadata * * Copies counter meta data from @user and stores it in @info. * * vmallocs memory to hold the counters, then copies the counter data * from @user to the new memory and returns a pointer to it. * * If called from a compat syscall, @info gets converted automatically to the * 64bit representation. * * The metadata associated with the counters is stored in @info. * * Return: returns pointer that caller has to test via IS_ERR(). * If IS_ERR is false, caller has to vfree the pointer. */ void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info) { size_t offset; void *mem; u64 size; #ifdef CONFIG_NETFILTER_XTABLES_COMPAT if (in_compat_syscall()) { /* structures only differ in size due to alignment */ struct compat_xt_counters_info compat_tmp; if (len <= sizeof(compat_tmp)) return ERR_PTR(-EINVAL); len -= sizeof(compat_tmp); if (copy_from_sockptr(&compat_tmp, arg, sizeof(compat_tmp)) != 0) return ERR_PTR(-EFAULT); memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1); info->num_counters = compat_tmp.num_counters; offset = sizeof(compat_tmp); } else #endif { if (len <= sizeof(*info)) return ERR_PTR(-EINVAL); len -= sizeof(*info); if (copy_from_sockptr(info, arg, sizeof(*info)) != 0) return ERR_PTR(-EFAULT); offset = sizeof(*info); } info->name[sizeof(info->name) - 1] = '\0'; size = sizeof(struct xt_counters); size *= info->num_counters; if (size != (u64)len) return ERR_PTR(-EINVAL); mem = vmalloc(len); if (!mem) return ERR_PTR(-ENOMEM); if (copy_from_sockptr_offset(mem, arg, offset, len) == 0) return mem; vfree(mem); return ERR_PTR(-EFAULT); } EXPORT_SYMBOL_GPL(xt_copy_counters); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT int xt_compat_target_offset(const struct xt_target *target) { u_int16_t csize = target->compatsize ? : target->targetsize; return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize); } EXPORT_SYMBOL_GPL(xt_compat_target_offset); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; t = *dstptr; memcpy(t, ct, sizeof(*ct)); if (target->compat_from_user) target->compat_from_user(t->data, ct->data); else memcpy(t->data, ct->data, tsize - sizeof(*ct)); tsize += off; t->u.user.target_size = tsize; strscpy(name, target->name, sizeof(name)); module_put(target->me); strncpy(t->u.user.name, name, sizeof(t->u.user.name)); *size += off; *dstptr += tsize; } EXPORT_SYMBOL_GPL(xt_compat_target_from_user); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size) { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target __user *ct = *dstptr; int off = xt_compat_target_offset(target); u_int16_t tsize = t->u.user.target_size - off; if (XT_OBJ_TO_USER(ct, t, target, tsize)) return -EFAULT; if (target->compat_to_user) { if (target->compat_to_user((void __user *)ct->data, t->data)) return -EFAULT; } else { if (COMPAT_XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct))) return -EFAULT; } *size -= off; *dstptr += tsize; return 0; } EXPORT_SYMBOL_GPL(xt_compat_target_to_user); #endif struct xt_table_info *xt_alloc_table_info(unsigned int size) { struct xt_table_info *info = NULL; size_t sz = sizeof(*info) + size; if (sz < sizeof(*info) || sz >= XT_MAX_TABLE_SIZE) return NULL; info = kvmalloc(sz, GFP_KERNEL_ACCOUNT); if (!info) return NULL; memset(info, 0, sizeof(*info)); info->size = size; return info; } EXPORT_SYMBOL(xt_alloc_table_info); void xt_free_table_info(struct xt_table_info *info) { int cpu; if (info->jumpstack != NULL) { for_each_possible_cpu(cpu) kvfree(info->jumpstack[cpu]); kvfree(info->jumpstack); } kvfree(info); } EXPORT_SYMBOL(xt_free_table_info); struct xt_table *xt_find_table(struct net *net, u8 af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) { if (strcmp(t->name, name) == 0) { mutex_unlock(&xt[af].mutex); return t; } } mutex_unlock(&xt[af].mutex); return NULL; } EXPORT_SYMBOL(xt_find_table); /* Find table by name, grabs mutex & ref. Returns ERR_PTR on error. */ struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct module *owner = NULL; struct xt_template *tmpl; struct xt_table *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0 && try_module_get(t->me)) return t; /* Table doesn't exist in this netns, check larval list */ list_for_each_entry(tmpl, &xt_templates[af], list) { int err; if (strcmp(tmpl->name, name)) continue; if (!try_module_get(tmpl->me)) goto out; owner = tmpl->me; mutex_unlock(&xt[af].mutex); err = tmpl->table_init(net); if (err < 0) { module_put(owner); return ERR_PTR(err); } mutex_lock(&xt[af].mutex); break; } /* and once again: */ list_for_each_entry(t, &xt_net->tables[af], list) if (strcmp(t->name, name) == 0) return t; module_put(owner); out: mutex_unlock(&xt[af].mutex); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(xt_find_table_lock); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name) { struct xt_table *t = xt_find_table_lock(net, af, name); #ifdef CONFIG_MODULES if (IS_ERR(t)) { int err = request_module("%stable_%s", xt_prefix[af], name); if (err < 0) return ERR_PTR(err); t = xt_find_table_lock(net, af, name); } #endif return t; } EXPORT_SYMBOL_GPL(xt_request_find_table_lock); void xt_table_unlock(struct xt_table *table) { mutex_unlock(&xt[table->af].mutex); } EXPORT_SYMBOL_GPL(xt_table_unlock); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT void xt_compat_lock(u_int8_t af) { mutex_lock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_lock); void xt_compat_unlock(u_int8_t af) { mutex_unlock(&xt[af].compat_mutex); } EXPORT_SYMBOL_GPL(xt_compat_unlock); #endif DEFINE_PER_CPU(seqcount_t, xt_recseq); EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq); struct static_key xt_tee_enabled __read_mostly; EXPORT_SYMBOL_GPL(xt_tee_enabled); static int xt_jumpstack_alloc(struct xt_table_info *i) { unsigned int size; int cpu; size = sizeof(void **) * nr_cpu_ids; if (size > PAGE_SIZE) i->jumpstack = kvzalloc(size, GFP_KERNEL); else i->jumpstack = kzalloc(size, GFP_KERNEL); if (i->jumpstack == NULL) return -ENOMEM; /* ruleset without jumps -- no stack needed */ if (i->stacksize == 0) return 0; /* Jumpstack needs to be able to record two full callchains, one * from the first rule set traversal, plus one table reentrancy * via -j TEE without clobbering the callchain that brought us to * TEE target. * * This is done by allocating two jumpstacks per cpu, on reentry * the upper half of the stack is used. * * see the jumpstack setup in ipt_do_table() for more details. */ size = sizeof(void *) * i->stacksize * 2u; for_each_possible_cpu(cpu) { i->jumpstack[cpu] = kvmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (i->jumpstack[cpu] == NULL) /* * Freeing will be done later on by the callers. The * chain is: xt_replace_table -> __do_replace -> * do_replace -> xt_free_table_info. */ return -ENOMEM; } return 0; } struct xt_counters *xt_counters_alloc(unsigned int counters) { struct xt_counters *mem; if (counters == 0 || counters > INT_MAX / sizeof(*mem)) return NULL; counters *= sizeof(*mem); if (counters > XT_MAX_TABLE_SIZE) return NULL; return vzalloc(counters); } EXPORT_SYMBOL(xt_counters_alloc); struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error) { struct xt_table_info *private; unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); if (ret < 0) { *error = ret; return NULL; } /* Do the substitution. */ local_bh_disable(); private = table->private; /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; /* * Ensure contents of newinfo are visible before assigning to * private. */ smp_wmb(); table->private = newinfo; /* make sure all cpus see new ->private value */ smp_mb(); /* * Even though table entries have now been swapped, other CPU's * may still be using the old entries... */ local_bh_enable(); /* ... so wait for even xt_recseq on all cpus */ for_each_possible_cpu(cpu) { seqcount_t *s = &per_cpu(xt_recseq, cpu); u32 seq = raw_read_seqcount(s); if (seq & 1) { do { cond_resched(); cpu_relax(); } while (seq == raw_read_seqcount(s)); } } audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : AUDIT_XT_OP_REPLACE, GFP_KERNEL); return private; } EXPORT_SYMBOL_GPL(xt_replace_table); struct xt_table *xt_register_table(struct net *net, const struct xt_table *input_table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); struct xt_table_info *private; struct xt_table *t, *table; int ret; /* Don't add one object to multiple lists. */ table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL); if (!table) { ret = -ENOMEM; goto out; } mutex_lock(&xt[table->af].mutex); /* Don't autoload: we'd eat our tail... */ list_for_each_entry(t, &xt_net->tables[table->af], list) { if (strcmp(t->name, table->name) == 0) { ret = -EEXIST; goto unlock; } } /* Simplifies replace_table code. */ table->private = bootstrap; if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; private = table->private; pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ private->initial_entries = private->number; list_add(&table->list, &xt_net->tables[table->af]); mutex_unlock(&xt[table->af].mutex); return table; unlock: mutex_unlock(&xt[table->af].mutex); kfree(table); out: return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(xt_register_table); void *xt_unregister_table(struct xt_table *table) { struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); private = table->private; list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, AUDIT_XT_OP_UNREGISTER, GFP_KERNEL); kfree(table->ops); kfree(table); return private; } EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); mutex_lock(&xt[af].mutex); return seq_list_start(&xt_net->tables[af], *pos); } static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; xt_net = net_generic(net, xt_pernet_id); return seq_list_next(v, &xt_net->tables[af], pos); } static void xt_table_seq_stop(struct seq_file *seq, void *v) { u_int8_t af = (unsigned long)pde_data(file_inode(seq->file)); mutex_unlock(&xt[af].mutex); } static int xt_table_seq_show(struct seq_file *seq, void *v) { struct xt_table *table = list_entry(v, struct xt_table, list); if (*table->name) seq_printf(seq, "%s\n", table->name); return 0; } static const struct seq_operations xt_table_seq_ops = { .start = xt_table_seq_start, .next = xt_table_seq_next, .stop = xt_table_seq_stop, .show = xt_table_seq_show, }; /* * Traverse state for ip{,6}_{tables,matches} for helping crossing * the multi-AF mutexes. */ struct nf_mttg_trav { struct list_head *head, *curr; uint8_t class; }; enum { MTTG_TRAV_INIT, MTTG_TRAV_NFP_UNSPEC, MTTG_TRAV_NFP_SPEC, MTTG_TRAV_DONE, }; static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, bool is_target) { static const uint8_t next_class[] = { [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, }; uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; if (ppos != NULL) ++(*ppos); switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; mutex_lock(&xt[NFPROTO_UNSPEC].mutex); trav->head = trav->curr = is_target ? &xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match; break; case MTTG_TRAV_NFP_UNSPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); mutex_lock(&xt[nfproto].mutex); trav->head = trav->curr = is_target ? &xt[nfproto].target : &xt[nfproto].match; trav->class = next_class[trav->class]; break; case MTTG_TRAV_NFP_SPEC: trav->curr = trav->curr->next; if (trav->curr != trav->head) break; fallthrough; default: return NULL; } return trav; } static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, bool is_target) { struct nf_mttg_trav *trav = seq->private; unsigned int j; trav->class = MTTG_TRAV_INIT; for (j = 0; j < *pos; ++j) if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL) return NULL; return trav; } static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: mutex_unlock(&xt[NFPROTO_UNSPEC].mutex); break; case MTTG_TRAV_NFP_SPEC: mutex_unlock(&xt[nfproto].mutex); break; } } static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, false); } static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, false); } static int xt_match_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_match *match; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; match = list_entry(trav->curr, struct xt_match, list); if (*match->name) seq_printf(seq, "%s\n", match->name); } return 0; } static const struct seq_operations xt_match_seq_ops = { .start = xt_match_seq_start, .next = xt_match_seq_next, .stop = xt_mttg_seq_stop, .show = xt_match_seq_show, }; static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos) { return xt_mttg_seq_start(seq, pos, true); } static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos) { return xt_mttg_seq_next(seq, v, ppos, true); } static int xt_target_seq_show(struct seq_file *seq, void *v) { const struct nf_mttg_trav *trav = seq->private; const struct xt_target *target; switch (trav->class) { case MTTG_TRAV_NFP_UNSPEC: case MTTG_TRAV_NFP_SPEC: if (trav->curr == trav->head) return 0; target = list_entry(trav->curr, struct xt_target, list); if (*target->name) seq_printf(seq, "%s\n", target->name); } return 0; } static const struct seq_operations xt_target_seq_ops = { .start = xt_target_seq_start, .next = xt_target_seq_next, .stop = xt_mttg_seq_stop, .show = xt_target_seq_show, }; #define FORMAT_TABLES "_tables_names" #define FORMAT_MATCHES "_tables_matches" #define FORMAT_TARGETS "_tables_targets" #endif /* CONFIG_PROC_FS */ /** * xt_hook_ops_alloc - set up hooks for a new table * @table: table with metadata needed to set up hooks * @fn: Hook function * * This function will create the nf_hook_ops that the x_table needs * to hand to xt_hook_link_net(). */ struct nf_hook_ops * xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn) { unsigned int hook_mask = table->valid_hooks; uint8_t i, num_hooks = hweight32(hook_mask); uint8_t hooknum; struct nf_hook_ops *ops; if (!num_hooks) return ERR_PTR(-EINVAL); ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0; hook_mask >>= 1, ++hooknum) { if (!(hook_mask & 1)) continue; ops[i].hook = fn; ops[i].pf = table->af; ops[i].hooknum = hooknum; ops[i].priority = table->priority; ++i; } return ops; } EXPORT_SYMBOL_GPL(xt_hook_ops_alloc); int xt_register_template(const struct xt_table *table, int (*table_init)(struct net *net)) { int ret = -EEXIST, af = table->af; struct xt_template *t; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (WARN_ON_ONCE(strcmp(table->name, t->name) == 0)) goto out_unlock; } ret = -ENOMEM; t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) goto out_unlock; BUILD_BUG_ON(sizeof(t->name) != sizeof(table->name)); strscpy(t->name, table->name, sizeof(t->name)); t->table_init = table_init; t->me = table->me; list_add(&t->list, &xt_templates[af]); ret = 0; out_unlock: mutex_unlock(&xt[af].mutex); return ret; } EXPORT_SYMBOL_GPL(xt_register_template); void xt_unregister_template(const struct xt_table *table) { struct xt_template *t; int af = table->af; mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt_templates[af], list) { if (strcmp(table->name, t->name)) continue; list_del(&t->list); mutex_unlock(&xt[af].mutex); kfree(t); return; } mutex_unlock(&xt[af].mutex); WARN_ON_ONCE(1); } EXPORT_SYMBOL_GPL(xt_unregister_template); int xt_proto_init(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif if (af >= ARRAY_SIZE(xt_prefix)) return -EINVAL; #ifdef CONFIG_PROC_FS root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); proc = proc_create_net_data(buf, 0440, net->proc_net, &xt_table_seq_ops, sizeof(struct seq_net_private), (void *)(unsigned long)af); if (!proc) goto out; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_match_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_tables; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); proc = proc_create_seq_private(buf, 0440, net->proc_net, &xt_target_seq_ops, sizeof(struct nf_mttg_trav), (void *)(unsigned long)af); if (!proc) goto out_remove_matches; if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; #ifdef CONFIG_PROC_FS out_remove_matches: strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out_remove_tables: strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); out: return -1; #endif } EXPORT_SYMBOL_GPL(xt_proto_init); void xt_proto_fini(struct net *net, u_int8_t af) { #ifdef CONFIG_PROC_FS char buf[XT_FUNCTION_MAXNAMELEN]; strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TABLES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_TARGETS, sizeof(buf)); remove_proc_entry(buf, net->proc_net); strscpy(buf, xt_prefix[af], sizeof(buf)); strlcat(buf, FORMAT_MATCHES, sizeof(buf)); remove_proc_entry(buf, net->proc_net); #endif /*CONFIG_PROC_FS*/ } EXPORT_SYMBOL_GPL(xt_proto_fini); /** * xt_percpu_counter_alloc - allocate x_tables rule counter * * @state: pointer to xt_percpu allocation state * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct * * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then * contain the address of the real (percpu) counter. * * Rule evaluation needs to use xt_get_this_cpu_counter() helper * to fetch the real percpu counter. * * To speed up allocation and improve data locality, a 4kb block is * allocated. Freeing any counter may free an entire block, so all * counters allocated using the same state must be freed at the same * time. * * xt_percpu_counter_alloc_state contains the base address of the * allocated page and the current sub-offset. * * returns false on error. */ bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter) { BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2)); if (nr_cpu_ids <= 1) return true; if (!state->mem) { state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE, XT_PCPU_BLOCK_SIZE); if (!state->mem) return false; } counter->pcnt = (__force unsigned long)(state->mem + state->off); state->off += sizeof(*counter); if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) { state->mem = NULL; state->off = 0; } return true; } EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc); void xt_percpu_counter_free(struct xt_counters *counters) { unsigned long pcnt = counters->pcnt; if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0) free_percpu((void __percpu *)pcnt); } EXPORT_SYMBOL_GPL(xt_percpu_counter_free); static int __net_init xt_net_init(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) INIT_LIST_HEAD(&xt_net->tables[i]); return 0; } static void __net_exit xt_net_exit(struct net *net) { struct xt_pernet *xt_net = net_generic(net, xt_pernet_id); int i; for (i = 0; i < NFPROTO_NUMPROTO; i++) WARN_ON_ONCE(!list_empty(&xt_net->tables[i])); } static struct pernet_operations xt_net_ops = { .init = xt_net_init, .exit = xt_net_exit, .id = &xt_pernet_id, .size = sizeof(struct xt_pernet), }; static int __init xt_init(void) { unsigned int i; int rv; for_each_possible_cpu(i) { seqcount_init(&per_cpu(xt_recseq, i)); } xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; for (i = 0; i < NFPROTO_NUMPROTO; i++) { mutex_init(&xt[i].mutex); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT mutex_init(&xt[i].compat_mutex); xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); INIT_LIST_HEAD(&xt_templates[i]); } rv = register_pernet_subsys(&xt_net_ops); if (rv < 0) kfree(xt); return rv; } static void __exit xt_fini(void) { unregister_pernet_subsys(&xt_net_ops); kfree(xt); } module_init(xt_init); module_exit(xt_fini); |
| 226 22 226 226 21 226 226 427 202 226 238 68 238 29 29 7 7 7 7 36 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Pid namespaces * * Authors: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/pid.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/syscalls.h> #include <linux/cred.h> #include <linux/err.h> #include <linux/acct.h> #include <linux/slab.h> #include <linux/proc_ns.h> #include <linux/reboot.h> #include <linux/export.h> #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/idr.h> static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; /* Write once array, filled from the beginning. */ static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL]; /* * creates the kmem cache to allocate pids from. * @level: pid namespace level */ static struct kmem_cache *create_pid_cachep(unsigned int level) { /* Level 0 is init_pid_ns.pid_cachep */ struct kmem_cache **pkc = &pid_cache[level - 1]; struct kmem_cache *kc; char name[4 + 10 + 1]; unsigned int len; kc = READ_ONCE(*pkc); if (kc) return kc; snprintf(name, sizeof(name), "pid_%u", level + 1); len = sizeof(struct pid) + level * sizeof(struct upid); mutex_lock(&pid_caches_mutex); /* Name collision forces to do allocation under mutex. */ if (!*pkc) *pkc = kmem_cache_create(name, len, 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); mutex_unlock(&pid_caches_mutex); /* current can fail, but someone else can succeed. */ return READ_ONCE(*pkc); } static struct ucounts *inc_pid_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES); } static void dec_pid_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_PID_NAMESPACES); } static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; unsigned int level = parent_pid_ns->level + 1; struct ucounts *ucounts; int err; err = -EINVAL; if (!in_userns(parent_pid_ns->user_ns, user_ns)) goto out; err = -ENOSPC; if (level > MAX_PID_NS_LEVEL) goto out; ucounts = inc_pid_namespaces(user_ns); if (!ucounts) goto out; err = -ENOMEM; ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL); if (ns == NULL) goto out_dec; idr_init(&ns->idr); ns->pid_cachep = create_pid_cachep(level); if (ns->pid_cachep == NULL) goto out_free_idr; err = ns_alloc_inum(&ns->ns); if (err) goto out_free_idr; ns->ns.ops = &pidns_operations; refcount_set(&ns->ns.count, 1); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; return ns; out_free_idr: idr_destroy(&ns->idr); kmem_cache_free(pid_ns_cachep, ns); out_dec: dec_pid_namespaces(ucounts); out: return ERR_PTR(err); } static void delayed_free_pidns(struct rcu_head *p) { struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu); dec_pid_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kmem_cache_free(pid_ns_cachep, ns); } static void destroy_pid_namespace(struct pid_namespace *ns) { ns_free_inum(&ns->ns); idr_destroy(&ns->idr); call_rcu(&ns->rcu, delayed_free_pidns); } struct pid_namespace *copy_pid_ns(unsigned long flags, struct user_namespace *user_ns, struct pid_namespace *old_ns) { if (!(flags & CLONE_NEWPID)) return get_pid_ns(old_ns); if (task_active_pid_ns(current) != old_ns) return ERR_PTR(-EINVAL); return create_pid_namespace(user_ns, old_ns); } void put_pid_ns(struct pid_namespace *ns) { struct pid_namespace *parent; while (ns != &init_pid_ns) { parent = ns->parent; if (!refcount_dec_and_test(&ns->ns.count)) break; destroy_pid_namespace(ns); ns = parent; } } EXPORT_SYMBOL_GPL(put_pid_ns); void zap_pid_ns_processes(struct pid_namespace *pid_ns) { int nr; int rc; struct task_struct *task, *me = current; int init_pids = thread_group_leader(me) ? 1 : 2; struct pid *pid; /* Don't allow any more processes into the pid namespace */ disable_pid_allocation(pid_ns); /* * Ignore SIGCHLD causing any terminated children to autoreap. * This speeds up the namespace shutdown, plus see the comment * below. */ spin_lock_irq(&me->sighand->siglock); me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN; spin_unlock_irq(&me->sighand->siglock); /* * The last thread in the cgroup-init thread group is terminating. * Find remaining pid_ts in the namespace, signal and wait for them * to exit. * * Note: This signals each threads in the namespace - even those that * belong to the same thread group, To avoid this, we would have * to walk the entire tasklist looking a processes in this * namespace, but that could be unnecessarily expensive if the * pid namespace has just a few processes. Or we need to * maintain a tasklist for each pid namespace. * */ rcu_read_lock(); read_lock(&tasklist_lock); nr = 2; idr_for_each_entry_continue(&pid_ns->idr, pid, nr) { task = pid_task(pid, PIDTYPE_PID); if (task && !__fatal_signal_pending(task)) group_send_sig_info(SIGKILL, SEND_SIG_PRIV, task, PIDTYPE_MAX); } read_unlock(&tasklist_lock); rcu_read_unlock(); /* * Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD. * kernel_wait4() will also block until our children traced from the * parent namespace are detached and become EXIT_DEAD. */ do { clear_thread_flag(TIF_SIGPENDING); rc = kernel_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); /* * kernel_wait4() misses EXIT_DEAD children, and EXIT_ZOMBIE * process whose parents processes are outside of the pid * namespace. Such processes are created with setns()+fork(). * * If those EXIT_ZOMBIE processes are not reaped by their * parents before their parents exit, they will be reparented * to pid_ns->child_reaper. Thus pidns->child_reaper needs to * stay valid until they all go away. * * The code relies on the pid_ns->child_reaper ignoring * SIGCHILD to cause those EXIT_ZOMBIE processes to be * autoreaped if reparented. * * Semantically it is also desirable to wait for EXIT_ZOMBIE * processes before allowing the child_reaper to be reaped, as * that gives the invariant that when the init process of a * pid namespace is reaped all of the processes in the pid * namespace are gone. * * Once all of the other tasks are gone from the pid_namespace * free_pid() will awaken this task. */ for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->pid_allocated == init_pids) break; /* * Release tasks_rcu_exit_srcu to avoid following deadlock: * * 1) TASK A unshare(CLONE_NEWPID) * 2) TASK A fork() twice -> TASK B (child reaper for new ns) * and TASK C * 3) TASK B exits, kills TASK C, waits for TASK A to reap it * 4) TASK A calls synchronize_rcu_tasks() * -> synchronize_srcu(tasks_rcu_exit_srcu) * 5) *DEADLOCK* * * It is considered safe to release tasks_rcu_exit_srcu here * because we assume the current task can not be concurrently * reaped at this point. */ exit_tasks_rcu_stop(); schedule(); exit_tasks_rcu_start(); } __set_current_state(TASK_RUNNING); if (pid_ns->reboot) current->signal->group_exit_code = pid_ns->reboot; acct_exit_ns(pid_ns); return; } #ifdef CONFIG_CHECKPOINT_RESTORE static int pid_ns_ctl_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct pid_namespace *pid_ns = task_active_pid_ns(current); struct ctl_table tmp = *table; int ret, next; if (write && !checkpoint_restore_ns_capable(pid_ns->user_ns)) return -EPERM; /* * Writing directly to ns' last_pid field is OK, since this field * is volatile in a living namespace anyway and a code writing to * it should synchronize its usage with external means. */ next = idr_get_cursor(&pid_ns->idr) - 1; tmp.data = &next; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (!ret && write) idr_set_cursor(&pid_ns->idr, next + 1); return ret; } extern int pid_max; static struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), .mode = 0666, /* permissions are checked in the handler */ .proc_handler = pid_ns_ctl_handler, .extra1 = SYSCTL_ZERO, .extra2 = &pid_max, }, { } }; static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; #endif /* CONFIG_CHECKPOINT_RESTORE */ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) { if (pid_ns == &init_pid_ns) return 0; switch (cmd) { case LINUX_REBOOT_CMD_RESTART2: case LINUX_REBOOT_CMD_RESTART: pid_ns->reboot = SIGHUP; break; case LINUX_REBOOT_CMD_POWER_OFF: case LINUX_REBOOT_CMD_HALT: pid_ns->reboot = SIGINT; break; default: return -EINVAL; } read_lock(&tasklist_lock); send_sig(SIGKILL, pid_ns->child_reaper, 1); read_unlock(&tasklist_lock); do_exit(0); /* Not reached */ return 0; } static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) { return container_of(ns, struct pid_namespace, ns); } static struct ns_common *pidns_get(struct task_struct *task) { struct pid_namespace *ns; rcu_read_lock(); ns = task_active_pid_ns(task); if (ns) get_pid_ns(ns); rcu_read_unlock(); return ns ? &ns->ns : NULL; } static struct ns_common *pidns_for_children_get(struct task_struct *task) { struct pid_namespace *ns = NULL; task_lock(task); if (task->nsproxy) { ns = task->nsproxy->pid_ns_for_children; get_pid_ns(ns); } task_unlock(task); if (ns) { read_lock(&tasklist_lock); if (!ns->child_reaper) { put_pid_ns(ns); ns = NULL; } read_unlock(&tasklist_lock); } return ns ? &ns->ns : NULL; } static void pidns_put(struct ns_common *ns) { put_pid_ns(to_pid_ns(ns)); } static int pidns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *ancestor, *new = to_pid_ns(ns); if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* * Only allow entering the current active pid namespace * or a child of the current active pid namespace. * * This is required for fork to return a usable pid value and * this maintains the property that processes and their * children can not escape their current pid namespace. */ if (new->level < active->level) return -EINVAL; ancestor = new; while (ancestor->level > active->level) ancestor = ancestor->parent; if (ancestor != active) return -EINVAL; put_pid_ns(nsproxy->pid_ns_for_children); nsproxy->pid_ns_for_children = get_pid_ns(new); return 0; } static struct ns_common *pidns_get_parent(struct ns_common *ns) { struct pid_namespace *active = task_active_pid_ns(current); struct pid_namespace *pid_ns, *p; /* See if the parent is in the current namespace */ pid_ns = p = to_pid_ns(ns)->parent; for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == active) break; p = p->parent; } return &get_pid_ns(pid_ns)->ns; } static struct user_namespace *pidns_owner(struct ns_common *ns) { return to_pid_ns(ns)->user_ns; } const struct proc_ns_operations pidns_operations = { .name = "pid", .type = CLONE_NEWPID, .get = pidns_get, .put = pidns_put, .install = pidns_install, .owner = pidns_owner, .get_parent = pidns_get_parent, }; const struct proc_ns_operations pidns_for_children_operations = { .name = "pid_for_children", .real_ns_name = "pid", .type = CLONE_NEWPID, .get = pidns_for_children_get, .put = pidns_put, .install = pidns_install, .owner = pidns_owner, .get_parent = pidns_get_parent, }; static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC | SLAB_ACCOUNT); #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_paths(kern_path, pid_ns_ctl_table); #endif return 0; } __initcall(pid_namespaces_init); |
| 150 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. */ /* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #include <linux/kernel_read_file.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/signal.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/perf_event.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> #include <linux/utsname.h> #include <linux/pid_namespace.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> #include <linux/kmod.h> #include <linux/fsnotify.h> #include <linux/fs_struct.h> #include <linux/oom.h> #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlb.h> #include <trace/events/task.h> #include "internal.h" #include <trace/events/sched.h> static int bprm_creds_from_file(struct linux_binprm *bprm); int suid_dumpable = 0; static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt) { write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt) { module_put(fmt->module); } bool path_noexec(const struct path *path) { return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } #ifdef CONFIG_USELIB /* * Note that a shared library must be both readable and executable due to * security reasons. * * Also note that we take the address to load from the file itself. */ SYSCALL_DEFINE1(uselib, const char __user *, library) { struct linux_binfmt *fmt; struct file *file; struct filename *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if (IS_ERR(tmp)) goto out; file = do_filp_open(AT_FDCWD, tmp, &uselib_flags); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) goto out; /* * may_open() has already checked for this, so it should be * impossible to trip now. But we need to be extra cautious * and check again at the very end too. */ error = -EACCES; if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || path_noexec(&file->f_path))) goto exit; fsnotify_open(file); error = -ENOEXEC; read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!fmt->load_shlib) continue; if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); error = fmt->load_shlib(file); read_lock(&binfmt_lock); put_binfmt(fmt); if (error != -ENOEXEC) break; } read_unlock(&binfmt_lock); exit: fput(file); out: return error; } #endif /* #ifdef CONFIG_USELIB */ #ifdef CONFIG_MMU /* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); if (!mm || !diff) return; bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff); } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; struct vm_area_struct *vma = bprm->vma; struct mm_struct *mm = bprm->mm; int ret; /* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it * by hand ahead of time. */ if (write && pos < vma->vm_start) { mmap_write_lock(mm); ret = expand_downwards(vma, pos); if (unlikely(ret < 0)) { mmap_write_unlock(mm); return NULL; } mmap_write_downgrade(mm); } else mmap_read_lock(mm); /* * We are doing an exec(). 'current' is the process * doing the exec and 'mm' is the new process's mm. */ ret = get_user_pages_remote(mm, pos, 1, write ? FOLL_WRITE : 0, &page, NULL, NULL); mmap_read_unlock(mm); if (ret <= 0) return NULL; if (write) acct_arg_size(bprm, vma_pages(vma)); return page; } static void put_arg_page(struct page *page) { put_page(page); } static void free_arg_pages(struct linux_binprm *bprm) { } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { flush_cache_page(bprm->vma, pos, page_to_pfn(page)); } static int __bprm_mm_init(struct linux_binprm *bprm) { int err; struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; vma_set_anonymous(vma); if (mmap_write_lock_killable(mm)) { err = -EINTR; goto err_free; } /* * Place the stack at the largest stack address the architecture * supports. Later, we'll move this to an appropriate place. We don't * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); err = insert_vm_struct(mm, vma); if (err) goto err; mm->stack_vm = mm->total_vm = 1; mmap_write_unlock(mm); bprm->p = vma->vm_end - sizeof(void *); return 0; err: mmap_write_unlock(mm); err_free: bprm->vma = NULL; vm_area_free(vma); return err; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= MAX_ARG_STRLEN; } #else static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; } return page; } static void put_arg_page(struct page *page) { } static void free_arg_page(struct linux_binprm *bprm, int i) { if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; } } static void free_arg_pages(struct linux_binprm *bprm) { int i; for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i); } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { } static int __bprm_mm_init(struct linux_binprm *bprm) { bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); return 0; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= bprm->p; } #endif /* CONFIG_MMU */ /* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err; /* Save current stack limit for all calculations made during exec. */ task_lock(current->group_leader); bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader); err = __bprm_mm_init(bprm); if (err) goto err; return 0; err: if (mm) { bprm->mm = NULL; mmdrop(mm); } return err; } struct user_arg_ptr { #ifdef CONFIG_COMPAT bool is_compat; #endif union { const char __user *const __user *native; #ifdef CONFIG_COMPAT const compat_uptr_t __user *compat; #endif } ptr; }; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { const char __user *native; #ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat; if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT); return compat_ptr(compat); } #endif if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); return native; } /* * count() counts the number of strings in array ARGV. */ static int count(struct user_arg_ptr argv, int max) { int i = 0; if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); if (!p) break; if (IS_ERR(p)) return -EFAULT; if (i >= max) return -E2BIG; ++i; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i; } static int count_strings_kernel(const char *const *argv) { int i; if (!argv) return 0; for (i = 0; argv[i]; ++i) { if (i >= MAX_ARG_STRINGS) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return i; } static int bprm_stack_limits(struct linux_binprm *bprm) { unsigned long limit, ptr_size; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, bprm->rlim_stack.rlim_cur / 4); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. * * In the case of argc = 0, make sure there is space for adding a * empty string (which will bump argc to 1), to ensure confused * userspace programs don't start processing from argv[1], thinking * argc can never be 0, to keep them from walking envp by accident. * See do_execveat_common(). */ ptr_size = (max(bprm->argc, 1) + bprm->envc) * sizeof(void *); if (limit <= ptr_size) return -E2BIG; limit -= ptr_size; bprm->argmin = bprm->p - limit; return 0; } /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret; while (argc-- > 0) { const char __user *str; int len; unsigned long pos; ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out; len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out; ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out; /* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; #ifdef CONFIG_MMU if (bprm->p < bprm->argmin) goto out; #endif while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy; len -= bytes_to_copy; if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page; page = get_arg_page(bprm, pos, 1); if (!page) { ret = -E2BIG; goto out; } if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } } } ret = 0; out: if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret; } /* * Copy and argument/environment string from the kernel to the processes stack. */ int copy_string_kernel(const char *arg, struct linux_binprm *bprm) { int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */; unsigned long pos = bprm->p; if (len == 0) return -EFAULT; if (!valid_arg_len(bprm, len)) return -E2BIG; /* We're going to work our way backwards. */ arg += len; bprm->p -= len; if (IS_ENABLED(CONFIG_MMU) && bprm->p < bprm->argmin) return -E2BIG; while (len > 0) { unsigned int bytes_to_copy = min_t(unsigned int, len, min_not_zero(offset_in_page(pos), PAGE_SIZE)); struct page *page; pos -= bytes_to_copy; arg -= bytes_to_copy; len -= bytes_to_copy; page = get_arg_page(bprm, pos, 1); if (!page) return -E2BIG; flush_arg_page(bprm, pos & PAGE_MASK, page); memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy); put_arg_page(page); } return 0; } EXPORT_SYMBOL(copy_string_kernel); static int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm) { while (argc-- > 0) { int ret = copy_string_kernel(argv[argc], bprm); if (ret < 0) return ret; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return 0; } #ifdef CONFIG_MMU /* * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once * the binfmt code determines where the new stack should reside, we shift it to * its final location. The process proceeds as follows: * * 1) Use shift to calculate the new vma endpoints. * 2) Extend vma to cover both the old and new ranges. This ensures the * arguments passed to subsequent functions are consistent. * 3) Move vma's page tables to the new range. * 4) Free up any cleared pgd range. * 5) Shrink the vma to cover only the new range. */ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) { struct mm_struct *mm = vma->vm_mm; unsigned long old_start = vma->vm_start; unsigned long old_end = vma->vm_end; unsigned long length = old_end - old_start; unsigned long new_start = old_start - shift; unsigned long new_end = old_end - shift; VMA_ITERATOR(vmi, mm, new_start); struct vm_area_struct *next; struct mmu_gather tlb; BUG_ON(new_start > new_end); /* * ensure there are no vmas between where we want to go * and where we are */ if (vma != vma_next(&vmi)) return -EFAULT; /* * cover the whole range: [new_start, old_end) */ if (vma_adjust(vma, new_start, old_end, vma->vm_pgoff, NULL)) return -ENOMEM; /* * move the page tables downwards, on failure we rely on * process cleanup to remove whatever mess we made. */ if (length != move_page_tables(vma, old_start, vma, new_start, length, false)) return -ENOMEM; lru_add_drain(); tlb_gather_mmu(&tlb, mm); next = vma_next(&vmi); if (new_end > old_start) { /* * when the old and new regions overlap clear from new_end. */ free_pgd_range(&tlb, new_end, old_end, new_end, next ? next->vm_start : USER_PGTABLES_CEILING); } else { /* * otherwise, clean from old_start; this is done to not touch * the address space in [new_end, old_start) some architectures * have constraints on va-space that make this illegal (IA64) - * for the others its just a little faster. */ free_pgd_range(&tlb, old_start, old_end, new_end, next ? next->vm_start : USER_PGTABLES_CEILING); } tlb_finish_mmu(&tlb); /* * Shrink the vma to just the new range. Always succeeds. */ vma_adjust(vma, new_start, new_end, vma->vm_pgoff, NULL); return 0; } /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. */ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { unsigned long ret; unsigned long stack_shift; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = bprm->vma; struct vm_area_struct *prev = NULL; unsigned long vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; struct mmu_gather tlb; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ stack_base = bprm->rlim_stack.rlim_max; stack_base = calc_max_stack_size(stack_base); /* Add space for stack randomization. */ stack_base += (STACK_RND_MASK << PAGE_SHIFT); /* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) return -ENOMEM; stack_base = PAGE_ALIGN(stack_top - stack_base); stack_shift = vma->vm_start - stack_base; mm->arg_start = bprm->p - stack_shift; bprm->p = vma->vm_end - stack_shift; #else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top); if (unlikely(stack_top < mmap_min_addr) || unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) return -ENOMEM; stack_shift = vma->vm_end - stack_top; bprm->p -= stack_shift; mm->arg_start = bprm->p; #endif if (bprm->loader) bprm->loader -= stack_shift; bprm->exec -= stack_shift; if (mmap_write_lock_killable(mm)) return -EINTR; vm_flags = VM_STACK_FLAGS; /* * Adjust stack execute permissions; explicitly enable for * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone * (arch default) otherwise. */ if (unlikely(executable_stack == EXSTACK_ENABLE_X)) vm_flags |= VM_EXEC; else if (executable_stack == EXSTACK_DISABLE_X) vm_flags &= ~VM_EXEC; vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; tlb_gather_mmu(&tlb, mm); ret = mprotect_fixup(&tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); tlb_finish_mmu(&tlb); if (ret) goto out_unlock; BUG_ON(prev != vma); if (unlikely(vm_flags & VM_EXEC)) { pr_warn_once("process '%pD4' started with executable stack\n", bprm->file); } /* Move stack pages down in memory. */ if (stack_shift) { ret = shift_arg_pages(vma, stack_shift); if (ret) goto out_unlock; } /* mprotect_fixup is overkill to remove the temporary stack flags */ vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP); stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; /* * Align this down to a page boundary as expand_stack * will align it up. */ rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK; #ifdef CONFIG_STACK_GROWSUP if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_start + rlim_stack; else stack_base = vma->vm_end + stack_expand; #else if (stack_size + stack_expand > rlim_stack) stack_base = vma->vm_end - rlim_stack; else stack_base = vma->vm_start - stack_expand; #endif current->mm->start_stack = bprm->p; ret = expand_stack_locked(vma, stack_base); if (ret) ret = -EFAULT; out_unlock: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(setup_arg_pages); #else /* * Transfer the program arguments and environment from the holding pages * onto the stack. The provided stack pointer is adjusted accordingly. */ int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location) { unsigned long index, stop, sp; int ret = 0; stop = bprm->p >> PAGE_SHIFT; sp = *sp_location; for (index = MAX_ARG_PAGES - 1; index >= stop; index--) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; char *src = kmap_local_page(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; kunmap_local(src); if (ret) goto out; } bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: return ret; } EXPORT_SYMBOL(transfer_args_to_stack); #endif /* CONFIG_MMU */ static struct file *do_open_execat(int fd, struct filename *name, int flags) { struct file *file; int err; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) open_exec_flags.lookup_flags |= LOOKUP_EMPTY; file = do_filp_open(fd, name, &open_exec_flags); if (IS_ERR(file)) goto out; /* * may_open() has already checked for this, so it should be * impossible to trip now. But we need to be extra cautious * and check again at the very end too. */ err = -EACCES; if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || path_noexec(&file->f_path))) goto exit; err = deny_write_access(file); if (err) goto exit; if (name->name[0] != '\0') fsnotify_open(file); out: return file; exit: fput(file); return ERR_PTR(err); } struct file *open_exec(const char *name) { struct filename *filename = getname_kernel(name); struct file *f = ERR_CAST(filename); if (!IS_ERR(filename)) { f = do_open_execat(AT_FDCWD, filename, 0); putname(filename); } return f; } EXPORT_SYMBOL(open_exec); #if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC) ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) { ssize_t res = vfs_read(file, (void __user *)addr, len, &pos); if (res > 0) flush_icache_user_range(addr, addr + len); return res; } EXPORT_SYMBOL(read_code); #endif /* * Maps the mm_struct mm into the current task struct. * On success, this function returns with exec_update_lock * held for writing. */ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); if (old_mm) sync_mm_rss(old_mm); ret = down_write_killable(&tsk->signal->exec_update_lock); if (ret) return ret; if (old_mm) { /* * If there is a pending fatal signal perhaps a signal * whose default action is to create a coredump get * out and die instead of going through with the exec. */ ret = mmap_read_lock_killable(old_mm); if (ret) { up_write(&tsk->signal->exec_update_lock); return ret; } } task_lock(tsk); membarrier_exec_mmap(mm); local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; /* * This prevents preemption while active_mm is being loaded and * it and mm are being updated, which could cause problems for * lazy tlb mm refcounting when these are updated by context * switches. Not all architectures can handle irqs off over * activate_mm yet. */ if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); activate_mm(active_mm, mm); if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); lru_gen_add_mm(mm); task_unlock(tsk); lru_gen_use_mm(mm); if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm); mm_update_next_owner(old_mm); mmput(old_mm); return 0; } mmdrop(active_mm); return 0; } static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. */ spin_lock_irq(lock); if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); return -EAGAIN; } sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; while (sig->notify_count) { __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); if (__fatal_signal_pending(tsk)) goto killed; spin_lock_irq(lock); } spin_unlock_irq(lock); /* * At this point all other threads have exited, all we have to * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader; for (;;) { cgroup_threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); schedule(); if (__fatal_signal_pending(tsk)) goto killed; } /* * The only record we have of the real-time age of a * process, regardless of execs it's done, is start_time. * All the past CPU time is accumulated in signal_struct * from sister threads now dead. But in this non-leader * exec, nothing survives from the original leader thread, * whose birth marks the true age of this process now. * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; tsk->start_boottime = leader->start_boottime; BUG_ON(!same_thread_group(leader, tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */ /* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. */ exchange_tids(tsk, leader); transfer_pid(leader, tsk, PIDTYPE_TGID); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); list_replace_rcu(&leader->tasks, &tsk->tasks); list_replace_init(&leader->sibling, &tsk->sibling); tsk->group_leader = tsk; leader->group_leader = tsk; tsk->exit_signal = SIGCHLD; leader->exit_signal = -1; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees * the tracer won't block again waiting for this thread. */ if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); release_task(leader); } sig->group_exec_task = NULL; sig->notify_count = 0; no_thread_group: /* we have changed execution domain */ tsk->exit_signal = SIGCHLD; BUG_ON(!thread_group_leader(tsk)); return 0; killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); sig->group_exec_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN; } /* * This function makes sure the current process has its own signal table, * so that flush_signal_handlers can later reset the handlers without * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ static int unshare_sighand(struct task_struct *me) { struct sighand_struct *oldsighand = me->sighand; if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND * but not CLONE_THREAD task, switch to the new one. */ newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); if (!newsighand) return -ENOMEM; refcount_set(&newsighand->count, 1); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); rcu_assign_pointer(me->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); __cleanup_sighand(oldsighand); } return 0; } char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { task_lock(tsk); /* Always NUL terminated and zero-padded */ strscpy_pad(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable * so that a new one can be started */ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); strscpy_pad(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk, exec); } /* * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal * signal (via de_thread() or coredump), or will have SEGV raised * (after exec_mmap()) by search_binary_handler (see below). */ int begin_new_exec(struct linux_binprm * bprm) { struct task_struct *me = current; int retval; /* Once we are committed compute the creds */ retval = bprm_creds_from_file(bprm); if (retval) return retval; /* * Ensure all future errors are fatal. */ bprm->point_of_no_return = true; /* * Make this the only thread in the thread group. */ retval = de_thread(me); if (retval) goto out; /* * Cancel any io_uring activity across execve */ io_uring_task_cancel(); /* Ensure the files table is not shared. */ retval = unshare_files(); if (retval) goto out; /* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. This also enables the update * to be lockless. */ retval = set_mm_exe_file(bprm->mm, bprm->file); if (retval) goto out; /* If the binary is not readable then enforce mm->dumpable=0 */ would_dump(bprm, bprm->file); if (bprm->have_execfd) would_dump(bprm, bprm->executable); /* * Release all of the old mmap stuff */ acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) goto out; bprm->mm = NULL; #ifdef CONFIG_POSIX_TIMERS spin_lock_irq(&me->sighand->siglock); posix_cpu_timers_exit(me); spin_unlock_irq(&me->sighand->siglock); exit_itimers(me); flush_itimer_signals(); #endif /* * Make the signal table private. */ retval = unshare_sighand(me); if (retval) goto out_unlock; me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); me->personality &= ~bprm->per_clear; clear_syscall_work_syscall_user_dispatch(me); /* * We have to apply CLOEXEC before we change whether the process is * dumpable (in setup_new_exec) to avoid a race with a process in userspace * trying to access the should-be-closed file descriptors of a process * undergoing exec(2). */ do_close_on_exec(me->files); if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0; /* * For secureexec, reset the stack limit to sane default to * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ if (bprm->rlim_stack.rlim_cur > _STK_LIM) bprm->rlim_stack.rlim_cur = _STK_LIM; } me->sas_ss_sp = me->sas_ss_size = 0; /* * Figure out dumpability. Note that this checking only of current * is wrong, but userspace depends on it. This should be testing * bprm->secureexec instead. */ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || !(uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))) set_dumpable(current->mm, suid_dumpable); else set_dumpable(current->mm, SUID_DUMP_USER); perf_event_exec(); __set_task_comm(me, kbasename(bprm->filename), true); /* An exec changes our domain. We are no longer part of the thread group */ WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); flush_signal_handlers(me, 0); retval = set_cred_ucounts(bprm->cred); if (retval < 0) goto out_unlock; /* * install the new credentials for this executable */ security_bprm_committing_creds(bprm); commit_creds(bprm->cred); bprm->cred = NULL; /* * Disable monitoring for regular users * when executing setuid binaries. Must * wait until new credentials are committed * by commit_creds() above */ if (get_dumpable(me->mm) != SUID_DUMP_USER) perf_event_exit_task(me); /* * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); /* Pass the opened binary to the interpreter. */ if (bprm->have_execfd) { retval = get_unused_fd_flags(0); if (retval < 0) goto out_unlock; fd_install(retval, bprm->executable); bprm->executable = NULL; bprm->execfd = retval; } return 0; out_unlock: up_write(&me->signal->exec_update_lock); if (!bprm->cred) mutex_unlock(&me->signal->cred_guard_mutex); out: return retval; } EXPORT_SYMBOL(begin_new_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); struct user_namespace *mnt_userns = file_mnt_user_ns(file); if (inode_permission(mnt_userns, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; /* Ensure mm->user_ns contains the executable */ user_ns = old = bprm->mm->user_ns; while ((user_ns != &init_user_ns) && !privileged_wrt_inode_uidgid(user_ns, mnt_userns, inode)) user_ns = user_ns->parent; if (old != user_ns) { bprm->mm->user_ns = get_user_ns(user_ns); put_user_ns(old); } } } EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { /* Setup things that can depend upon the personality */ struct task_struct *me = current; arch_pick_mmap_layout(me->mm, &bprm->rlim_stack); arch_setup_new_exec(); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on * some architectures like powerpc */ me->mm->task_size = TASK_SIZE; up_write(&me->signal->exec_update_lock); mutex_unlock(&me->signal->cred_guard_mutex); } EXPORT_SYMBOL(setup_new_exec); /* Runs immediately before start_thread() takes over. */ void finalize_exec(struct linux_binprm *bprm) { /* Store any stack rlimit changes before starting thread. */ task_lock(current->group_leader); current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack; task_unlock(current->group_leader); } EXPORT_SYMBOL(finalize_exec); /* * Prepare credentials and lock ->cred_guard_mutex. * setup_new_exec() commits the new creds and drops the lock. * Or, if exec fails before, free_bprm() should release ->cred * and unlock. */ static int prepare_bprm_creds(struct linux_binprm *bprm) { if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM; } static void free_bprm(struct linux_binprm *bprm) { if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); } free_arg_pages(bprm); if (bprm->cred) { mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } if (bprm->file) { allow_write_access(bprm->file); fput(bprm->file); } if (bprm->executable) fput(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); kfree(bprm->fdpath); kfree(bprm); } static struct linux_binprm *alloc_bprm(int fd, struct filename *filename) { struct linux_binprm *bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); int retval = -ENOMEM; if (!bprm) goto out; if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { if (filename->name[0] == '\0') bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); else bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); if (!bprm->fdpath) goto out_free; bprm->filename = bprm->fdpath; } bprm->interp = bprm->filename; retval = bprm_mm_init(bprm); if (retval) goto out_free; return bprm; out_free: free_bprm(bprm); out: return ERR_PTR(retval); } int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); bprm->interp = kstrdup(interp, GFP_KERNEL); if (!bprm->interp) return -ENOMEM; return 0; } EXPORT_SYMBOL(bprm_change_interp); /* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH or seccomp thread-sync */ static void check_unsafe_exec(struct linux_binprm *bprm) { struct task_struct *p = current, *t; unsigned n_fs; if (p->ptrace) bprm->unsafe |= LSM_UNSAFE_PTRACE; /* * This isn't strictly necessary, but it makes it harder for LSMs to * mess up. */ if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; t = p; n_fs = 1; spin_lock(&p->fs->lock); rcu_read_lock(); while_each_thread(p, t) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock(); if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else p->fs->in_exec = 1; spin_unlock(&p->fs->lock); } static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) { /* Handle suid and sgid on files */ struct user_namespace *mnt_userns; struct inode *inode = file_inode(file); unsigned int mode; kuid_t uid; kgid_t gid; if (!mnt_may_suid(file->f_path.mnt)) return; if (task_no_new_privs(current)) return; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; mnt_userns = file_mnt_user_ns(file); /* Be careful if suid/sgid is set */ inode_lock(inode); /* reload atomically mode/uid/gid now that lock held */ mode = inode->i_mode; uid = i_uid_into_mnt(mnt_userns, inode); gid = i_gid_into_mnt(mnt_userns, inode); inode_unlock(inode); /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || !kgid_has_mapping(bprm->cred->user_ns, gid)) return; if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = uid; } if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = gid; } } /* * Compute brpm->cred based upon the final binary. */ static int bprm_creds_from_file(struct linux_binprm *bprm) { /* Compute creds based on which file? */ struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file; bprm_fill_uid(bprm, file); return security_bprm_creds_from_file(bprm, file); } /* * Fill the binprm structure from the inode. * Read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */ static int prepare_binprm(struct linux_binprm *bprm) { loff_t pos = 0; memset(bprm->buf, 0, BINPRM_BUF_SIZE); return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos); } /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after * the first '\0' encountered. */ int remove_arg_zero(struct linux_binprm *bprm) { int ret = 0; unsigned long offset; char *kaddr; struct page *page; if (!bprm->argc) return 0; do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); if (!page) { ret = -EFAULT; goto out; } kaddr = kmap_local_page(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); bprm->p++; bprm->argc--; ret = 0; out: return ret; } EXPORT_SYMBOL(remove_arg_zero); #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ static int search_binary_handler(struct linux_binprm *bprm) { bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; retval = prepare_binprm(bprm); if (retval < 0) return retval; retval = security_bprm_check(bprm); if (retval) return retval; retval = -ENOENT; retry: read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); retval = fmt->load_binary(bprm); read_lock(&binfmt_lock); put_binfmt(fmt); if (bprm->point_of_no_return || (retval != -ENOEXEC)) { read_unlock(&binfmt_lock); return retval; } } read_unlock(&binfmt_lock); if (need_retry) { if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && printable(bprm->buf[2]) && printable(bprm->buf[3])) return retval; if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) return retval; need_retry = false; goto retry; } return retval; } static int exec_binprm(struct linux_binprm *bprm) { pid_t old_pid, old_vpid; int ret, depth; /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; rcu_read_lock(); old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); /* This allows 4 levels of binfmt rewrites before failing hard. */ for (depth = 0;; depth++) { struct file *exec; if (depth > 5) return -ELOOP; ret = search_binary_handler(bprm); if (ret < 0) return ret; if (!bprm->interpreter) break; exec = bprm->file; bprm->file = bprm->interpreter; bprm->interpreter = NULL; allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); return -ENOEXEC; } bprm->executable = exec; } else fput(exec); } audit_bprm(bprm); trace_sched_process_exec(current, old_pid, bprm); ptrace_event(PTRACE_EVENT_EXEC, old_vpid); proc_exec_connector(current); return 0; } /* * sys_execve() executes a new program. */ static int bprm_execve(struct linux_binprm *bprm, int fd, struct filename *filename, int flags) { struct file *file; int retval; retval = prepare_bprm_creds(bprm); if (retval) return retval; check_unsafe_exec(bprm); current->in_execve = 1; file = do_open_execat(fd, filename, flags); retval = PTR_ERR(file); if (IS_ERR(file)) goto out_unmark; sched_exec(); bprm->file = file; /* * Record that a name derived from an O_CLOEXEC fd will be * inaccessible after exec. This allows the code in exec to * choose to fail when the executable is not mmaped into the * interpreter and an open file descriptor is not passed to * the interpreter. This makes for a better user experience * than having the interpreter start and then immediately fail * when it finds the executable is inaccessible. */ if (bprm->fdpath && get_close_on_exec(fd)) bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE; /* Set the unchanging part of bprm->cred */ retval = security_bprm_creds_for_exec(bprm); if (retval) goto out; retval = exec_binprm(bprm); if (retval < 0) goto out; /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; rseq_execve(current); acct_update_integrals(current); task_numa_free(current, false); return retval; out: /* * If past the point of no return ensure the code never * returns to the userspace process. Use an existing fatal * signal if present otherwise terminate the process with * SIGSEGV. */ if (bprm->point_of_no_return && !fatal_signal_pending(current)) force_fatal_sig(SIGSEGV); out_unmark: current->fs->in_exec = 0; current->in_execve = 0; return retval; } static int do_execveat_common(int fd, struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp, int flags) { struct linux_binprm *bprm; int retval; if (IS_ERR(filename)) return PTR_ERR(filename); /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs * don't check setuid() return code. Here we additionally recheck * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { retval = -EAGAIN; goto out_ret; } /* We're below the limit (still or again), so we don't want to make * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED; bprm = alloc_bprm(fd, filename); if (IS_ERR(bprm)) { retval = PTR_ERR(bprm); goto out_ret; } retval = count(argv, MAX_ARG_STRINGS); if (retval == 0) pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", current->comm, bprm->filename); if (retval < 0) goto out_free; bprm->argc = retval; retval = count(envp, MAX_ARG_STRINGS); if (retval < 0) goto out_free; bprm->envc = retval; retval = bprm_stack_limits(bprm); if (retval < 0) goto out_free; retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out_free; bprm->exec = bprm->p; retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) goto out_free; retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) goto out_free; /* * When argv is empty, add an empty string ("") as argv[0] to * ensure confused userspace programs that start processing * from argv[1] won't end up walking envp. See also * bprm_stack_limits(). */ if (bprm->argc == 0) { retval = copy_string_kernel("", bprm); if (retval < 0) goto out_free; bprm->argc = 1; } retval = bprm_execve(bprm, fd, filename, flags); out_free: free_bprm(bprm); out_ret: putname(filename); return retval; } int kernel_execve(const char *kernel_filename, const char *const *argv, const char *const *envp) { struct filename *filename; struct linux_binprm *bprm; int fd = AT_FDCWD; int retval; /* It is non-sense for kernel threads to call execve */ if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return -EINVAL; filename = getname_kernel(kernel_filename); if (IS_ERR(filename)) return PTR_ERR(filename); bprm = alloc_bprm(fd, filename); if (IS_ERR(bprm)) { retval = PTR_ERR(bprm); goto out_ret; } retval = count_strings_kernel(argv); if (WARN_ON_ONCE(retval == 0)) retval = -EINVAL; if (retval < 0) goto out_free; bprm->argc = retval; retval = count_strings_kernel(envp); if (retval < 0) goto out_free; bprm->envc = retval; retval = bprm_stack_limits(bprm); if (retval < 0) goto out_free; retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out_free; bprm->exec = bprm->p; retval = copy_strings_kernel(bprm->envc, envp, bprm); if (retval < 0) goto out_free; retval = copy_strings_kernel(bprm->argc, argv, bprm); if (retval < 0) goto out_free; retval = bprm_execve(bprm, fd, filename, 0); out_free: free_bprm(bprm); out_ret: putname(filename); return retval; } static int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int do_execveat(int fd, struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp, int flags) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(fd, filename, argv, envp, flags); } #ifdef CONFIG_COMPAT static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int compat_do_execveat(int fd, struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp, int flags) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(fd, filename, argv, envp, flags); } #endif void set_binfmt(struct linux_binfmt *new) { struct mm_struct *mm = current->mm; if (mm->binfmt) module_put(mm->binfmt->module); mm->binfmt = new; if (new) __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); /* * set_dumpable stores three-value SUID_DUMP_* into mm->flags. */ void set_dumpable(struct mm_struct *mm, int value) { if (WARN_ON((unsigned)value > SUID_DUMP_ROOT)) return; set_mask_bits(&mm->flags, MMF_DUMPABLE_MASK, value); } SYSCALL_DEFINE3(execve, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp) { return do_execve(getname(filename), argv, envp); } SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp, int, flags) { return do_execveat(fd, getname_uflags(filename, flags), argv, envp, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp) { return compat_do_execve(getname(filename), argv, envp); } COMPAT_SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp, int, flags) { return compat_do_execveat(fd, getname_uflags(filename, flags), argv, envp, flags); } #endif #ifdef CONFIG_SYSCTL static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!error) validate_coredump_safety(); return error; } static struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { } }; static int __init init_fs_exec_sysctls(void) { register_sysctl_init("fs", fs_exec_sysctls); return 0; } fs_initcall(init_fs_exec_sysctls); #endif /* CONFIG_SYSCTL */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi.h - ACPI Interface * * Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ #include <linux/irqdomain.h> #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> #include <linux/uuid.h> #ifndef _LINUX #define _LINUX #endif #include <acpi/acpi.h> #ifdef CONFIG_ACPI #include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> #include <acpi/acpi_numa.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return adev ? adev->handle : NULL; } #define ACPI_COMPANION(dev) to_acpi_device_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) #define ACPI_HANDLE_FWNODE(fwnode) \ acpi_device_handle(to_acpi_device_node(fwnode)) static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; fwnode = kzalloc(sizeof(struct fwnode_handle), GFP_KERNEL); if (!fwnode) return NULL; fwnode_init(fwnode, &acpi_static_fwnode_ops); return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); } /** * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with * the PCI-defined class-code information * * @_cls : the class, subclass, prog-if triple for this device * @_msk : the class mask for this device * * This macro is used to create a struct acpi_device_id that matches a * specific PCI class. The .id and .driver_data fields will be left * initialized with the default value. */ #define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (_cls), .cls_msk = (_msk), static inline bool has_acpi_companion(struct device *dev) { return is_acpi_device_node(dev->fwnode); } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } static inline const char *acpi_dev_name(struct acpi_device *adev) { return dev_name(&adev->dev); } struct device *acpi_get_first_physical_node(struct acpi_device *adev); enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, ACPI_IRQ_MODEL_IOSAPIC, ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_LPIC, ACPI_IRQ_MODEL_COUNT }; extern enum acpi_irq_model_id acpi_irq_model; enum acpi_interrupt_id { ACPI_INTERRUPT_PMI = 1, ACPI_INTERRUPT_INIT, ACPI_INTERRUPT_CPEI, ACPI_INTERRUPT_COUNT }; #define ACPI_SPACE_MEM 0 enum acpi_address_range_id { ACPI_ADDRESS_RANGE_MEMORY = 1, ACPI_ADDRESS_RANGE_RESERVED = 2, ACPI_ADDRESS_RANGE_ACPI = 3, ACPI_ADDRESS_RANGE_NVS = 4, ACPI_ADDRESS_RANGE_COUNT }; /* Table Handlers */ union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; struct acpi_prmt_module_header prmt; struct acpi_cedt_header cedt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header, const unsigned long end); typedef int (*acpi_tbl_entry_handler_arg)(union acpi_subtable_headers *header, void *arg, const unsigned long end); /* Debugger support */ struct acpi_debugger_ops { int (*create_thread)(acpi_osd_exec_callback function, void *context); ssize_t (*write_log)(const char *msg); ssize_t (*read_cmd)(char *buffer, size_t length); int (*wait_command_ready)(bool single_step, char *buffer, size_t length); int (*notify_command_complete)(void); }; struct acpi_debugger { const struct acpi_debugger_ops *ops; struct module *owner; struct mutex lock; }; #ifdef CONFIG_ACPI_DEBUGGER int __init acpi_debugger_init(void); int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops); void acpi_unregister_debugger(const struct acpi_debugger_ops *ops); int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context); ssize_t acpi_debugger_write_log(const char *msg); ssize_t acpi_debugger_read_cmd(char *buffer, size_t buffer_length); int acpi_debugger_wait_command_ready(void); int acpi_debugger_notify_command_complete(void); #else static inline int acpi_debugger_init(void) { return -ENODEV; } static inline int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops) { return -ENODEV; } static inline void acpi_unregister_debugger(const struct acpi_debugger_ops *ops) { } static inline int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context) { return -ENODEV; } static inline int acpi_debugger_write_log(const char *msg) { return -ENODEV; } static inline int acpi_debugger_read_cmd(char *buffer, u32 buffer_length) { return -ENODEV; } static inline int acpi_debugger_wait_command_ready(void) { return -ENODEV; } static inline int acpi_debugger_notify_command_complete(void) { return -ENODEV; } #endif #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) struct acpi_subtable_proc { int id; acpi_tbl_entry_handler handler; acpi_tbl_entry_handler_arg handler_arg; void *arg; int count; }; void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_prepare (void); void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); #ifdef CONFIG_ACPI_TABLE_LIB #define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) #define __init_or_acpilib #define __initdata_or_acpilib #else #define EXPORT_SYMBOL_ACPI_LIB(x) #define __init_or_acpilib __init #define __initdata_or_acpilib __initdata #endif int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init_or_acpilib acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_entries_array(char *id, unsigned long table_size, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_cedt(enum acpi_cedt_type id, acpi_tbl_entry_handler_arg handler_arg, void *arg); int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); /* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); #if defined(CONFIG_X86) || defined(CONFIG_IA64) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } #endif void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); #if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) void acpi_arch_dma_setup(struct device *dev); #else static inline void acpi_arch_dma_setup(struct device *dev) { } #endif #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif static inline bool invalid_logical_cpuid(u32 cpuid) { return (int)cpuid < 0; } static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) { return phys_id == PHYS_CPUID_INVALID; } /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ struct acpi_processor_power; #ifdef CONFIG_ACPI_PROCESSOR_CSTATE bool acpi_processor_claim_cst_control(void); int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info); #else static inline bool acpi_processor_claim_cst_control(void) { return false; } static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; extern unsigned int acpi_sci_irq; extern bool acpi_no_s5; #define INVALID_ACPI_IRQ ((unsigned)-1) static inline bool acpi_sci_irq_valid(void) { return acpi_sci_irq != INVALID_ACPI_IRQ; } extern int sbf_port; extern unsigned long acpi_realmode_flags; int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); void acpi_set_irq_model(enum acpi_irq_model_id model, struct fwnode_handle *(*)(u32)); void acpi_set_gsi_to_irq_fallback(u32 (*)(u32)); struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, unsigned int size, struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data); #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else static inline int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { return -1; } #endif /* * This function undoes the effect of one call to acpi_register_gsi(). * If this matches the last registration, any IRQ resources for gsi * are freed. */ void acpi_unregister_gsi (u32 gsi); struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); #ifdef CONFIG_PCI void acpi_penalize_sci_irq(int irq, int trigger, int polarity); #else static inline void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { } #endif void acpi_pci_irq_disable (struct pci_dev *dev); extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); extern int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len); extern acpi_handle ec_get_handle(void); extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) typedef void (*wmi_notify_handler) (u32 value, void *context); extern acpi_status wmi_evaluate_method(const char *guid, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out); extern acpi_status wmi_query_block(const char *guid, u8 instance, struct acpi_buffer *out); extern acpi_status wmi_set_block(const char *guid, u8 instance, const struct acpi_buffer *in); extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); #endif /* CONFIG_ACPI_WMI */ #define ACPI_VIDEO_OUTPUT_SWITCHING 0x0001 #define ACPI_VIDEO_DEVICE_POSTING 0x0002 #define ACPI_VIDEO_ROM_AVAILABLE 0x0004 #define ACPI_VIDEO_BACKLIGHT 0x0008 #define ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR 0x0010 #define ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO 0x0020 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VENDOR 0x0040 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VIDEO 0x0080 #define ACPI_VIDEO_BACKLIGHT_DMI_VENDOR 0x0100 #define ACPI_VIDEO_BACKLIGHT_DMI_VIDEO 0x0200 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); extern int acpi_blacklisted(void); extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); /** * pxm_to_online_node - Map proximity ID to online node * @pxm: ACPI proximity ID * * This is similar to pxm_to_node(), but always returns an online * node. When the mapped node from a given proximity ID is offline, it * looks up the node distance table and returns the nearest online node. * * ACPI device drivers, which are called after the NUMA initialization has * completed in the kernel, can call this interface to obtain their device * NUMA topology from ACPI tables. Such drivers do not have to deal with * offline nodes. A node may be offline when SRAT memory entry does not exist, * or NUMA is disabled, ex. "numa=off" on x86. */ static inline int pxm_to_online_node(int pxm) { int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } #else static inline int pxm_to_online_node(int pxm) { return 0; } static inline int acpi_map_pxm_to_node(int pxm) { return 0; } static inline int acpi_get_node(acpi_handle handle) { return 0; } #endif extern int acpi_paddr_to_node(u64 start_addr, u64 size); extern int pnpacpi_disabled; #define PXM_INVAL (-1) bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, void *arg) { return acpi_dev_filter_resource_type(ares, (unsigned long)arg); } struct acpi_device *acpi_resource_consumer(struct resource *res); int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); void __init acpi_nvs_nosave_s3(void); void __init acpi_sleep_no_blacklist(void); #endif /* CONFIG_PM_SLEEP */ int acpi_register_wakeup_handler( int wake_irq, bool (*wakeup)(void *context), void *context); void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context); struct acpi_osc_context { char *uuid_str; /* UUID string */ int rev; struct acpi_buffer cap; /* list of DWORD capabilities */ struct acpi_buffer ret; /* free by caller if success */ }; acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Number of _OSC capability DWORDS depends on bridge type */ #define OSC_PCI_CAPABILITY_DWORDS 3 #define OSC_CXL_CAPABILITY_DWORDS 5 /* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ #define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ #define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ #define OSC_REQUEST_ERROR 0x00000002 /* return */ #define OSC_INVALID_UUID_ERROR 0x00000004 /* return */ #define OSC_INVALID_REVISION_ERROR 0x00000008 /* return */ #define OSC_CAPABILITIES_MASK_ERROR 0x00000010 /* return */ /* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */ #define OSC_SB_PAD_SUPPORT 0x00000001 #define OSC_SB_PPC_OST_SUPPORT 0x00000002 #define OSC_SB_PR3_SUPPORT 0x00000004 #define OSC_SB_HOTPLUG_OST_SUPPORT 0x00000008 #define OSC_SB_APEI_SUPPORT 0x00000010 #define OSC_SB_CPC_SUPPORT 0x00000020 #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc2_support_acked; extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 #define OSC_USB_DP_TUNNELING 0x00000002 #define OSC_USB_PCIE_TUNNELING 0x00000004 #define OSC_USB_XDOMAIN 0x00000008 extern u32 osc_sb_native_usb4_control; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 #define OSC_PCI_ASPM_SUPPORT 0x00000002 #define OSC_PCI_CLOCK_PM_SUPPORT 0x00000004 #define OSC_PCI_SEGMENT_GROUPS_SUPPORT 0x00000008 #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 #define OSC_PCI_SHPC_NATIVE_HP_CONTROL 0x00000002 #define OSC_PCI_EXPRESS_PME_CONTROL 0x00000004 #define OSC_PCI_EXPRESS_AER_CONTROL 0x00000008 #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 /* CXL _OSC: Capabilities DWORD 4: Support Field */ #define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 #define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 #define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 #define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 /* CXL _OSC: Capabilities DWORD 5: Control Field */ #define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_CONTROL_DWORD]; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_EXT_CONTROL_DWORD]; } #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 #define ACPI_GSB_ACCESS_ATTRIB_WORD 0x00000008 #define ACPI_GSB_ACCESS_ATTRIB_BLOCK 0x0000000A #define ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE 0x0000000B #define ACPI_GSB_ACCESS_ATTRIB_WORD_CALL 0x0000000C #define ACPI_GSB_ACCESS_ATTRIB_BLOCK_CALL 0x0000000D #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif /* _OST Source Event Code (OSPM Action) */ #define ACPI_OST_EC_OSPM_SHUTDOWN 0x100 #define ACPI_OST_EC_OSPM_EJECT 0x103 #define ACPI_OST_EC_OSPM_INSERTION 0x200 /* _OST General Processing Status Code */ #define ACPI_OST_SC_SUCCESS 0x0 #define ACPI_OST_SC_NON_SPECIFIC_FAILURE 0x1 #define ACPI_OST_SC_UNRECOGNIZED_NOTIFY 0x2 /* _OST OS Shutdown Processing (0x100) Status Code */ #define ACPI_OST_SC_OS_SHUTDOWN_DENIED 0x80 #define ACPI_OST_SC_OS_SHUTDOWN_IN_PROGRESS 0x81 #define ACPI_OST_SC_OS_SHUTDOWN_COMPLETED 0x82 #define ACPI_OST_SC_OS_SHUTDOWN_NOT_SUPPORTED 0x83 /* _OST Ejection Request (0x3, 0x103) Status Code */ #define ACPI_OST_SC_EJECT_NOT_SUPPORTED 0x80 #define ACPI_OST_SC_DEVICE_IN_USE 0x81 #define ACPI_OST_SC_DEVICE_BUSY 0x82 #define ACPI_OST_SC_EJECT_DEPENDENCY_BUSY 0x83 #define ACPI_OST_SC_EJECT_IN_PROGRESS 0x84 /* _OST Insertion Request (0x200) Status Code */ #define ACPI_OST_SC_INSERT_IN_PROGRESS 0x80 #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 enum acpi_predicate { all_versions, less_than_or_equal, equal, greater_than_or_equal, }; /* Table must be terminted by a NULL entry */ struct acpi_platform_list { char oem_id[ACPI_OEM_ID_SIZE+1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; u32 oem_revision; char *table; enum acpi_predicate pred; char *reason; u32 data; }; int acpi_match_platform_list(const struct acpi_platform_list *plat); extern void acpi_early_init(void); extern void acpi_subsystem_init(void); extern void arch_post_acpi_subsys_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data); const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { adev->flags.visited = true; } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { adev->flags.visited = false; } enum acpi_reconfig_event { ACPI_RECONFIG_DEVICE_ADD = 0, ACPI_RECONFIG_DEVICE_REMOVE, }; int acpi_reconfig_notifier_register(struct notifier_block *nb); int acpi_reconfig_notifier_unregister(struct notifier_block *nb); #ifdef CONFIG_ACPI_GTDT int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); int acpi_gtdt_map_ppi(int type); bool acpi_gtdt_c3stop(int type); int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); #endif #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER static inline void acpi_arch_set_root_pointer(u64 addr) { } #endif #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER static inline u64 acpi_arch_get_root_pointer(void) { return 0; } #endif int acpi_get_local_address(acpi_handle handle, u32 *addr); const char *acpi_get_subsystem_id(acpi_handle handle); #else /* !CONFIG_ACPI */ #define acpi_disabled 1 #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) #define ACPI_HANDLE_FWNODE(fwnode) (NULL) #define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0), #include <acpi/acpi_numa.h> struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) { return false; } static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) { return false; } struct acpi_device; static inline bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2) { return false; } static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer) { return -ENODEV; } static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { return NULL; } static inline bool acpi_reduced_hardware(void) { return false; } static inline void acpi_dev_put(struct acpi_device *adev) {} static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return false; } static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return NULL; } static inline bool has_acpi_companion(struct device *dev) { return false; } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { } static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; } static inline struct device *acpi_get_first_physical_node(struct acpi_device *adev) { return NULL; } static inline void acpi_early_init(void) { } static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { return 0; } static inline int acpi_boot_init(void) { return 0; } static inline void acpi_boot_table_prepare(void) { } static inline void acpi_boot_table_init(void) { } static inline int acpi_mps_check(void) { return 0; } static inline int acpi_check_resource_conflict(struct resource *res) { return 0; } static inline int acpi_check_region(resource_size_t start, resource_size_t n, const char *name) { return 0; } struct acpi_table_header; static inline int acpi_table_parse(char *id, int (*handler)(struct acpi_table_header *)) { return -ENODEV; } static inline int acpi_nvs_register(__u64 start, __u64 size) { return 0; } static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data) { return 0; } struct acpi_device_id; static inline const struct acpi_device_id *acpi_match_device( const struct acpi_device_id *ids, const struct device *dev) { return NULL; } static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } static inline bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv) { return false; } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { return NULL; } static inline int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; } static inline int acpi_device_modalias(struct device *dev, char *buf, int size) { return -ENODEV; } static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, const struct property_entry *properties) { return NULL; } static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) { return DEV_DMA_NOT_SUPPORTED; } static inline int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map) { return -ENODEV; } static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return 0; } static inline int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id) { return 0; } #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { } static inline int acpi_reconfig_notifier_register(struct notifier_block *nb) { return -EINVAL; } static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) { return -EINVAL; } static inline struct acpi_device *acpi_resource_consumer(struct resource *res) { return NULL; } static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) { return -ENODEV; } static inline const char *acpi_get_subsystem_id(acpi_handle handle) { return ERR_PTR(-ENODEV); } static inline int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context), void *context) { return -ENXIO; } static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } struct acpi_osc_context; static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { return 0; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { return 0; } #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_ioapic_add(acpi_handle root); #else static inline int acpi_ioapic_add(acpi_handle root) { return 0; } #endif #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, u32 val_a, u32 val_b)); acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); #ifdef CONFIG_X86 struct acpi_s2idle_dev_ops { struct list_head list_node; void (*prepare)(void); void (*check)(void); void (*restore)(void); }; int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); #endif /* CONFIG_X86 */ #ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else static inline void arch_reserve_mem_area(acpi_physical_address addr, size_t size) { } #endif /* CONFIG_X86 */ #else #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0) #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM) int acpi_dev_suspend(struct device *dev, bool wakeup); int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } static inline bool acpi_storage_d3(struct device *dev) { return false; } static inline bool acpi_dev_state_d0(struct device *dev) { return true; } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); void acpi_ec_mark_gpe_for_wake(void); void acpi_ec_set_gpe_wake_mask(u8 action); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status); #else /* !CONFIG_ACPI */ static inline __printf(3, 4) void acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} static inline void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status) {} #endif /* !CONFIG_ACPI */ #if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG) __printf(3, 4) void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...); #endif /* * acpi_handle_<level>: Print message with ACPI prefix and object path * * These interfaces acquire the global namespace mutex to obtain an object * path. In interrupt context, it shows the object path as <n/a>. */ #define acpi_handle_emerg(handle, fmt, ...) \ acpi_handle_printk(KERN_EMERG, handle, fmt, ##__VA_ARGS__) #define acpi_handle_alert(handle, fmt, ...) \ acpi_handle_printk(KERN_ALERT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_crit(handle, fmt, ...) \ acpi_handle_printk(KERN_CRIT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_err(handle, fmt, ...) \ acpi_handle_printk(KERN_ERR, handle, fmt, ##__VA_ARGS__) #define acpi_handle_warn(handle, fmt, ...) \ acpi_handle_printk(KERN_WARNING, handle, fmt, ##__VA_ARGS__) #define acpi_handle_notice(handle, fmt, ...) \ acpi_handle_printk(KERN_NOTICE, handle, fmt, ##__VA_ARGS__) #define acpi_handle_info(handle, fmt, ...) \ acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__) #if defined(DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__) #else #if defined(CONFIG_DYNAMIC_DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ _dynamic_func_call(fmt, __acpi_handle_debug, \ handle, pr_fmt(fmt), ##__VA_ARGS__) #else #define acpi_handle_debug(handle, fmt, ...) \ ({ \ if (0) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); \ 0; \ }) #endif #endif #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, bool *wake_capable) { return -ENXIO; } #endif static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, bool *wake_capable) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, NR_FWNODE_REFERENCE_ARGS, args); } static inline bool acpi_dev_has_props(const struct acpi_device *adev) { return !list_empty(&adev->data.properties); } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties); int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); #define ACPI_TABLE_ID_LEN 5 /** * struct acpi_probe_entry - boot-time probing entry * @id: ACPI table name * @type: Optional subtable type to match * (if @id contains subtables) * @subtable_valid: Optional callback to check the validity of * the subtable * @probe_table: Callback to the driver being probed when table * match is successful * @probe_subtbl: Callback to the driver being probed when table and * subtable match (and optional callback is successful) * @driver_data: Sideband data provided back to the driver */ struct acpi_probe_entry { __u8 id[ACPI_TABLE_ID_LEN]; __u8 type; acpi_probe_entry_validate_subtbl subtable_valid; union { acpi_tbl_table_handler probe_table; acpi_tbl_entry_handler probe_subtbl; }; kernel_ulong_t driver_data; }; #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_table = fn, \ .driver_data = data, \ } #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_subtbl = fn, \ .driver_data = data, \ } #define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table #define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end int __acpi_probe_device_table(struct acpi_probe_entry *start, int nr); #define acpi_probe_device_table(t) \ ({ \ extern struct acpi_probe_entry ACPI_PROBE_TABLE(t), \ ACPI_PROBE_TABLE_END(t); \ __acpi_probe_device_table(&ACPI_PROBE_TABLE(t), \ (&ACPI_PROBE_TABLE_END(t) - \ &ACPI_PROBE_TABLE(t))); \ }) #else static inline int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return -ENXIO; } static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { return NULL; } static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) { return -ENXIO; } #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ (void *) subtable, \ (void *) valid, \ (void *) fn, \ (void *) data } #define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif #ifdef CONFIG_ACPI_TABLE_UPGRADE void acpi_table_upgrade(void); #else static inline void acpi_table_upgrade(void) { } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_ACPI_WATCHDOG) extern bool acpi_has_watchdog(void); #else static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE extern bool qdf2400_e44_present; int acpi_parse_spcr(bool enable_earlycon, bool enable_console); #else static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) { return 0; } #endif #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_LPIT int lpit_read_residency_count_address(u64 *address); #else static inline int lpit_read_residency_count_address(u64 *address) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } static inline int find_acpi_cpu_topology_cluster(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); #else static inline void acpi_init_pcc(void) { } #endif #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); #else static inline void acpi_device_notify(struct device *dev) { } static inline void acpi_device_notify_remove(struct device *dev) { } #endif #endif /*_LINUX_ACPI_H*/ |
| 65 65 65 65 65 65 65 4 3 1 30 30 6 30 30 2128 2024 411 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netprio_cgroup.c Priority Control Group * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/atomic.h> #include <linux/sched/task.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/netprio_cgroup.h> #include <linux/fdtable.h> /* * netprio allocates per-net_device priomap array which is indexed by * css->id. Limiting css ID to 16bits doesn't lose anything. */ #define NETPRIO_ID_MAX USHRT_MAX #define PRIOMAP_MIN_SZ 128 /* * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ static int extend_netdev_table(struct net_device *dev, u32 target_idx) { struct netprio_map *old, *new; size_t new_sz, new_len; /* is the existing priomap large enough? */ old = rtnl_dereference(dev->priomap); if (old && old->priomap_len > target_idx) return 0; /* * Determine the new size. Let's keep it power-of-two. We start * from PRIOMAP_MIN_SZ and double it until it's large enough to * accommodate @target_idx. */ new_sz = PRIOMAP_MIN_SZ; while (true) { new_len = (new_sz - offsetof(struct netprio_map, priomap)) / sizeof(new->priomap[0]); if (new_len > target_idx) break; new_sz *= 2; /* overflowed? */ if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) return -ENOSPC; } /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); if (!new) return -ENOMEM; if (old) memcpy(new->priomap, old->priomap, old->priomap_len * sizeof(old->priomap[0])); new->priomap_len = new_len; /* install the new priomap */ rcu_assign_pointer(dev->priomap, new); if (old) kfree_rcu(old, rcu); return 0; } /** * netprio_prio - return the effective netprio of a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * * Should be called under RCU read or rtnl lock. */ static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; return 0; } /** * netprio_set_prio - set netprio on a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * @prio: prio to set * * Set netprio to @prio on @css-@dev pair. Should be called under rtnl * lock and may fail under memory pressure for non-zero @prio. */ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; int id = css->id; int ret; /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); if (!prio && (!map || map->priomap_len <= id)) return 0; ret = extend_netdev_table(dev, id); if (ret) return ret; map = rtnl_dereference(dev->priomap); map->priomap[id] = prio; return 0; } static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *parent_css = css->parent; struct net_device *dev; int ret = 0; if (css->id > NETPRIO_ID_MAX) return -ENOSPC; if (!parent_css) return 0; rtnl_lock(); /* * Inherit prios from the parent. As all prios are set during * onlining, there is no need to clear them on offline. */ for_each_netdev(&init_net, dev) { u32 prio = netprio_prio(parent_css, dev); ret = netprio_set_prio(css, dev, prio); if (ret) break; } rtnl_unlock(); return ret; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css); } static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { return css->id; } static int read_priomap(struct seq_file *sf, void *v) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) seq_printf(sf, "%s %u\n", dev->name, netprio_prio(seq_css(sf), dev)); rcu_read_unlock(); return 0; } static ssize_t write_priomap(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; int ret; if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) return -ENODEV; rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); rtnl_unlock(); dev_put(dev); return ret ?: nbytes; } static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); return 0; } static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); } } static struct cftype ss_files[] = { { .name = "prioidx", .read_u64 = read_prioidx, }, { .name = "ifpriomap", .seq_show = read_priomap, .write = write_priomap, }, { } /* terminate */ }; struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, .legacy_cftypes = ss_files, }; static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* * Note this is called with rtnl_lock held so we have update side * protection on our rcu assignments */ switch (event) { case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); if (old) kfree_rcu(old, rcu); break; } return NOTIFY_DONE; } static struct notifier_block netprio_device_notifier = { .notifier_call = netprio_device_event }; static int __init init_cgroup_netprio(void) { register_netdevice_notifier(&netprio_device_notifier); return 0; } subsys_initcall(init_cgroup_netprio); |
| 2128 2128 2126 2128 288 1 1 1 2 2 2 1 1 1 1 1 7 1 2 1 2 11 11 11 11 2 2 2 11 1 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 | /* * This file implement the Wireless Extensions core API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * * (As all part of the Linux kernel, this file is GPL) */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/wireless.h> #include <linux/uaccess.h> #include <linux/export.h> #include <net/cfg80211.h> #include <net/iw_handler.h> #include <net/netlink.h> #include <net/wext.h> #include <net/net_namespace.h> typedef int (*wext_ioctl_func)(struct net_device *, struct iwreq *, unsigned int, struct iw_request_info *, iw_handler); /* * Meta-data about all the standard Wireless Extension request we * know about. */ static const struct iw_ioctl_description standard_ioctl[] = { [IW_IOCTL_IDX(SIOCSIWCOMMIT)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWNAME)] = { .header_type = IW_HEADER_TYPE_CHAR, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWNWID)] = { .header_type = IW_HEADER_TYPE_PARAM, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWNWID)] = { .header_type = IW_HEADER_TYPE_PARAM, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWFREQ)] = { .header_type = IW_HEADER_TYPE_FREQ, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWFREQ)] = { .header_type = IW_HEADER_TYPE_FREQ, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWMODE)] = { .header_type = IW_HEADER_TYPE_UINT, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWMODE)] = { .header_type = IW_HEADER_TYPE_UINT, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWSENS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWSENS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWRANGE)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWRANGE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_range), .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWPRIV)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWPRIV)] = { /* (handled directly by us) */ .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct iw_priv_args), .max_tokens = 16, .flags = IW_DESCR_FLAG_NOMAX, }, [IW_IOCTL_IDX(SIOCSIWSTATS)] = { .header_type = IW_HEADER_TYPE_NULL, }, [IW_IOCTL_IDX(SIOCGIWSTATS)] = { /* (handled directly by us) */ .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_statistics), .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr), .max_tokens = IW_MAX_SPY, }, [IW_IOCTL_IDX(SIOCGIWSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr) + sizeof(struct iw_quality), .max_tokens = IW_MAX_SPY, }, [IW_IOCTL_IDX(SIOCSIWTHRSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct iw_thrspy), .min_tokens = 1, .max_tokens = 1, }, [IW_IOCTL_IDX(SIOCGIWTHRSPY)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct iw_thrspy), .min_tokens = 1, .max_tokens = 1, }, [IW_IOCTL_IDX(SIOCSIWAP)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_IOCTL_IDX(SIOCGIWAP)] = { .header_type = IW_HEADER_TYPE_ADDR, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWMLME)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_mlme), .max_tokens = sizeof(struct iw_mlme), }, [IW_IOCTL_IDX(SIOCGIWAPLIST)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr) + sizeof(struct iw_quality), .max_tokens = IW_MAX_AP, .flags = IW_DESCR_FLAG_NOMAX, }, [IW_IOCTL_IDX(SIOCSIWSCAN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = 0, .max_tokens = sizeof(struct iw_scan_req), }, [IW_IOCTL_IDX(SIOCGIWSCAN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_SCAN_MAX_DATA, .flags = IW_DESCR_FLAG_NOMAX, }, [IW_IOCTL_IDX(SIOCSIWESSID)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_EVENT, }, [IW_IOCTL_IDX(SIOCGIWESSID)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_DUMP, }, [IW_IOCTL_IDX(SIOCSIWNICKN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, }, [IW_IOCTL_IDX(SIOCGIWNICKN)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ESSID_MAX_SIZE, }, [IW_IOCTL_IDX(SIOCSIWRATE)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWRATE)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWRTS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWRTS)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWFRAG)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWFRAG)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWTXPOW)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWTXPOW)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWRETRY)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWRETRY)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWENCODE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ENCODING_TOKEN_MAX, .flags = IW_DESCR_FLAG_EVENT | IW_DESCR_FLAG_RESTRICT, }, [IW_IOCTL_IDX(SIOCGIWENCODE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_ENCODING_TOKEN_MAX, .flags = IW_DESCR_FLAG_DUMP | IW_DESCR_FLAG_RESTRICT, }, [IW_IOCTL_IDX(SIOCSIWPOWER)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWPOWER)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWGENIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_IOCTL_IDX(SIOCGIWGENIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_IOCTL_IDX(SIOCSIWAUTH)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCGIWAUTH)] = { .header_type = IW_HEADER_TYPE_PARAM, }, [IW_IOCTL_IDX(SIOCSIWENCODEEXT)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_encode_ext), .max_tokens = sizeof(struct iw_encode_ext) + IW_ENCODING_TOKEN_MAX, }, [IW_IOCTL_IDX(SIOCGIWENCODEEXT)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_encode_ext), .max_tokens = sizeof(struct iw_encode_ext) + IW_ENCODING_TOKEN_MAX, }, [IW_IOCTL_IDX(SIOCSIWPMKSA)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .min_tokens = sizeof(struct iw_pmksa), .max_tokens = sizeof(struct iw_pmksa), }, }; static const unsigned int standard_ioctl_num = ARRAY_SIZE(standard_ioctl); /* * Meta-data about all the additional standard Wireless Extension events * we know about. */ static const struct iw_ioctl_description standard_event[] = { [IW_EVENT_IDX(IWEVTXDROP)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_EVENT_IDX(IWEVQUAL)] = { .header_type = IW_HEADER_TYPE_QUAL, }, [IW_EVENT_IDX(IWEVCUSTOM)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_CUSTOM_MAX, }, [IW_EVENT_IDX(IWEVREGISTERED)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_EVENT_IDX(IWEVEXPIRED)] = { .header_type = IW_HEADER_TYPE_ADDR, }, [IW_EVENT_IDX(IWEVGENIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_EVENT_IDX(IWEVMICHAELMICFAILURE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_michaelmicfailure), }, [IW_EVENT_IDX(IWEVASSOCREQIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_EVENT_IDX(IWEVASSOCRESPIE)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = IW_GENERIC_IE_MAX, }, [IW_EVENT_IDX(IWEVPMKIDCAND)] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, .max_tokens = sizeof(struct iw_pmkid_cand), }, }; static const unsigned int standard_event_num = ARRAY_SIZE(standard_event); /* Size (in bytes) of various events */ static const int event_type_size[] = { IW_EV_LCP_LEN, /* IW_HEADER_TYPE_NULL */ 0, IW_EV_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ 0, IW_EV_UINT_LEN, /* IW_HEADER_TYPE_UINT */ IW_EV_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ IW_EV_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ 0, IW_EV_POINT_LEN, /* Without variable payload */ IW_EV_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ IW_EV_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ }; #ifdef CONFIG_COMPAT static const int compat_event_type_size[] = { IW_EV_COMPAT_LCP_LEN, /* IW_HEADER_TYPE_NULL */ 0, IW_EV_COMPAT_CHAR_LEN, /* IW_HEADER_TYPE_CHAR */ 0, IW_EV_COMPAT_UINT_LEN, /* IW_HEADER_TYPE_UINT */ IW_EV_COMPAT_FREQ_LEN, /* IW_HEADER_TYPE_FREQ */ IW_EV_COMPAT_ADDR_LEN, /* IW_HEADER_TYPE_ADDR */ 0, IW_EV_COMPAT_POINT_LEN, /* Without variable payload */ IW_EV_COMPAT_PARAM_LEN, /* IW_HEADER_TYPE_PARAM */ IW_EV_COMPAT_QUAL_LEN, /* IW_HEADER_TYPE_QUAL */ }; #endif /* IW event code */ void wireless_nlevent_flush(void) { struct sk_buff *skb; struct net *net; down_read(&net_rwsem); for_each_net(net) { while ((skb = skb_dequeue(&net->wext_nlevents))) rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); } up_read(&net_rwsem); } EXPORT_SYMBOL_GPL(wireless_nlevent_flush); static int wext_netdev_notifier_call(struct notifier_block *nb, unsigned long state, void *ptr) { /* * When a netdev changes state in any way, flush all pending messages * to avoid them going out in a strange order, e.g. RTM_NEWLINK after * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() * or similar - all of which could otherwise happen due to delays from * schedule_work(). */ wireless_nlevent_flush(); return NOTIFY_OK; } static struct notifier_block wext_netdev_notifier = { .notifier_call = wext_netdev_notifier_call, }; static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); return 0; } static void __net_exit wext_pernet_exit(struct net *net) { skb_queue_purge(&net->wext_nlevents); } static struct pernet_operations wext_pernet_ops = { .init = wext_pernet_init, .exit = wext_pernet_exit, }; static int __init wireless_nlevent_init(void) { int err = register_pernet_subsys(&wext_pernet_ops); if (err) return err; err = register_netdevice_notifier(&wext_netdev_notifier); if (err) unregister_pernet_subsys(&wext_pernet_ops); return err; } subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { wireless_nlevent_flush(); } static DECLARE_WORK(wireless_nlevent_work, wireless_nlevent_process); static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, struct sk_buff *skb) { struct ifinfomsg *r; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, 0, 0, RTM_NEWLINK, sizeof(*r), 0); if (!nlh) return NULL; r = nlmsg_data(nlh); r->ifi_family = AF_UNSPEC; r->__ifi_pad = 0; r->ifi_type = dev->type; r->ifi_index = dev->ifindex; r->ifi_flags = dev_get_flags(dev); r->ifi_change = 0; /* Wireless changes don't affect those flags */ if (nla_put_string(skb, IFLA_IFNAME, dev->name)) goto nla_put_failure; return nlh; nla_put_failure: nlmsg_cancel(skb, nlh); return NULL; } /* * Main event dispatcher. Called from other parts and drivers. * Send the event on the appropriate channels. * May be called from interrupt context. */ void wireless_send_event(struct net_device * dev, unsigned int cmd, union iwreq_data * wrqu, const char * extra) { const struct iw_ioctl_description * descr = NULL; int extra_len = 0; struct iw_event *event; /* Mallocated whole event */ int event_len; /* Its size */ int hdr_len; /* Size of the event header */ int wrqu_off = 0; /* Offset in wrqu */ /* Don't "optimise" the following variable, it will crash */ unsigned int cmd_index; /* *MUST* be unsigned */ struct sk_buff *skb; struct nlmsghdr *nlh; struct nlattr *nla; #ifdef CONFIG_COMPAT struct __compat_iw_event *compat_event; struct compat_iw_point compat_wrqu; struct sk_buff *compskb; int ptr_len; #endif /* * Nothing in the kernel sends scan events with data, be safe. * This is necessary because we cannot fix up scan event data * for compat, due to being contained in 'extra', but normally * applications are required to retrieve the scan data anyway * and no data is included in the event, this codifies that * practice. */ if (WARN_ON(cmd == SIOCGIWSCAN && extra)) extra = NULL; /* Get the description of the Event */ if (cmd <= SIOCIWLAST) { cmd_index = IW_IOCTL_IDX(cmd); if (cmd_index < standard_ioctl_num) descr = &(standard_ioctl[cmd_index]); } else { cmd_index = IW_EVENT_IDX(cmd); if (cmd_index < standard_event_num) descr = &(standard_event[cmd_index]); } /* Don't accept unknown events */ if (descr == NULL) { /* Note : we don't return an error to the driver, because * the driver would not know what to do about it. It can't * return an error to the user, because the event is not * initiated by a user request. * The best the driver could do is to log an error message. * We will do it ourselves instead... */ netdev_err(dev, "(WE) : Invalid/Unknown Wireless Event (0x%04X)\n", cmd); return; } /* Check extra parameters and set extra_len */ if (descr->header_type == IW_HEADER_TYPE_POINT) { /* Check if number of token fits within bounds */ if (wrqu->data.length > descr->max_tokens) { netdev_err(dev, "(WE) : Wireless Event (cmd=0x%04X) too big (%d)\n", cmd, wrqu->data.length); return; } if (wrqu->data.length < descr->min_tokens) { netdev_err(dev, "(WE) : Wireless Event (cmd=0x%04X) too small (%d)\n", cmd, wrqu->data.length); return; } /* Calculate extra_len - extra is NULL for restricted events */ if (extra != NULL) extra_len = wrqu->data.length * descr->token_size; /* Always at an offset in wrqu */ wrqu_off = IW_EV_POINT_OFF; } /* Total length of the event */ hdr_len = event_type_size[descr->header_type]; event_len = hdr_len + extra_len; /* * The problem for 64/32 bit. * * On 64-bit, a regular event is laid out as follows: * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | * | event.len | event.cmd | p a d d i n g | * | wrqu data ... (with the correct size) | * * This padding exists because we manipulate event->u, * and 'event' is not packed. * * An iw_point event is laid out like this instead: * | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | * | event.len | event.cmd | p a d d i n g | * | iwpnt.len | iwpnt.flg | p a d d i n g | * | extra data ... * * The second padding exists because struct iw_point is extended, * but this depends on the platform... * * On 32-bit, all the padding shouldn't be there. */ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; /* Send via the RtNetlink event channel */ nlh = rtnetlink_ifinfo_prep(dev, skb); if (WARN_ON(!nlh)) { kfree_skb(skb); return; } /* Add the wireless events in the netlink packet */ nla = nla_reserve(skb, IFLA_WIRELESS, event_len); if (!nla) { kfree_skb(skb); return; } event = nla_data(nla); /* Fill event - first clear to avoid data leaking */ memset(event, 0, hdr_len); event->len = event_len; event->cmd = cmd; memcpy(&event->u, ((char *) wrqu) + wrqu_off, hdr_len - IW_EV_LCP_LEN); if (extra_len) memcpy(((char *) event) + hdr_len, extra, extra_len); nlmsg_end(skb, nlh); #ifdef CONFIG_COMPAT hdr_len = compat_event_type_size[descr->header_type]; /* ptr_len is remaining size in event header apart from LCP */ ptr_len = hdr_len - IW_EV_COMPAT_LCP_LEN; event_len = hdr_len + extra_len; compskb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!compskb) { kfree_skb(skb); return; } /* Send via the RtNetlink event channel */ nlh = rtnetlink_ifinfo_prep(dev, compskb); if (WARN_ON(!nlh)) { kfree_skb(skb); kfree_skb(compskb); return; } /* Add the wireless events in the netlink packet */ nla = nla_reserve(compskb, IFLA_WIRELESS, event_len); if (!nla) { kfree_skb(skb); kfree_skb(compskb); return; } compat_event = nla_data(nla); compat_event->len = event_len; compat_event->cmd = cmd; if (descr->header_type == IW_HEADER_TYPE_POINT) { compat_wrqu.length = wrqu->data.length; compat_wrqu.flags = wrqu->data.flags; memcpy(compat_event->ptr_bytes, ((char *)&compat_wrqu) + IW_EV_COMPAT_POINT_OFF, ptr_len); if (extra_len) memcpy(&compat_event->ptr_bytes[ptr_len], extra, extra_len); } else { /* extra_len must be zero, so no if (extra) needed */ memcpy(compat_event->ptr_bytes, wrqu, ptr_len); } nlmsg_end(compskb, nlh); skb_shinfo(skb)->frag_list = compskb; #endif skb_queue_tail(&dev_net(dev)->wext_nlevents, skb); schedule_work(&wireless_nlevent_work); } EXPORT_SYMBOL(wireless_send_event); /* IW handlers */ struct iw_statistics *get_wireless_stats(struct net_device *dev) { #ifdef CONFIG_WIRELESS_EXT if ((dev->wireless_handlers != NULL) && (dev->wireless_handlers->get_wireless_stats != NULL)) return dev->wireless_handlers->get_wireless_stats(dev); #endif #ifdef CONFIG_CFG80211_WEXT if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy && dev->ieee80211_ptr->wiphy->wext && dev->ieee80211_ptr->wiphy->wext->get_wireless_stats) return dev->ieee80211_ptr->wiphy->wext->get_wireless_stats(dev); #endif /* not found */ return NULL; } /* noinline to avoid a bogus warning with -O3 */ static noinline int iw_handler_get_iwstats(struct net_device * dev, struct iw_request_info * info, union iwreq_data * wrqu, char * extra) { /* Get stats from the driver */ struct iw_statistics *stats; stats = get_wireless_stats(dev); if (stats) { /* Copy statistics to extra */ memcpy(extra, stats, sizeof(struct iw_statistics)); wrqu->data.length = sizeof(struct iw_statistics); /* Check if we need to clear the updated flag */ if (wrqu->data.flags != 0) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; return 0; } else return -EOPNOTSUPP; } static iw_handler get_handler(struct net_device *dev, unsigned int cmd) { /* Don't "optimise" the following variable, it will crash */ unsigned int index; /* *MUST* be unsigned */ const struct iw_handler_def *handlers = NULL; #ifdef CONFIG_CFG80211_WEXT if (dev->ieee80211_ptr && dev->ieee80211_ptr->wiphy) handlers = dev->ieee80211_ptr->wiphy->wext; #endif #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) handlers = dev->wireless_handlers; #endif if (!handlers) return NULL; /* Try as a standard command */ index = IW_IOCTL_IDX(cmd); if (index < handlers->num_standard) return handlers->standard[index]; #ifdef CONFIG_WEXT_PRIV /* Try as a private command */ index = cmd - SIOCIWFIRSTPRIV; if (index < handlers->num_private) return handlers->private[index]; #endif /* Not found */ return NULL; } static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, const struct iw_ioctl_description *descr, iw_handler handler, struct net_device *dev, struct iw_request_info *info) { int err, extra_size, user_length = 0, essid_compat = 0; char *extra; /* Calculate space needed by arguments. Always allocate * for max space. */ extra_size = descr->max_tokens * descr->token_size; /* Check need for ESSID compatibility for WE < 21 */ switch (cmd) { case SIOCSIWESSID: case SIOCGIWESSID: case SIOCSIWNICKN: case SIOCGIWNICKN: if (iwp->length == descr->max_tokens + 1) essid_compat = 1; else if (IW_IS_SET(cmd) && (iwp->length != 0)) { char essid[IW_ESSID_MAX_SIZE + 1]; unsigned int len; len = iwp->length * descr->token_size; if (len > IW_ESSID_MAX_SIZE) return -EFAULT; err = copy_from_user(essid, iwp->pointer, len); if (err) return -EFAULT; if (essid[iwp->length - 1] == '\0') essid_compat = 1; } break; default: break; } iwp->length -= essid_compat; /* Check what user space is giving us */ if (IW_IS_SET(cmd)) { /* Check NULL pointer */ if (!iwp->pointer && iwp->length != 0) return -EFAULT; /* Check if number of token fits within bounds */ if (iwp->length > descr->max_tokens) return -E2BIG; if (iwp->length < descr->min_tokens) return -EINVAL; } else { /* Check NULL pointer */ if (!iwp->pointer) return -EFAULT; /* Save user space buffer size for checking */ user_length = iwp->length; /* Don't check if user_length > max to allow forward * compatibility. The test user_length < min is * implied by the test at the end. */ /* Support for very large requests */ if ((descr->flags & IW_DESCR_FLAG_NOMAX) && (user_length > descr->max_tokens)) { /* Allow userspace to GET more than max so * we can support any size GET requests. * There is still a limit : -ENOMEM. */ extra_size = user_length * descr->token_size; /* Note : user_length is originally a __u16, * and token_size is controlled by us, * so extra_size won't get negative and * won't overflow... */ } } /* Sanity-check to ensure we never end up _allocating_ zero * bytes of data for extra. */ if (extra_size <= 0) return -EFAULT; /* kzalloc() ensures NULL-termination for essid_compat. */ extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) return -ENOMEM; /* If it is a SET, get all the extra data in here */ if (IW_IS_SET(cmd) && (iwp->length != 0)) { if (copy_from_user(extra, iwp->pointer, iwp->length * descr->token_size)) { err = -EFAULT; goto out; } if (cmd == SIOCSIWENCODEEXT) { struct iw_encode_ext *ee = (void *) extra; if (iwp->length < sizeof(*ee) + ee->key_len) { err = -EFAULT; goto out; } } } if (IW_IS_GET(cmd) && !(descr->flags & IW_DESCR_FLAG_NOMAX)) { /* * If this is a GET, but not NOMAX, it means that the extra * data is not bounded by userspace, but by max_tokens. Thus * set the length to max_tokens. This matches the extra data * allocation. * The driver should fill it with the number of tokens it * provided, and it may check iwp->length rather than having * knowledge of max_tokens. If the driver doesn't change the * iwp->length, this ioctl just copies back max_token tokens * filled with zeroes. Hopefully the driver isn't claiming * them to be valid data. */ iwp->length = descr->max_tokens; } err = handler(dev, info, (union iwreq_data *) iwp, extra); iwp->length += essid_compat; /* If we have something to return to the user */ if (!err && IW_IS_GET(cmd)) { /* Check if there is enough buffer up there */ if (user_length < iwp->length) { err = -E2BIG; goto out; } if (copy_to_user(iwp->pointer, extra, iwp->length * descr->token_size)) { err = -EFAULT; goto out; } } /* Generate an event to notify listeners of the change */ if ((descr->flags & IW_DESCR_FLAG_EVENT) && ((err == 0) || (err == -EIWCOMMIT))) { union iwreq_data *data = (union iwreq_data *) iwp; if (descr->flags & IW_DESCR_FLAG_RESTRICT) /* If the event is restricted, don't * export the payload. */ wireless_send_event(dev, cmd, data, NULL); else wireless_send_event(dev, cmd, data, extra); } out: kfree(extra); return err; } /* * Call the commit handler in the driver * (if exist and if conditions are right) * * Note : our current commit strategy is currently pretty dumb, * but we will be able to improve on that... * The goal is to try to agreagate as many changes as possible * before doing the commit. Drivers that will define a commit handler * are usually those that need a reset after changing parameters, so * we want to minimise the number of reset. * A cool idea is to use a timer : at each "set" command, we re-set the * timer, when the timer eventually fires, we call the driver. * Hopefully, more on that later. * * Also, I'm waiting to see how many people will complain about the * netif_running(dev) test. I'm open on that one... * Hopefully, the driver will remember to do a commit in "open()" ;-) */ int call_commit_handler(struct net_device *dev) { #ifdef CONFIG_WIRELESS_EXT if (netif_running(dev) && dev->wireless_handlers && dev->wireless_handlers->standard[0]) /* Call the commit handler on the driver */ return dev->wireless_handlers->standard[0](dev, NULL, NULL, NULL); else return 0; /* Command completed successfully */ #else /* cfg80211 has no commit */ return 0; #endif } /* * Main IOCTl dispatcher. * Check the type of IOCTL and call the appropriate wrapper... */ static int wireless_process_ioctl(struct net *net, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, wext_ioctl_func standard, wext_ioctl_func private) { struct net_device *dev; iw_handler handler; /* Permissions are already checked in dev_ioctl() before calling us. * The copy_to/from_user() of ifr is also dealt with in there */ /* Make sure the device exist */ if ((dev = __dev_get_by_name(net, iwr->ifr_name)) == NULL) return -ENODEV; /* A bunch of special cases, then the generic case... * Note that 'cmd' is already filtered in dev_ioctl() with * (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) */ if (cmd == SIOCGIWSTATS) return standard(dev, iwr, cmd, info, &iw_handler_get_iwstats); #ifdef CONFIG_WEXT_PRIV if (cmd == SIOCGIWPRIV && dev->wireless_handlers) return standard(dev, iwr, cmd, info, iw_handler_get_private); #endif /* Basic check */ if (!netif_device_present(dev)) return -ENODEV; /* New driver API : try to find the handler */ handler = get_handler(dev, cmd); if (handler) { /* Standard and private are not the same */ if (cmd < SIOCIWFIRSTPRIV) return standard(dev, iwr, cmd, info, handler); else if (private) return private(dev, iwr, cmd, info, handler); } return -EOPNOTSUPP; } /* If command is `set a parameter', or `get the encoding parameters', * check if the user has the right to do it. */ static int wext_permission_check(unsigned int cmd) { if ((IW_IS_SET(cmd) || cmd == SIOCGIWENCODE || cmd == SIOCGIWENCODEEXT) && !capable(CAP_NET_ADMIN)) return -EPERM; return 0; } /* entry point from dev ioctl */ static int wext_ioctl_dispatch(struct net *net, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, wext_ioctl_func standard, wext_ioctl_func private) { int ret = wext_permission_check(cmd); if (ret) return ret; dev_load(net, iwr->ifr_name); rtnl_lock(); ret = wireless_process_ioctl(net, iwr, cmd, info, standard, private); rtnl_unlock(); return ret; } /* * Wrapper to call a standard Wireless Extension handler. * We do various checks and also take care of moving data between * user space and kernel space. */ static int ioctl_standard_call(struct net_device * dev, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, iw_handler handler) { const struct iw_ioctl_description * descr; int ret = -EINVAL; /* Get the description of the IOCTL */ if (IW_IOCTL_IDX(cmd) >= standard_ioctl_num) return -EOPNOTSUPP; descr = &(standard_ioctl[IW_IOCTL_IDX(cmd)]); /* Check if we have a pointer to user space data or not */ if (descr->header_type != IW_HEADER_TYPE_POINT) { /* No extra arguments. Trivial to handle */ ret = handler(dev, info, &(iwr->u), NULL); /* Generate an event to notify listeners of the change */ if ((descr->flags & IW_DESCR_FLAG_EVENT) && ((ret == 0) || (ret == -EIWCOMMIT))) wireless_send_event(dev, cmd, &(iwr->u), NULL); } else { ret = ioctl_standard_iw_point(&iwr->u.data, cmd, descr, handler, dev, info); } /* Call commit handler if needed and defined */ if (ret == -EIWCOMMIT) ret = call_commit_handler(dev); /* Here, we will generate the appropriate event if needed */ return ret; } int wext_handle_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct iw_request_info info = { .cmd = cmd, .flags = 0 }; struct iwreq iwr; int ret; if (copy_from_user(&iwr, arg, sizeof(iwr))) return -EFAULT; iwr.ifr_name[sizeof(iwr.ifr_name) - 1] = 0; ret = wext_ioctl_dispatch(net, &iwr, cmd, &info, ioctl_standard_call, ioctl_private_call); if (ret >= 0 && IW_IS_GET(cmd) && copy_to_user(arg, &iwr, sizeof(struct iwreq))) return -EFAULT; return ret; } #ifdef CONFIG_COMPAT static int compat_standard_call(struct net_device *dev, struct iwreq *iwr, unsigned int cmd, struct iw_request_info *info, iw_handler handler) { const struct iw_ioctl_description *descr; struct compat_iw_point *iwp_compat; struct iw_point iwp; int err; descr = standard_ioctl + IW_IOCTL_IDX(cmd); if (descr->header_type != IW_HEADER_TYPE_POINT) return ioctl_standard_call(dev, iwr, cmd, info, handler); iwp_compat = (struct compat_iw_point *) &iwr->u.data; iwp.pointer = compat_ptr(iwp_compat->pointer); iwp.length = iwp_compat->length; iwp.flags = iwp_compat->flags; err = ioctl_standard_iw_point(&iwp, cmd, descr, handler, dev, info); iwp_compat->pointer = ptr_to_compat(iwp.pointer); iwp_compat->length = iwp.length; iwp_compat->flags = iwp.flags; return err; } int compat_wext_handle_ioctl(struct net *net, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct iw_request_info info; struct iwreq iwr; char *colon; int ret; if (copy_from_user(&iwr, argp, sizeof(struct iwreq))) return -EFAULT; iwr.ifr_name[IFNAMSIZ-1] = 0; colon = strchr(iwr.ifr_name, ':'); if (colon) *colon = 0; info.cmd = cmd; info.flags = IW_REQUEST_FLAG_COMPAT; ret = wext_ioctl_dispatch(net, &iwr, cmd, &info, compat_standard_call, compat_private_call); if (ret >= 0 && IW_IS_GET(cmd) && copy_to_user(argp, &iwr, sizeof(struct iwreq))) return -EFAULT; return ret; } #endif char *iwe_stream_add_event(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, int event_len) { int lcp_len = iwe_stream_lcp_len(info); event_len = iwe_stream_event_len_adjust(info, event_len); /* Check if it's possible */ if (likely((stream + event_len) < ends)) { iwe->len = event_len; /* Beware of alignement issues on 64 bits */ memcpy(stream, (char *) iwe, IW_EV_LCP_PK_LEN); memcpy(stream + lcp_len, &iwe->u, event_len - lcp_len); stream += event_len; } return stream; } EXPORT_SYMBOL(iwe_stream_add_event); char *iwe_stream_add_point(struct iw_request_info *info, char *stream, char *ends, struct iw_event *iwe, char *extra) { int event_len = iwe_stream_point_len(info) + iwe->u.data.length; int point_len = iwe_stream_point_len(info); int lcp_len = iwe_stream_lcp_len(info); /* Check if it's possible */ if (likely((stream + event_len) < ends)) { iwe->len = event_len; memcpy(stream, (char *) iwe, IW_EV_LCP_PK_LEN); memcpy(stream + lcp_len, ((char *) &iwe->u) + IW_EV_POINT_OFF, IW_EV_POINT_PK_LEN - IW_EV_LCP_PK_LEN); if (iwe->u.data.length && extra) memcpy(stream + point_len, extra, iwe->u.data.length); stream += event_len; } return stream; } EXPORT_SYMBOL(iwe_stream_add_point); char *iwe_stream_add_value(struct iw_request_info *info, char *event, char *value, char *ends, struct iw_event *iwe, int event_len) { int lcp_len = iwe_stream_lcp_len(info); /* Don't duplicate LCP */ event_len -= IW_EV_LCP_LEN; /* Check if it's possible */ if (likely((value + event_len) < ends)) { /* Add new value */ memcpy(value, &iwe->u, event_len); value += event_len; /* Patch LCP */ iwe->len = value - event; memcpy(event, (char *) iwe, lcp_len); } return value; } EXPORT_SYMBOL(iwe_stream_add_value); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void cpuset_wait_for_hotplug(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_node_allowed(node, gfp_mask); return true; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return __cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } static inline int cpuset_do_slab_mem_spread(void) { return task_spread_slab(current); } extern bool current_cpuset_is_being_rebound(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_wait_for_hotplug(void) { } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) { return true; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_slab_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline int cpuset_do_slab_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 397 20 397 397 386 393 2127 386 2127 24 24 603 360 393 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/atomic.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <net/netfilter/nf_nat_masquerade.h> struct masq_dev_work { struct work_struct work; struct net *net; netns_tracker ns_tracker; union nf_inet_addr addr; int ifindex; int (*iter)(struct nf_conn *i, void *data); }; #define MAX_MASQ_WORKER_COUNT 16 static DEFINE_MUTEX(masq_mutex); static unsigned int masq_refcnt __read_mostly; static atomic_t masq_worker_count __read_mostly; unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, const struct nf_nat_range2 *range, const struct net_device *out) { struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; struct nf_nat_range2 newrange; const struct rtable *rt; __be32 newsrc, nh; WARN_ON(hooknum != NF_INET_POST_ROUTING); ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. */ if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0) return NF_ACCEPT; rt = skb_rtable(skb); nh = rt_nexthop(rt, ip_hdr(skb)->daddr); newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE); if (!newsrc) { pr_info("%s ate my IP address\n", out->name); return NF_DROP; } nat = nf_ct_nat_ext_add(ct); if (nat) nat->masq_index = out->ifindex; /* Transfer from original range. */ memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.ip = newsrc; newrange.max_addr.ip = newsrc; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4); static void iterate_cleanup_work(struct work_struct *work) { struct nf_ct_iter_data iter_data = {}; struct masq_dev_work *w; w = container_of(work, struct masq_dev_work, work); iter_data.net = w->net; iter_data.data = (void *)w; nf_ct_iterate_cleanup_net(w->iter, &iter_data); put_net_track(w->net, &w->ns_tracker); kfree(w); atomic_dec(&masq_worker_count); module_put(THIS_MODULE); } /* Iterate conntrack table in the background and remove conntrack entries * that use the device/address being removed. * * In case too many work items have been queued already or memory allocation * fails iteration is skipped, conntrack entries will time out eventually. */ static void nf_nat_masq_schedule(struct net *net, union nf_inet_addr *addr, int ifindex, int (*iter)(struct nf_conn *i, void *data), gfp_t gfp_flags) { struct masq_dev_work *w; if (atomic_read(&masq_worker_count) > MAX_MASQ_WORKER_COUNT) return; net = maybe_get_net(net); if (!net) return; if (!try_module_get(THIS_MODULE)) goto err_module; w = kzalloc(sizeof(*w), gfp_flags); if (w) { /* We can overshoot MAX_MASQ_WORKER_COUNT, no big deal */ atomic_inc(&masq_worker_count); INIT_WORK(&w->work, iterate_cleanup_work); w->ifindex = ifindex; w->net = net; netns_tracker_alloc(net, &w->ns_tracker, gfp_flags); w->iter = iter; if (addr) w->addr = *addr; schedule_work(&w->work); return; } module_put(THIS_MODULE); err_module: put_net(net); } static int device_cmp(struct nf_conn *i, void *arg) { const struct nf_conn_nat *nat = nfct_nat(i); const struct masq_dev_work *w = arg; if (!nat) return 0; return nat->masq_index == w->ifindex; } static int masq_device_event(struct notifier_block *this, unsigned long event, void *ptr) { const struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (event == NETDEV_DOWN) { /* Device was downed. Search entire table for * conntracks which were associated with that device, * and forget them. */ nf_nat_masq_schedule(net, NULL, dev->ifindex, device_cmp, GFP_KERNEL); } return NOTIFY_DONE; } static int inet_cmp(struct nf_conn *ct, void *ptr) { struct nf_conntrack_tuple *tuple; struct masq_dev_work *w = ptr; if (!device_cmp(ct, ptr)) return 0; tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; return nf_inet_addr_cmp(&w->addr, &tuple->dst.u3); } static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { const struct in_ifaddr *ifa = ptr; const struct in_device *idev; const struct net_device *dev; union nf_inet_addr addr; if (event != NETDEV_DOWN) return NOTIFY_DONE; /* The masq_dev_notifier will catch the case of the device going * down. So if the inetdev is dead and being destroyed we have * no work to do. Otherwise this is an individual address removal * and we have to perform the flush. */ idev = ifa->ifa_dev; if (idev->dead) return NOTIFY_DONE; memset(&addr, 0, sizeof(addr)); addr.ip = ifa->ifa_address; dev = idev->dev; nf_nat_masq_schedule(dev_net(idev->dev), &addr, dev->ifindex, inet_cmp, GFP_KERNEL); return NOTIFY_DONE; } static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; #if IS_ENABLED(CONFIG_IPV6) static int nat_ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr) { #ifdef CONFIG_IPV6_MODULE const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); if (!v6_ops) return -EHOSTUNREACH; return v6_ops->dev_get_saddr(net, dev, daddr, srcprefs, saddr); #else return ipv6_dev_get_saddr(net, dev, daddr, srcprefs, saddr); #endif } unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out) { enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; struct in6_addr src; struct nf_conn *ct; struct nf_nat_range2 newrange; ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); if (nat_ipv6_dev_get_saddr(nf_ct_net(ct), out, &ipv6_hdr(skb)->daddr, 0, &src) < 0) return NF_DROP; nat = nf_ct_nat_ext_add(ct); if (nat) nat->masq_index = out->ifindex; newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; newrange.min_addr.in6 = src; newrange.max_addr.in6 = src; newrange.min_proto = range->min_proto; newrange.max_proto = range->max_proto; return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6); /* atomic notifier; can't call nf_ct_iterate_cleanup_net (it can sleep). * * Defer it to the system workqueue. * * As we can have 'a lot' of inet_events (depending on amount of ipv6 * addresses being deleted), we also need to limit work item queue. */ static int masq_inet6_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; union nf_inet_addr addr; if (event != NETDEV_DOWN) return NOTIFY_DONE; dev = ifa->idev->dev; memset(&addr, 0, sizeof(addr)); addr.in6 = ifa->addr; nf_nat_masq_schedule(dev_net(dev), &addr, dev->ifindex, inet_cmp, GFP_ATOMIC); return NOTIFY_DONE; } static struct notifier_block masq_inet6_notifier = { .notifier_call = masq_inet6_event, }; static int nf_nat_masquerade_ipv6_register_notifier(void) { return register_inet6addr_notifier(&masq_inet6_notifier); } #else static inline int nf_nat_masquerade_ipv6_register_notifier(void) { return 0; } #endif int nf_nat_masquerade_inet_register_notifiers(void) { int ret = 0; mutex_lock(&masq_mutex); if (WARN_ON_ONCE(masq_refcnt == UINT_MAX)) { ret = -EOVERFLOW; goto out_unlock; } /* check if the notifier was already set */ if (++masq_refcnt > 1) goto out_unlock; /* Register for device down reports */ ret = register_netdevice_notifier(&masq_dev_notifier); if (ret) goto err_dec; /* Register IP address change reports */ ret = register_inetaddr_notifier(&masq_inet_notifier); if (ret) goto err_unregister; ret = nf_nat_masquerade_ipv6_register_notifier(); if (ret) goto err_unreg_inet; mutex_unlock(&masq_mutex); return ret; err_unreg_inet: unregister_inetaddr_notifier(&masq_inet_notifier); err_unregister: unregister_netdevice_notifier(&masq_dev_notifier); err_dec: masq_refcnt--; out_unlock: mutex_unlock(&masq_mutex); return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_register_notifiers); void nf_nat_masquerade_inet_unregister_notifiers(void) { mutex_lock(&masq_mutex); /* check if the notifiers still have clients */ if (--masq_refcnt > 0) goto out_unlock; unregister_netdevice_notifier(&masq_dev_notifier); unregister_inetaddr_notifier(&masq_inet_notifier); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&masq_inet6_notifier); #endif out_unlock: mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_inet_unregister_notifiers); |
| 206 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | #undef TRACE_SYSTEM #define TRACE_SYSTEM bridge #if !defined(_TRACE_BRIDGE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BRIDGE_H #include <linux/netdevice.h> #include <linux/tracepoint.h> #include "../../../net/bridge/br_private.h" TRACE_EVENT(br_fdb_add, TP_PROTO(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags), TP_ARGS(ndm, dev, addr, vid, nlh_flags), TP_STRUCT__entry( __field(u8, ndm_flags) __string(dev, dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(u16, nlh_flags) ), TP_fast_assign( __assign_str(dev, dev->name); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->nlh_flags = nlh_flags; __entry->ndm_flags = ndm->ndm_flags; ), TP_printk("dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u nlh_flags %04x ndm_flags %02x", __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->nlh_flags, __entry->ndm_flags) ); TRACE_EVENT(br_fdb_external_learn_add, TP_PROTO(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid), TP_ARGS(br, p, addr, vid), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, p ? p->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, p ? p->dev->name : "null"); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; ), TP_printk("br_dev %s port %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(fdb_delete, TP_PROTO(struct net_bridge *br, struct net_bridge_fdb_entry *f), TP_ARGS(br, f), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, f->dst ? f->dst->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, f->dst ? f->dst->dev->name : "null"); memcpy(__entry->addr, f->key.addr.addr, ETH_ALEN); __entry->vid = f->key.vlan_id; ), TP_printk("br_dev %s dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(br_fdb_update, TP_PROTO(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, unsigned long flags), TP_ARGS(br, source, addr, vid, flags), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, source->dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(unsigned long, flags) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, source->dev->name); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->flags = flags; ), TP_printk("br_dev %s source %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u flags 0x%lx", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->flags) ); #endif /* _TRACE_BRIDGE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2195 1225 2178 1426 2194 2196 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 | // SPDX-License-Identifier: GPL-2.0 OR MIT /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * This is an implementation of the BLAKE2s hash and PRF functions. * * Information: https://blake2.net/ * */ #include <crypto/internal/blake2s.h> #include <linux/types.h> #include <linux/string.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/bug.h> static inline void blake2s_set_lastblock(struct blake2s_state *state) { state->f[0] = -1; } void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; if (unlikely(!inlen)) return; if (inlen > fill) { memcpy(state->buf + state->buflen, in, fill); blake2s_compress(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); state->buflen = 0; in += fill; inlen -= fill; } if (inlen > BLAKE2S_BLOCK_SIZE) { const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); blake2s_compress(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); } memcpy(state->buf + state->buflen, in, inlen); state->buflen += inlen; } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); blake2s_set_lastblock(state); memset(state->buf + state->buflen, 0, BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ blake2s_compress(state, state->buf, 1, state->buflen); cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); memcpy(out, state->h, state->outlen); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); static int __init blake2s_mod_init(void) { if (!IS_ENABLED(CONFIG_CRYPTO_MANAGER_DISABLE_TESTS) && WARN_ON(!blake2s_selftest())) return -ENODEV; return 0; } module_init(blake2s_mod_init); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("BLAKE2s hash function"); MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>"); |
| 286 286 1147 65 234 235 235 234 562 3 3 277 1 32 244 242 242 277 277 277 242 242 114 114 108 107 98 57 484 412 412 280 408 408 412 98 536 114 114 6 108 6 6 422 536 476 64 2 529 10 2 83 406 47 121 6 107 108 536 519 5 14 250 562 562 65 3 252 16 1 234 246 23 64 4 2 8 3 5 246 1 4 2 312 25 171 177 2 12 33 77 540 314 314 33 3 288 672 286 286 286 286 286 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * ROUTE - implementation of the IP router. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Linus Torvalds, <Linus.Torvalds@helsinki.fi> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * Alan Cox : Verify area fixes. * Alan Cox : cli() protects routing changes * Rui Oliveira : ICMP routing table updates * (rco@di.uminho.pt) Routing table insertion and update * Linus Torvalds : Rewrote bits to be sensible * Alan Cox : Added BSD route gw semantics * Alan Cox : Super /proc >4K * Alan Cox : MTU in route table * Alan Cox : MSS actually. Also added the window * clamper. * Sam Lantinga : Fixed route matching in rt_del() * Alan Cox : Routing cache support. * Alan Cox : Removed compatibility cruft. * Alan Cox : RTF_REJECT support. * Alan Cox : TCP irtt support. * Jonathan Naylor : Added Metric support. * Miquel van Smoorenburg : BSD API fixes. * Miquel van Smoorenburg : Metrics. * Alan Cox : Use __u32 properly * Alan Cox : Aligned routing errors more closely with BSD * our system is still very different. * Alan Cox : Faster /proc handling * Alexey Kuznetsov : Massive rework to support tree based routing, * routing caches and better behaviour. * * Olaf Erb : irtt wasn't being copied right. * Bjorn Ekwall : Kerneld route support. * Alan Cox : Multicast fixed (I hope) * Pavel Krauz : Limited broadcast fixed * Mike McLagan : Routing by source * Alexey Kuznetsov : End of old history. Split to fib.c and * route.c and rewritten from scratch. * Andi Kleen : Load-limit warning messages. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Vitaly E. Lavrov : Race condition in ip_route_input_slow. * Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow. * Vladimir V. Ivanov : IP rule info (flowid) is really useful. * Marc Boucher : routing by fwmark * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect * Ilia Sotnikov : Removed TOS from hash calculations */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/socket.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/pkt_sched.h> #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/route.h> #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> #include "fib_lookup.h" #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) #define RT_GC_TIMEOUT (300*HZ) #define DEFAULT_MIN_PMTU (512 + 20 + 20) #define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) #define DEFAULT_MIN_ADVMSS 256 static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); return NULL; } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr); static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .negative_advice = (void *)ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, .confirm_neigh = ipv4_confirm_neigh, }; #define ECN_OR_COST(class) TC_PRIO_##class const __u8 ip_tos2prio[16] = { TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos) return NULL; return SEQ_START_TOKEN; } static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return NULL; } static void rt_cache_seq_stop(struct seq_file *seq, void *v) { } static int rt_cache_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t" "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t" "HHUptod\tSpecDst"); return 0; } static const struct seq_operations rt_cache_seq_ops = { .start = rt_cache_seq_start, .next = rt_cache_seq_next, .stop = rt_cache_seq_stop, .show = rt_cache_seq_show, }; static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) { int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } return NULL; } static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } (*pos)++; return NULL; } static void rt_cpu_seq_stop(struct seq_file *seq, void *v) { } static int rt_cpu_seq_show(struct seq_file *seq, void *v) { struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x\n", dst_entries_get_slow(&ipv4_dst_ops), 0, /* st->in_hit */ st->in_slow_tot, st->in_slow_mc, st->in_no_route, st->in_brd, st->in_martian_dst, st->in_martian_src, 0, /* st->out_hit */ st->out_slow_tot, st->out_slow_mc, 0, /* st->gc_total */ 0, /* st->gc_ignored */ 0, /* st->gc_goal_miss */ 0, /* st->gc_dst_overflow */ 0, /* st->in_hlist_search */ 0 /* st->out_hlist_search */ ); return 0; } static const struct seq_operations rt_cpu_seq_ops = { .start = rt_cpu_seq_start, .next = rt_cpu_seq_next, .stop = rt_cpu_seq_stop, .show = rt_cpu_seq_show, }; #ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; unsigned int i, j; dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); if (!dst) return -ENOMEM; for_each_possible_cpu(i) { src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); for (j = 0; j < 256; j++) { dst[j].o_bytes += src[j].o_bytes; dst[j].o_packets += src[j].o_packets; dst[j].i_bytes += src[j].i_bytes; dst[j].i_packets += src[j].i_packets; } } seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); kfree(dst); return 0; } #endif static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; pde = proc_create_seq("rt_cache", 0444, net->proc_net, &rt_cache_seq_ops); if (!pde) goto err1; pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat, &rt_cpu_seq_ops); if (!pde) goto err2; #ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create_single("rt_acct", 0, net->proc_net, rt_acct_proc_show); if (!pde) goto err3; #endif return 0; #ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif err2: remove_proc_entry("rt_cache", net->proc_net); err1: return -ENOMEM; } static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); #ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, }; static int __init ip_rt_proc_init(void) { return register_pernet_subsys(&ip_rt_proc_ops); } #else static inline int ip_rt_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ static inline bool rt_is_expired(const struct rtable *rth) { return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); } void rt_cache_flush(struct net *net) { rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; struct neighbour *n; rcu_read_lock(); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { n = ip_neigh_gw6(dev, &rt->rt_gw6); } else { __be32 pkey; pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr); n = ip_neigh_gw4(dev, pkey); } if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock(); return n; } static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { pkey = (const __be32 *)&rt->rt_gw4; } else if (rt->rt_gw_family == AF_INET6) { return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6); } else if (!daddr || (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) { return; } __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } /* Hash tables of size 2048..262144 depending on RAM size. * Each bucket uses 8 bytes. */ static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ static u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; u32 *p_tstamp; u32 delta = 0; bucket = hash & ip_idents_mask; p_tstamp = ip_tstamps + bucket; p_id = ip_idents + bucket; old = READ_ONCE(*p_tstamp); if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); /* If UBSAN reports an error there, please make sure your compiler * supports -fno-strict-overflow before reporting it that was a bug * in UBSAN, and it has been fixed in GCC-8. */ return atomic_add_return(segs + delta, p_id) - segs; } void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { u32 hash, id; /* Note the following code is not safe, but this is okay. */ if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) get_random_bytes(&net->ipv4.ip_id_key, sizeof(net->ipv4.ip_id_key)); hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); static void ip_rt_fix_tos(struct flowi4 *fl4) { __u8 tos = RT_FL_TOS(fl4); fl4->flowi4_tos = tos & IPTOS_RT_MASK; if (tos & RTO_ONLINK) fl4->flowi4_scope = RT_SCOPE_LINK; } static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, __u8 tos, u8 prot, u32 mark, int flow_flags) { __u8 scope = RT_SCOPE_UNIVERSE; if (sk) { const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; mark = READ_ONCE(sk->sk_mark); tos = ip_sock_rt_tos(sk); scope = ip_sock_rt_scope(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, const struct sock *sk) { const struct net *net = dev_net(skb->dev); const struct iphdr *iph = ip_hdr(skb); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0); } static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), ip_sock_rt_tos(sk) & IPTOS_RT_MASK, ip_sock_rt_scope(sk), inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk->sk_uid); rcu_read_unlock(); } static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, const struct sk_buff *skb) { if (skb) build_skb_flow_key(fl4, skb, sk); else build_sk_flow_key(fl4, sk); } static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) { struct rtable *rt; rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } } static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception __rcu **fnhe_p, **oldest_p; struct fib_nh_exception *fnhe, *oldest = NULL; for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); if (!fnhe) break; if (!oldest || time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; oldest_p = fnhe_p; } } fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); } static u32 fnhe_hashfun(__be32 daddr) { static siphash_aligned_key_t fnhe_hash_key; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } } static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, __be32 gw, u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; struct rtable *rt; u32 genid, hval; unsigned int i; int depth; genid = fnhe_genid(dev_net(nhc->nhc_dev)); hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference(nhc->nhc_exceptions); if (!hash) { hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC); if (!hash) goto out_unlock; rcu_assign_pointer(nhc->nhc_exceptions, hash); } hash += hval; depth = 0; for (fnhe = rcu_dereference(hash->chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) break; depth++; } if (fnhe) { if (fnhe->fnhe_genid != genid) fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; if (pmtu) { fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) fill_route_from_fnhe(rt, fnhe); rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) fill_route_from_fnhe(rt, fnhe); } else { /* Randomize max depth to avoid some side channels attacks. */ int max_depth = FNHE_RECLAIM_DEPTH + prandom_u32_max(FNHE_RECLAIM_DEPTH); while (depth > max_depth) { fnhe_remove_oldest(hash); depth--; } fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); if (!fnhe) goto out_unlock; fnhe->fnhe_next = hash->chain; fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); rcu_assign_pointer(hash->chain, fnhe); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; for_each_possible_cpu(i) { struct rtable __rcu **prt; prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; } } fnhe->fnhe_stamp = jiffies; out_unlock: spin_unlock_bh(&fnhe_lock); } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { __be32 new_gw = icmp_hdr(skb)->un.gateway; __be32 old_gw = ip_hdr(skb)->saddr; struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct neighbour *n; struct net *net; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: case ICMP_REDIR_NETTOS: case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: break; default: return; } if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw) return; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; net = dev_net(dev); if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev)) goto reject_redirect; } else { if (inet_addr_type(net, new_gw) != RTN_UNICAST) goto reject_redirect; } n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(READ_ONCE(n->nud_state) & NUD_VALID)) { neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, skb); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) { const struct iphdr *iph = (const struct iphdr *) skb->data; __be32 daddr = iph->daddr; __be32 saddr = iph->saddr; net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); } #endif ; } static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; struct flowi4 fl4; const struct iphdr *iph = (const struct iphdr *) skb->data; struct net *net = dev_net(skb->dev); int oif = skb->dev->ifindex; u8 prot = iph->protocol; u32 mark = skb->mark; __u8 tos = iph->tos; rt = (struct rtable *) dst; __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; if ((dst->obsolete > 0) || (rt->rt_flags & RTCF_REDIRECTED) || rt->dst.expires) sk_dst_reset(sk); } /* * Algorithm: * 1. The first ip_rt_redirect_number redirects are sent * with exponential backoff, then we stop sending them at all, * assuming that the host ignores our redirects. * 2. If we did not see packets requiring redirects * during ip_rt_redirect_silence, we assume that the host * forgot redirected route and start to send redirects again. * * This algorithm is much cheaper and more intelligent than dumb load limiting * in icmp.c. * * NOTE. Do not forget to inhibit load limiting for redirects (redundant) * and "frag. need" (breaks PMTU discovery) in icmp.c. */ void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; struct net *net; int log_martians; int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { rcu_read_unlock(); return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; peer->n_redirects = 0; } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } /* Check for load limit; set rate_last to the latest sent * redirect. */ if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } out_put_peer: inet_putpeer(peer); } static int ip_error(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; SKB_DR(reason); bool send; int code; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) goto out; } in_dev = __in_dev_get_rcu(dev); /* IP on this device is disabled. */ if (!in_dev) goto out; net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { case EHOSTUNREACH: SKB_DR_SET(reason, IP_INADDRERRORS); __IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS); break; case ENETUNREACH: SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; } goto out; } switch (rt->dst.error) { case EINVAL: default: goto out; case EHOSTUNREACH: code = ICMP_HOST_UNREACH; break; case ENETUNREACH: code = ICMP_NET_UNREACH; SKB_DR_SET(reason, IP_INNOROUTES); __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { now = jiffies; peer->rate_tokens += now - peer->rate_last; if (peer->rate_tokens > ip_rt_error_burst) peer->rate_tokens = ip_rt_error_burst; peer->rate_last = now; if (peer->rate_tokens >= ip_rt_error_cost) peer->rate_tokens -= ip_rt_error_cost; else send = false; inet_putpeer(peer); } if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); out: kfree_skb_reason(skb, reason); return 0; } static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct net *net = dev_net(dst->dev); struct fib_result res; bool lock = false; u32 old_mtu; if (ip_mtu_locked(dst)) return; old_mtu = ipv4_mtu(dst); if (old_mtu < mtu) return; if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) return; rcu_read_lock(); if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } rcu_read_unlock(); } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); /* Don't make lookup fail for bridged encapsulations */ if (skb && netif_is_any_bridge_port(skb->dev)) fl4.flowi4_oif = 0; __ip_rt_update_pmtu(rt, &fl4, mtu); } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, mark, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0); if (!fl4.flowi4_mark) fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark); rt = __ip_route_output_key(sock_net(sk), &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; bool new = false; struct net *net = sock_net(sk); bh_lock_sock(sk); if (!ip_sk_accept_pmtu(sk)) goto out; odst = sk_dst_get(sk); if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = (struct rtable *)odst; if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } __ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } if (new) sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(net, &fl4, NULL, iph, oif, iph->tos, protocol, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_sk_redirect); INDIRECT_CALLABLE_SCOPE struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = (struct rtable *) dst; /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. * * When a PMTU/redirect information update invalidates a route, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; return dst; } EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct net_device *dev; struct ip_options opt; int res; /* Recompile ip options since IPCB may not be valid anymore. * Also check we have a reasonable ipv4 header. */ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return; memset(&opt, 0, sizeof(opt)); if (ip_hdr(skb)->ihl > 5) { if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) return; opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) return; } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); } static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; } /* * We do not cache source address of outgoing interface, * because it is used only by IP RR, TS and SRR options, * so that it out of fast path. * * BTW remember: "addr" is allowed to be not aligned * in IP options! */ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) { __be32 src; if (rt_is_output_route(rt)) src = ip_hdr(skb)->saddr; else { struct fib_result res; struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = RT_TOS(iph->tos), .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, }; rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) src = fib_result_prefsrc(dev_net(rt->dst.dev), &res); else src = inet_select_addr(rt->dst.dev, rt_nexthop(rt, iph->daddr), RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); } #ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) rt->dst.tclassid |= tag & 0xFFFF; if (!(rt->dst.tclassid & 0xFFFF0000)) rt->dst.tclassid |= tag & 0xFFFF0000; } #endif static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, net->ipv4.ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); } INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) { return ip_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ipv4_mtu); static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe, __rcu **fnhe_p; u32 hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference_protected(nhc->nhc_exceptions, lockdep_is_held(&fnhe_lock)); hash += hval; fnhe_p = &hash->chain; fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); while (fnhe) { if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); /* set fnhe_daddr to 0 to ensure it won't bind with * new dsts in rt_bind_exception(). */ fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; } fnhe_p = &fnhe->fnhe_next; fnhe = rcu_dereference_protected(fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)); } spin_unlock_bh(&fnhe_lock); } static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions); struct fib_nh_exception *fnhe; u32 hval; if (!hash) return NULL; hval = fnhe_hashfun(daddr); for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) { if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) { ip_del_fnhe(nhc, daddr); break; } return fnhe; } } return NULL; } /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device */ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) { struct fib_nh_common *nhc = res->nhc; struct net_device *dev = nhc->nhc_dev; struct fib_info *fi = res->fi; u32 mtu = 0; if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; if (likely(!mtu)) { struct fib_nh_exception *fnhe; fnhe = find_exception(nhc, daddr); if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires)) mtu = fnhe->fnhe_pmtu; } if (likely(!mtu)) mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu); } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr, const bool do_cache) { bool ret = false; spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { struct rtable __rcu **porig; struct rtable *orig; int genid = fnhe_genid(dev_net(rt->dst.dev)); if (rt_is_input_route(rt)) porig = &fnhe->fnhe_rth_input; else porig = &fnhe->fnhe_rth_output; orig = rcu_dereference(*porig); if (fnhe->fnhe_genid != genid) { fnhe->fnhe_genid = genid; fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } fill_route_from_fnhe(rt, fnhe); if (!rt->rt_gw4) { rt->rt_gw4 = daddr; rt->rt_gw_family = AF_INET; } if (do_cache) { dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); if (orig) { dst_dev_put(&orig->dst); dst_release(&orig->dst); } ret = true; } fnhe->fnhe_stamp = jiffies; } spin_unlock_bh(&fnhe_lock); return ret; } static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) { struct rtable *orig, *prev, **p; bool ret = true; if (rt_is_input_route(rt)) { p = (struct rtable **)&nhc->nhc_rth_input; } else { p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } orig = *p; /* hold dst before doing cmpxchg() to avoid race condition * on this dst */ dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { dst_release(&rt->dst); ret = false; } return ret; } struct uncached_list { spinlock_t lock; struct list_head head; struct list_head quarantine; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); rt->rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt_del_uncached_list(struct rtable *rt) { if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->rt_uncached); spin_unlock_bh(&ul->lock); } } static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; ip_dst_metrics_put(dst); rt_del_uncached_list(rt); } void rt_flush_dev(struct net_device *dev) { struct rtable *rt, *safe; int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; netdev_ref_replace(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); list_move(&rt->rt_uncached, &ul->quarantine); } spin_unlock_bh(&ul->lock); } } static bool rt_cache_valid(const struct rtable *rt) { return rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag, const bool do_cache) { bool cached = false; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) rt->rt_gw4 = nhc->nhc_gw.ipv4; else rt->rt_gw6 = nhc->nhc_gw.ipv6; } ip_dst_init_metrics(&rt->dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); rt->dst.tclassid = nh->nh_tclassid; } #endif rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr, do_cache); else if (do_cache) cached = rt_cache_route(nhc, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or * FIB nexthop have the DST_NOCACHE bit clear. * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ if (!rt->rt_gw4) { rt->rt_gw_family = AF_INET; rt->rt_gw4 = daddr; } rt_add_uncached_list(rt); } } else rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool noxfrm) { struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, (noxfrm ? DST_NOXFRM : 0)); if (rt) { rt->rt_genid = rt_genid_ipv4(dev_net(dev)); rt->rt_flags = flags; rt->rt_type = type; rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; if (flags & RTCF_LOCAL) rt->dst.input = ip_local_deliver; } return rt; } EXPORT_SYMBOL(rt_dst_alloc); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) { struct rtable *new_rt; new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, rt->dst.flags); if (new_rt) { new_rt->rt_genid = rt_genid_ipv4(dev_net(dev)); new_rt->rt_flags = rt->rt_flags; new_rt->rt_type = rt->rt_type; new_rt->rt_is_input = rt->rt_is_input; new_rt->rt_iif = rt->rt_iif; new_rt->rt_pmtu = rt->rt_pmtu; new_rt->rt_mtu_locked = rt->rt_mtu_locked; new_rt->rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) new_rt->rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; INIT_LIST_HEAD(&new_rt->rt_uncached); new_rt->dst.input = rt->dst.input; new_rt->dst.output = rt->dst.output; new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); } return new_rt; } EXPORT_SYMBOL(rt_dst_clone); /* called in rcu_read_lock() section */ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct in_device *in_dev, u32 *itag) { int err; /* Primary sanity checks. */ if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr) && ip_hdr(skb)->protocol != IPPROTO_IGMP) return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, itag); if (err < 0) return err; } return 0; } /* called in rcu_read_lock() section */ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, int our) { struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; u32 itag = 0; int err; err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); if (err) return err; if (our) flags |= RTCF_LOCAL; if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, false); if (!rth) return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; rth->rt_is_input= 1; #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) rth->dst.input = ip_mr_input; #endif RT_CACHE_STAT_INC(in_slow_mc); skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } static void ip_handle_martian_source(struct net_device *dev, struct in_device *in_dev, struct sk_buff *skb, __be32 daddr, __be32 saddr) { RT_CACHE_STAT_INC(in_martian_src); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) { /* * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ pr_warn("martian source %pI4 from %pI4, on dev %s\n", &daddr, &saddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { print_hex_dump(KERN_WARNING, "ll header: ", DUMP_PREFIX_OFFSET, 16, 1, skb_mac_header(skb), dev->hard_header_len, false); } } #endif } /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; struct rtable *rth; int err; struct in_device *out_dev; bool do_cache; u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); goto cleanup; } do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && skb->protocol == htons(ETH_P_IP)) { __be32 gw; gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0; if (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, gw)) IPCB(skb)->flags |= IPSKB_DOREDIRECT; } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. * * Proxy arp feature have been extended to allow, ARP * replies back to the same interface, to support * Private VLAN switch technologies. See arp.c. */ if (out_dev == in_dev && IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { err = -EINVAL; goto cleanup; } } if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; } } rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_ORCONF(out_dev, NOXFRM)); if (!rth) { err = -ENOBUFS; goto cleanup; } rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: err = 0; cleanup: return err; } #ifdef CONFIG_IP_ROUTE_MULTIPATH /* To make ICMP packets follow the right flow, the multipath hash is * calculated from the inner IP addresses. */ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; if (likely(outer_iph->protocol != IPPROTO_ICMP)) goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmp_is_err(icmph->type)) goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; out: hash_keys->addrs.v4addrs.src = key_iph->saddr; hash_keys->addrs.v4addrs.dst = key_iph->daddr; } static u32 fib_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return flow_hash_from_keys(&hash_keys); } static u32 fib_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return flow_hash_from_keys(&hash_keys); } static u32 fib_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 fib_multipath_custom_hash_fl4(const struct net *net, const struct flowi4 *fl4) { u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v4addrs.src = fl4->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v4addrs.dst = fl4->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl4->flowi4_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = fl4->fl4_sport; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; return flow_hash_from_keys(&hash_keys); } /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; u32 mhash = 0; switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (skb) { ip_multipath_l3_keys(skb, &hash_keys); } else { hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = flow_hash_from_keys(&hash_keys); break; case 1: /* skb is currently provided only when forwarding */ if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; hash_keys.ports.src = fl4->fl4_sport; hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } mhash = flow_hash_from_keys(&hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); /* skb is currently provided only when forwarding */ if (skb) { struct flow_keys keys; skb_flow_dissect_flow_keys(skb, &keys, 0); /* Inner can be v4 or v6 */ if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; hash_keys.tags.flow_label = keys.tags.flow_label; hash_keys.basic.ip_proto = keys.basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; ip_multipath_l3_keys(skb, &hash_keys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } mhash = flow_hash_from_keys(&hash_keys); break; case 3: if (skb) mhash = fib_multipath_custom_hash_skb(net, skb); else mhash = fib_multipath_custom_hash_fl4(net, fl4); break; } if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); return mhash >> 1; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); IPCB(skb)->flags |= IPSKB_MULTIPATH; } #endif /* create a routing cache entry */ return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* Implements all the saddr-related checks as ip_route_input_slow(), * assuming daddr is valid and the destination is not a local broadcast one. * Uses the provided hint instead of performing a route lookup. */ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, const struct sk_buff *hint) { struct in_device *in_dev = __in_dev_get_rcu(dev); struct rtable *rt = skb_rtable(hint); struct net *net = dev_net(dev); int err = -EINVAL; u32 tag = 0; if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; if (ipv4_is_zeronet(saddr)) goto martian_source; if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; tos &= IPTOS_RT_MASK; err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag); if (err < 0) goto martian_source; skip_validate_source: skb_dst_copy(skb, hint); return 0; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); return err; } /* get device for dst_alloc with local routes */ static struct net_device *ip_rt_get_dev(struct net *net, const struct fib_result *res) { struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; struct net_device *dev = NULL; if (nhc) dev = l3mdev_master_dev_rcu(nhc->nhc_dev); return dev ? : net->loopback_dev; } /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet * must have correct destination already attached by output routine. * Changes in the enforced policies must be applied also to * ip_route_use_hint(). * * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. * called with rcu_read_lock() */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { struct in_device *in_dev = __in_dev_get_rcu(dev); struct flow_keys *flkeys = NULL, _flkeys; struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; struct flowi4 fl4; bool do_cache = true; /* IP on this device is disabled. */ if (!in_dev) goto out; /* Check for the most weird martians, which can be not detected * by fib_lookup. */ tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; else fl4.flowi4_tun_key.tun_id = 0; skb_dst_drop(skb); if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; res->fi = NULL; res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; * I even do not know to fix it or not. Waiting for complains :-) */ if (ipv4_is_zeronet(saddr)) goto martian_source; if (ipv4_is_zeronet(daddr)) goto martian_destination; /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), * and call it once if daddr or/and saddr are loopback addresses */ if (ipv4_is_loopback(daddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_destination; } else if (ipv4_is_loopback(saddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; } /* * Now we are ready to route packet. */ fl4.flowi4_l3mdev = 0; fl4.flowi4_oif = 0; fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; } else { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } if (res->type == RTN_BROADCAST) { if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ if (IPV4_DEVCONF_ALL(net, BC_FORWARDING)) do_cache = false; goto brd_input; } if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) goto martian_source; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) { err = -EHOSTUNREACH; goto no_route; } if (res->type != RTN_UNICAST) goto martian_destination; make_route: err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; brd_input: if (skb->protocol != htons(ETH_P_IP)) goto e_inval; if (!ipv4_is_zeronet(saddr)) { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, &itag); if (err < 0) goto martian_source; } flags |= RTCF_BROADCAST; res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: if (IN_DEV_ORCONF(in_dev, NOPOLICY)) IPCB(skb)->flags |= IPSKB_NOPOLICY; do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; goto out; } } rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, false); if (!rth) goto e_nobufs; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { WARN_ON(rth->dst.input == lwtunnel_input); rth->dst.lwtstate->orig_input = rth->dst.input; rth->dst.input = lwtunnel_input; } if (unlikely(!rt_cache_route(nhc, rth))) rt_add_uncached_list(rth); } skb_dst_set(skb, &rth->dst); err = 0; goto out; no_route: RT_CACHE_STAT_INC(in_no_route); res->type = RTN_UNREACHABLE; res->fi = NULL; res->table = NULL; goto local_input; /* * Do not cache martian addresses: they should be logged (RFC1812) */ martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif e_inval: err = -EINVAL; goto out; e_nobufs: err = -ENOBUFS; goto out; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } /* called with rcu_read_lock held */ static int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. * The problem was that too many Ethernet cards have broken/missing * hardware multicast filters :-( As result the host on multicasting * network acquires a lot of useless route cache entries, sort of * SDR messages from all the world. Now we try to get rid of them. * Really, provided software IP multicast filter is organized * reasonably (at least, hashed), it does not result in a slowdown * comparing with route cache reject entries. * Note, that multicast routers are not affected, because * route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; int err = -EINVAL; if (!in_dev) return err; our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); /* check l3 master if no match yet */ if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); if (l3_in_dev) our = ip_check_mc_rcu(l3_in_dev, daddr, saddr, ip_hdr(skb)->protocol); } if (our #ifdef CONFIG_IP_MROUTE || (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) #endif ) { err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } return err; } return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { struct fib_result res; int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); rcu_read_unlock(); return err; } EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; bool do_cache; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) type = RTN_MULTICAST; else if (ipv4_is_zeronet(fl4->daddr)) return ERR_PTR(-EINVAL); if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; else do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. */ if (fi && res->prefixlen < 4) fi = NULL; } else if ((type == RTN_LOCAL) && (orig_oif != 0) && (orig_oif != dev_out->ifindex)) { /* For local routes that require a particular output interface * we do not want to cache the result. Caching the result * causes incorrect behaviour when there are multiple source * addresses on the interface, the end result being that if the * intended recipient is waiting on that interface for the * packet he won't receive it because it will be delivered on * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct rtable __rcu **prth; fnhe = find_exception(nhc, fl4->daddr); if (!do_cache) goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; } else { if (unlikely(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH && !(nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK))) { do_cache = false; goto add; } prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } rth = rcu_dereference(*prth); if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } add: rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_ORCONF(in_dev, NOXFRM)); if (!rth) return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; RT_CACHE_STAT_INC(out_slow_tot); if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; rth->dst.output = ip_mc_output; } } #endif } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); lwtunnel_set_redirect(&rth->dst); return rth; } /* * Major route resolver routine. */ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { struct fib_result res = { .type = RTN_UNSPEC, .fi = NULL, .table = NULL, .tclassid = 0, }; struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; ip_rt_fix_tos(fl4); rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); rcu_read_unlock(); return rth; } EXPORT_SYMBOL_GPL(ip_route_output_key_hash); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, struct fib_result *res, const struct sk_buff *skb) { struct net_device *dev_out = NULL; int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; int err; if (fl4->saddr) { if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || ipv4_is_zeronet(fl4->saddr)) { rth = ERR_PTR(-EINVAL); goto out; } rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. * It was wrong for two reasons: * 1. ip_dev_find(net, saddr) can return wrong iface, if saddr * is assigned to multiple interfaces. * 2. Moreover, we are allowed to send packets with saddr * of another iface. --ANK */ if (fl4->flowi4_oif == 0 && (ipv4_is_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); if (!dev_out) goto out; /* Special hack: user can direct multicasts * and limited broadcast via necessary interface * without fiddling with IP_MULTICAST_IF or IP_PKTINFO. * This hack is not just for fun, it allows * vic,vat and friends to work. * They bind socket to loopback, set ttl to zero * and expect that it will work. * From the viewpoint of routing cache they are broken, * because we are not allowed to build multicast path * with loopback source addr (look, routing cache * cannot know, that ttl is zero, so that packet * will not leave this host and route is valid). * Luckily, this hack is good workaround. */ fl4->flowi4_oif = dev_out->ifindex; goto make_route; } if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ if (!__ip_dev_find(net, fl4->saddr, false)) goto out; } } if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { rth = ERR_PTR(-ENETUNREACH); goto out; } if (ipv4_is_local_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr) || fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); goto make_route; } if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); else if (!fl4->daddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } } if (!fl4->daddr) { fl4->daddr = fl4->saddr; if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } err = fib_lookup(net, fl4, res, 0); if (err) { res->fi = NULL; res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !fl4->flowi4_l3mdev)) { /* Apparently, routing tables are wrong. Assume, * that the destination is on link. * * WHY? DW. * Because we are allowed to send to iface * even if it has NO routes and NO assigned * addresses. When oif is specified, routing * tables are looked up with only one purpose: * to catch if destination is gatewayed, rather than * direct. Moreover, if MSG_DONTROUTE is set, * we send packet, ignoring both routing tables * and ifaddr state. --ANK * * * We could make it even if oif is unknown, * likely IPv6, but we do not. */ if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } if (res->type == RTN_LOCAL) { if (!fl4->saddr) { if (res->fi->fib_prefsrc) fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; /* make sure orig_oif points to fib result device even * though packet rx/tx happens over loopback or l3mdev */ orig_oif = FIB_RES_OIF(*res); fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: return rth; } static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .default_advmss = ipv4_default_advmss, .neigh_lookup = ipv4_neigh_lookup, .check = dst_blackhole_check, .cow_metrics = dst_blackhole_cow_metrics, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; new->dev = net->loopback_dev; netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; else if (rt->rt_gw_family == AF_INET6) rt->rt_gw6 = ort->rt_gw6; INIT_LIST_HEAD(&rt->rt_uncached); } dst_release(dst_orig); return rt ? &rt->dst : ERR_PTR(-ENOMEM); } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); if (IS_ERR(rt)) return rt; if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); } return rt; } EXPORT_SYMBOL_GPL(ip_route_output_flow); struct rtable *ip_route_output_tunnel(struct sk_buff *skb, struct net_device *dev, struct net *net, __be32 *saddr, const struct ip_tunnel_info *info, u8 protocol, bool use_cache) { #ifdef CONFIG_DST_CACHE struct dst_cache *dst_cache; #endif struct rtable *rt = NULL; struct flowi4 fl4; __u8 tos; #ifdef CONFIG_DST_CACHE dst_cache = (struct dst_cache *)&info->dst_cache; if (use_cache) { rt = dst_cache_get_ip4(dst_cache, saddr); if (rt) return rt; } #endif memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_mark = skb->mark; fl4.flowi4_proto = protocol; fl4.daddr = info->key.u.ipv4.dst; fl4.saddr = info->key.u.ipv4.src; tos = info->key.tos; fl4.flowi4_tos = RT_TOS(tos); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); return ERR_PTR(-ENETUNREACH); } if (rt->dst.dev == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); ip_rt_put(rt); return ERR_PTR(-ELOOP); } #ifdef CONFIG_DST_CACHE if (use_cache) dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); #endif *saddr = fl4.saddr; return rt; } EXPORT_SYMBOL_GPL(ip_route_output_tunnel); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; u32 error; u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; if (IPCB(skb)->flags & IPSKB_DOREDIRECT) r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (src) { r->rtm_src_len = 32; if (nla_put_in_addr(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; if (rt->dst.lwtstate && lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif if (fl4 && !rt_is_input_route(rt) && fl4->saddr != src) { if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } if (rt->rt_uses_gateway) { if (rt->rt_gw_family == AF_INET && nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; } else if (rt->rt_gw_family == AF_INET6) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) goto nla_put_failure; via = nla_data(nla); via->rtvia_family = AF_INET6; memcpy(via->rtvia_addr, &rt->rt_gw6, alen); } } expires = rt->dst.expires; if (expires) { unsigned long now = jiffies; if (time_before(now, expires)) expires -= now; else expires = 0; } memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; if (rt->rt_mtu_locked && expires) metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (fl4) { if (fl4->flowi4_mark && nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && nla_put_u32(skb, RTA_UID, from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) goto nla_put_failure; if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); if (err <= 0) { if (err == 0) return 0; goto nla_put_failure; } } else #endif if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) goto nla_put_failure; } } error = rt->dst.error; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, int *fa_index, int fa_start, unsigned int flags) { int i; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; for (fnhe = rcu_dereference(bucket[i].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { struct rtable *rt; int err; if (*fa_index < fa_start) goto next; if (fnhe->fnhe_genid != genid) goto next; if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) goto next; rt = rcu_dereference(fnhe->fnhe_rth_input); if (!rt) rt = rcu_dereference(fnhe->fnhe_rth_output); if (!rt) goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) return err; next: (*fa_index)++; } } return 0; } int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); struct fnhe_hash_bucket *bucket; int err; if (nhc->nhc_flags & RTNH_F_DEAD) continue; rcu_read_lock(); bucket = rcu_dereference(nhc->nhc_exceptions); err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, genid, fa_index, fa_start, flags); rcu_read_unlock(); if (err) return err; } return 0; } static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, u8 ip_proto, __be16 sport, __be16 dport) { struct sk_buff *skb; struct iphdr *iph; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return NULL; /* Reserve room for dummy headers, this skb can pass * through good chunk of routing engine. */ skb_reset_mac_header(skb); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); iph = skb_put(skb, sizeof(struct iphdr)); iph->protocol = ip_proto; iph->saddr = src; iph->daddr = dst; iph->version = 0x4; iph->frag_off = 0; iph->ihl = 0x5; skb_set_transport_header(skb, skb->len); switch (iph->protocol) { case IPPROTO_UDP: { struct udphdr *udph; udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } case IPPROTO_TCP: { struct tcphdr *tcph; tcph = skb_put_zero(skb, sizeof(struct tcphdr)); tcph->source = sport; tcph->dest = dport; tcph->doff = sizeof(struct tcphdr) / 4; tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), src, dst, 0); break; } case IPPROTO_ICMP: { struct icmphdr *icmph; icmph = skb_put_zero(skb, sizeof(struct icmphdr)); icmph->type = ICMP_ECHO; icmph->code = 0; } } return skb; } static int inet_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for route get request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_NOTIFY | RTM_F_LOOKUP_TABLE | RTM_F_FIB_MATCH)) { NL_SET_ERR_MSG(extack, "ipv4: Unsupported rtm_flags for route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_IIF: case RTA_OIF: case RTA_SRC: case RTA_DST: case RTA_IP_PROTO: case RTA_SPORT: case RTA_DPORT: case RTA_MARK: case RTA_UID: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in route get request"); return -EINVAL; } } return 0; } static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; u32 table_id = RT_TABLE_MAIN; __be16 sport = 0, dport = 0; struct fib_result res = {}; u8 ip_proto = IPPROTO_UDP; struct rtable *rt = NULL; struct sk_buff *skb; struct rtmsg *rtm; struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; kuid_t uid; u32 iif; int err; int mark; err = inet_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; rtm = nlmsg_data(nlh); src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else uid = (iif ? INVALID_UID : current_uid()); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &ip_proto, AF_INET, extack); if (err) return err; } if (tb[RTA_SPORT]) sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) dport = nla_get_be16(tb[RTA_DPORT]); skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport); if (!skb) return -ENOBUFS; fl4.daddr = dst; fl4.saddr = src; fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; if (sport) fl4.fl4_sport = sport; if (dport) fl4.fl4_dport = dport; fl4.flowi4_proto = ip_proto; rcu_read_lock(); if (iif) { struct net_device *dev; dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_rcu; } fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos & IPTOS_RT_MASK, dev, &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { fl4.flowi4_iif = LOOPBACK_IFINDEX; skb->dev = net->loopback_dev; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); else skb_dst_set(skb, &rt->dst); } if (err) goto errout_rcu; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = res.table ? res.table->tb_id : 0; /* reset skb for netlink reply msg */ skb_trim(skb, 0); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { struct fib_rt_info fri; if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } fri.fi = res.fi; fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos); fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; fri.offload_failed = 0; if (res.fa_head) { struct fib_alias *fa; hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { u8 slen = 32 - fri.dst_len; if (fa->fa_slen == slen && fa->tb_id == fri.tb_id && fa->fa_dscp == fri.dscp && fa->fa_info == res.fi && fa->fa_type == fri.type) { fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); break; } } } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; rcu_read_unlock(); err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: return err; errout_rcu: rcu_read_unlock(); kfree_skb(skb); goto errout_free; } void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; if (write) { rt_cache_flush(net); fnhe_genid_bump(net); return 0; } return -EINVAL; } static struct ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_size", .data = &ip_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { /* Deprecated. Use gc_min_interval_ms */ .procname = "gc_min_interval", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_min_interval_ms", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "gc_timeout", .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_number", .data = &ip_rt_redirect_number, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_silence", .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_cost", .data = &ip_rt_error_cost, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_burst", .data = &ip_rt_error_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_elasticity", .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static const char ipv4_route_flush_procname[] = "flush"; static struct ctl_table ipv4_route_netns_table[] = { { .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, }, { .procname = "min_pmtu", .data = &init_net.ipv4.ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &ip_min_valid_pmtu, }, { .procname = "mtu_expires", .data = &init_net.ipv4.ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv4.ip_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { }, }; static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; tbl = ipv4_route_netns_table; if (!net_eq(net, &init_net)) { int i; tbl = kmemdup(tbl, sizeof(ipv4_route_netns_table), GFP_KERNEL); if (!tbl) goto err_dup; /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { if (tbl[0].procname != ipv4_route_flush_procname) tbl[0].procname = NULL; } /* Update the variables to point into the current struct net * except for the first element flush */ for (i = 1; i < ARRAY_SIZE(ipv4_route_netns_table) - 1; i++) tbl[i].data += (void *)net - (void *)&init_net; } tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl); if (!net->ipv4.route_hdr) goto err_reg; return 0; err_reg: if (tbl != ipv4_route_netns_table) kfree(tbl); err_dup: return -ENOMEM; } static __net_exit void sysctl_route_net_exit(struct net *net) { struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); BUG_ON(tbl == ipv4_route_netns_table); kfree(tbl); } static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, }; #endif static __net_init int netns_ip_rt_init(struct net *net) { /* Set default value for namespaceified sysctls */ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS; return 0; } static struct pernet_operations __net_initdata ip_rt_ops = { .init = netns_ip_rt_init, }; static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); atomic_set(&net->ipv4.dev_addr_genid, get_random_u32()); return 0; } static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; static int __net_init ipv4_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv4.peers = bp; return 0; } static void __net_exit ipv4_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv4.peers; net->ipv4.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, }; #ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; #endif /* CONFIG_IP_ROUTE_CLASSID */ int __init ip_rt_init(void) { void *idents_hash; int cpu; /* For modern hosts, this will use 2 MB of memory */ idents_hash = alloc_large_system_hash("IP idents", sizeof(*ip_idents) + sizeof(*ip_tstamps), 0, 16, /* one bucket per 64 KB */ HASH_ZERO, NULL, &ip_idents_mask, 2048, 256*1024); ip_idents = idents_hash; get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); INIT_LIST_HEAD(&ul->quarantine); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); #endif ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; if (dst_entries_init(&ipv4_dst_ops) < 0) panic("IP: failed to allocate ipv4_dst_ops counter\n"); if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); ipv4_dst_ops.gc_thresh = ~0; ip_rt_max_size = INT_MAX; devinet_init(); ip_fib_init(); if (ip_rt_proc_init()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); xfrm4_init(); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, RTNL_FLAG_DOIT_UNLOCKED); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&ip_rt_ops); register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); return 0; } #ifdef CONFIG_SYSCTL /* * We really need to sanitize the damn ipv4 init order, then all * this nonsense will go away. */ void __init ip_static_sysctl_init(void) { register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif |
| 33 33 33 2 5 13 41 2 40 38 2 2 17 35 35 33 14 16 16 23 27 3 80 11 39 3 19 27 26 93 21 80 80 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Cong Wang <cong.wang@bytedance.com> */ #include <linux/skmsg.h> #include <linux/bpf.h> #include <net/sock.h> #include <net/af_unix.h> #define unix_sk_has_data(__sk, __psock) \ ({ !skb_queue_empty(&__sk->sk_receive_queue) || \ !skb_queue_empty(&__psock->ingress_skb) || \ !list_empty(&__psock->ingress_msg); \ }) static int unix_msg_wait_data(struct sock *sk, struct sk_psock *psock, long timeo) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct unix_sock *u = unix_sk(sk); int ret = 0; if (sk->sk_shutdown & RCV_SHUTDOWN) return 1; if (!timeo) return ret; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); if (!unix_sk_has_data(sk, psock)) { mutex_unlock(&u->iolock); wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); mutex_lock(&u->iolock); ret = unix_sk_has_data(sk, psock); } sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); return ret; } static int __unix_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { if (sk->sk_type == SOCK_DGRAM) return __unix_dgram_recvmsg(sk, msg, len, flags); else return __unix_stream_recvmsg(sk, msg, len, flags); } static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct unix_sock *u = unix_sk(sk); struct sk_psock *psock; int copied; if (!len) return 0; psock = sk_psock_get(sk); if (unlikely(!psock)) return __unix_recvmsg(sk, msg, len, flags); mutex_lock(&u->iolock); if (!skb_queue_empty(&sk->sk_receive_queue) && sk_psock_queue_empty(psock)) { mutex_unlock(&u->iolock); sk_psock_put(sk, psock); return __unix_recvmsg(sk, msg, len, flags); } msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { long timeo; int data; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = unix_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; mutex_unlock(&u->iolock); sk_psock_put(sk, psock); return __unix_recvmsg(sk, msg, len, flags); } copied = -EAGAIN; } mutex_unlock(&u->iolock); sk_psock_put(sk, psock); return copied; } static struct proto *unix_dgram_prot_saved __read_mostly; static DEFINE_SPINLOCK(unix_dgram_prot_lock); static struct proto unix_dgram_bpf_prot; static struct proto *unix_stream_prot_saved __read_mostly; static DEFINE_SPINLOCK(unix_stream_prot_lock); static struct proto unix_stream_bpf_prot; static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; prot->sock_is_readable = sk_msg_is_readable; } static void unix_stream_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; prot->close = sock_map_close; prot->recvmsg = unix_bpf_recvmsg; prot->sock_is_readable = sk_msg_is_readable; prot->unhash = sock_map_unhash; } static void unix_dgram_bpf_check_needs_rebuild(struct proto *ops) { if (unlikely(ops != smp_load_acquire(&unix_dgram_prot_saved))) { spin_lock_bh(&unix_dgram_prot_lock); if (likely(ops != unix_dgram_prot_saved)) { unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, ops); smp_store_release(&unix_dgram_prot_saved, ops); } spin_unlock_bh(&unix_dgram_prot_lock); } } static void unix_stream_bpf_check_needs_rebuild(struct proto *ops) { if (unlikely(ops != smp_load_acquire(&unix_stream_prot_saved))) { spin_lock_bh(&unix_stream_prot_lock); if (likely(ops != unix_stream_prot_saved)) { unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, ops); smp_store_release(&unix_stream_prot_saved, ops); } spin_unlock_bh(&unix_stream_prot_lock); } } int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { if (sk->sk_type != SOCK_DGRAM) return -EOPNOTSUPP; if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } unix_dgram_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_dgram_bpf_prot); return 0; } int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; } void __init unix_bpf_build_proto(void) { unix_dgram_bpf_rebuild_protos(&unix_dgram_bpf_prot, &unix_dgram_proto); unix_stream_bpf_rebuild_protos(&unix_stream_bpf_prot, &unix_stream_proto); } |
| 5 6 6 2 4 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV6 GSO/GRO offload support * Linux INET6 implementation * * UDPv6 GSO support */ #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/indirect_call_wrapper.h> #include <net/protocol.h> #include <net/ipv6.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include "ip6_offload.h" #include <net/gro.h> static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; unsigned int unfrag_ip6hlen, unfrag_len; struct frag_hdr *fptr; u8 *packet_start, *prevhdr; u8 nexthdr; u8 frag_hdr_sz = sizeof(struct frag_hdr); __wsum csum; int tnl_hlen; int err; if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); else { const struct ipv6hdr *ipv6h; struct udphdr *uh; if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ uh = udp_hdr(skb); ipv6h = ipv6_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v6_check(skb->len, &ipv6h->saddr, &ipv6h->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Check if there is enough headroom to insert fragment header. */ tnl_hlen = skb_tnl_header_len(skb); if (skb->mac_header < (tnl_hlen + frag_hdr_sz)) { if (gso_pskb_expand_head(skb, tnl_hlen + frag_hdr_sz)) goto out; } /* Find the unfragmentable header and shift it left by frag_hdr_sz * bytes to insert fragment header. */ err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) return ERR_PTR(err); unfrag_ip6hlen = err; nexthdr = *prevhdr; *prevhdr = NEXTHDR_FRAGMENT; unfrag_len = (skb_network_header(skb) - skb_mac_header(skb)) + unfrag_ip6hlen + tnl_hlen; packet_start = (u8 *) skb->head + SKB_GSO_CB(skb)->mac_offset; memmove(packet_start-frag_hdr_sz, packet_start, unfrag_len); SKB_GSO_CB(skb)->mac_offset -= frag_hdr_sz; skb->mac_header -= frag_hdr_sz; skb->network_header -= frag_hdr_sz; fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; fptr->identification = ipv6_proxy_select_ident(dev_net(skb->dev), skb); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() */ segs = skb_segment(skb, features); } out: return segs; } static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct ipv6hdr *iph = skb_gro_network_header(skb); return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), inet6_sdif(skb), &udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, ip6_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, ip6_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; if (static_branch_unlikely(&udpv6_encap_needed_key)) sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) { const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v6_check(skb->len - nhoff, &ipv6h->saddr, &ipv6h->daddr, 0); return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } static const struct net_offload udpv6_offload = { .callbacks = { .gso_segment = udp6_ufo_fragment, .gro_receive = udp6_gro_receive, .gro_complete = udp6_gro_complete, }, }; int udpv6_offload_init(void) { return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Checksumming functions for IP, TCP, UDP and so on * * Authors: Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Borrows very liberally from tcp.c and ip.c, see those * files for more names. */ #ifndef _CHECKSUM_H #define _CHECKSUM_H #include <linux/errno.h> #include <asm/types.h> #include <asm/byteorder.h> #include <linux/uaccess.h> #include <asm/checksum.h> #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER static __always_inline __wsum csum_and_copy_from_user (const void __user *src, void *dst, int len) { if (copy_from_user(dst, src, len)) return 0; return csum_partial(dst, len, ~0U); } #endif #ifndef HAVE_CSUM_COPY_USER static __always_inline __wsum csum_and_copy_to_user (const void *src, void __user *dst, int len) { __wsum sum = csum_partial(src, len, ~0U); if (copy_to_user(dst, src, len) == 0) return sum; return 0; } #endif #ifndef _HAVE_ARCH_CSUM_AND_COPY static __always_inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) { memcpy(dst, src, len); return csum_partial(dst, len, 0); } #endif #ifndef HAVE_ARCH_CSUM_ADD static __always_inline __wsum csum_add(__wsum csum, __wsum addend) { u32 res = (__force u32)csum; res += (__force u32)addend; return (__force __wsum)(res + (res < (__force u32)addend)); } #endif static __always_inline __wsum csum_sub(__wsum csum, __wsum addend) { return csum_add(csum, ~addend); } static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend) { u16 res = (__force u16)csum; res += (__force u16)addend; return (__force __sum16)(res + (res < (__force u16)addend)); } static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend) { return csum16_add(csum, ~addend); } #ifndef HAVE_ARCH_CSUM_SHIFT static __always_inline __wsum csum_shift(__wsum sum, int offset) { /* rotate sum to align it with a 16b boundary */ if (offset & 1) return (__force __wsum)ror32((__force u32)sum, 8); return sum; } #endif static __always_inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { return csum_add(csum, csum_shift(csum2, offset)); } static __always_inline __wsum csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) { return csum_block_add(csum, csum2, offset); } static __always_inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { return csum_block_add(csum, ~csum2, offset); } static __always_inline __wsum csum_unfold(__sum16 n) { return (__force __wsum)n; } static __always_inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) { return csum_partial(buff, len, sum); } #define CSUM_MANGLED_0 ((__force __sum16)0xffff) static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); } static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); *sum = csum_fold(csum_add(tmp, (__force __wsum)to)); } /* Implements RFC 1624 (Incremental Internet Checksum) * 3. Discussion states : * HC' = ~(~HC + ~m + m') * m : old value of a 16bit field * m' : new value of a 16bit field */ static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new) { *sum = ~csum16_add(csum16_sub(~(*sum), old), new); } static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) { *csum = csum_add(csum_sub(*csum, old), new); } struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr); static __always_inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, __be16 from, __be16 to, bool pseudohdr) { inet_proto_csum_replace4(sum, skb, (__force __be32)from, (__force __be32)to, pseudohdr); } static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum, int start, int offset) { __sum16 *psum = (__sum16 *)(ptr + offset); __wsum delta; /* Subtract out checksum up to start */ csum = csum_sub(csum, csum_partial(ptr, start, 0)); /* Set derived checksum in packet */ delta = csum_sub((__force __wsum)csum_fold(csum), (__force __wsum)*psum); *psum = csum_fold(csum); return delta; } static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta) { *psum = csum_fold(csum_sub(delta, (__force __wsum)*psum)); } static __always_inline __wsum wsum_negate(__wsum val) { return (__force __wsum)-((__force u32)val); } #endif |
| 243 4 239 878 878 623 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 454 212 23 203 19 204 511 492 485 499 50 20 495 35 302 7 8 7 214 222 222 225 10 13 5 196 192 8 183 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 | // SPDX-License-Identifier: GPL-2.0 /* * Convert integer string representation to an integer. * If an integer doesn't fit into specified type, -E is returned. * * Integer starts with optional sign. * kstrtou*() functions do not accept sign "-". * * Radix 0 means autodetection: leading "0x" implies radix 16, * leading "0" implies radix 8, otherwise radix is 10. * Autodetection hints work after optional sign, but not before. * * If -E is returned, result is not touched. */ #include <linux/ctype.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/kstrtox.h> #include <linux/math64.h> #include <linux/types.h> #include <linux/uaccess.h> #include "kstrtox.h" noinline const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) { if (*base == 0) { if (s[0] == '0') { if (_tolower(s[1]) == 'x' && isxdigit(s[2])) *base = 16; else *base = 8; } else *base = 10; } if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x') s += 2; return s; } /* * Convert non-negative integer string representation in explicitly given radix * to an integer. A maximum of max_chars characters will be converted. * * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ noinline unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p, size_t max_chars) { unsigned long long res; unsigned int rv; res = 0; rv = 0; while (max_chars--) { unsigned int c = *s; unsigned int lc = c | 0x20; /* don't tolower() this line */ unsigned int val; if ('0' <= c && c <= '9') val = c - '0'; else if ('a' <= lc && lc <= 'f') val = lc - 'a' + 10; else break; if (val >= base) break; /* * Check for overflow only if we are within range of * it in the max base we support (16) */ if (unlikely(res & (~0ull << 60))) { if (res > div_u64(ULLONG_MAX - val, base)) rv |= KSTRTOX_OVERFLOW; } res = res * base + val; rv++; s++; } *p = res; return rv; } noinline unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) { return _parse_integer_limit(s, base, p, INT_MAX); } static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; unsigned int rv; s = _parse_integer_fixup_radix(s, &base); rv = _parse_integer(s, base, &_res); if (rv & KSTRTOX_OVERFLOW) return -ERANGE; if (rv == 0) return -EINVAL; s += rv; if (*s == '\n') s++; if (*s) return -EINVAL; *res = _res; return 0; } /** * kstrtoull - convert a string to an unsigned long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoull(). Return code must be checked. */ noinline int kstrtoull(const char *s, unsigned int base, unsigned long long *res) { if (s[0] == '+') s++; return _kstrtoull(s, base, res); } EXPORT_SYMBOL(kstrtoull); /** * kstrtoll - convert a string to a long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoll(). Return code must be checked. */ noinline int kstrtoll(const char *s, unsigned int base, long long *res) { unsigned long long tmp; int rv; if (s[0] == '-') { rv = _kstrtoull(s + 1, base, &tmp); if (rv < 0) return rv; if ((long long)-tmp > 0) return -ERANGE; *res = -tmp; } else { rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if ((long long)tmp < 0) return -ERANGE; *res = tmp; } return 0; } EXPORT_SYMBOL(kstrtoll); /* Internal, do not use. */ int _kstrtoul(const char *s, unsigned int base, unsigned long *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtoul); /* Internal, do not use. */ int _kstrtol(const char *s, unsigned int base, long *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtol); /** * kstrtouint - convert a string to an unsigned int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ noinline int kstrtouint(const char *s, unsigned int base, unsigned int *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtouint); /** * kstrtoint - convert a string to an int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ noinline int kstrtoint(const char *s, unsigned int base, int *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtoint); noinline int kstrtou16(const char *s, unsigned int base, u16 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou16); noinline int kstrtos16(const char *s, unsigned int base, s16 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos16); noinline int kstrtou8(const char *s, unsigned int base, u8 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou8); noinline int kstrtos8(const char *s, unsigned int base, s8 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos8); /** * kstrtobool - convert common user inputs into boolean values * @s: input string * @res: result * * This routine returns 0 iff the first character is one of 'YyTt1NnFf0', or * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ noinline int kstrtobool(const char *s, bool *res) { if (!s) return -EINVAL; switch (s[0]) { case 'y': case 'Y': case 't': case 'T': case '1': *res = true; return 0; case 'n': case 'N': case 'f': case 'F': case '0': *res = false; return 0; case 'o': case 'O': switch (s[1]) { case 'n': case 'N': *res = true; return 0; case 'f': case 'F': *res = false; return 0; default: break; } break; default: break; } return -EINVAL; } EXPORT_SYMBOL(kstrtobool); /* * Since "base" would be a nonsense argument, this open-codes the * _from_user helper instead of using the helper macro below. */ int kstrtobool_from_user(const char __user *s, size_t count, bool *res) { /* Longest string needed to differentiate, newline, terminator */ char buf[4]; count = min(count, sizeof(buf) - 1); if (copy_from_user(buf, s, count)) return -EFAULT; buf[count] = '\0'; return kstrtobool(buf, res); } EXPORT_SYMBOL(kstrtobool_from_user); #define kstrto_from_user(f, g, type) \ int f(const char __user *s, size_t count, unsigned int base, type *res) \ { \ /* sign, base 2 representation, newline, terminator */ \ char buf[1 + sizeof(type) * 8 + 1 + 1]; \ \ count = min(count, sizeof(buf) - 1); \ if (copy_from_user(buf, s, count)) \ return -EFAULT; \ buf[count] = '\0'; \ return g(buf, base, res); \ } \ EXPORT_SYMBOL(f) kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long); kstrto_from_user(kstrtoll_from_user, kstrtoll, long long); kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long); kstrto_from_user(kstrtol_from_user, kstrtol, long); kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int); kstrto_from_user(kstrtoint_from_user, kstrtoint, int); kstrto_from_user(kstrtou16_from_user, kstrtou16, u16); kstrto_from_user(kstrtos16_from_user, kstrtos16, s16); kstrto_from_user(kstrtou8_from_user, kstrtou8, u8); kstrto_from_user(kstrtos8_from_user, kstrtos8, s8); |
| 903 1275 945 1900 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_USER_NAMESPACE_H #define _LINUX_USER_NAMESPACE_H #include <linux/kref.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/rwsem.h> #include <linux/sysctl.h> #include <linux/err.h> #include <linux/android_kabi.h> #define UID_GID_MAP_MAX_BASE_EXTENTS 5 #define UID_GID_MAP_MAX_EXTENTS 340 struct uid_gid_extent { u32 first; u32 lower_first; u32 count; }; struct uid_gid_map { /* 64 bytes -- 1 cache line */ u32 nr_extents; union { struct uid_gid_extent extent[UID_GID_MAP_MAX_BASE_EXTENTS]; struct { struct uid_gid_extent *forward; struct uid_gid_extent *reverse; }; }; }; #define USERNS_SETGROUPS_ALLOWED 1UL #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED struct ucounts; enum ucount_type { UCOUNT_USER_NAMESPACES, UCOUNT_PID_NAMESPACES, UCOUNT_UTS_NAMESPACES, UCOUNT_IPC_NAMESPACES, UCOUNT_NET_NAMESPACES, UCOUNT_MNT_NAMESPACES, UCOUNT_CGROUP_NAMESPACES, UCOUNT_TIME_NAMESPACES, #ifdef CONFIG_INOTIFY_USER UCOUNT_INOTIFY_INSTANCES, UCOUNT_INOTIFY_WATCHES, #endif #ifdef CONFIG_FANOTIFY UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif UCOUNT_COUNTS, }; enum rlimit_type { UCOUNT_RLIMIT_NPROC, UCOUNT_RLIMIT_MSGQUEUE, UCOUNT_RLIMIT_SIGPENDING, UCOUNT_RLIMIT_MEMLOCK, UCOUNT_RLIMIT_COUNTS, }; struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; struct uid_gid_map projid_map; struct user_namespace *parent; int level; kuid_t owner; kgid_t group; struct ns_common ns; unsigned long flags; /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP * in its effective capability set at the child ns creation time. */ bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of * these pointers is controlled by keyring_sem. Once * user_keyring_register is set, it won't be changed, so it can be * accessed directly with READ_ONCE(). */ struct list_head keyring_name_list; struct key *user_keyring_register; struct rw_semaphore keyring_sem; #endif /* Register of per-UID persistent keyrings for this namespace */ #ifdef CONFIG_PERSISTENT_KEYRINGS struct key *persistent_keyring_register; #endif struct work_struct work; #ifdef CONFIG_SYSCTL struct ctl_table_set set; struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; long ucount_max[UCOUNT_COUNTS]; long rlimit_max[UCOUNT_RLIMIT_COUNTS]; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); } __randomize_layout; struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; atomic_t count; atomic_long_t ucount[UCOUNT_COUNTS]; atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS]; }; extern struct user_namespace init_user_ns; extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); void put_ucounts(struct ucounts *ucounts); static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type type) { return atomic_long_read(&ucounts->rlimit[type]); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); static inline long get_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type) { return READ_ONCE(ns->rlimit_max[type]); } static inline void set_userns_rlimit_max(struct user_namespace *ns, enum rlimit_type type, unsigned long max) { ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } #ifdef CONFIG_USER_NS static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) refcount_inc(&ns->ns.count); return ns; } extern int create_user_ns(struct cred *new); extern int unshare_userns(unsigned long unshare_flags, struct cred **new_cred); extern void __put_user_ns(struct user_namespace *ns); static inline void put_user_ns(struct user_namespace *ns) { if (ns && refcount_dec_and_test(&ns->ns.count)) __put_user_ns(ns); } struct seq_operations; extern const struct seq_operations proc_uid_seq_operations; extern const struct seq_operations proc_gid_seq_operations; extern const struct seq_operations proc_projid_seq_operations; extern ssize_t proc_uid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_gid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); extern bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); struct ns_common *ns_get_owner(struct ns_common *ns); #else static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { return &init_user_ns; } static inline int create_user_ns(struct cred *new) { return -EINVAL; } static inline int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { if (unshare_flags & CLONE_NEWUSER) return -EINVAL; return 0; } static inline void put_user_ns(struct user_namespace *ns) { } static inline bool userns_may_setgroups(const struct user_namespace *ns) { return true; } static inline bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { return true; } static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; } static inline struct ns_common *ns_get_owner(struct ns_common *ns) { return ERR_PTR(-EPERM); } #endif #endif /* _LINUX_USER_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 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct coalesce_req_info { struct ethnl_req_info base; }; struct coalesce_reply_data { struct ethnl_reply_data base; struct ethtool_coalesce coalesce; struct kernel_ethtool_coalesce kernel_coalesce; u32 supported_params; }; #define COALESCE_REPDATA(__reply_base) \ container_of(__reply_base, struct coalesce_reply_data, base) #define __SUPPORTED_OFFSET ETHTOOL_A_COALESCE_RX_USECS static u32 attr_to_mask(unsigned int attr_type) { return BIT(attr_type - __SUPPORTED_OFFSET); } /* build time check that indices in ethtool_ops::supported_coalesce_params * match corresponding attribute types with an offset */ #define __CHECK_SUPPORTED_OFFSET(x) \ static_assert((ETHTOOL_ ## x) == \ BIT((ETHTOOL_A_ ## x) - __SUPPORTED_OFFSET)) __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_IRQ); __CHECK_SUPPORTED_OFFSET(COALESCE_STATS_BLOCK_USECS); __CHECK_SUPPORTED_OFFSET(COALESCE_USE_ADAPTIVE_RX); __CHECK_SUPPORTED_OFFSET(COALESCE_USE_ADAPTIVE_TX); __CHECK_SUPPORTED_OFFSET(COALESCE_PKT_RATE_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_LOW); __CHECK_SUPPORTED_OFFSET(COALESCE_PKT_RATE_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_USECS_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RX_MAX_FRAMES_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_HIGH); __CHECK_SUPPORTED_OFFSET(COALESCE_RATE_SAMPLE_INTERVAL); const struct nla_policy ethnl_coalesce_get_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int coalesce_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) { struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; data->supported_params = dev->ethtool_ops->supported_coalesce_params; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev->ethtool_ops->get_coalesce(dev, &data->coalesce, &data->kernel_coalesce, extack); ethnl_ops_complete(dev); return ret; } static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_IRQ */ nla_total_size(sizeof(u32)) + /* _TX_USECS */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _TX_USECS_IRQ */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_IRQ */ nla_total_size(sizeof(u32)) + /* _STATS_BLOCK_USECS */ nla_total_size(sizeof(u8)) + /* _USE_ADAPTIVE_RX */ nla_total_size(sizeof(u8)) + /* _USE_ADAPTIVE_TX */ nla_total_size(sizeof(u32)) + /* _PKT_RATE_LOW */ nla_total_size(sizeof(u32)) + /* _RX_USECS_LOW */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_LOW */ nla_total_size(sizeof(u32)) + /* _TX_USECS_LOW */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_LOW */ nla_total_size(sizeof(u32)) + /* _PKT_RATE_HIGH */ nla_total_size(sizeof(u32)) + /* _RX_USECS_HIGH */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_USECS_HIGH */ nla_total_size(sizeof(u32)) + /* _TX_MAX_FRAMES_HIGH */ nla_total_size(sizeof(u32)) + /* _RATE_SAMPLE_INTERVAL */ nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_TX */ nla_total_size(sizeof(u8)); /* _USE_CQE_MODE_RX */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, u32 supported_params) { if (!val && !(supported_params & attr_to_mask(attr_type))) return false; return nla_put_u32(skb, attr_type, val); } static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, u32 supported_params) { if (!val && !(supported_params & attr_to_mask(attr_type))) return false; return nla_put_u8(skb, attr_type, !!val); } static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES, coal->rx_max_coalesced_frames, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_IRQ, coal->rx_coalesce_usecs_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ, coal->rx_max_coalesced_frames_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS, coal->tx_coalesce_usecs, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES, coal->tx_max_coalesced_frames, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_IRQ, coal->tx_coalesce_usecs_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ, coal->tx_max_coalesced_frames_irq, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_STATS_BLOCK_USECS, coal->stats_block_coalesce_usecs, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX, coal->use_adaptive_rx_coalesce, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX, coal->use_adaptive_tx_coalesce, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_PKT_RATE_LOW, coal->pkt_rate_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_LOW, coal->rx_coalesce_usecs_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW, coal->rx_max_coalesced_frames_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_LOW, coal->tx_coalesce_usecs_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW, coal->tx_max_coalesced_frames_low, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_PKT_RATE_HIGH, coal->pkt_rate_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS_HIGH, coal->rx_coalesce_usecs_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH, coal->rx_max_coalesced_frames_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_USECS_HIGH, coal->tx_coalesce_usecs_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH, coal->tx_max_coalesced_frames_high, supported) || coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL, coal->rate_sample_interval, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_TX, kcoal->use_cqe_mode_tx, supported) || coalesce_put_bool(skb, ETHTOOL_A_COALESCE_USE_CQE_MODE_RX, kcoal->use_cqe_mode_rx, supported)) return -EMSGSIZE; return 0; } const struct ethnl_request_ops ethnl_coalesce_request_ops = { .request_cmd = ETHTOOL_MSG_COALESCE_GET, .reply_cmd = ETHTOOL_MSG_COALESCE_GET_REPLY, .hdr_attr = ETHTOOL_A_COALESCE_HEADER, .req_info_size = sizeof(struct coalesce_req_info), .reply_data_size = sizeof(struct coalesce_reply_data), .prepare_data = coalesce_prepare_data, .reply_size = coalesce_reply_size, .fill_reply = coalesce_fill_reply, }; /* COALESCE_SET */ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_COALESCE_RX_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_STATS_BLOCK_USECS] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX] = { .type = NLA_U8 }, [ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX] = { .type = NLA_U8 }, [ETHTOOL_A_COALESCE_PKT_RATE_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_PKT_RATE_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_USECS_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_USECS_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_USE_CQE_MODE_TX] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_COALESCE_USE_CQE_MODE_RX] = NLA_POLICY_MAX(NLA_U8, 1), }; int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info) { struct kernel_ethtool_coalesce kernel_coalesce = {}; struct ethtool_coalesce coalesce = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; const struct ethtool_ops *ops; struct net_device *dev; u32 supported_params; bool mod = false; int ret; u16 a; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_COALESCE_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; ops = dev->ethtool_ops; ret = -EOPNOTSUPP; if (!ops->get_coalesce || !ops->set_coalesce) goto out_dev; /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { ret = -EINVAL; NL_SET_ERR_MSG_ATTR(info->extack, tb[a], "cannot modify an unsupported parameter"); goto out_dev; } rtnl_lock(); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; ret = ops->get_coalesce(dev, &coalesce, &kernel_coalesce, info->extack); if (ret < 0) goto out_ops; ethnl_update_u32(&coalesce.rx_coalesce_usecs, tb[ETHTOOL_A_COALESCE_RX_USECS], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES], &mod); ethnl_update_u32(&coalesce.rx_coalesce_usecs_irq, tb[ETHTOOL_A_COALESCE_RX_USECS_IRQ], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames_irq, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs, tb[ETHTOOL_A_COALESCE_TX_USECS], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs_irq, tb[ETHTOOL_A_COALESCE_TX_USECS_IRQ], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames_irq, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ], &mod); ethnl_update_u32(&coalesce.stats_block_coalesce_usecs, tb[ETHTOOL_A_COALESCE_STATS_BLOCK_USECS], &mod); ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod); ethnl_update_bool32(&coalesce.use_adaptive_tx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX], &mod); ethnl_update_u32(&coalesce.pkt_rate_low, tb[ETHTOOL_A_COALESCE_PKT_RATE_LOW], &mod); ethnl_update_u32(&coalesce.rx_coalesce_usecs_low, tb[ETHTOOL_A_COALESCE_RX_USECS_LOW], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames_low, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs_low, tb[ETHTOOL_A_COALESCE_TX_USECS_LOW], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames_low, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW], &mod); ethnl_update_u32(&coalesce.pkt_rate_high, tb[ETHTOOL_A_COALESCE_PKT_RATE_HIGH], &mod); ethnl_update_u32(&coalesce.rx_coalesce_usecs_high, tb[ETHTOOL_A_COALESCE_RX_USECS_HIGH], &mod); ethnl_update_u32(&coalesce.rx_max_coalesced_frames_high, tb[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH], &mod); ethnl_update_u32(&coalesce.tx_coalesce_usecs_high, tb[ETHTOOL_A_COALESCE_TX_USECS_HIGH], &mod); ethnl_update_u32(&coalesce.tx_max_coalesced_frames_high, tb[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH], &mod); ethnl_update_u32(&coalesce.rate_sample_interval, tb[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL], &mod); ethnl_update_u8(&kernel_coalesce.use_cqe_mode_tx, tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_TX], &mod); ethnl_update_u8(&kernel_coalesce.use_cqe_mode_rx, tb[ETHTOOL_A_COALESCE_USE_CQE_MODE_RX], &mod); ret = 0; if (!mod) goto out_ops; ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce, info->extack); if (ret < 0) goto out_ops; ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL); out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(&req_info); 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 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | /* 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 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, bool ign_usage_count); 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 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_update_max_time_suspended(struct device *dev, s64 delta_ns); 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); extern int devm_pm_runtime_enable(struct device *dev); /** * pm_runtime_get_if_in_use - Conditionally bump up runtime PM usage counter. * @dev: Target device. * * Increment the runtime PM usage counter of @dev if its runtime PM status is * %RPM_ACTIVE and its runtime PM usage counter is greater than 0. */ static inline int pm_runtime_get_if_in_use(struct device *dev) { return pm_runtime_get_if_active(dev, false); } /** * 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_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 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, bool ign_usage_count) { 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 void pm_runtime_enable(struct device *dev) {} static inline void __pm_runtime_disable(struct device *dev, bool c) {} static inline void pm_runtime_allow(struct device *dev) {} static inline void pm_runtime_forbid(struct device *dev) {} static inline int devm_pm_runtime_enable(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); } /** * 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 * "blocking" counter). * * For each invocation of this function for @dev there must be a matching * pm_runtime_enable() call in order for runtime PM to be enabled for it. */ 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 |
| 494 495 555 371 393 125 365 365 365 110 1098 1101 1101 1099 1097 1098 1098 1098 1096 561 815 1097 1 284 1092 1097 1097 1097 399 398 6 398 1333 1333 1333 1331 440 1113 1113 1113 1114 1333 1333 1332 390 390 390 390 390 361 361 361 361 290 2 361 361 361 362 362 1 361 361 360 361 84 103 62 62 85 103 85 84 84 45 83 21 64 84 83 83 83 81 103 103 103 46 85 46 103 103 21 24 59 44 44 44 102 3 103 50 50 309 315 305 195 39 84 88 37 37 12 11 34 11 271 210 1 1 1 1 1 2 145 141 137 1 1 2 1 1 359 360 360 360 359 1 344 344 344 4 344 55 1 54 54 54 53 53 53 3 2 51 51 51 51 1 50 51 3 3 1 2 308 308 308 308 308 169 169 169 169 1 344 32 169 169 141 4 347 344 2 1 4 178 168 51 51 1 48 1 2 2 2 402 2 51 2 3 347 457 8 454 2125 2114 290 1084 13 5 13 494 3 134 401 398 136 7 203 238 7 398 398 397 18 18 1 37 62 37 37 37 675 675 6 422 388 674 674 674 393 393 393 674 422 388 674 674 393 674 393 393 393 392 393 393 3 387 422 422 203 203 203 308 407 408 66 308 146 203 285 75 390 65 412 412 412 412 412 412 411 412 1988 1988 1990 1990 1990 1989 1990 1990 2104 2104 714 1990 398 207 193 278 121 398 398 398 398 412 412 412 54 54 54 393 393 393 393 393 54 1114 1114 1114 1114 285 285 1112 1112 1113 440 285 285 285 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 Address [auto]configuration * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ /* * Changes: * * Janos Farkas : delete timer on ifdown * <chexum@bankinf.banki.hu> * Andi Kleen : kill double kfree on module * unload. * Maciej W. Rozycki : FDDI support * sekiya@USAGI : Don't send too many RS * packets. * yoshfuji@USAGI : Fixed interval between DAD * packets. * YOSHIFUJI Hideaki @USAGI : improved accuracy of * address validation timer. * YOSHIFUJI Hideaki @USAGI : Privacy Extensions (RFC3041) * support. * Yuji SEKIYA @USAGI : Don't assign a same IPv6 * address on a same interface. * YOSHIFUJI Hideaki @USAGI : ARCnet support * YOSHIFUJI Hideaki @USAGI : convert /proc/net/if_inet6 to * seq_file. * YOSHIFUJI Hideaki @USAGI : improved source address * selection; consider scope, * status etc. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/if_arcnet.h> #include <linux/if_infiniband.h> #include <linux/route.h> #include <linux/inetdevice.h> #include <linux/init.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/capability.h> #include <linux/delay.h> #include <linux/notifier.h> #include <linux/string.h> #include <linux/hash.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> #include <net/6lowpan.h> #include <net/firewire.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/tcp.h> #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/l3mdev.h> #include <linux/if_tunnel.h> #include <linux/rtnetlink.h> #include <linux/netconf.h> #include <linux/random.h> #include <linux/uaccess.h> #include <asm/unaligned.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #include <linux/ioam6.h> #define INFINITY_LIFE_TIME 0xFFFFFFFF #define IPV6_MAX_STRLEN \ sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static inline s32 rfc3315_s14_backoff_init(s32 irt) { /* multiply 'initial retransmission time' by 0.9 .. 1.1 */ u64 tmp = (900000 + prandom_u32_max(200001)) * (u64)irt; do_div(tmp, 1000000); return (s32)tmp; } static inline s32 rfc3315_s14_backoff_update(s32 rt, s32 mrt) { /* multiply 'retransmission timeout' by 1.9 .. 2.1 */ u64 tmp = (1900000 + prandom_u32_max(200001)) * (u64)rt; do_div(tmp, 1000000); if ((s32)tmp > mrt) { /* multiply 'maximum retransmission time' by 0.9 .. 1.1 */ tmp = (900000 + prandom_u32_max(200001)) * (u64)mrt; do_div(tmp, 1000000); } return (s32)tmp; } #ifdef CONFIG_SYSCTL static int addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); #else static inline int addrconf_sysctl_register(struct inet6_dev *idev) { return 0; } static inline void addrconf_sysctl_unregister(struct inet6_dev *idev) { } #endif static void ipv6_gen_rnd_iid(struct in6_addr *addr); static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(const struct inet6_dev *idev); static int ipv6_generate_stable_address(struct in6_addr *addr, u8 dad_count, const struct inet6_dev *idev); #define IN6_ADDR_HSIZE_SHIFT 8 #define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) static void addrconf_verify(struct net *net); static void addrconf_verify_rtnl(struct net *net); static struct workqueue_struct *addrconf_wq; static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, bool unregister); static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags, bool no_gw); static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_work(struct work_struct *w); static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, bool send_na); static void addrconf_dad_run(struct inet6_dev *idev, bool restart); static void addrconf_rs_timer(struct timer_list *t); static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa); static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo); static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, .accept_ra = 1, .accept_redirects = 1, .autoconf = 1, .force_mld_version = 0, .mldv1_unsolicited_report_interval = 10 * HZ, .mldv2_unsolicited_report_interval = HZ, .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif .accept_ra_rt_table = 0, .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, .accept_dad = 0, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, .stable_secret = { .initialized = false, }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, .seg6_enabled = 0, #ifdef CONFIG_IPV6_SEG6_HMAC .seg6_require_hmac = 0, #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, .mtu6 = IPV6_MIN_MTU, .accept_ra = 1, .accept_redirects = 1, .autoconf = 1, .force_mld_version = 0, .mldv1_unsolicited_report_interval = 10 * HZ, .mldv2_unsolicited_report_interval = HZ, .dad_transmits = 1, .rtr_solicits = MAX_RTR_SOLICITATIONS, .rtr_solicit_interval = RTR_SOLICITATION_INTERVAL, .rtr_solicit_max_interval = RTR_SOLICITATION_MAX_INTERVAL, .rtr_solicit_delay = MAX_RTR_SOLICITATION_DELAY, .use_tempaddr = 0, .temp_valid_lft = TEMP_VALID_LIFETIME, .temp_prefered_lft = TEMP_PREFERRED_LIFETIME, .regen_max_retry = REGEN_MAX_RETRY, .max_desync_factor = MAX_DESYNC_FACTOR, .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .ra_defrtr_metric = IP6_RT_PRIO_USER, .accept_ra_from_local = 0, .accept_ra_min_hop_limit= 1, .accept_ra_min_lft = 0, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, .rtr_probe_interval = 60 * HZ, #ifdef CONFIG_IPV6_ROUTE_INFO .accept_ra_rt_info_min_plen = 0, .accept_ra_rt_info_max_plen = 0, #endif #endif .accept_ra_rt_table = 0, .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, .accept_dad = 1, .suppress_frag_ndisc = 1, .accept_ra_mtu = 1, .stable_secret = { .initialized = false, }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, .keep_addr_on_down = 0, .seg6_enabled = 0, #ifdef CONFIG_IPV6_SEG6_HMAC .seg6_require_hmac = 0, #endif .enhanced_dad = 1, .addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64, .disable_policy = 0, .rpl_seg_enabled = 0, .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, }; /* Check if link is ready: is it up and is a valid qdisc available */ static inline bool addrconf_link_ready(const struct net_device *dev) { return netif_oper_up(dev) && !qdisc_tx_is_noop(dev); } static void addrconf_del_rs_timer(struct inet6_dev *idev) { if (del_timer(&idev->rs_timer)) __in6_dev_put(idev); } static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) { if (cancel_delayed_work(&ifp->dad_work)) __in6_ifa_put(ifp); } static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, unsigned long delay) { in6_ifa_hold(ifp); if (mod_delayed_work(addrconf_wq, &ifp->dad_work, delay)) in6_ifa_put(ifp); } static int snmp6_alloc_dev(struct inet6_dev *idev) { int i; idev->stats.ipv6 = alloc_percpu_gfp(struct ipstats_mib, GFP_KERNEL_ACCOUNT); if (!idev->stats.ipv6) goto err_ip; for_each_possible_cpu(i) { struct ipstats_mib *addrconf_stats; addrconf_stats = per_cpu_ptr(idev->stats.ipv6, i); u64_stats_init(&addrconf_stats->syncp); } idev->stats.icmpv6dev = kzalloc(sizeof(struct icmpv6_mib_device), GFP_KERNEL); if (!idev->stats.icmpv6dev) goto err_icmp; idev->stats.icmpv6msgdev = kzalloc(sizeof(struct icmpv6msg_mib_device), GFP_KERNEL_ACCOUNT); if (!idev->stats.icmpv6msgdev) goto err_icmpmsg; return 0; err_icmpmsg: kfree(idev->stats.icmpv6dev); err_icmp: free_percpu(idev->stats.ipv6); err_ip: return -ENOMEM; } static struct inet6_dev *ipv6_add_dev(struct net_device *dev) { struct inet6_dev *ndev; int err = -ENOMEM; ASSERT_RTNL(); if (dev->mtu < IPV6_MIN_MTU && dev != blackhole_netdev) return ERR_PTR(-EINVAL); ndev = kzalloc(sizeof(*ndev), GFP_KERNEL_ACCOUNT); if (!ndev) return ERR_PTR(err); rwlock_init(&ndev->lock); ndev->dev = dev; INIT_LIST_HEAD(&ndev->addr_list); timer_setup(&ndev->rs_timer, addrconf_rs_timer, 0); memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); if (ndev->cnf.stable_secret.initialized) ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; ndev->cnf.mtu6 = dev->mtu; ndev->ra_mtu = 0; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); if (!ndev->nd_parms) { kfree(ndev); return ERR_PTR(err); } if (ndev->cnf.forwarding) dev_disable_lro(dev); /* We refer to the device */ netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL); if (snmp6_alloc_dev(ndev) < 0) { netdev_dbg(dev, "%s: cannot allocate memory for statistics\n", __func__); neigh_parms_release(&nd_tbl, ndev->nd_parms); netdev_put(dev, &ndev->dev_tracker); kfree(ndev); return ERR_PTR(err); } if (dev != blackhole_netdev) { if (snmp6_register_dev(ndev) < 0) { netdev_dbg(dev, "%s: cannot create /proc/net/dev_snmp6/%s\n", __func__, dev->name); goto err_release; } } /* One reference from device. */ refcount_set(&ndev->refcnt, 1); if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) ndev->cnf.accept_dad = -1; #if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { pr_info("%s: Disabled Multicast RS\n", dev->name); ndev->cnf.rtr_solicits = 0; } #endif INIT_LIST_HEAD(&ndev->tempaddr_list); ndev->desync_factor = U32_MAX; if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || dev->type == ARPHRD_TUNNEL6 || dev->type == ARPHRD_SIT || dev->type == ARPHRD_NONE) { ndev->cnf.use_tempaddr = -1; } ndev->token = in6addr_any; if (netif_running(dev) && addrconf_link_ready(dev)) ndev->if_flags |= IF_READY; ipv6_mc_init_dev(ndev); ndev->tstamp = jiffies; if (dev != blackhole_netdev) { err = addrconf_sysctl_register(ndev); if (err) { ipv6_mc_destroy_dev(ndev); snmp6_unregister_dev(ndev); goto err_release; } } /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); if (dev != blackhole_netdev) { /* Join interface-local all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); /* Join all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); /* Join all-router multicast group if forwarding is set */ if (ndev->cnf.forwarding && (dev->flags & IFF_MULTICAST)) ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); } return ndev; err_release: neigh_parms_release(&nd_tbl, ndev->nd_parms); ndev->dead = 1; in6_dev_finish_destroy(ndev); return ERR_PTR(err); } static struct inet6_dev *ipv6_find_idev(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) { idev = ipv6_add_dev(dev); if (IS_ERR(idev)) return idev; } if (dev->flags&IFF_UP) ipv6_mc_up(idev); return idev; } static int inet6_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_FORWARDING) size += nla_total_size(4); #ifdef CONFIG_IPV6_MROUTE if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); #endif if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, struct ipv6_devconf *devconf, 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_INET6; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, devconf->forwarding) < 0) goto nla_put_failure; #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, atomic_read(&devconf->mc_forwarding)) < 0) goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, devconf->ignore_routes_with_linkdown) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet6_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv6_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet6_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_NETCONF, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_NETCONF, err); } static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet6_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_ipv6_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct netconfmsg), tb, NETCONFA_MAX, devconf_ipv6_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 inet6_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 inet6_dev *in6_dev = NULL; struct net_device *dev = NULL; struct sk_buff *skb; struct ipv6_devconf *devconf; int ifindex; int err; err = inet6_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (!tb[NETCONFA_IFINDEX]) return -EINVAL; err = -EINVAL; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv6.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv6.devconf_dflt; break; default: dev = dev_get_by_index(net, ifindex); if (!dev) return -EINVAL; in6_dev = in6_dev_get(dev); if (!in6_dev) goto errout; devconf = &in6_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet6_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet6_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: if (in6_dev) in6_dev_put(in6_dev); dev_put(dev); return err; } /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet6_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv6.dev_addr_genid) + net->dev_base_seq; /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. */ if (!res) res = 0x80000000; return res; } static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); int h, s_h; int idx, s_idx; struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; 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; } } s_h = cb->args[0]; s_idx = idx = cb->args[1]; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; idev = __in6_dev_get(dev); if (!idev) goto cont; if (inet6_netconf_fill_devconf(skb, dev->ifindex, &idev->cnf, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL) < 0) { rcu_read_unlock(); goto done; } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } rcu_read_unlock(); } if (h == NETDEV_HASHENTRIES) { if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL) < 0) goto done; else h++; } if (h == NETDEV_HASHENTRIES + 1) { if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL) < 0) goto done; else h++; } done: cb->args[0] = h; cb->args[1] = idx; return skb->len; } #ifdef CONFIG_SYSCTL static void dev_forward_change(struct inet6_dev *idev) { struct net_device *dev; struct inet6_ifaddr *ifa; LIST_HEAD(tmp_addr_list); if (!idev) return; dev = idev->dev; if (idev->cnf.forwarding) dev_disable_lro(dev); if (dev->flags & IFF_MULTICAST) { if (idev->cnf.forwarding) { ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allrouters); ipv6_dev_mc_inc(dev, &in6addr_sitelocal_allrouters); } else { ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); ipv6_dev_mc_dec(dev, &in6addr_interfacelocal_allrouters); ipv6_dev_mc_dec(dev, &in6addr_sitelocal_allrouters); } } read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa->flags&IFA_F_TENTATIVE) continue; list_add_tail(&ifa->if_list_aux, &tmp_addr_list); } read_unlock_bh(&idev->lock); while (!list_empty(&tmp_addr_list)) { ifa = list_first_entry(&tmp_addr_list, struct inet6_ifaddr, if_list_aux); list_del(&ifa->if_list_aux); if (idev->cnf.forwarding) addrconf_join_anycast(ifa); else addrconf_leave_anycast(ifa); } inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &idev->cnf); } static void addrconf_forward_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); idev->cnf.forwarding = newf; if (changed) dev_forward_change(idev); } } } static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) { struct net *net; int old; if (!rtnl_trylock()) return restart_syscall(); net = (struct net *)table->extra2; old = *p; *p = newf; if (p == &net->ipv6.devconf_dflt->forwarding) { if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); rtnl_unlock(); return 0; } if (p == &net->ipv6.devconf_all->forwarding) { int old_dflt = net->ipv6.devconf_dflt->forwarding; net->ipv6.devconf_dflt->forwarding = newf; if ((!newf) ^ (!old_dflt)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); addrconf_forward_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } else if ((!newf) ^ (!old)) dev_forward_change((struct inet6_dev *)table->extra1); rtnl_unlock(); if (newf) rt6_purge_dflt_routers(net); return 1; } static void addrconf_linkdown_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); idev->cnf.ignore_routes_with_linkdown = newf; if (changed) inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, dev->ifindex, &idev->cnf); } } } static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) { struct net *net; int old; if (!rtnl_trylock()) return restart_syscall(); net = (struct net *)table->extra2; old = *p; *p = newf; if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); rtnl_unlock(); return 0; } if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf; addrconf_linkdown_change(net, newf); if ((!newf) ^ (!old)) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); } rtnl_unlock(); return 1; } #endif /* Nobody refers to this ifaddr, destroy it */ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { WARN_ON(!hlist_unhashed(&ifp->addr_lst)); #ifdef NET_REFCNT_DEBUG pr_debug("%s\n", __func__); #endif in6_dev_put(ifp->idev); if (cancel_delayed_work(&ifp->dad_work)) pr_notice("delayed DAD work was pending while freeing ifa=%p\n", ifp); if (ifp->state != INET6_IFADDR_STATE_DEAD) { pr_warn("Freeing alive inet6 address %p\n", ifp); return; } kfree_rcu(ifp, rcu); } static void ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { struct list_head *p; int ifp_scope = ipv6_addr_src_scope(&ifp->addr); /* * Each device address list is sorted in order of scope - * global before linklocal. */ list_for_each(p, &idev->addr_list) { struct inet6_ifaddr *ifa = list_entry(p, struct inet6_ifaddr, if_list); if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr)) break; } list_add_tail_rcu(&ifp->if_list, p); } static u32 inet6_addr_hash(const struct net *net, const struct in6_addr *addr) { u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); return hash_32(val, IN6_ADDR_HSIZE_SHIFT); } static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev, unsigned int hash) { struct inet6_ifaddr *ifp; hlist_for_each_entry(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev) return true; } } return false; } static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa) { struct net *net = dev_net(dev); unsigned int hash = inet6_addr_hash(net, &ifa->addr); int err = 0; spin_lock_bh(&net->ipv6.addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(net, &ifa->addr, dev, hash)) { netdev_dbg(dev, "ipv6_add_addr: already assigned\n"); err = -EEXIST; } else { hlist_add_head_rcu(&ifa->addr_lst, &net->ipv6.inet6_addr_lst[hash]); } spin_unlock_bh(&net->ipv6.addrconf_hash_lock); return err; } /* On success it returns ifp with increased reference count */ static struct inet6_ifaddr * ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, bool can_block, struct netlink_ext_ack *extack) { gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; int addr_type = ipv6_addr_type(cfg->pfx); struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; struct fib6_info *f6i = NULL; int err = 0; if (addr_type == IPV6_ADDR_ANY || (addr_type & IPV6_ADDR_MULTICAST && !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) || (!(idev->dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(idev->dev) && addr_type & IPV6_ADDR_LOOPBACK)) return ERR_PTR(-EADDRNOTAVAIL); if (idev->dead) { err = -ENODEV; /*XXX*/ goto out; } if (idev->cnf.disable_ipv6) { err = -EACCES; goto out; } /* validator notifier needs to be blocking; * do not call in atomic context */ if (can_block) { struct in6_validator_info i6vi = { .i6vi_addr = *cfg->pfx, .i6vi_dev = idev, .extack = extack, }; err = inet6addr_validator_notifier_call_chain(NETDEV_UP, &i6vi); err = notifier_to_errno(err); if (err < 0) goto out; } ifa = kzalloc(sizeof(*ifa), gfp_flags | __GFP_ACCOUNT); if (!ifa) { err = -ENOBUFS; goto out; } f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags); if (IS_ERR(f6i)) { err = PTR_ERR(f6i); f6i = NULL; goto out; } neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *cfg->pfx; if (cfg->peer_pfx) ifa->peer_addr = *cfg->peer_pfx; spin_lock_init(&ifa->lock); INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work); INIT_HLIST_NODE(&ifa->addr_lst); ifa->scope = cfg->scope; ifa->prefix_len = cfg->plen; ifa->rt_priority = cfg->rt_priority; ifa->flags = cfg->ifa_flags; ifa->ifa_proto = cfg->ifa_proto; /* No need to add the TENTATIVE flag for addresses with NODAD */ if (!(cfg->ifa_flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; ifa->valid_lft = cfg->valid_lft; ifa->prefered_lft = cfg->preferred_lft; ifa->cstamp = ifa->tstamp = jiffies; ifa->tokenized = false; ifa->rt = f6i; ifa->idev = idev; in6_dev_hold(idev); /* For caller */ refcount_set(&ifa->refcnt, 1); rcu_read_lock(); err = ipv6_add_addr_hash(idev->dev, ifa); if (err < 0) { rcu_read_unlock(); goto out; } write_lock_bh(&idev->lock); /* Add to inet6_dev unicast addr list. */ ipv6_link_dev_addr(idev, ifa); if (ifa->flags&IFA_F_TEMPORARY) { list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } in6_ifa_hold(ifa); write_unlock_bh(&idev->lock); rcu_read_unlock(); inet6addr_notifier_call_chain(NETDEV_UP, ifa); out: if (unlikely(err < 0)) { fib6_info_release(f6i); if (ifa) { if (ifa->idev) in6_dev_put(ifa->idev); kfree(ifa); } ifa = ERR_PTR(err); } return ifa; } enum cleanup_prefix_rt_t { CLEANUP_PREFIX_RT_NOP, /* no cleanup action for prefix route */ CLEANUP_PREFIX_RT_DEL, /* delete the prefix route */ CLEANUP_PREFIX_RT_EXPIRE, /* update the lifetime of the prefix route */ }; /* * Check, whether the prefix for ifp would still need a prefix route * after deleting ifp. The function returns one of the CLEANUP_PREFIX_RT_* * constants. * * 1) we don't purge prefix if address was not permanent. * prefix is managed by its own lifetime. * 2) we also don't purge, if the address was IFA_F_NOPREFIXROUTE. * 3) if there are no addresses, delete prefix. * 4) if there are still other permanent address(es), * corresponding prefix is still permanent. * 5) if there are still other addresses with IFA_F_NOPREFIXROUTE, * don't purge the prefix, assume user space is managing it. * 6) otherwise, update prefix lifetime to the * longest valid lifetime among the corresponding * addresses on the device. * Note: subsequent RA will update lifetime. **/ static enum cleanup_prefix_rt_t check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) { struct inet6_ifaddr *ifa; struct inet6_dev *idev = ifp->idev; unsigned long lifetime; enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_DEL; *expires = jiffies; list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; if (ifa->prefix_len != ifp->prefix_len || !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) return CLEANUP_PREFIX_RT_NOP; action = CLEANUP_PREFIX_RT_EXPIRE; spin_lock(&ifa->lock); lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); /* * Note: Because this address is * not permanent, lifetime < * LONG_MAX / HZ here. */ if (time_before(*expires, ifa->tstamp + lifetime * HZ)) *expires = ifa->tstamp + lifetime * HZ; spin_unlock(&ifa->lock); } return action; } static void cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt, bool del_peer) { struct fib6_info *f6i; f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (f6i) { if (del_rt) ip6_del_rt(dev_net(ifp->idev->dev), f6i, false); else { if (!(f6i->fib6_flags & RTF_EXPIRES)) fib6_set_expires(f6i, expires); fib6_info_release(f6i); } } } /* This function wants to get referenced ifp and releases it before return */ static void ipv6_del_addr(struct inet6_ifaddr *ifp) { enum cleanup_prefix_rt_t action = CLEANUP_PREFIX_RT_NOP; struct net *net = dev_net(ifp->idev->dev); unsigned long expires; int state; ASSERT_RTNL(); spin_lock_bh(&ifp->lock); state = ifp->state; ifp->state = INET6_IFADDR_STATE_DEAD; spin_unlock_bh(&ifp->lock); if (state == INET6_IFADDR_STATE_DEAD) goto out; spin_lock_bh(&net->ipv6.addrconf_hash_lock); hlist_del_init_rcu(&ifp->addr_lst); spin_unlock_bh(&net->ipv6.addrconf_hash_lock); write_lock_bh(&ifp->idev->lock); if (ifp->flags&IFA_F_TEMPORARY) { list_del(&ifp->tmp_list); if (ifp->ifpub) { in6_ifa_put(ifp->ifpub); ifp->ifpub = NULL; } __in6_ifa_put(ifp); } if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); list_del_rcu(&ifp->if_list); __in6_ifa_put(ifp); write_unlock_bh(&ifp->idev->lock); addrconf_del_dad_work(ifp); ipv6_ifa_notify(RTM_DELADDR, ifp); inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, expires, action == CLEANUP_PREFIX_RT_DEL, false); } /* clean up prefsrc entries */ rt6_remove_prefsrc(ifp); out: in6_ifa_put(ifp); } static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block) { struct inet6_dev *idev = ifp->idev; unsigned long tmp_tstamp, age; unsigned long regen_advance; unsigned long now = jiffies; s32 cnf_temp_preferred_lft; struct inet6_ifaddr *ift; struct ifa6_config cfg; long max_desync_factor; struct in6_addr addr; int ret = 0; write_lock_bh(&idev->lock); retry: in6_dev_hold(idev); if (idev->cnf.use_tempaddr <= 0) { write_unlock_bh(&idev->lock); pr_info("%s: use_tempaddr is disabled\n", __func__); in6_dev_put(idev); ret = -1; goto out; } spin_lock_bh(&ifp->lock); if (ifp->regen_count++ >= idev->cnf.regen_max_retry) { idev->cnf.use_tempaddr = -1; /*XXX*/ spin_unlock_bh(&ifp->lock); write_unlock_bh(&idev->lock); pr_warn("%s: regeneration time exceeded - disabled temporary address support\n", __func__); in6_dev_put(idev); ret = -1; goto out; } in6_ifa_hold(ifp); memcpy(addr.s6_addr, ifp->addr.s6_addr, 8); ipv6_gen_rnd_iid(&addr); age = (now - ifp->tstamp) / HZ; regen_advance = idev->cnf.regen_max_retry * idev->cnf.dad_transmits * max(NEIGH_VAR(idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; /* recalculate max_desync_factor each time and update * idev->desync_factor if it's larger */ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft); max_desync_factor = min_t(long, idev->cnf.max_desync_factor, cnf_temp_preferred_lft - regen_advance); if (unlikely(idev->desync_factor > max_desync_factor)) { if (max_desync_factor > 0) { get_random_bytes(&idev->desync_factor, sizeof(idev->desync_factor)); idev->desync_factor %= max_desync_factor; } else { idev->desync_factor = 0; } } memset(&cfg, 0, sizeof(cfg)); cfg.valid_lft = min_t(__u32, ifp->valid_lft, idev->cnf.temp_valid_lft + age); cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft); cfg.plen = ifp->prefix_len; tmp_tstamp = ifp->tstamp; spin_unlock_bh(&ifp->lock); write_unlock_bh(&idev->lock); /* A temporary address is created only if this calculated Preferred * Lifetime is greater than REGEN_ADVANCE time units. In particular, * an implementation must not create a temporary address with a zero * Preferred Lifetime. * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (cfg.preferred_lft <= regen_advance + age) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; goto out; } cfg.ifa_flags = IFA_F_TEMPORARY; /* set in addrconf_prefix_rcv() */ if (ifp->flags & IFA_F_OPTIMISTIC) cfg.ifa_flags |= IFA_F_OPTIMISTIC; cfg.pfx = &addr; cfg.scope = ipv6_addr_scope(cfg.pfx); ift = ipv6_add_addr(idev, &cfg, block, NULL); if (IS_ERR(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); write_lock_bh(&idev->lock); goto retry; } spin_lock_bh(&ift->lock); ift->ifpub = ifp; ift->cstamp = now; ift->tstamp = tmp_tstamp; spin_unlock_bh(&ift->lock); addrconf_dad_start(ift); in6_ifa_put(ift); in6_dev_put(idev); out: return ret; } /* * Choose an appropriate source address (RFC3484) */ enum { IPV6_SADDR_RULE_INIT = 0, IPV6_SADDR_RULE_LOCAL, IPV6_SADDR_RULE_SCOPE, IPV6_SADDR_RULE_PREFERRED, #ifdef CONFIG_IPV6_MIP6 IPV6_SADDR_RULE_HOA, #endif IPV6_SADDR_RULE_OIF, IPV6_SADDR_RULE_LABEL, IPV6_SADDR_RULE_PRIVACY, IPV6_SADDR_RULE_ORCHID, IPV6_SADDR_RULE_PREFIX, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD IPV6_SADDR_RULE_NOT_OPTIMISTIC, #endif IPV6_SADDR_RULE_MAX }; struct ipv6_saddr_score { int rule; int addr_type; struct inet6_ifaddr *ifa; DECLARE_BITMAP(scorebits, IPV6_SADDR_RULE_MAX); int scopedist; int matchlen; }; struct ipv6_saddr_dst { const struct in6_addr *addr; int ifindex; int scope; int label; unsigned int prefs; }; static inline int ipv6_saddr_preferred(int type) { if (type & (IPV6_ADDR_MAPPED|IPV6_ADDR_COMPATv4|IPV6_ADDR_LOOPBACK)) return 1; return 0; } static bool ipv6_use_optimistic_addr(struct net *net, struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) return false; if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic) return false; return true; #else return false; #endif } static bool ipv6_allow_optimistic_dad(struct net *net, struct inet6_dev *idev) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (!idev) return false; if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad) return false; return true; #else return false; #endif } static int ipv6_get_saddr_eval(struct net *net, struct ipv6_saddr_score *score, struct ipv6_saddr_dst *dst, int i) { int ret; if (i <= score->rule) { switch (i) { case IPV6_SADDR_RULE_SCOPE: ret = score->scopedist; break; case IPV6_SADDR_RULE_PREFIX: ret = score->matchlen; break; default: ret = !!test_bit(i, score->scorebits); } goto out; } switch (i) { case IPV6_SADDR_RULE_INIT: /* Rule 0: remember if hiscore is not ready yet */ ret = !!score->ifa; break; case IPV6_SADDR_RULE_LOCAL: /* Rule 1: Prefer same address */ ret = ipv6_addr_equal(&score->ifa->addr, dst->addr); break; case IPV6_SADDR_RULE_SCOPE: /* Rule 2: Prefer appropriate scope * * ret * ^ * -1 | d 15 * ---+--+-+---> scope * | * | d is scope of the destination. * B-d | \ * | \ <- smaller scope is better if * B-15 | \ if scope is enough for destination. * | ret = B - scope (-1 <= scope >= d <= 15). * d-C-1 | / * |/ <- greater is better * -C / if scope is not enough for destination. * /| ret = scope - C (-1 <= d < scope <= 15). * * d - C - 1 < B -15 (for all -1 <= d <= 15). * C > d + 14 - B >= 15 + 14 - B = 29 - B. * Assume B = 0 and we get C > 29. */ ret = __ipv6_addr_src_scope(score->addr_type); if (ret >= dst->scope) ret = -ret; else ret -= 128; /* 30 is enough */ score->scopedist = ret; break; case IPV6_SADDR_RULE_PREFERRED: { /* Rule 3: Avoid deprecated and optimistic addresses */ u8 avoid = IFA_F_DEPRECATED; if (!ipv6_use_optimistic_addr(net, score->ifa->idev)) avoid |= IFA_F_OPTIMISTIC; ret = ipv6_saddr_preferred(score->addr_type) || !(score->ifa->flags & avoid); break; } #ifdef CONFIG_IPV6_MIP6 case IPV6_SADDR_RULE_HOA: { /* Rule 4: Prefer home address */ int prefhome = !(dst->prefs & IPV6_PREFER_SRC_COA); ret = !(score->ifa->flags & IFA_F_HOMEADDRESS) ^ prefhome; break; } #endif case IPV6_SADDR_RULE_OIF: /* Rule 5: Prefer outgoing interface */ ret = (!dst->ifindex || dst->ifindex == score->ifa->idev->dev->ifindex); break; case IPV6_SADDR_RULE_LABEL: /* Rule 6: Prefer matching label */ ret = ipv6_addr_label(net, &score->ifa->addr, score->addr_type, score->ifa->idev->dev->ifindex) == dst->label; break; case IPV6_SADDR_RULE_PRIVACY: { /* Rule 7: Prefer public address * Note: prefer temporary address if use_tempaddr >= 2 */ int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? !!(dst->prefs & IPV6_PREFER_SRC_TMP) : score->ifa->idev->cnf.use_tempaddr >= 2; ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; } case IPV6_SADDR_RULE_ORCHID: /* Rule 8-: Prefer ORCHID vs ORCHID or * non-ORCHID vs non-ORCHID */ ret = !(ipv6_addr_orchid(&score->ifa->addr) ^ ipv6_addr_orchid(dst->addr)); break; case IPV6_SADDR_RULE_PREFIX: /* Rule 8: Use longest matching prefix */ ret = ipv6_addr_diff(&score->ifa->addr, dst->addr); if (ret > score->ifa->prefix_len) ret = score->ifa->prefix_len; score->matchlen = ret; break; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD case IPV6_SADDR_RULE_NOT_OPTIMISTIC: /* Optimistic addresses still have lower precedence than other * preferred addresses. */ ret = !(score->ifa->flags & IFA_F_OPTIMISTIC); break; #endif default: ret = 0; } if (ret) __set_bit(i, score->scorebits); score->rule = i; out: return ret; } static int __ipv6_dev_get_saddr(struct net *net, struct ipv6_saddr_dst *dst, struct inet6_dev *idev, struct ipv6_saddr_score *scores, int hiscore_idx) { struct ipv6_saddr_score *score = &scores[1 - hiscore_idx], *hiscore = &scores[hiscore_idx]; list_for_each_entry_rcu(score->ifa, &idev->addr_list, if_list) { int i; /* * - Tentative Address (RFC2462 section 5.4) * - A tentative address is not considered * "assigned to an interface" in the traditional * sense, unless it is also flagged as optimistic. * - Candidate Source Address (section 4) * - In any case, anycast addresses, multicast * addresses, and the unspecified address MUST * NOT be included in a candidate set. */ if ((score->ifa->flags & IFA_F_TENTATIVE) && (!(score->ifa->flags & IFA_F_OPTIMISTIC))) continue; score->addr_type = __ipv6_addr_type(&score->ifa->addr); if (unlikely(score->addr_type == IPV6_ADDR_ANY || score->addr_type & IPV6_ADDR_MULTICAST)) { net_dbg_ratelimited("ADDRCONF: unspecified / multicast address assigned as unicast address on %s", idev->dev->name); continue; } score->rule = -1; bitmap_zero(score->scorebits, IPV6_SADDR_RULE_MAX); for (i = 0; i < IPV6_SADDR_RULE_MAX; i++) { int minihiscore, miniscore; minihiscore = ipv6_get_saddr_eval(net, hiscore, dst, i); miniscore = ipv6_get_saddr_eval(net, score, dst, i); if (minihiscore > miniscore) { if (i == IPV6_SADDR_RULE_SCOPE && score->scopedist > 0) { /* * special case: * each remaining entry * has too small (not enough) * scope, because ifa entries * are sorted by their scope * values. */ goto out; } break; } else if (minihiscore < miniscore) { swap(hiscore, score); hiscore_idx = 1 - hiscore_idx; /* restore our iterator */ score->ifa = hiscore->ifa; break; } } } out: return hiscore_idx; } static int ipv6_get_saddr_master(struct net *net, const struct net_device *dst_dev, const struct net_device *master, struct ipv6_saddr_dst *dst, struct ipv6_saddr_score *scores, int hiscore_idx) { struct inet6_dev *idev; idev = __in6_dev_get(dst_dev); if (idev) hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev, scores, hiscore_idx); idev = __in6_dev_get(master); if (idev) hiscore_idx = __ipv6_dev_get_saddr(net, dst, idev, scores, hiscore_idx); return hiscore_idx; } int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { struct ipv6_saddr_score scores[2], *hiscore; struct ipv6_saddr_dst dst; struct inet6_dev *idev; struct net_device *dev; int dst_type; bool use_oif_addr = false; int hiscore_idx = 0; int ret = 0; dst_type = __ipv6_addr_type(daddr); dst.addr = daddr; dst.ifindex = dst_dev ? dst_dev->ifindex : 0; dst.scope = __ipv6_addr_src_scope(dst_type); dst.label = ipv6_addr_label(net, daddr, dst_type, dst.ifindex); dst.prefs = prefs; scores[hiscore_idx].rule = -1; scores[hiscore_idx].ifa = NULL; rcu_read_lock(); /* Candidate Source Address (section 4) * - multicast and link-local destination address, * the set of candidate source address MUST only * include addresses assigned to interfaces * belonging to the same link as the outgoing * interface. * (- For site-local destination addresses, the * set of candidate source addresses MUST only * include addresses assigned to interfaces * belonging to the same site as the outgoing * interface.) * - "It is RECOMMENDED that the candidate source addresses * be the set of unicast addresses assigned to the * interface that will be used to send to the destination * (the 'outgoing' interface)." (RFC 6724) */ if (dst_dev) { idev = __in6_dev_get(dst_dev); if ((dst_type & IPV6_ADDR_MULTICAST) || dst.scope <= IPV6_ADDR_SCOPE_LINKLOCAL || (idev && idev->cnf.use_oif_addrs_only)) { use_oif_addr = true; } } if (use_oif_addr) { if (idev) hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } else { const struct net_device *master; int master_idx = 0; /* if dst_dev exists and is enslaved to an L3 device, then * prefer addresses from dst_dev and then the master over * any other enslaved devices in the L3 domain. */ master = l3mdev_master_dev_rcu(dst_dev); if (master) { master_idx = master->ifindex; hiscore_idx = ipv6_get_saddr_master(net, dst_dev, master, &dst, scores, hiscore_idx); if (scores[hiscore_idx].ifa) goto out; } for_each_netdev_rcu(net, dev) { /* only consider addresses on devices in the * same L3 domain */ if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; idev = __in6_dev_get(dev); if (!idev) continue; hiscore_idx = __ipv6_dev_get_saddr(net, &dst, idev, scores, hiscore_idx); } } out: hiscore = &scores[hiscore_idx]; if (!hiscore->ifa) ret = -EADDRNOTAVAIL; else *saddr = hiscore->ifa->addr; rcu_read_unlock(); return ret; } EXPORT_SYMBOL(ipv6_dev_get_saddr); static int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, u32 banned_flags) { struct inet6_ifaddr *ifp; int err = -EADDRNOTAVAIL; list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { if (ifp->scope > IFA_LINK) break; if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { *addr = ifp->addr; err = 0; break; } } return err; } int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags) { struct inet6_dev *idev; int err = -EADDRNOTAVAIL; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); err = __ipv6_get_lladdr(idev, addr, banned_flags); read_unlock_bh(&idev->lock); } rcu_read_unlock(); return err; } static int ipv6_count_addresses(const struct inet6_dev *idev) { const struct inet6_ifaddr *ifp; int cnt = 0; rcu_read_lock(); list_for_each_entry_rcu(ifp, &idev->addr_list, if_list) cnt++; rcu_read_unlock(); return cnt; } int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, const struct net_device *dev, int strict) { return ipv6_chk_addr_and_flags(net, addr, dev, !dev, strict, IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_chk_addr); /* device argument is used to find the L3 domain of interest. If * skip_dev_check is set, then the ifp device is not checked against * the passed in dev argument. So the 2 cases for addresses checks are: * 1. does the address exist in the L3 domain that dev is part of * (skip_dev_check = true), or * * 2. does the address exist on the specific device * (skip_dev_check = false) */ static struct net_device * __ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags) { unsigned int hash = inet6_addr_hash(net, addr); struct net_device *l3mdev, *ndev; struct inet6_ifaddr *ifp; u32 ifp_flags; rcu_read_lock(); l3mdev = l3mdev_master_dev_rcu(dev); if (skip_dev_check) dev = NULL; hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { ndev = ifp->idev->dev; if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; /* Decouple optimistic from tentative for evaluation here. * Ban optimistic addresses explicitly, when required. */ ifp_flags = (ifp->flags&IFA_F_OPTIMISTIC) ? (ifp->flags&~IFA_F_TENTATIVE) : ifp->flags; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp_flags&banned_flags) && (!dev || ndev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { rcu_read_unlock(); return ndev; } } rcu_read_unlock(); return NULL; } int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, const struct net_device *dev, bool skip_dev_check, int strict, u32 banned_flags) { return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check, strict, banned_flags) ? 1 : 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); /* Compares an address/prefix_len with addresses on device @dev. * If one is found it returns true. */ bool ipv6_chk_custom_prefix(const struct in6_addr *addr, const unsigned int prefix_len, struct net_device *dev) { const struct inet6_ifaddr *ifa; const struct inet6_dev *idev; bool ret = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { ret = ipv6_prefix_equal(addr, &ifa->addr, prefix_len); if (ret) break; } } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(ipv6_chk_custom_prefix); int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev) { const struct inet6_ifaddr *ifa; const struct inet6_dev *idev; int onlink; onlink = 0; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) break; } } rcu_read_unlock(); return onlink; } EXPORT_SYMBOL(ipv6_chk_prefix); /** * ipv6_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @dev: used to find the L3 domain of interest * * The caller should be protected by RCU, or RTNL. */ struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev) { return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1, IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_dev_find); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp, *result = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { if (in6_ifa_hold_safe(ifp)) { result = ifp; break; } } } } rcu_read_unlock(); return result; } /* Gets referenced address, destroys ifaddr */ static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { if (dad_failed) ifp->flags |= IFA_F_DADFAILED; if (ifp->flags&IFA_F_TEMPORARY) { struct inet6_ifaddr *ifpub; spin_lock_bh(&ifp->lock); ifpub = ifp->ifpub; if (ifpub) { in6_ifa_hold(ifpub); spin_unlock_bh(&ifp->lock); ipv6_create_tempaddr(ifpub, true); in6_ifa_put(ifpub); } else { spin_unlock_bh(&ifp->lock); } ipv6_del_addr(ifp); } else if (ifp->flags&IFA_F_PERMANENT || !dad_failed) { spin_lock_bh(&ifp->lock); addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; if (dad_failed) ifp->flags &= ~IFA_F_OPTIMISTIC; spin_unlock_bh(&ifp->lock); if (dad_failed) ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); } else { ipv6_del_addr(ifp); } } static int addrconf_dad_end(struct inet6_ifaddr *ifp) { int err = -ENOENT; spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DAD) { ifp->state = INET6_IFADDR_STATE_POSTDAD; err = 0; } spin_unlock_bh(&ifp->lock); return err; } void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net *net = dev_net(idev->dev); if (addrconf_dad_end(ifp)) { in6_ifa_put(ifp); return; } net_info_ratelimited("%s: IPv6 duplicate address %pI6c used by %pM detected!\n", ifp->idev->dev->name, &ifp->addr, eth_hdr(skb)->h_source); spin_lock_bh(&ifp->lock); if (ifp->flags & IFA_F_STABLE_PRIVACY) { struct in6_addr new_addr; struct inet6_ifaddr *ifp2; int retries = ifp->stable_privacy_retry + 1; struct ifa6_config cfg = { .pfx = &new_addr, .plen = ifp->prefix_len, .ifa_flags = ifp->flags, .valid_lft = ifp->valid_lft, .preferred_lft = ifp->prefered_lft, .scope = ifp->scope, }; if (retries > net->ipv6.sysctl.idgen_retries) { net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n", ifp->idev->dev->name); goto errdad; } new_addr = ifp->addr; if (ipv6_generate_stable_address(&new_addr, retries, idev)) goto errdad; spin_unlock_bh(&ifp->lock); if (idev->cnf.max_addresses && ipv6_count_addresses(idev) >= idev->cnf.max_addresses) goto lock_errdad; net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n", ifp->idev->dev->name); ifp2 = ipv6_add_addr(idev, &cfg, false, NULL); if (IS_ERR(ifp2)) goto lock_errdad; spin_lock_bh(&ifp2->lock); ifp2->stable_privacy_retry = retries; ifp2->state = INET6_IFADDR_STATE_PREDAD; spin_unlock_bh(&ifp2->lock); addrconf_mod_dad_work(ifp2, net->ipv6.sysctl.idgen_delay); in6_ifa_put(ifp2); lock_errdad: spin_lock_bh(&ifp->lock); } errdad: /* transition from _POSTDAD to _ERRDAD */ ifp->state = INET6_IFADDR_STATE_ERRDAD; spin_unlock_bh(&ifp->lock); addrconf_mod_dad_work(ifp, 0); in6_ifa_put(ifp); } /* Join to solicited addr multicast group. * caller must hold RTNL */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr; if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); } /* caller must hold RTNL */ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) { struct in6_addr maddr; if (idev->dev->flags&(IFF_LOOPBACK|IFF_NOARP)) return; addrconf_addr_solict_mult(addr, &maddr); __ipv6_dev_mc_dec(idev, &maddr); } /* caller must hold RTNL */ static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; __ipv6_dev_ac_inc(ifp->idev, &addr); } /* caller must hold RTNL */ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; if (ifp->prefix_len >= 127) /* RFC 6164 */ return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; __ipv6_dev_ac_dec(ifp->idev, &addr); } static int addrconf_ifid_6lowpan(u8 *eui, struct net_device *dev) { switch (dev->addr_len) { case ETH_ALEN: memcpy(eui, dev->dev_addr, 3); eui[3] = 0xFF; eui[4] = 0xFE; memcpy(eui + 5, dev->dev_addr + 3, 3); break; case EUI64_ADDR_LEN: memcpy(eui, dev->dev_addr, EUI64_ADDR_LEN); eui[0] ^= 2; break; default: return -1; } return 0; } static int addrconf_ifid_ieee1394(u8 *eui, struct net_device *dev) { const union fwnet_hwaddr *ha; if (dev->addr_len != FWNET_ALEN) return -1; ha = (const union fwnet_hwaddr *)dev->dev_addr; memcpy(eui, &ha->uc.uniq_id, sizeof(ha->uc.uniq_id)); eui[0] ^= 2; return 0; } static int addrconf_ifid_arcnet(u8 *eui, struct net_device *dev) { /* XXX: inherit EUI-64 from other interface -- yoshfuji */ if (dev->addr_len != ARCNET_ALEN) return -1; memset(eui, 0, 7); eui[7] = *(u8 *)dev->dev_addr; return 0; } static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev) { if (dev->addr_len != INFINIBAND_ALEN) return -1; memcpy(eui, dev->dev_addr + 12, 8); eui[0] |= 2; return 0; } static int __ipv6_isatap_ifid(u8 *eui, __be32 addr) { if (addr == 0) return -1; eui[0] = (ipv4_is_zeronet(addr) || ipv4_is_private_10(addr) || ipv4_is_loopback(addr) || ipv4_is_linklocal_169(addr) || ipv4_is_private_172(addr) || ipv4_is_test_192(addr) || ipv4_is_anycast_6to4(addr) || ipv4_is_private_192(addr) || ipv4_is_test_198(addr) || ipv4_is_multicast(addr) || ipv4_is_lbcast(addr)) ? 0x00 : 0x02; eui[1] = 0; eui[2] = 0x5E; eui[3] = 0xFE; memcpy(eui + 4, &addr, 4); return 0; } static int addrconf_ifid_sit(u8 *eui, struct net_device *dev) { if (dev->priv_flags & IFF_ISATAP) return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); return -1; } static int addrconf_ifid_gre(u8 *eui, struct net_device *dev) { return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); } static int addrconf_ifid_ip6tnl(u8 *eui, struct net_device *dev) { memcpy(eui, dev->perm_addr, 3); memcpy(eui + 5, dev->perm_addr + 3, 3); eui[3] = 0xFF; eui[4] = 0xFE; eui[0] ^= 2; return 0; } static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_FDDI: return addrconf_ifid_eui48(eui, dev); case ARPHRD_ARCNET: return addrconf_ifid_arcnet(eui, dev); case ARPHRD_INFINIBAND: return addrconf_ifid_infiniband(eui, dev); case ARPHRD_SIT: return addrconf_ifid_sit(eui, dev); case ARPHRD_IPGRE: case ARPHRD_TUNNEL: return addrconf_ifid_gre(eui, dev); case ARPHRD_6LOWPAN: return addrconf_ifid_6lowpan(eui, dev); case ARPHRD_IEEE1394: return addrconf_ifid_ieee1394(eui, dev); case ARPHRD_TUNNEL6: case ARPHRD_IP6GRE: case ARPHRD_RAWIP: return addrconf_ifid_ip6tnl(eui, dev); } return -1; } static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) { int err = -1; struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry_reverse(ifp, &idev->addr_list, if_list) { if (ifp->scope > IFA_LINK) break; if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { memcpy(eui, ifp->addr.s6_addr+8, 8); err = 0; break; } } read_unlock_bh(&idev->lock); return err; } /* Generation of a randomized Interface Identifier * draft-ietf-6man-rfc4941bis, Section 3.3.1 */ static void ipv6_gen_rnd_iid(struct in6_addr *addr) { regen: get_random_bytes(&addr->s6_addr[8], 8); /* <draft-ietf-6man-rfc4941bis-08.txt>, Section 3.3.1: * check if generated address is not inappropriate: * * - Reserved IPv6 Interface Identifiers * - XXX: already assigned to an address on the device */ /* Subnet-router anycast: 0000:0000:0000:0000 */ if (!(addr->s6_addr32[2] | addr->s6_addr32[3])) goto regen; /* IANA Ethernet block: 0200:5EFF:FE00:0000-0200:5EFF:FE00:5212 * Proxy Mobile IPv6: 0200:5EFF:FE00:5213 * IANA Ethernet block: 0200:5EFF:FE00:5214-0200:5EFF:FEFF:FFFF */ if (ntohl(addr->s6_addr32[2]) == 0x02005eff && (ntohl(addr->s6_addr32[3]) & 0Xff000000) == 0xfe000000) goto regen; /* Reserved subnet anycast addresses */ if (ntohl(addr->s6_addr32[2]) == 0xfdffffff && ntohl(addr->s6_addr32[3]) >= 0Xffffff80) goto regen; } u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) { struct inet6_dev *idev = in6_dev_get(dev); int sysctl; u32 table; if (!idev) return default_table; sysctl = idev->cnf.accept_ra_rt_table; if (sysctl == 0) { table = default_table; } else if (sysctl > 0) { table = (u32) sysctl; } else { table = (unsigned) dev->ifindex + (-sysctl); } in6_dev_put(idev); return table; } /* * Add prefix route. */ static void addrconf_prefix_route(struct in6_addr *pfx, int plen, u32 metric, struct net_device *dev, unsigned long expires, u32 flags, gfp_t gfp_flags) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX), .fc_metric = metric ? : IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_expires = expires, .fc_dst_len = plen, .fc_flags = RTF_UP | flags, .fc_nlinfo.nl_net = dev_net(dev), .fc_protocol = RTPROT_KERNEL, .fc_type = RTN_UNICAST, }; cfg.fc_dst = *pfx; /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ #if IS_ENABLED(CONFIG_IPV6_SIT) if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) cfg.fc_flags |= RTF_NONEXTHOP; #endif ip6_route_add(&cfg, gfp_flags, NULL); } static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags, bool no_gw) { struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX); table = fib6_get_table(dev_net(dev), tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* prefix routes only use builtin fib6_nh */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != dev->ifindex) continue; if (no_gw && rt->fib6_nh->fib_nh_gw_family) continue; if ((rt->fib6_flags & flags) != flags) continue; if ((rt->fib6_flags & noflags) != 0) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } /* Create "default" multicast route to the interface */ static void addrconf_add_mroute(struct net_device *dev) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_LOCAL, .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, .fc_type = RTN_MULTICAST, .fc_nlinfo.nl_net = dev_net(dev), .fc_protocol = RTPROT_KERNEL, }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); ip6_route_add(&cfg, GFP_KERNEL, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) return idev; if (idev->cnf.disable_ipv6) return ERR_PTR(-EACCES); /* Add default multicast route */ if (!(dev->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev)) addrconf_add_mroute(dev); return idev; } static void manage_tempaddrs(struct inet6_dev *idev, struct inet6_ifaddr *ifp, __u32 valid_lft, __u32 prefered_lft, bool create, unsigned long now) { u32 flags; struct inet6_ifaddr *ift; read_lock_bh(&idev->lock); /* update all temporary addresses in the list */ list_for_each_entry(ift, &idev->tempaddr_list, tmp_list) { int age, max_valid, max_prefered; if (ifp != ift->ifpub) continue; /* RFC 4941 section 3.3: * If a received option will extend the lifetime of a public * address, the lifetimes of temporary addresses should * be extended, subject to the overall constraint that no * temporary addresses should ever remain "valid" or "preferred" * for a time longer than (TEMP_VALID_LIFETIME) or * (TEMP_PREFERRED_LIFETIME - DESYNC_FACTOR), respectively. */ age = (now - ift->cstamp) / HZ; max_valid = idev->cnf.temp_valid_lft - age; if (max_valid < 0) max_valid = 0; max_prefered = idev->cnf.temp_prefered_lft - idev->desync_factor - age; if (max_prefered < 0) max_prefered = 0; if (valid_lft > max_valid) valid_lft = max_valid; if (prefered_lft > max_prefered) prefered_lft = max_prefered; spin_lock(&ift->lock); flags = ift->flags; ift->valid_lft = valid_lft; ift->prefered_lft = prefered_lft; ift->tstamp = now; if (prefered_lft > 0) ift->flags &= ~IFA_F_DEPRECATED; spin_unlock(&ift->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ift); } /* Also create a temporary address if it's enabled but no temporary * address currently exists. * However, we get called with valid_lft == 0, prefered_lft == 0, create == false * as part of cleanup (ie. deleting the mngtmpaddr). * We don't want that to result in creating a new temporary ip address. */ if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft)) create = true; if (create && idev->cnf.use_tempaddr > 0) { /* When a new public address is created as described * in [ADDRCONF], also create a new temporary address. */ read_unlock_bh(&idev->lock); ipv6_create_tempaddr(ifp, false); } else { read_unlock_bh(&idev->lock); } } static bool is_addr_mode_generate_stable(struct inet6_dev *idev) { return idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY || idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM; } int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, const struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1); int create = 0, update_lft = 0; if (!ifp && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; struct ifa6_config cfg = { .pfx = addr, .plen = pinfo->prefix_len, .ifa_flags = addr_flags, .valid_lft = valid_lft, .preferred_lft = prefered_lft, .scope = addr_type & IPV6_ADDR_SCOPE_MASK, .ifa_proto = IFAPROT_KERNEL_RA }; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if ((net->ipv6.devconf_all->optimistic_dad || in6_dev->cnf.optimistic_dad) && !net->ipv6.devconf_all->forwarding && sllao) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif /* Do not allow to create too much of autoconfigured * addresses; this would be too easy way to crash kernel. */ if (!max_addresses || ipv6_count_addresses(in6_dev) < max_addresses) ifp = ipv6_add_addr(in6_dev, &cfg, false, NULL); if (IS_ERR_OR_NULL(ifp)) return -1; create = 1; spin_lock_bh(&ifp->lock); ifp->flags |= IFA_F_MANAGETEMPADDR; ifp->cstamp = jiffies; ifp->tokenized = tokenized; spin_unlock_bh(&ifp->lock); addrconf_dad_start(ifp); } if (ifp) { u32 flags; unsigned long now; u32 stored_lft; /* update lifetime (RFC2462 5.5.3 e) */ spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; if (!create && stored_lft) { const u32 minimum_lft = min_t(u32, stored_lft, MIN_VALID_LIFETIME); valid_lft = max(valid_lft, minimum_lft); /* RFC4862 Section 5.5.3e: * "Note that the preferred lifetime of the * corresponding address is always reset to * the Preferred Lifetime in the received * Prefix Information option, regardless of * whether the valid lifetime is also reset or * ignored." * * So we should always update prefered_lft here. */ update_lft = 1; } if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; ifp->tstamp = now; flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; spin_unlock_bh(&ifp->lock); if (!(flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); } else spin_unlock_bh(&ifp->lock); manage_tempaddrs(in6_dev, ifp, valid_lft, prefered_lft, create, now); in6_ifa_put(ifp); addrconf_verify(net); } return 0; } EXPORT_SYMBOL_GPL(addrconf_prefix_rcv_add_addr); void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; __u32 valid_lft; __u32 prefered_lft; int addr_type, err; u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); pinfo = (struct prefix_info *) opt; if (len < sizeof(struct prefix_info)) { netdev_dbg(dev, "addrconf: prefix option too short\n"); return; } /* * Validation checks ([ADDRCONF], page 19) */ addr_type = ipv6_addr_type(&pinfo->prefix); if (addr_type & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)) return; valid_lft = ntohl(pinfo->valid); prefered_lft = ntohl(pinfo->prefered); if (prefered_lft > valid_lft) { net_warn_ratelimited("addrconf: prefix option has invalid lifetime\n"); return; } in6_dev = in6_dev_get(dev); if (!in6_dev) { net_dbg_ratelimited("addrconf: device %s not configured\n", dev->name); return; } if (valid_lft != 0 && valid_lft < in6_dev->cnf.accept_ra_min_lft) goto put; /* * Two things going on here: * 1) Add routes for on-link prefixes * 2) Configure prefixes with the auto flag set */ if (pinfo->onlink) { struct fib6_info *rt; unsigned long rt_expires; /* Avoid arithmetic overflow. Really, we could * save rt_expires in seconds, likely valid_lft, * but it would require division in fib gc, that it * not good. */ if (HZ > USER_HZ) rt_expires = addrconf_timeout_fixup(valid_lft, HZ); else rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); if (addrconf_finite_timeout(rt_expires)) rt_expires *= HZ; rt = addrconf_get_prefix_route(&pinfo->prefix, pinfo->prefix_len, dev, RTF_ADDRCONF | RTF_PREFIX_RT, RTF_DEFAULT, true); if (rt) { /* Autoconf prefix route */ if (valid_lft == 0) { ip6_del_rt(net, rt, false); rt = NULL; } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ fib6_set_expires(rt, jiffies + rt_expires); } else { fib6_clean_expires(rt); } } else if (valid_lft) { clock_t expires = 0; int flags = RTF_ADDRCONF | RTF_PREFIX_RT; if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ flags |= RTF_EXPIRES; expires = jiffies_to_clock_t(rt_expires); } addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, 0, dev, expires, flags, GFP_ATOMIC); } fib6_info_release(rt); } /* Try to figure out our local address for this prefix */ if (pinfo->autoconf && in6_dev->cnf.autoconf) { struct in6_addr addr; bool tokenized = false, dev_addr_generated = false; if (pinfo->prefix_len == 64) { memcpy(&addr, &pinfo->prefix, 8); if (!ipv6_addr_any(&in6_dev->token)) { read_lock_bh(&in6_dev->lock); memcpy(addr.s6_addr + 8, in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; } else if (is_addr_mode_generate_stable(in6_dev) && !ipv6_generate_stable_address(&addr, 0, in6_dev)) { addr_flags |= IFA_F_STABLE_PRIVACY; goto ok; } else if (ipv6_generate_eui64(addr.s6_addr + 8, dev) && ipv6_inherit_eui64(addr.s6_addr + 8, in6_dev)) { goto put; } else { dev_addr_generated = true; } goto ok; } net_dbg_ratelimited("IPv6 addrconf: prefix with wrong length %d\n", pinfo->prefix_len); goto put; ok: err = addrconf_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft); if (err) goto put; /* Ignore error case here because previous prefix add addr was * successful which will be notified. */ ndisc_ops_prefix_rcv_add_addr(net, dev, pinfo, in6_dev, &addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft, dev_addr_generated); } inet6_prefix_notify(RTM_NEWPREFIX, in6_dev, pinfo); put: in6_dev_put(in6_dev); } static int addrconf_set_sit_dstaddr(struct net *net, struct net_device *dev, struct in6_ifreq *ireq) { struct ip_tunnel_parm p = { }; int err; if (!(ipv6_addr_type(&ireq->ifr6_addr) & IPV6_ADDR_COMPATv4)) return -EADDRNOTAVAIL; p.iph.daddr = ireq->ifr6_addr.s6_addr32[3]; p.iph.version = 4; p.iph.ihl = 5; p.iph.protocol = IPPROTO_IPV6; p.iph.ttl = 64; if (!dev->netdev_ops->ndo_tunnel_ctl) return -EOPNOTSUPP; err = dev->netdev_ops->ndo_tunnel_ctl(dev, &p, SIOCADDTUNNEL); if (err) return err; dev = __dev_get_by_name(net, p.name); if (!dev) return -ENOBUFS; return dev_open(dev, NULL); } /* * Set destination address. * Special case for SIT interfaces where we create a new "virtual" * device. */ int addrconf_set_dstaddr(struct net *net, void __user *arg) { struct net_device *dev; struct in6_ifreq ireq; int err = -ENODEV; if (!IS_ENABLED(CONFIG_IPV6_SIT)) return -ENODEV; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; rtnl_lock(); dev = __dev_get_by_index(net, ireq.ifr6_ifindex); if (dev && dev->type == ARPHRD_SIT) err = addrconf_set_sit_dstaddr(net, dev, &ireq); rtnl_unlock(); return err; } static int ipv6_mc_config(struct sock *sk, bool join, const struct in6_addr *addr, int ifindex) { int ret; ASSERT_RTNL(); lock_sock(sk); if (join) ret = ipv6_sock_mc_join(sk, ifindex, addr); else ret = ipv6_sock_mc_drop(sk, ifindex, addr); release_sock(sk); return ret; } /* * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, int ifindex, struct ifa6_config *cfg, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; unsigned long timeout; clock_t expires; u32 flags; ASSERT_RTNL(); if (cfg->plen > 128) return -EINVAL; /* check the lifetime */ if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) return -EINVAL; if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64) return -EINVAL; dev = __dev_get_by_index(net, ifindex); if (!dev) return -ENODEV; idev = addrconf_add_dev(dev); if (IS_ERR(idev)) return PTR_ERR(idev); if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk, true, cfg->pfx, ifindex); if (ret < 0) return ret; } cfg->scope = ipv6_addr_scope(cfg->pfx); timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); cfg->valid_lft = timeout; flags = RTF_EXPIRES; } else { expires = 0; flags = 0; cfg->ifa_flags |= IFA_F_PERMANENT; } timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) cfg->ifa_flags |= IFA_F_DEPRECATED; cfg->preferred_lft = timeout; } ifp = ipv6_add_addr(idev, cfg, true, extack); if (!IS_ERR(ifp)) { if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, dev, expires, flags, GFP_KERNEL); } /* Send a netlink notification if DAD is enabled and * optimistic flag is not set */ if (!(ifp->flags & (IFA_F_OPTIMISTIC | IFA_F_NODAD))) ipv6_ifa_notify(0, ifp); /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for * manually configured addresses */ addrconf_dad_start(ifp); if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR) manage_tempaddrs(idev, ifp, cfg->valid_lft, cfg->preferred_lft, true, jiffies); in6_ifa_put(ifp); addrconf_verify_rtnl(net); return 0; } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, cfg->pfx, ifindex); } return PTR_ERR(ifp); } static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags, const struct in6_addr *pfx, unsigned int plen) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; if (plen > 128) return -EINVAL; dev = __dev_get_by_index(net, ifindex); if (!dev) return -ENODEV; idev = __in6_dev_get(dev); if (!idev) return -ENXIO; read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->prefix_len == plen && ipv6_addr_equal(pfx, &ifp->addr)) { in6_ifa_hold(ifp); read_unlock_bh(&idev->lock); if (!(ifp->flags & IFA_F_TEMPORARY) && (ifa_flags & IFA_F_MANAGETEMPADDR)) manage_tempaddrs(idev, ifp, 0, 0, false, jiffies); ipv6_del_addr(ifp); addrconf_verify_rtnl(net); if (ipv6_addr_is_multicast(pfx)) { ipv6_mc_config(net->ipv6.mc_autojoin_sk, false, pfx, dev->ifindex); } return 0; } } read_unlock_bh(&idev->lock); return -EADDRNOTAVAIL; } int addrconf_add_ifaddr(struct net *net, void __user *arg) { struct ifa6_config cfg = { .ifa_flags = IFA_F_PERMANENT, .preferred_lft = INFINITY_LIFE_TIME, .valid_lft = INFINITY_LIFE_TIME, }; struct in6_ifreq ireq; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; cfg.pfx = &ireq.ifr6_addr; cfg.plen = ireq.ifr6_prefixlen; rtnl_lock(); err = inet6_addr_add(net, ireq.ifr6_ifindex, &cfg, NULL); rtnl_unlock(); return err; } int addrconf_del_ifaddr(struct net *net, void __user *arg) { struct in6_ifreq ireq; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq))) return -EFAULT; rtnl_lock(); err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr, ireq.ifr6_prefixlen); rtnl_unlock(); return err; } static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int plen, int scope, u8 proto) { struct inet6_ifaddr *ifp; struct ifa6_config cfg = { .pfx = addr, .plen = plen, .ifa_flags = IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, .scope = scope, .ifa_proto = proto }; ifp = ipv6_add_addr(idev, &cfg, true, NULL); if (!IS_ERR(ifp)) { spin_lock_bh(&ifp->lock); ifp->flags &= ~IFA_F_TENTATIVE; spin_unlock_bh(&ifp->lock); rt_genid_bump_ipv6(dev_net(idev->dev)); ipv6_ifa_notify(RTM_NEWADDR, ifp); in6_ifa_put(ifp); } } #if IS_ENABLED(CONFIG_IPV6_SIT) || IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) static void add_v4_addrs(struct inet6_dev *idev) { struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); int scope, plen, offset = 0; u32 pflags = 0; ASSERT_RTNL(); memset(&addr, 0, sizeof(struct in6_addr)); /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */ if (idev->dev->addr_len == sizeof(struct in6_addr)) offset = sizeof(struct in6_addr) - 4; memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { scope = IPV6_ADDR_COMPATv4; plen = 96; pflags |= RTF_NONEXTHOP; } else { if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE) return; addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; plen = 64; } if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope, IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); return; } for_each_netdev(net, dev) { struct in_device *in_dev = __in_dev_get_rtnl(dev); if (in_dev && (dev->flags & IFF_UP)) { struct in_ifaddr *ifa; int flag = scope; in_dev_for_each_ifa_rtnl(ifa, in_dev) { addr.s6_addr32[3] = ifa->ifa_local; if (ifa->ifa_scope == RT_SCOPE_LINK) continue; if (ifa->ifa_scope >= RT_SCOPE_HOST) { if (idev->dev->flags&IFF_POINTOPOINT) continue; flag |= IFA_HOST; } add_addr(idev, &addr, plen, flag, IFAPROT_UNSPEC); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, GFP_KERNEL); } } } } #endif static void init_loopback(struct net_device *dev) { struct inet6_dev *idev; /* ::1 */ ASSERT_RTNL(); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } add_addr(idev, &in6addr_loopback, 128, IFA_HOST, IFAPROT_KERNEL_LO); } void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr, u32 flags) { struct ifa6_config cfg = { .pfx = addr, .plen = 64, .ifa_flags = flags | IFA_F_PERMANENT, .valid_lft = INFINITY_LIFE_TIME, .preferred_lft = INFINITY_LIFE_TIME, .scope = IFA_LINK, .ifa_proto = IFAPROT_KERNEL_LL }; struct inet6_ifaddr *ifp; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad || idev->cnf.optimistic_dad) && !dev_net(idev->dev)->ipv6.devconf_all->forwarding) cfg.ifa_flags |= IFA_F_OPTIMISTIC; #endif ifp = ipv6_add_addr(idev, &cfg, true, NULL); if (!IS_ERR(ifp)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, 0, idev->dev, 0, 0, GFP_ATOMIC); addrconf_dad_start(ifp); in6_ifa_put(ifp); } } EXPORT_SYMBOL_GPL(addrconf_add_linklocal); static bool ipv6_reserved_interfaceid(struct in6_addr address) { if ((address.s6_addr32[2] | address.s6_addr32[3]) == 0) return true; if (address.s6_addr32[2] == htonl(0x02005eff) && ((address.s6_addr32[3] & htonl(0xfe000000)) == htonl(0xfe000000))) return true; if (address.s6_addr32[2] == htonl(0xfdffffff) && ((address.s6_addr32[3] & htonl(0xffffff80)) == htonl(0xffffff80))) return true; return false; } static int ipv6_generate_stable_address(struct in6_addr *address, u8 dad_count, const struct inet6_dev *idev) { static DEFINE_SPINLOCK(lock); static __u32 digest[SHA1_DIGEST_WORDS]; static __u32 workspace[SHA1_WORKSPACE_WORDS]; static union { char __data[SHA1_BLOCK_SIZE]; struct { struct in6_addr secret; __be32 prefix[2]; unsigned char hwaddr[MAX_ADDR_LEN]; u8 dad_count; } __packed; } data; struct in6_addr secret; struct in6_addr temp; struct net *net = dev_net(idev->dev); BUILD_BUG_ON(sizeof(data.__data) != sizeof(data)); if (idev->cnf.stable_secret.initialized) secret = idev->cnf.stable_secret.secret; else if (net->ipv6.devconf_dflt->stable_secret.initialized) secret = net->ipv6.devconf_dflt->stable_secret.secret; else return -1; retry: spin_lock_bh(&lock); sha1_init(digest); memset(&data, 0, sizeof(data)); memset(workspace, 0, sizeof(workspace)); memcpy(data.hwaddr, idev->dev->perm_addr, idev->dev->addr_len); data.prefix[0] = address->s6_addr32[0]; data.prefix[1] = address->s6_addr32[1]; data.secret = secret; data.dad_count = dad_count; sha1_transform(digest, data.__data, workspace); temp = *address; temp.s6_addr32[2] = (__force __be32)digest[0]; temp.s6_addr32[3] = (__force __be32)digest[1]; spin_unlock_bh(&lock); if (ipv6_reserved_interfaceid(temp)) { dad_count++; if (dad_count > dev_net(idev->dev)->ipv6.sysctl.idgen_retries) return -1; goto retry; } *address = temp; return 0; } static void ipv6_gen_mode_random_init(struct inet6_dev *idev) { struct ipv6_stable_secret *s = &idev->cnf.stable_secret; if (s->initialized) return; s = &idev->cnf.stable_secret; get_random_bytes(&s->secret, sizeof(s->secret)); s->initialized = true; } static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { struct in6_addr addr; /* no link local addresses on L3 master devices */ if (netif_is_l3_master(idev->dev)) return; /* no link local addresses on devices flagged as slaves */ if (idev->dev->flags & IFF_SLAVE) return; ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); switch (idev->cnf.addr_gen_mode) { case IN6_ADDR_GEN_MODE_RANDOM: ipv6_gen_mode_random_init(idev); fallthrough; case IN6_ADDR_GEN_MODE_STABLE_PRIVACY: if (!ipv6_generate_stable_address(&addr, 0, idev)) addrconf_add_linklocal(idev, &addr, IFA_F_STABLE_PRIVACY); else if (prefix_route) addrconf_prefix_route(&addr, 64, 0, idev->dev, 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_EUI64: /* addrconf_add_linklocal also adds a prefix_route and we * only need to care about prefix routes if ipv6_generate_eui64 * couldn't generate one. */ if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, 0, idev->dev, 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_NONE: default: /* will not add any link local address */ break; } } static void addrconf_dev_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_FDDI) && (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && (dev->type != ARPHRD_IEEE1394) && (dev->type != ARPHRD_TUNNEL6) && (dev->type != ARPHRD_6LOWPAN) && (dev->type != ARPHRD_TUNNEL) && (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { /* Alas, we support only Ethernet autoconfiguration. */ idev = __in6_dev_get(dev); if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && dev->flags & IFF_MULTICAST) ipv6_mc_up(idev); return; } idev = addrconf_add_dev(dev); if (IS_ERR(idev)) return; /* this device type has no EUI support */ if (dev->type == ARPHRD_NONE && idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; addrconf_addr_gen(idev, false); } #if IS_ENABLED(CONFIG_IPV6_SIT) static void addrconf_sit_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); /* * Configure the tunnel with one of our IPv4 * addresses... we should configure all of * our v4 addrs in the tunnel */ idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } if (dev->priv_flags & IFF_ISATAP) { addrconf_addr_gen(idev, false); return; } add_v4_addrs(idev); if (dev->flags&IFF_POINTOPOINT) addrconf_add_mroute(dev); } #endif #if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) static void addrconf_gre_config(struct net_device *dev) { struct inet6_dev *idev; ASSERT_RTNL(); idev = ipv6_find_idev(dev); if (IS_ERR(idev)) { pr_debug("%s: add_dev failed\n", __func__); return; } if (dev->type == ARPHRD_ETHER) { addrconf_addr_gen(idev, true); return; } add_v4_addrs(idev); if (dev->flags & IFF_POINTOPOINT) addrconf_add_mroute(dev); } #endif static void addrconf_init_auto_addrs(struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: addrconf_sit_config(dev); break; #endif #if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) case ARPHRD_IP6GRE: case ARPHRD_IPGRE: addrconf_gre_config(dev); break; #endif case ARPHRD_LOOPBACK: init_loopback(dev); break; default: addrconf_dev_config(dev); break; } } static int fixup_permanent_addr(struct net *net, struct inet6_dev *idev, struct inet6_ifaddr *ifp) { /* !fib6_node means the host route was removed from the * FIB, for example, if 'lo' device is taken down. In that * case regenerate the host route. */ if (!ifp->rt || !ifp->rt->fib6_node) { struct fib6_info *f6i, *prev; f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false, GFP_ATOMIC); if (IS_ERR(f6i)) return PTR_ERR(f6i); /* ifp->rt can be accessed outside of rtnl */ spin_lock(&ifp->lock); prev = ifp->rt; ifp->rt = f6i; spin_unlock(&ifp->lock); fib6_info_release(prev); } if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, idev->dev, 0, 0, GFP_ATOMIC); } if (ifp->state == INET6_IFADDR_STATE_PREDAD) addrconf_dad_start(ifp); return 0; } static void addrconf_permanent_addr(struct net *net, struct net_device *dev) { struct inet6_ifaddr *ifp, *tmp; struct inet6_dev *idev; idev = __in6_dev_get(dev); if (!idev) return; write_lock_bh(&idev->lock); list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { if ((ifp->flags & IFA_F_PERMANENT) && fixup_permanent_addr(net, idev, ifp) < 0) { write_unlock_bh(&idev->lock); in6_ifa_hold(ifp); ipv6_del_addr(ifp); write_lock_bh(&idev->lock); net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", idev->dev->name, &ifp->addr); } } write_unlock_bh(&idev->lock); } static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct netdev_notifier_changeupper_info *info; struct inet6_dev *idev = __in6_dev_get(dev); struct net *net = dev_net(dev); int run_pending = 0; int err; switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { idev = ipv6_add_dev(dev); if (IS_ERR(idev)) return notifier_from_errno(PTR_ERR(idev)); } break; case NETDEV_CHANGEMTU: /* if MTU under IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) { addrconf_ifdown(dev, dev != net->loopback_dev); break; } if (idev) { rt6_mtu_change(dev, dev->mtu); idev->cnf.mtu6 = dev->mtu; break; } /* allocate new idev */ idev = ipv6_add_dev(dev); if (IS_ERR(idev)) break; /* device is still not ready */ if (!(idev->if_flags & IF_READY)) break; run_pending = 1; fallthrough; case NETDEV_UP: case NETDEV_CHANGE: if (idev && idev->cnf.disable_ipv6) break; if (dev->flags & IFF_SLAVE) { if (event == NETDEV_UP && !IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && dev->flags & IFF_MULTICAST) ipv6_mc_up(idev); break; } if (event == NETDEV_UP) { /* restore routes for permanent addresses */ addrconf_permanent_addr(net, dev); if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ pr_debug("ADDRCONF(NETDEV_UP): %s: link is not ready\n", dev->name); break; } if (!idev && dev->mtu >= IPV6_MIN_MTU) idev = ipv6_add_dev(dev); if (!IS_ERR_OR_NULL(idev)) { idev->if_flags |= IF_READY; run_pending = 1; } } else if (event == NETDEV_CHANGE) { if (!addrconf_link_ready(dev)) { /* device is still not ready. */ rt6_sync_down_dev(dev, event); break; } if (!IS_ERR_OR_NULL(idev)) { if (idev->if_flags & IF_READY) { /* device is already configured - * but resend MLD reports, we might * have roamed and need to update * multicast snooping switches */ ipv6_mc_up(idev); change_info = ptr; if (change_info->flags_changed & IFF_NOARP) addrconf_dad_run(idev, true); rt6_sync_up(dev, RTNH_F_LINKDOWN); break; } idev->if_flags |= IF_READY; } pr_info("ADDRCONF(NETDEV_CHANGE): %s: link becomes ready\n", dev->name); run_pending = 1; } addrconf_init_auto_addrs(dev); if (!IS_ERR_OR_NULL(idev)) { if (run_pending) addrconf_dad_run(idev, false); /* Device has an address by now */ rt6_sync_up(dev, RTNH_F_DEAD); /* * If the MTU changed during the interface down, * when the interface up, the changed MTU must be * reflected in the idev as well as routers. */ if (idev->cnf.mtu6 != dev->mtu && dev->mtu >= IPV6_MIN_MTU) { rt6_mtu_change(dev, dev->mtu); idev->cnf.mtu6 = dev->mtu; } idev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, idev); /* * If the changed mtu during down is lower than * IPV6_MIN_MTU stop IPv6 on this interface. */ if (dev->mtu < IPV6_MIN_MTU) addrconf_ifdown(dev, dev != net->loopback_dev); } break; case NETDEV_DOWN: case NETDEV_UNREGISTER: /* * Remove all addresses from this interface. */ addrconf_ifdown(dev, event != NETDEV_DOWN); break; case NETDEV_CHANGENAME: if (idev) { snmp6_unregister_dev(idev); addrconf_sysctl_unregister(idev); err = addrconf_sysctl_register(idev); if (err) return notifier_from_errno(err); err = snmp6_register_dev(idev); if (err) { addrconf_sysctl_unregister(idev); return notifier_from_errno(err); } } break; case NETDEV_PRE_TYPE_CHANGE: case NETDEV_POST_TYPE_CHANGE: if (idev) addrconf_type_change(dev, event); break; case NETDEV_CHANGEUPPER: info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (info->upper_dev && netif_is_l3_master(info->upper_dev)) addrconf_ifdown(dev, false); } return NOTIFY_OK; } /* * addrconf module should be notified of a device going up */ static struct notifier_block ipv6_dev_notf = { .notifier_call = addrconf_notify, .priority = ADDRCONF_NOTIFY_PRIORITY, }; static void addrconf_type_change(struct net_device *dev, unsigned long event) { struct inet6_dev *idev; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (event == NETDEV_POST_TYPE_CHANGE) ipv6_mc_remap(idev); else if (event == NETDEV_PRE_TYPE_CHANGE) ipv6_mc_unmap(idev); } static bool addr_is_local(const struct in6_addr *addr) { return ipv6_addr_type(addr) & (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } static int addrconf_ifdown(struct net_device *dev, bool unregister) { unsigned long event = unregister ? NETDEV_UNREGISTER : NETDEV_DOWN; struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa; LIST_HEAD(tmp_addr_list); bool keep_addr = false; bool was_ready; int state, i; ASSERT_RTNL(); rt6_disable_ip(dev, event); idev = __in6_dev_get(dev); if (!idev) return -ENODEV; /* * Step 1: remove reference to ipv6 device from parent device. * Do not dev_put! */ if (unregister) { idev->dead = 1; /* protected by rtnl_lock */ RCU_INIT_POINTER(dev->ip6_ptr, NULL); /* Step 1.5: remove snmp6 entry */ snmp6_unregister_dev(idev); } /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ if (!unregister && !idev->cnf.disable_ipv6) { /* aggregate the system setting and interface setting */ int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; if (!_keep_addr) _keep_addr = idev->cnf.keep_addr_on_down; keep_addr = (_keep_addr > 0); } /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &net->ipv6.inet6_addr_lst[i]; spin_lock_bh(&net->ipv6.addrconf_hash_lock); restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { addrconf_del_dad_work(ifa); /* combined flag + permanent flag decide if * address is retained on a down event */ if (!keep_addr || !(ifa->flags & IFA_F_PERMANENT) || addr_is_local(&ifa->addr)) { hlist_del_init_rcu(&ifa->addr_lst); goto restart; } } } spin_unlock_bh(&net->ipv6.addrconf_hash_lock); } write_lock_bh(&idev->lock); addrconf_del_rs_timer(idev); /* Step 2: clear flags for stateless addrconf, repeated down * detection */ was_ready = idev->if_flags & IF_READY; if (!unregister) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); /* Step 3: clear tempaddr list */ while (!list_empty(&idev->tempaddr_list)) { ifa = list_first_entry(&idev->tempaddr_list, struct inet6_ifaddr, tmp_list); list_del(&ifa->tmp_list); write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); if (ifa->ifpub) { in6_ifa_put(ifa->ifpub); ifa->ifpub = NULL; } spin_unlock_bh(&ifa->lock); in6_ifa_put(ifa); write_lock_bh(&idev->lock); } list_for_each_entry(ifa, &idev->addr_list, if_list) list_add_tail(&ifa->if_list_aux, &tmp_addr_list); write_unlock_bh(&idev->lock); while (!list_empty(&tmp_addr_list)) { struct fib6_info *rt = NULL; bool keep; ifa = list_first_entry(&tmp_addr_list, struct inet6_ifaddr, if_list_aux); list_del(&ifa->if_list_aux); addrconf_del_dad_work(ifa); keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); spin_lock_bh(&ifa->lock); if (keep) { /* set state to skip the notifier below */ state = INET6_IFADDR_STATE_DEAD; ifa->state = INET6_IFADDR_STATE_PREDAD; if (!(ifa->flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; rt = ifa->rt; ifa->rt = NULL; } else { state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; } spin_unlock_bh(&ifa->lock); if (rt) ip6_del_rt(net, rt, false); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } else { if (idev->cnf.forwarding) addrconf_leave_anycast(ifa); addrconf_leave_solict(ifa->idev, &ifa->addr); } if (!keep) { write_lock_bh(&idev->lock); list_del_rcu(&ifa->if_list); write_unlock_bh(&idev->lock); in6_ifa_put(ifa); } } /* Step 5: Discard anycast and multicast list */ if (unregister) { ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); } else if (was_ready) { ipv6_mc_down(idev); } idev->tstamp = jiffies; idev->ra_mtu = 0; /* Last: Shot the device (if unregistered) */ if (unregister) { addrconf_sysctl_unregister(idev); neigh_parms_release(&nd_tbl, idev->nd_parms); neigh_ifdown(&nd_tbl, dev); in6_dev_put(idev); } return 0; } static void addrconf_rs_timer(struct timer_list *t) { struct inet6_dev *idev = from_timer(idev, t, rs_timer); struct net_device *dev = idev->dev; struct in6_addr lladdr; write_lock(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) goto out; if (!ipv6_accept_ra(idev)) goto out; /* Announcement received after solicitation was sent */ if (idev->if_flags & IF_RA_RCVD) goto out; if (idev->rs_probes++ < idev->cnf.rtr_solicits || idev->cnf.rtr_solicits < 0) { write_unlock(&idev->lock); if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters); else goto put; write_lock(&idev->lock); idev->rs_interval = rfc3315_s14_backoff_update( idev->rs_interval, idev->cnf.rtr_solicit_max_interval); /* The wait after the last probe can be shorter */ addrconf_mod_rs_timer(idev, (idev->rs_probes == idev->cnf.rtr_solicits) ? idev->cnf.rtr_solicit_delay : idev->rs_interval); } else { /* * Note: we do not support deprecated "all on-link" * assumption any longer. */ pr_debug("%s: no IPv6 routers present\n", idev->dev->name); } out: write_unlock(&idev->lock); put: in6_dev_put(idev); } /* * Duplicate Address Detection */ static void addrconf_dad_kick(struct inet6_ifaddr *ifp) { unsigned long rand_num; struct inet6_dev *idev = ifp->idev; u64 nonce; if (ifp->flags & IFA_F_OPTIMISTIC) rand_num = 0; else rand_num = prandom_u32_max(idev->cnf.rtr_solicit_delay ?: 1); nonce = 0; if (idev->cnf.enhanced_dad || dev_net(idev->dev)->ipv6.devconf_all->enhanced_dad) { do get_random_bytes(&nonce, 6); while (nonce == 0); } ifp->dad_nonce = nonce; ifp->dad_probes = idev->cnf.dad_transmits; addrconf_mod_dad_work(ifp, rand_num); } static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; bool bump_id, notify = false; struct net *net; addrconf_join_solict(dev, &ifp->addr); read_lock_bh(&idev->lock); spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; net = dev_net(dev); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || (net->ipv6.devconf_all->accept_dad < 1 && idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { bool send_na = false; if (ifp->flags & IFA_F_TENTATIVE && !(ifp->flags & IFA_F_OPTIMISTIC)) send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); addrconf_dad_completed(ifp, bump_id, send_na); return; } if (!(idev->if_flags & IF_READY)) { spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); /* * If the device is not ready: * - keep it tentative if it is a permanent address. * - otherwise, kill it. */ in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 0); return; } /* * Optimistic nodes can start receiving * Frames right away */ if (ifp->flags & IFA_F_OPTIMISTIC) { ip6_ins_rt(net, ifp->rt); if (ipv6_use_optimistic_addr(net, idev)) { /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ notify = true; } } addrconf_dad_kick(ifp); out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); if (notify) ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) { bool begin_dad = false; spin_lock_bh(&ifp->lock); if (ifp->state != INET6_IFADDR_STATE_DEAD) { ifp->state = INET6_IFADDR_STATE_PREDAD; begin_dad = true; } spin_unlock_bh(&ifp->lock); if (begin_dad) addrconf_mod_dad_work(ifp, 0); } static void addrconf_dad_work(struct work_struct *w) { struct inet6_ifaddr *ifp = container_of(to_delayed_work(w), struct inet6_ifaddr, dad_work); struct inet6_dev *idev = ifp->idev; bool bump_id, disable_ipv6 = false; struct in6_addr mcaddr; enum { DAD_PROCESS, DAD_BEGIN, DAD_ABORT, } action = DAD_PROCESS; rtnl_lock(); spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { action = DAD_BEGIN; ifp->state = INET6_IFADDR_STATE_DAD; } else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) { action = DAD_ABORT; ifp->state = INET6_IFADDR_STATE_POSTDAD; if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 || idev->cnf.accept_dad > 1) && !idev->cnf.disable_ipv6 && !(ifp->flags & IFA_F_STABLE_PRIVACY)) { struct in6_addr addr; addr.s6_addr32[0] = htonl(0xfe800000); addr.s6_addr32[1] = 0; if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && ipv6_addr_equal(&ifp->addr, &addr)) { /* DAD failed for link-local based on MAC */ idev->cnf.disable_ipv6 = 1; pr_info("%s: IPv6 being disabled!\n", ifp->idev->dev->name); disable_ipv6 = true; } } } spin_unlock_bh(&ifp->lock); if (action == DAD_BEGIN) { addrconf_dad_begin(ifp); goto out; } else if (action == DAD_ABORT) { in6_ifa_hold(ifp); addrconf_dad_stop(ifp, 1); if (disable_ipv6) addrconf_ifdown(idev->dev, false); goto out; } if (!ifp->dad_probes && addrconf_dad_end(ifp)) goto out; write_lock_bh(&idev->lock); if (idev->dead || !(idev->if_flags & IF_READY)) { write_unlock_bh(&idev->lock); goto out; } spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) { spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); goto out; } if (ifp->dad_probes == 0) { bool send_na = false; /* * DAD was successful */ if (ifp->flags & IFA_F_TENTATIVE && !(ifp->flags & IFA_F_OPTIMISTIC)) send_na = true; bump_id = ifp->flags & IFA_F_TENTATIVE; ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|IFA_F_DADFAILED); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); addrconf_dad_completed(ifp, bump_id, send_na); goto out; } ifp->dad_probes--; addrconf_mod_dad_work(ifp, max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100)); spin_unlock(&ifp->lock); write_unlock_bh(&idev->lock); /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, ifp->dad_nonce); out: in6_ifa_put(ifp); rtnl_unlock(); } /* ifp->idev must be at least read locked */ static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp) { struct inet6_ifaddr *ifpiter; struct inet6_dev *idev = ifp->idev; list_for_each_entry_reverse(ifpiter, &idev->addr_list, if_list) { if (ifpiter->scope > IFA_LINK) break; if (ifp != ifpiter && ifpiter->scope == IFA_LINK && (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE| IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) == IFA_F_PERMANENT) return false; } return true; } static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, bool send_na) { struct net_device *dev = ifp->idev->dev; struct in6_addr lladdr; bool send_rs, send_mld; addrconf_del_dad_work(ifp); /* * Configure the address for reception. Now it is valid. */ ipv6_ifa_notify(RTM_NEWADDR, ifp); /* If added prefix is link local and we are prepared to process router advertisements, start sending router solicitations. */ read_lock_bh(&ifp->idev->lock); send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp); send_rs = send_mld && ipv6_accept_ra(ifp->idev) && ifp->idev->cnf.rtr_solicits != 0 && (dev->flags & IFF_LOOPBACK) == 0 && (dev->type != ARPHRD_TUNNEL); read_unlock_bh(&ifp->idev->lock); /* While dad is in progress mld report's source address is in6_addrany. * Resend with proper ll now. */ if (send_mld) ipv6_mc_dad_complete(ifp->idev); /* send unsolicited NA if enabled */ if (send_na && (ifp->idev->cnf.ndisc_notify || dev_net(dev)->ipv6.devconf_all->ndisc_notify)) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifp->addr, /*router=*/ !!ifp->idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } if (send_rs) { /* * If a host as already performed a random delay * [...] as part of DAD [...] there is no need * to delay again before sending the first RS */ if (ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE)) return; ndisc_send_rs(dev, &lladdr, &in6addr_linklocal_allrouters); write_lock_bh(&ifp->idev->lock); spin_lock(&ifp->lock); ifp->idev->rs_interval = rfc3315_s14_backoff_init( ifp->idev->cnf.rtr_solicit_interval); ifp->idev->rs_probes = 1; ifp->idev->if_flags |= IF_RS_SENT; addrconf_mod_rs_timer(ifp->idev, ifp->idev->rs_interval); spin_unlock(&ifp->lock); write_unlock_bh(&ifp->idev->lock); } if (bump_id) rt_genid_bump_ipv6(dev_net(dev)); /* Make sure that a new temporary address will be created * before this temporary address becomes deprecated. */ if (ifp->flags & IFA_F_TEMPORARY) addrconf_verify_rtnl(dev_net(dev)); } static void addrconf_dad_run(struct inet6_dev *idev, bool restart) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); if ((ifp->flags & IFA_F_TENTATIVE && ifp->state == INET6_IFADDR_STATE_DAD) || restart) { if (restart) ifp->state = INET6_IFADDR_STATE_PREDAD; addrconf_dad_kick(ifp); } spin_unlock(&ifp->lock); } read_unlock_bh(&idev->lock); } #ifdef CONFIG_PROC_FS struct if6_iter_state { struct seq_net_private p; int bucket; int offset; }; static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); struct inet6_ifaddr *ifa = NULL; int p = 0; /* initial bucket if pos is 0 */ if (pos == 0) { state->bucket = 0; state->offset = 0; } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { /* sync with offset */ if (p < state->offset) { p++; continue; } return ifa; } /* prepare for next bucket */ state->offset = 0; p = 0; } return NULL; } static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa) { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); hlist_for_each_entry_continue_rcu(ifa, addr_lst) { state->offset++; return ifa; } state->offset = 0; while (++state->bucket < IN6_ADDR_HSIZE) { hlist_for_each_entry_rcu(ifa, &net->ipv6.inet6_addr_lst[state->bucket], addr_lst) { return ifa; } } return NULL; } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return if6_get_first(seq, *pos); } static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct inet6_ifaddr *ifa; ifa = if6_get_next(seq, v); ++*pos; return ifa; } static void if6_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } static int if6_seq_show(struct seq_file *seq, void *v) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v; seq_printf(seq, "%pi6 %02x %02x %02x %02x %8s\n", &ifp->addr, ifp->idev->dev->ifindex, ifp->prefix_len, ifp->scope, (u8) ifp->flags, ifp->idev->dev->name); return 0; } static const struct seq_operations if6_seq_ops = { .start = if6_seq_start, .next = if6_seq_next, .show = if6_seq_show, .stop = if6_seq_stop, }; static int __net_init if6_proc_net_init(struct net *net) { if (!proc_create_net("if_inet6", 0444, net->proc_net, &if6_seq_ops, sizeof(struct if6_iter_state))) return -ENOMEM; return 0; } static void __net_exit if6_proc_net_exit(struct net *net) { remove_proc_entry("if_inet6", net->proc_net); } static struct pernet_operations if6_proc_net_ops = { .init = if6_proc_net_init, .exit = if6_proc_net_exit, }; int __init if6_proc_init(void) { return register_pernet_subsys(&if6_proc_net_ops); } void if6_proc_exit(void) { unregister_pernet_subsys(&if6_proc_net_ops); } #endif /* CONFIG_PROC_FS */ #if IS_ENABLED(CONFIG_IPV6_MIP6) /* Check if address is a home address configured on any interface. */ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { unsigned int hash = inet6_addr_hash(net, addr); struct inet6_ifaddr *ifp = NULL; int ret = 0; rcu_read_lock(); hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr) && (ifp->flags & IFA_F_HOMEADDRESS)) { ret = 1; break; } } rcu_read_unlock(); return ret; } #endif /* RFC6554 has some algorithm to avoid loops in segment routing by * checking if the segments contains any of a local interface address. * * Quote: * * To detect loops in the SRH, a router MUST determine if the SRH * includes multiple addresses assigned to any interface on that router. * If such addresses appear more than once and are separated by at least * one address not assigned to that router. */ int ipv6_chk_rpl_srh_loop(struct net *net, const struct in6_addr *segs, unsigned char nsegs) { const struct in6_addr *addr; int i, ret = 0, found = 0; struct inet6_ifaddr *ifp; bool separated = false; unsigned int hash; bool hash_found; rcu_read_lock(); for (i = 0; i < nsegs; i++) { addr = &segs[i]; hash = inet6_addr_hash(net, addr); hash_found = false; hlist_for_each_entry_rcu(ifp, &net->ipv6.inet6_addr_lst[hash], addr_lst) { if (ipv6_addr_equal(&ifp->addr, addr)) { hash_found = true; break; } } if (hash_found) { if (found > 1 && separated) { ret = 1; break; } separated = false; found++; } else { separated = true; } } rcu_read_unlock(); return ret; } /* * Periodic address status verification */ static void addrconf_verify_rtnl(struct net *net) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; int i; ASSERT_RTNL(); rcu_read_lock_bh(); now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); cancel_delayed_work(&net->ipv6.addr_chk_work); for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: hlist_for_each_entry_rcu_bh(ifp, &net->ipv6.inet6_addr_lst[i], addr_lst) { unsigned long age; /* When setting preferred_lft to a value not zero or * infinity, while valid_lft is infinity * IFA_F_PERMANENT has a non-infinity life time. */ if ((ifp->flags & IFA_F_PERMANENT) && (ifp->prefered_lft == INFINITY_LIFE_TIME)) continue; spin_lock(&ifp->lock); /* We try to batch several events at once. */ age = (now - ifp->tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if ((ifp->flags&IFA_F_TEMPORARY) && !(ifp->flags&IFA_F_TENTATIVE) && ifp->prefered_lft != INFINITY_LIFE_TIME && !ifp->regen_count && ifp->ifpub) { /* This is a non-regenerated temporary addr. */ unsigned long regen_advance = ifp->idev->cnf.regen_max_retry * ifp->idev->cnf.dad_transmits * max(NEIGH_VAR(ifp->idev->nd_parms, RETRANS_TIME), HZ/100) / HZ; if (age + regen_advance >= ifp->prefered_lft) { struct inet6_ifaddr *ifpub = ifp->ifpub; if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ; ifp->regen_count++; in6_ifa_hold(ifp); in6_ifa_hold(ifpub); spin_unlock(&ifp->lock); spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); rcu_read_unlock_bh(); ipv6_create_tempaddr(ifpub, true); in6_ifa_put(ifpub); in6_ifa_put(ifp); rcu_read_lock_bh(); goto restart; } else if (time_before(ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ - regen_advance * HZ; } if (ifp->valid_lft != INFINITY_LIFE_TIME && age >= ifp->valid_lft) { spin_unlock(&ifp->lock); in6_ifa_hold(ifp); rcu_read_unlock_bh(); ipv6_del_addr(ifp); rcu_read_lock_bh(); goto restart; } else if (ifp->prefered_lft == INFINITY_LIFE_TIME) { spin_unlock(&ifp->lock); continue; } else if (age >= ifp->prefered_lft) { /* jiffies - ifp->tstamp > age >= ifp->prefered_lft */ int deprecate = 0; if (!(ifp->flags&IFA_F_DEPRECATED)) { deprecate = 1; ifp->flags |= IFA_F_DEPRECATED; } if ((ifp->valid_lft != INFINITY_LIFE_TIME) && (time_before(ifp->tstamp + ifp->valid_lft * HZ, next))) next = ifp->tstamp + ifp->valid_lft * HZ; spin_unlock(&ifp->lock); if (deprecate) { in6_ifa_hold(ifp); ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); goto restart; } } else { /* ifp->prefered_lft <= ifp->valid_lft */ if (time_before(ifp->tstamp + ifp->prefered_lft * HZ, next)) next = ifp->tstamp + ifp->prefered_lft * HZ; spin_unlock(&ifp->lock); } } } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX; pr_debug("now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n", now, next, next_sec, next_sched); mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, next_sched - now); rcu_read_unlock_bh(); } static void addrconf_verify_work(struct work_struct *w) { struct net *net = container_of(to_delayed_work(w), struct net, ipv6.addr_chk_work); rtnl_lock(); addrconf_verify_rtnl(net); rtnl_unlock(); } static void addrconf_verify(struct net *net) { mod_delayed_work(addrconf_wq, &net->ipv6.addr_chk_work, 0); } static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local, struct in6_addr **peer_pfx) { struct in6_addr *pfx = NULL; *peer_pfx = NULL; if (addr) pfx = nla_data(addr); if (local) { if (pfx && nla_memcmp(local, pfx, sizeof(*pfx))) *peer_pfx = pfx; pfx = nla_data(local); } return pfx; } static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_ADDRESS] = { .len = sizeof(struct in6_addr) }, [IFA_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFA_PROTO] = { .type = NLA_U8 }, }; static int inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx, *peer_pfx; u32 ifa_flags; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) return err; ifm = nlmsg_data(nlh); pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (!pfx) return -EINVAL; ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; /* We ignore other flags so far. */ ifa_flags &= IFA_F_MANAGETEMPADDR; return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx, ifm->ifa_prefixlen); } static int modify_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, u32 flags, bool modify_peer) { struct fib6_info *f6i; u32 prio; f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (!f6i) return -ENOENT; prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF; if (f6i->fib6_metric != prio) { /* delete old one */ ip6_del_rt(dev_net(ifp->idev->dev), f6i, false); /* add new one */ addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } else { if (!expires) fib6_clean_expires(f6i); else fib6_set_expires(f6i, expires); fib6_info_release(f6i); } return 0; } static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, struct ifa6_config *cfg) { u32 flags; clock_t expires; unsigned long timeout; bool was_managetempaddr; bool had_prefixroute; bool new_peer = false; ASSERT_RTNL(); if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft) return -EINVAL; if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && (ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64)) return -EINVAL; if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED) cfg->ifa_flags &= ~IFA_F_OPTIMISTIC; timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ); if (addrconf_finite_timeout(timeout)) { expires = jiffies_to_clock_t(timeout * HZ); cfg->valid_lft = timeout; flags = RTF_EXPIRES; } else { expires = 0; flags = 0; cfg->ifa_flags |= IFA_F_PERMANENT; } timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) cfg->ifa_flags |= IFA_F_DEPRECATED; cfg->preferred_lft = timeout; } if (cfg->peer_pfx && memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) { if (!ipv6_addr_any(&ifp->peer_addr)) cleanup_prefix_route(ifp, expires, true, true); new_peer = true; } spin_lock_bh(&ifp->lock); was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; had_prefixroute = ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE); ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); ifp->flags |= cfg->ifa_flags; ifp->tstamp = jiffies; ifp->valid_lft = cfg->valid_lft; ifp->prefered_lft = cfg->preferred_lft; ifp->ifa_proto = cfg->ifa_proto; if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) ifp->rt_priority = cfg->rt_priority; if (new_peer) ifp->peer_addr = *cfg->peer_pfx; spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) { int rc = -ENOENT; if (had_prefixroute) rc = modify_prefix_route(ifp, expires, flags, false); /* prefix route could have been deleted; if so restore it */ if (rc == -ENOENT) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr)) rc = modify_prefix_route(ifp, expires, flags, true); if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) { addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; write_lock_bh(&ifp->idev->lock); action = check_cleanup_prefix_route(ifp, &rt_expires); write_unlock_bh(&ifp->idev->lock); if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, rt_expires, action == CLEANUP_PREFIX_RT_DEL, false); } } if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) { if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR)) { cfg->valid_lft = 0; cfg->preferred_lft = 0; } manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft, cfg->preferred_lft, !was_managetempaddr, jiffies); } addrconf_verify_rtnl(net); return 0; } static int inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *peer_pfx; struct inet6_ifaddr *ifa; struct net_device *dev; struct inet6_dev *idev; struct ifa6_config cfg; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) return err; memset(&cfg, 0, sizeof(cfg)); ifm = nlmsg_data(nlh); cfg.pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx); if (!cfg.pfx) return -EINVAL; cfg.peer_pfx = peer_pfx; cfg.plen = ifm->ifa_prefixlen; if (tb[IFA_RT_PRIORITY]) cfg.rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]); if (tb[IFA_PROTO]) cfg.ifa_proto = nla_get_u8(tb[IFA_PROTO]); cfg.valid_lft = INFINITY_LIFE_TIME; cfg.preferred_lft = INFINITY_LIFE_TIME; if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); cfg.valid_lft = ci->ifa_valid; cfg.preferred_lft = ci->ifa_prefered; } dev = __dev_get_by_index(net, ifm->ifa_index); if (!dev) return -ENODEV; if (tb[IFA_FLAGS]) cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]); else cfg.ifa_flags = ifm->ifa_flags; /* We ignore other flags so far. */ cfg.ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; idev = ipv6_find_idev(dev); if (IS_ERR(idev)) return PTR_ERR(idev); if (!ipv6_allow_optimistic_dad(net, idev)) cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; if (cfg.ifa_flags & IFA_F_NODAD && cfg.ifa_flags & IFA_F_OPTIMISTIC) { NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive"); return -EINVAL; } ifa = ipv6_get_ifaddr(net, cfg.pfx, dev, 1); if (!ifa) { /* * It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ return inet6_addr_add(net, ifm->ifa_index, &cfg, extack); } if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) err = -EEXIST; else err = inet6_addr_modify(net, ifa, &cfg); in6_ifa_put(ifa); return err; } static void put_ifaddrmsg(struct nlmsghdr *nlh, u8 prefixlen, u32 flags, u8 scope, int ifindex) { struct ifaddrmsg *ifm; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET6; ifm->ifa_prefixlen = prefixlen; ifm->ifa_flags = flags; ifm->ifa_scope = scope; ifm->ifa_index = ifindex; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static inline int rt_scope(int ifa_scope) { if (ifa_scope & IFA_HOST) return RT_SCOPE_HOST; else if (ifa_scope & IFA_LINK) return RT_SCOPE_LINK; else if (ifa_scope & IFA_SITE) return RT_SCOPE_SITE; else return RT_SCOPE_UNIVERSE; } static inline int inet6_ifaddr_msgsize(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(16) /* IFA_LOCAL */ + nla_total_size(16) /* IFA_ADDRESS */ + nla_total_size(sizeof(struct ifa_cacheinfo)) + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(1) /* IFA_PROTO */ + nla_total_size(4) /* IFA_RT_PRIORITY */; } enum addr_type_t { UNICAST_ADDR, MULTICAST_ADDR, ANYCAST_ADDR, }; struct inet6_fill_args { u32 portid; u32 seq; int event; unsigned int flags; int netnsid; int ifindex; enum addr_type_t type; }; static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, struct inet6_fill_args *args) { struct nlmsghdr *nlh; u32 preferred, valid; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; spin_lock_bh(&ifa->lock); if (!((ifa->flags&IFA_F_PERMANENT) && (ifa->prefered_lft == INFINITY_LIFE_TIME))) { preferred = ifa->prefered_lft; valid = ifa->valid_lft; if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->tstamp)/HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } spin_unlock_bh(&ifa->lock); if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; } else if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; if (ifa->rt_priority && nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority)) goto error; if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) goto error; if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) goto error; if (ifa->ifa_proto && nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) goto error; nlmsg_end(skb, nlh); return 0; error: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, struct inet6_fill_args *args) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; int ifindex = ifmca->idev->dev->ifindex; if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; if (args->netnsid >= 0 && nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } /* called with rcu_read_lock() */ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, struct netlink_callback *cb, int s_ip_idx, struct inet6_fill_args *fillargs) { struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; int ip_idx = 0; int err = 1; read_lock_bh(&idev->lock); switch (fillargs->type) { case UNICAST_ADDR: { struct inet6_ifaddr *ifa; fillargs->event = RTM_NEWADDR; /* unicast address incl. temp addr */ list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ip_idx < s_ip_idx) goto next; err = inet6_fill_ifaddr(skb, ifa, fillargs); if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); next: ip_idx++; } break; } case MULTICAST_ADDR: read_unlock_bh(&idev->lock); fillargs->event = RTM_GETMULTICAST; /* multicast address */ for (ifmca = rtnl_dereference(idev->mc_list); ifmca; ifmca = rtnl_dereference(ifmca->next), ip_idx++) { if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); if (err < 0) break; } read_lock_bh(&idev->lock); break; case ANYCAST_ADDR: fillargs->event = RTM_GETANYCAST; /* anycast address */ for (ifaca = idev->ac_list; ifaca; ifaca = ifaca->aca_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, fillargs); if (err < 0) break; } break; default: break; } read_unlock_bh(&idev->lock); cb->args[2] = ip_idx; return err; } static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, struct inet6_fill_args *fillargs, struct net **tgt_net, struct sock *sk, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[IFA_MAX+1]; struct ifaddrmsg *ifm; int err, i; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for address dump request"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address dump request"); return -EINVAL; } fillargs->ifindex = ifm->ifa_index; if (fillargs->ifindex) { cb->answer_flags |= NLM_F_DUMP_FILTERED; fillargs->flags |= NLM_F_DUMP_FILTERED; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err < 0) return err; for (i = 0; i <= IFA_MAX; ++i) { if (!tb[i]) continue; if (i == IFA_TARGET_NETNSID) { struct net *net; fillargs->netnsid = nla_get_s32(tb[i]); net = rtnl_get_net_ns_capable(sk, fillargs->netnsid); if (IS_ERR(net)) { fillargs->netnsid = -1; NL_SET_ERR_MSG_MOD(extack, "Invalid target network namespace id"); return PTR_ERR(net); } *tgt_net = net; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { const struct nlmsghdr *nlh = cb->nlh; struct inet6_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = cb->nlh->nlmsg_seq, .flags = NLM_F_MULTI, .netnsid = -1, .type = type, }; struct net *tgt_net = sock_net(skb->sk); int idx, s_idx, s_ip_idx; int h, s_h; struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; int err = 0; s_h = cb->args[0]; s_idx = idx = cb->args[1]; s_ip_idx = cb->args[2]; if (cb->strict_check) { err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) goto put_tgt_net; err = 0; if (fillargs.ifindex) { dev = __dev_get_by_index(tgt_net, fillargs.ifindex); if (!dev) { err = -ENODEV; goto put_tgt_net; } idev = __in6_dev_get(dev); if (idev) { err = in6_dump_addrs(idev, skb, cb, s_ip_idx, &fillargs); if (err > 0) err = 0; } goto put_tgt_net; } } rcu_read_lock(); cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) s_ip_idx = 0; idev = __in6_dev_get(dev); if (!idev) goto cont; if (in6_dump_addrs(idev, skb, cb, s_ip_idx, &fillargs) < 0) goto done; cont: idx++; } } done: rcu_read_unlock(); cb->args[0] = h; cb->args[1] = idx; put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); return skb->len ? : err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = UNICAST_ADDR; return inet6_dump_addr(skb, cb, type); } static int inet6_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = MULTICAST_ADDR; return inet6_dump_addr(skb, cb, type); } static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) { enum addr_type_t type = ANYCAST_ADDR; return inet6_dump_addr(skb, cb, type); } static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrmsg *ifm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) return err; for (i = 0; i <= IFA_MAX; i++) { if (!tb[i]) continue; switch (i) { case IFA_TARGET_NETNSID: case IFA_ADDRESS: case IFA_LOCAL: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get address request"); return -EINVAL; } } return 0; } static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *tgt_net = sock_net(in_skb->sk); struct inet6_fill_args fillargs = { .portid = NETLINK_CB(in_skb).portid, .seq = nlh->nlmsg_seq, .event = RTM_NEWADDR, .flags = 0, .netnsid = -1, }; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL, *peer; struct net_device *dev = NULL; struct inet6_ifaddr *ifa; struct sk_buff *skb; int err; err = inet6_rtm_valid_getaddr_req(in_skb, nlh, tb, extack); if (err < 0) return err; if (tb[IFA_TARGET_NETNSID]) { fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(in_skb).sk, fillargs.netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (!addr) { err = -EINVAL; goto errout; } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); ifa = ipv6_get_ifaddr(tgt_net, addr, dev, 1); if (!ifa) { err = -EADDRNOTAVAIL; goto errout; } skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout_ifa; } err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout_ifa; } err = rtnl_unicast(skb, tgt_net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: dev_put(dev); if (fillargs.netnsid >= 0) put_net(tgt_net); return err; } static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; struct net *net = dev_net(ifa->idev->dev); struct inet6_fill_args fillargs = { .portid = 0, .seq = 0, .event = event, .flags = 0, .netnsid = -1, }; int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, __s32 *array, int bytes) { BUG_ON(bytes < (DEVCONF_MAX * 4)); memset(array, 0, bytes); array[DEVCONF_FORWARDING] = cnf->forwarding; array[DEVCONF_HOPLIMIT] = cnf->hop_limit; array[DEVCONF_MTU6] = cnf->mtu6; array[DEVCONF_ACCEPT_RA] = cnf->accept_ra; array[DEVCONF_ACCEPT_REDIRECTS] = cnf->accept_redirects; array[DEVCONF_AUTOCONF] = cnf->autoconf; array[DEVCONF_DAD_TRANSMITS] = cnf->dad_transmits; array[DEVCONF_RTR_SOLICITS] = cnf->rtr_solicits; array[DEVCONF_RTR_SOLICIT_INTERVAL] = jiffies_to_msecs(cnf->rtr_solicit_interval); array[DEVCONF_RTR_SOLICIT_MAX_INTERVAL] = jiffies_to_msecs(cnf->rtr_solicit_max_interval); array[DEVCONF_RTR_SOLICIT_DELAY] = jiffies_to_msecs(cnf->rtr_solicit_delay); array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version; array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] = jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval); array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] = jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval); array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr; array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft; array[DEVCONF_TEMP_PREFERED_LFT] = cnf->temp_prefered_lft; array[DEVCONF_REGEN_MAX_RETRY] = cnf->regen_max_retry; array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; array[DEVCONF_RA_DEFRTR_METRIC] = cnf->ra_defrtr_metric; array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; array[DEVCONF_RTR_PROBE_INTERVAL] = jiffies_to_msecs(cnf->rtr_probe_interval); #ifdef CONFIG_IPV6_ROUTE_INFO array[DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN] = cnf->accept_ra_rt_info_min_plen; array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; #endif #endif array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad; array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify; array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown; /* we omit DEVCONF_STABLE_SECRET for now */ array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; array[DEVCONF_SEG6_ENABLED] = cnf->seg6_enabled; #ifdef CONFIG_IPV6_SEG6_HMAC array[DEVCONF_SEG6_REQUIRE_HMAC] = cnf->seg6_require_hmac; #endif array[DEVCONF_ENHANCED_DAD] = cnf->enhanced_dad; array[DEVCONF_ADDR_GEN_MODE] = cnf->addr_gen_mode; array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy; array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass; array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled; array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; array[DEVCONF_ACCEPT_UNTRACKED_NA] = cnf->accept_untracked_na; array[DEVCONF_ACCEPT_RA_MIN_LFT] = cnf->accept_ra_min_lft; } static inline size_t inet6_ifla6_size(void) { return nla_total_size(4) /* IFLA_INET6_FLAGS */ + nla_total_size(sizeof(struct ifla_cacheinfo)) + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */ + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */ + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */ + nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */ + nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */ + nla_total_size(4) /* IFLA_INET6_RA_MTU */ + 0; } static inline size_t inet6_if_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(inet6_ifla6_size()); /* IFLA_PROTINFO */ } static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib, int bytes) { int i; int pad = bytes - sizeof(u64) * ICMP6_MIB_MAX; BUG_ON(pad < 0); /* Use put_unaligned() because stats may not be aligned for u64. */ put_unaligned(ICMP6_MIB_MAX, &stats[0]); for (i = 1; i < ICMP6_MIB_MAX; i++) put_unaligned(atomic_long_read(&mib[i]), &stats[i]); memset(&stats[ICMP6_MIB_MAX], 0, pad); } static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib, int bytes, size_t syncpoff) { int i, c; u64 buff[IPSTATS_MIB_MAX]; int pad = bytes - sizeof(u64) * IPSTATS_MIB_MAX; BUG_ON(pad < 0); memset(buff, 0, sizeof(buff)); buff[0] = IPSTATS_MIB_MAX; for_each_possible_cpu(c) { for (i = 1; i < IPSTATS_MIB_MAX; i++) buff[i] += snmp_get_cpu_field64(mib, c, i, syncpoff); } memcpy(stats, buff, IPSTATS_MIB_MAX * sizeof(u64)); memset(&stats[IPSTATS_MIB_MAX], 0, pad); } static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, int bytes) { switch (attrtype) { case IFLA_INET6_STATS: __snmp6_fill_stats64(stats, idev->stats.ipv6, bytes, offsetof(struct ipstats_mib, syncp)); break; case IFLA_INET6_ICMP6STATS: __snmp6_fill_statsdev(stats, idev->stats.icmpv6dev->mibs, bytes); break; } } static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { struct nlattr *nla; struct ifla_cacheinfo ci; if (nla_put_u32(skb, IFLA_INET6_FLAGS, idev->if_flags)) goto nla_put_failure; ci.max_reasm_len = IPV6_MAXPLEN; ci.tstamp = cstamp_delta(idev->tstamp); ci.reachable_time = jiffies_to_msecs(idev->nd_parms->reachable_time); ci.retrans_time = jiffies_to_msecs(NEIGH_VAR(idev->nd_parms, RETRANS_TIME)); if (nla_put(skb, IFLA_INET6_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nla = nla_reserve(skb, IFLA_INET6_CONF, DEVCONF_MAX * sizeof(s32)); if (!nla) goto nla_put_failure; ipv6_store_devconf(&idev->cnf, nla_data(nla), nla_len(nla)); /* XXX - MC not implemented */ if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) return 0; nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); if (!nla) goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); if (!nla) goto nla_put_failure; snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (!nla) goto nla_put_failure; read_lock_bh(&idev->lock); memcpy(nla_data(nla), idev->token.s6_addr, nla_len(nla)); read_unlock_bh(&idev->lock); if (nla_put_u8(skb, IFLA_INET6_ADDR_GEN_MODE, idev->cnf.addr_gen_mode)) goto nla_put_failure; if (idev->ra_mtu && nla_put_u32(skb, IFLA_INET6_RA_MTU, idev->ra_mtu)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static size_t inet6_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { if (!__in6_dev_get(dev)) return 0; return inet6_ifla6_size(); } static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev) return -ENODATA; if (inet6_fill_ifla6_attrs(skb, idev, ext_filter_mask) < 0) return -EMSGSIZE; return 0; } static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token, struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct net_device *dev = idev->dev; bool clear_token, update_rs = false; struct in6_addr ll_addr; ASSERT_RTNL(); if (!token) return -EINVAL; if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG_MOD(extack, "Device is loopback"); return -EINVAL; } if (dev->flags & IFF_NOARP) { NL_SET_ERR_MSG_MOD(extack, "Device does not do neighbour discovery"); return -EINVAL; } if (!ipv6_accept_ra(idev)) { NL_SET_ERR_MSG_MOD(extack, "Router advertisement is disabled on device"); return -EINVAL; } if (idev->cnf.rtr_solicits == 0) { NL_SET_ERR_MSG(extack, "Router solicitation is disabled on device"); return -EINVAL; } write_lock_bh(&idev->lock); BUILD_BUG_ON(sizeof(token->s6_addr) != 16); memcpy(idev->token.s6_addr + 8, token->s6_addr + 8, 8); write_unlock_bh(&idev->lock); clear_token = ipv6_addr_any(token); if (clear_token) goto update_lft; if (!idev->dead && (idev->if_flags & IF_READY) && !ipv6_get_lladdr(dev, &ll_addr, IFA_F_TENTATIVE | IFA_F_OPTIMISTIC)) { /* If we're not ready, then normal ifup will take care * of this. Otherwise, we need to request our rs here. */ ndisc_send_rs(dev, &ll_addr, &in6addr_linklocal_allrouters); update_rs = true; } update_lft: write_lock_bh(&idev->lock); if (update_rs) { idev->if_flags |= IF_RS_SENT; idev->rs_interval = rfc3315_s14_backoff_init( idev->cnf.rtr_solicit_interval); idev->rs_probes = 1; addrconf_mod_rs_timer(idev, idev->rs_interval); } /* Well, that's kinda nasty ... */ list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); if (ifp->tokenized) { ifp->valid_lft = 0; ifp->prefered_lft = 0; } spin_unlock(&ifp->lock); } write_unlock_bh(&idev->lock); inet6_ifinfo_notify(RTM_NEWLINK, idev); addrconf_verify_rtnl(dev_net(dev)); return 0; } static const struct nla_policy inet6_af_policy[IFLA_INET6_MAX + 1] = { [IFLA_INET6_ADDR_GEN_MODE] = { .type = NLA_U8 }, [IFLA_INET6_TOKEN] = { .len = sizeof(struct in6_addr) }, [IFLA_INET6_RA_MTU] = { .type = NLA_REJECT, .reject_message = "IFLA_INET6_RA_MTU can not be set" }, }; static int check_addr_gen_mode(int mode) { if (mode != IN6_ADDR_GEN_MODE_EUI64 && mode != IN6_ADDR_GEN_MODE_NONE && mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY && mode != IN6_ADDR_GEN_MODE_RANDOM) return -EINVAL; return 1; } static int check_stable_privacy(struct inet6_dev *idev, struct net *net, int mode) { if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && !idev->cnf.stable_secret.initialized && !net->ipv6.devconf_dflt->stable_secret.initialized) return -EINVAL; return 1; } static int inet6_validate_link_af(const struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct nlattr *tb[IFLA_INET6_MAX + 1]; struct inet6_dev *idev = NULL; int err; if (dev) { idev = __in6_dev_get(dev); if (!idev) return -EAFNOSUPPORT; } err = nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, inet6_af_policy, extack); if (err) return err; if (!tb[IFLA_INET6_TOKEN] && !tb[IFLA_INET6_ADDR_GEN_MODE]) return -EINVAL; if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); if (check_addr_gen_mode(mode) < 0) return -EINVAL; if (dev && check_stable_privacy(idev, dev_net(dev), mode) < 0) return -EINVAL; } return 0; } static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); struct nlattr *tb[IFLA_INET6_MAX + 1]; int err; if (!idev) return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) return -EINVAL; if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), extack); if (err) return err; } if (tb[IFLA_INET6_ADDR_GEN_MODE]) { u8 mode = nla_get_u8(tb[IFLA_INET6_ADDR_GEN_MODE]); idev->cnf.addr_gen_mode = mode; } return 0; } static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, u32 portid, u32 seq, int event, unsigned int flags) { struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; void *protoinfo; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); if (!nlh) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_INET6; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev))) || nla_put_u8(skb, IFLA_OPERSTATE, netif_running(dev) ? dev->operstate : IF_OPER_DOWN)) goto nla_put_failure; protoinfo = nla_nest_start_noflag(skb, IFLA_PROTINFO); if (!protoinfo) goto nla_put_failure; if (inet6_fill_ifla6_attrs(skb, idev, 0) < 0) goto nla_put_failure; nla_nest_end(skb, protoinfo); nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifinfomsg *ifm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for link dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || ifm->ifi_change || ifm->ifi_index) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for dump request"); return -EINVAL; } return 0; } static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int h, s_h; int idx = 0, s_idx; struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; /* only requests using strict checking can pass data to * influence the dump */ if (cb->strict_check) { int err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack); if (err < 0) return err; } s_h = cb->args[0]; s_idx = cb->args[1]; rcu_read_lock(); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; idev = __in6_dev_get(dev); if (!idev) goto cont; if (inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI) < 0) goto out; cont: idx++; } } out: rcu_read_unlock(); cb->args[1] = idx; cb->args[0] = h; return skb->len; } void inet6_ifinfo_notify(int event, struct inet6_dev *idev) { struct sk_buff *skb; struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_if_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; err = inet6_fill_ifinfo(skb, idev, 0, 0, event, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); } static inline size_t inet6_prefix_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct prefixmsg)) + nla_total_size(sizeof(struct in6_addr)) + nla_total_size(sizeof(struct prefix_cacheinfo)); } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, struct prefix_info *pinfo, u32 portid, u32 seq, int event, unsigned int flags) { struct prefixmsg *pmsg; struct nlmsghdr *nlh; struct prefix_cacheinfo ci; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags); if (!nlh) return -EMSGSIZE; pmsg = nlmsg_data(nlh); pmsg->prefix_family = AF_INET6; pmsg->prefix_pad1 = 0; pmsg->prefix_pad2 = 0; pmsg->prefix_ifindex = idev->dev->ifindex; pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; pmsg->prefix_flags = pinfo->flags; if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) goto nla_put_failure; ci.preferred_time = ntohl(pinfo->prefered); ci.valid_time = ntohl(pinfo->valid); if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void inet6_prefix_notify(int event, struct inet6_dev *idev, struct prefix_info *pinfo) { struct sk_buff *skb; struct net *net = dev_net(idev->dev); int err = -ENOBUFS; skb = nlmsg_new(inet6_prefix_nlmsg_size(), GFP_ATOMIC); if (!skb) goto errout; err = inet6_fill_prefix(skb, idev, pinfo, 0, 0, event, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_prefix_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); if (event) ASSERT_RTNL(); inet6_ifa_notify(event ? : RTM_NEWADDR, ifp); switch (event) { case RTM_NEWADDR: /* * If the address was optimistic we inserted the route at the * start of our DAD process, so we don't need to do it again. * If the device was taken down in the middle of the DAD * cycle there is a race where we could get here without a * host route, so nothing to insert. That will be fixed when * the device is brought up. */ if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) { ip6_ins_rt(net, ifp->rt); } else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) { pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n", &ifp->addr, ifp->idev->dev->name); } if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) addrconf_prefix_route(&ifp->peer_addr, 128, ifp->rt_priority, ifp->idev->dev, 0, 0, GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { struct fib6_info *rt; rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, ifp->idev->dev, 0, 0, false); if (rt) ip6_del_rt(net, rt, false); } if (ifp->rt) { ip6_del_rt(net, ifp->rt, false); ifp->rt = NULL; } rt_genid_bump_ipv6(net); break; } atomic_inc(&net->ipv6.dev_addr_genid); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) { if (likely(ifp->idev->dead == 0)) __ipv6_ifa_notify(event, ifp); } #ifdef CONFIG_SYSCTL static int addrconf_sysctl_forward(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; /* * ctl->data points to idev->cnf.forwarding, we should * not modify it until we get the rtnl lock. */ lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_forwarding(ctl, valp, val); if (ret) *ppos = pos; return ret; } static int addrconf_sysctl_mtu(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct inet6_dev *idev = ctl->extra1; int min_mtu = IPV6_MIN_MTU; struct ctl_table lctl; lctl = *ctl; lctl.extra1 = &min_mtu; lctl.extra2 = idev ? &idev->dev->mtu : NULL; return proc_dointvec_minmax(&lctl, write, buffer, lenp, ppos); } static void dev_disable_change(struct inet6_dev *idev) { struct netdev_notifier_info info; if (!idev || !idev->dev) return; netdev_notifier_info_init(&info, idev->dev); if (idev->cnf.disable_ipv6) addrconf_notify(NULL, NETDEV_DOWN, &info); else addrconf_notify(NULL, NETDEV_UP, &info); } static void addrconf_disable_change(struct net *net, __s32 newf) { struct net_device *dev; struct inet6_dev *idev; for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); idev->cnf.disable_ipv6 = newf; if (changed) dev_disable_change(idev); } } } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) { struct net *net; int old; if (!rtnl_trylock()) return restart_syscall(); net = (struct net *)table->extra2; old = *p; *p = newf; if (p == &net->ipv6.devconf_dflt->disable_ipv6) { rtnl_unlock(); return 0; } if (p == &net->ipv6.devconf_all->disable_ipv6) { net->ipv6.devconf_dflt->disable_ipv6 = newf; addrconf_disable_change(net, newf); } else if ((!newf) ^ (!old)) dev_disable_change((struct inet6_dev *)table->extra1); rtnl_unlock(); return 0; } static int addrconf_sysctl_disable(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; /* * ctl->data points to idev->cnf.disable_ipv6, we should * not modify it until we get the rtnl lock. */ lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_disable_ipv6(ctl, valp, val); if (ret) *ppos = pos; return ret; } static int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int ret; int old, new; old = *valp; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); new = *valp; if (write && old != new) { struct net *net = ctl->extra2; if (!rtnl_trylock()) return restart_syscall(); if (valp == &net->ipv6.devconf_dflt->proxy_ndp) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_DEFAULT, net->ipv6.devconf_dflt); else if (valp == &net->ipv6.devconf_all->proxy_ndp) inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, NETCONFA_IFINDEX_ALL, net->ipv6.devconf_all); else { struct inet6_dev *idev = ctl->extra1; inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, idev->dev->ifindex, &idev->cnf); } rtnl_unlock(); } return ret; } static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; u32 new_val; struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1; struct net *net = (struct net *)ctl->extra2; struct ctl_table tmp = { .data = &new_val, .maxlen = sizeof(new_val), .mode = ctl->mode, }; if (!rtnl_trylock()) return restart_syscall(); new_val = *((u32 *)ctl->data); ret = proc_douintvec(&tmp, write, buffer, lenp, ppos); if (ret != 0) goto out; if (write) { if (check_addr_gen_mode(new_val) < 0) { ret = -EINVAL; goto out; } if (idev) { if (check_stable_privacy(idev, net, new_val) < 0) { ret = -EINVAL; goto out; } if (idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; net->ipv6.devconf_dflt->addr_gen_mode = new_val; for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev && idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; addrconf_init_auto_addrs(idev->dev); } } } *((u32 *)ctl->data) = new_val; } out: rtnl_unlock(); return ret; } static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; struct in6_addr addr; char str[IPV6_MAX_STRLEN]; struct ctl_table lctl = *ctl; struct net *net = ctl->extra2; struct ipv6_stable_secret *secret = ctl->data; if (&net->ipv6.devconf_all->stable_secret == ctl->data) return -EIO; lctl.maxlen = IPV6_MAX_STRLEN; lctl.data = str; if (!rtnl_trylock()) return restart_syscall(); if (!write && !secret->initialized) { err = -EIO; goto out; } err = snprintf(str, sizeof(str), "%pI6", &secret->secret); if (err >= sizeof(str)) { err = -EIO; goto out; } err = proc_dostring(&lctl, write, buffer, lenp, ppos); if (err || !write) goto out; if (in6_pton(str, -1, addr.in6_u.u6_addr8, -1, NULL) != 1) { err = -EIO; goto out; } secret->initialized = true; secret->secret = addr; if (&net->ipv6.devconf_dflt->stable_secret == ctl->data) { struct net_device *dev; for_each_netdev(net, dev) { struct inet6_dev *idev = __in6_dev_get(dev); if (idev) { idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; } } } else { struct inet6_dev *idev = ctl->extra1; idev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; } out: rtnl_unlock(); return err; } static int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; /* ctl->data points to idev->cnf.ignore_routes_when_linkdown * we should not modify it until we get the rtnl lock. */ lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write) ret = addrconf_fixup_linkdown(ctl, valp, val); if (ret) *ppos = pos; return ret; } static void addrconf_set_nopolicy(struct rt6_info *rt, int action) { if (rt) { if (action) rt->dst.flags |= DST_NOPOLICY; else rt->dst.flags &= ~DST_NOPOLICY; } } static void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) { struct inet6_ifaddr *ifa; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { spin_lock(&ifa->lock); if (ifa->rt) { /* host routes only use builtin fib6_nh */ struct fib6_nh *nh = ifa->rt->fib6_nh; int cpu; rcu_read_lock(); ifa->rt->dst_nopolicy = val ? true : false; if (nh->rt6i_pcpu) { for_each_possible_cpu(cpu) { struct rt6_info **rtp; rtp = per_cpu_ptr(nh->rt6i_pcpu, cpu); addrconf_set_nopolicy(*rtp, val); } } rcu_read_unlock(); } spin_unlock(&ifa->lock); } read_unlock_bh(&idev->lock); } static int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) { struct inet6_dev *idev; struct net *net; if (!rtnl_trylock()) return restart_syscall(); *valp = val; net = (struct net *)ctl->extra2; if (valp == &net->ipv6.devconf_dflt->disable_policy) { rtnl_unlock(); return 0; } if (valp == &net->ipv6.devconf_all->disable_policy) { struct net_device *dev; for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) addrconf_disable_policy_idev(idev, val); } } else { idev = (struct inet6_dev *)ctl->extra1; addrconf_disable_policy_idev(idev, val); } rtnl_unlock(); return 0; } static int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; struct ctl_table lctl; int ret; lctl = *ctl; lctl.data = &val; ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); if (write && (*valp != val)) ret = addrconf_disable_policy(ctl, valp, val); if (ret) *ppos = pos; return ret; } static int minus_one = -1; static const int two_five_five = 255; static u32 ioam6_if_id_max = U16_MAX; static const struct ctl_table addrconf_sysctl[] = { { .procname = "forwarding", .data = &ipv6_devconf.forwarding, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_forward, }, { .procname = "hop_limit", .data = &ipv6_devconf.hop_limit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ONE, .extra2 = (void *)&two_five_five, }, { .procname = "mtu", .data = &ipv6_devconf.mtu6, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_mtu, }, { .procname = "accept_ra", .data = &ipv6_devconf.accept_ra, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_redirects", .data = &ipv6_devconf.accept_redirects, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "autoconf", .data = &ipv6_devconf.autoconf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "dad_transmits", .data = &ipv6_devconf.dad_transmits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "router_solicitations", .data = &ipv6_devconf.rtr_solicits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &minus_one, }, { .procname = "router_solicitation_interval", .data = &ipv6_devconf.rtr_solicit_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "router_solicitation_max_interval", .data = &ipv6_devconf.rtr_solicit_max_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "router_solicitation_delay", .data = &ipv6_devconf.rtr_solicit_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "force_mld_version", .data = &ipv6_devconf.force_mld_version, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mldv1_unsolicited_report_interval", .data = &ipv6_devconf.mldv1_unsolicited_report_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "mldv2_unsolicited_report_interval", .data = &ipv6_devconf.mldv2_unsolicited_report_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "use_tempaddr", .data = &ipv6_devconf.use_tempaddr, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "temp_valid_lft", .data = &ipv6_devconf.temp_valid_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "temp_prefered_lft", .data = &ipv6_devconf.temp_prefered_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "regen_max_retry", .data = &ipv6_devconf.regen_max_retry, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_desync_factor", .data = &ipv6_devconf.max_desync_factor, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_addresses", .data = &ipv6_devconf.max_addresses, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_defrtr", .data = &ipv6_devconf.accept_ra_defrtr, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ra_defrtr_metric", .data = &ipv6_devconf.ra_defrtr_metric, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = (void *)SYSCTL_ONE, }, { .procname = "accept_ra_min_hop_limit", .data = &ipv6_devconf.accept_ra_min_hop_limit, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_min_lft", .data = &ipv6_devconf.accept_ra_min_lft, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_ROUTER_PREF { .procname = "accept_ra_rtr_pref", .data = &ipv6_devconf.accept_ra_rtr_pref, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "router_probe_interval", .data = &ipv6_devconf.rtr_probe_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #ifdef CONFIG_IPV6_ROUTE_INFO { .procname = "accept_ra_rt_info_min_plen", .data = &ipv6_devconf.accept_ra_rt_info_min_plen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_rt_info_max_plen", .data = &ipv6_devconf.accept_ra_rt_info_max_plen, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif #endif { .procname = "accept_ra_rt_table", .data = &ipv6_devconf.accept_ra_rt_table, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "proxy_ndp", .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_proxy_ndp, }, { .procname = "accept_source_route", .data = &ipv6_devconf.accept_source_route, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD { .procname = "optimistic_dad", .data = &ipv6_devconf.optimistic_dad, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "use_optimistic", .data = &ipv6_devconf.use_optimistic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif #ifdef CONFIG_IPV6_MROUTE { .procname = "mc_forwarding", .data = &ipv6_devconf.mc_forwarding, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, #endif { .procname = "disable_ipv6", .data = &ipv6_devconf.disable_ipv6, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_disable, }, { .procname = "accept_dad", .data = &ipv6_devconf.accept_dad, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "force_tllao", .data = &ipv6_devconf.force_tllao, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "ndisc_notify", .data = &ipv6_devconf.ndisc_notify, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "suppress_frag_ndisc", .data = &ipv6_devconf.suppress_frag_ndisc, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "accept_ra_from_local", .data = &ipv6_devconf.accept_ra_from_local, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "accept_ra_mtu", .data = &ipv6_devconf.accept_ra_mtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "stable_secret", .data = &ipv6_devconf.stable_secret, .maxlen = IPV6_MAX_STRLEN, .mode = 0600, .proc_handler = addrconf_sysctl_stable_secret, }, { .procname = "use_oif_addrs_only", .data = &ipv6_devconf.use_oif_addrs_only, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ignore_routes_with_linkdown", .data = &ipv6_devconf.ignore_routes_with_linkdown, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown, }, { .procname = "drop_unicast_in_l2_multicast", .data = &ipv6_devconf.drop_unicast_in_l2_multicast, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "drop_unsolicited_na", .data = &ipv6_devconf.drop_unsolicited_na, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "keep_addr_on_down", .data = &ipv6_devconf.keep_addr_on_down, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "seg6_enabled", .data = &ipv6_devconf.seg6_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #ifdef CONFIG_IPV6_SEG6_HMAC { .procname = "seg6_require_hmac", .data = &ipv6_devconf.seg6_require_hmac, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif { .procname = "enhanced_dad", .data = &ipv6_devconf.enhanced_dad, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "addr_gen_mode", .data = &ipv6_devconf.addr_gen_mode, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_addr_gen_mode, }, { .procname = "disable_policy", .data = &ipv6_devconf.disable_policy, .maxlen = sizeof(int), .mode = 0644, .proc_handler = addrconf_sysctl_disable_policy, }, { .procname = "ndisc_tclass", .data = &ipv6_devconf.ndisc_tclass, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)&two_five_five, }, { .procname = "rpl_seg_enabled", .data = &ipv6_devconf.rpl_seg_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "ioam6_enabled", .data = &ipv6_devconf.ioam6_enabled, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)SYSCTL_ONE, }, { .procname = "ioam6_id", .data = &ipv6_devconf.ioam6_id, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)&ioam6_if_id_max, }, { .procname = "ioam6_id_wide", .data = &ipv6_devconf.ioam6_id_wide, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec, }, { .procname = "ndisc_evict_nocarrier", .data = &ipv6_devconf.ndisc_evict_nocarrier, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = (void *)SYSCTL_ZERO, .extra2 = (void *)SYSCTL_ONE, }, { .procname = "accept_untracked_na", .data = &ipv6_devconf.accept_untracked_na, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { /* sentinel */ } }; static int __addrconf_sysctl_register(struct net *net, char *dev_name, struct inet6_dev *idev, struct ipv6_devconf *p) { int i, ifindex; struct ctl_table *table; char path[sizeof("net/ipv6/conf/") + IFNAMSIZ]; table = kmemdup(addrconf_sysctl, sizeof(addrconf_sysctl), GFP_KERNEL_ACCOUNT); if (!table) goto out; for (i = 0; table[i].data; i++) { table[i].data += (char *)p - (char *)&ipv6_devconf; /* If one of these is already set, then it is not safe to * overwrite either of them: this makes proc_dointvec_minmax * usable. */ if (!table[i].extra1 && !table[i].extra2) { table[i].extra1 = idev; /* embedded; no ref */ table[i].extra2 = net; } } snprintf(path, sizeof(path), "net/ipv6/conf/%s", dev_name); p->sysctl_header = register_net_sysctl(net, path, table); if (!p->sysctl_header) goto free; if (!strcmp(dev_name, "all")) ifindex = NETCONFA_IFINDEX_ALL; else if (!strcmp(dev_name, "default")) ifindex = NETCONFA_IFINDEX_DEFAULT; else ifindex = idev->dev->ifindex; inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(table); out: return -ENOBUFS; } static void __addrconf_sysctl_unregister(struct net *net, struct ipv6_devconf *p, int ifindex) { struct ctl_table *table; if (!p->sysctl_header) return; table = p->sysctl_header->ctl_table_arg; unregister_net_sysctl_table(p->sysctl_header); p->sysctl_header = NULL; kfree(table); inet6_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int addrconf_sysctl_register(struct inet6_dev *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->nd_parms, &ndisc_ifinfo_sysctl_change); if (err) return err; err = __addrconf_sysctl_register(dev_net(idev->dev), idev->dev->name, idev, &idev->cnf); if (err) neigh_sysctl_unregister(idev->nd_parms); return err; } static void addrconf_sysctl_unregister(struct inet6_dev *idev) { __addrconf_sysctl_unregister(dev_net(idev->dev), &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->nd_parms); } #endif static int __net_init addrconf_init_net(struct net *net) { int err = -ENOMEM; struct ipv6_devconf *all, *dflt; spin_lock_init(&net->ipv6.addrconf_hash_lock); INIT_DEFERRABLE_WORK(&net->ipv6.addr_chk_work, addrconf_verify_work); net->ipv6.inet6_addr_lst = kcalloc(IN6_ADDR_HSIZE, sizeof(struct hlist_head), GFP_KERNEL); if (!net->ipv6.inet6_addr_lst) goto err_alloc_addr; all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; if (!net_eq(net, &init_net)) { switch (net_inherit_devconf()) { case 1: /* copy from init_net */ memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf)); memcpy(dflt, init_net.ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt)); break; case 3: /* copy from the current netns */ memcpy(all, current->nsproxy->net_ns->ipv6.devconf_all, sizeof(ipv6_devconf)); memcpy(dflt, current->nsproxy->net_ns->ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt)); break; case 0: case 2: /* use compiled values */ break; } } /* these will be inherited by all namespaces */ dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; dflt->stable_secret.initialized = false; all->stable_secret.initialized = false; net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; #ifdef CONFIG_SYSCTL err = __addrconf_sysctl_register(net, "all", NULL, all); if (err < 0) goto err_reg_all; err = __addrconf_sysctl_register(net, "default", NULL, dflt); if (err < 0) goto err_reg_dflt; #endif return 0; #ifdef CONFIG_SYSCTL err_reg_dflt: __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(dflt); net->ipv6.devconf_dflt = NULL; #endif err_alloc_dflt: kfree(all); net->ipv6.devconf_all = NULL; err_alloc_all: kfree(net->ipv6.inet6_addr_lst); err_alloc_addr: return err; } static void __net_exit addrconf_exit_net(struct net *net) { int i; #ifdef CONFIG_SYSCTL __addrconf_sysctl_unregister(net, net->ipv6.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __addrconf_sysctl_unregister(net, net->ipv6.devconf_all, NETCONFA_IFINDEX_ALL); #endif kfree(net->ipv6.devconf_dflt); net->ipv6.devconf_dflt = NULL; kfree(net->ipv6.devconf_all); net->ipv6.devconf_all = NULL; cancel_delayed_work_sync(&net->ipv6.addr_chk_work); /* * Check hash table, then free it. */ for (i = 0; i < IN6_ADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&net->ipv6.inet6_addr_lst[i])); kfree(net->ipv6.inet6_addr_lst); net->ipv6.inet6_addr_lst = NULL; } static struct pernet_operations addrconf_ops = { .init = addrconf_init_net, .exit = addrconf_exit_net, }; static struct rtnl_af_ops inet6_ops __read_mostly = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, .get_link_af_size = inet6_get_link_af_size, .validate_link_af = inet6_validate_link_af, .set_link_af = inet6_set_link_af, }; /* * Init / cleanup code */ int __init addrconf_init(void) { struct inet6_dev *idev; int err; err = ipv6_addr_label_init(); if (err < 0) { pr_crit("%s: cannot initialize default policy table: %d\n", __func__, err); goto out; } err = register_pernet_subsys(&addrconf_ops); if (err < 0) goto out_addrlabel; addrconf_wq = create_workqueue("ipv6_addrconf"); if (!addrconf_wq) { err = -ENOMEM; goto out_nowq; } rtnl_lock(); idev = ipv6_add_dev(blackhole_netdev); rtnl_unlock(); if (IS_ERR(idev)) { err = PTR_ERR(idev); goto errlo; } ip6_route_init_special_entries(); register_netdevice_notifier(&ipv6_dev_notf); addrconf_verify(&init_net); rtnl_af_register(&inet6_ops); err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo, 0); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, 0); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, 0); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr, RTNL_FLAG_DOIT_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr, 0); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr, 0); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF, inet6_netconf_get_devconf, inet6_netconf_dump_devconf, RTNL_FLAG_DOIT_UNLOCKED); if (err < 0) goto errout; err = ipv6_addr_label_rtnl_register(); if (err < 0) goto errout; return 0; errout: rtnl_unregister_all(PF_INET6); rtnl_af_unregister(&inet6_ops); unregister_netdevice_notifier(&ipv6_dev_notf); errlo: destroy_workqueue(addrconf_wq); out_nowq: unregister_pernet_subsys(&addrconf_ops); out_addrlabel: ipv6_addr_label_cleanup(); out: return err; } void addrconf_cleanup(void) { struct net_device *dev; unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); ipv6_addr_label_cleanup(); rtnl_af_unregister(&inet6_ops); rtnl_lock(); /* clean dev list */ for_each_netdev(&init_net, dev) { if (__in6_dev_get(dev) == NULL) continue; addrconf_ifdown(dev, true); } addrconf_ifdown(init_net.loopback_dev, true); rtnl_unlock(); destroy_workqueue(addrconf_wq); } |
| 2 2 5 2 2 2 288 1117 1116 1116 1115 1117 442 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0-only /* -*- linux-c -*- * sysctl_net.c: sysctl interface to net subsystem. * * Begun April 1, 1996, Mike Shaver. * Added /proc/sys/net directories for each protocol family. [MS] * * Revision 1.2 1996/05/08 20:24:40 shaver * Added bits for NET_BRIDGE and the NET_IPV4_ARP stuff and * NET_IPV4_IP_FORWARD. * * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/sysctl.h> #include <linux/nsproxy.h> #include <net/sock.h> #ifdef CONFIG_INET #include <net/ip.h> #endif #ifdef CONFIG_NET #include <linux/if_ether.h> #endif static struct ctl_table_set * net_ctl_header_lookup(struct ctl_table_root *root) { return ¤t->nsproxy->net_ns->sysctls; } static int is_seen(struct ctl_table_set *set) { return ¤t->nsproxy->net_ns->sysctls == set; } /* Return standard mode bits for table entry. */ static int net_ctl_permissions(struct ctl_table_header *head, struct ctl_table *table) { struct net *net = container_of(head->set, struct net, sysctls); /* Allow network administrator to have same access as root. */ if (ns_capable_noaudit(net->user_ns, CAP_NET_ADMIN)) { int mode = (table->mode >> 6) & 7; return (mode << 6) | (mode << 3) | mode; } return table->mode; } static void net_ctl_set_ownership(struct ctl_table_header *head, struct ctl_table *table, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); kuid_t ns_root_uid; kgid_t ns_root_gid; ns_root_uid = make_kuid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; ns_root_gid = make_kgid(net->user_ns, 0); if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } static struct ctl_table_root net_sysctl_root = { .lookup = net_ctl_header_lookup, .permissions = net_ctl_permissions, .set_ownership = net_ctl_set_ownership, }; static int __net_init sysctl_net_init(struct net *net) { setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen); return 0; } static void __net_exit sysctl_net_exit(struct net *net) { retire_sysctl_set(&net->sysctls); } static struct pernet_operations sysctl_pernet_ops = { .init = sysctl_net_init, .exit = sysctl_net_exit, }; static struct ctl_table_header *net_header; __init int net_sysctl_init(void) { static struct ctl_table empty[1]; int ret = -ENOMEM; /* Avoid limitations in the sysctl implementation by * registering "/proc/sys/net" as an empty directory not in a * network namespace. */ net_header = register_sysctl("net", empty); if (!net_header) goto out; ret = register_pernet_subsys(&sysctl_pernet_ops); if (ret) goto out1; out: return ret; out1: unregister_sysctl_table(net_header); net_header = NULL; goto out; } /* Verify that sysctls for non-init netns are safe by either: * 1) being read-only, or * 2) having a data pointer which points outside of the global kernel/module * data segment, and rather into the heap where a per-net object was * allocated. */ static void ensure_safe_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { struct ctl_table *ent; pr_debug("Registering net sysctl (net %p): %s\n", net, path); for (ent = table; ent->procname; ent++) { unsigned long addr; const char *where; pr_debug(" procname=%s mode=%o proc_handler=%ps data=%p\n", ent->procname, ent->mode, ent->proc_handler, ent->data); /* If it's not writable inside the netns, then it can't hurt. */ if ((ent->mode & 0222) == 0) { pr_debug(" Not writable by anyone\n"); continue; } /* Where does data point? */ addr = (unsigned long)ent->data; if (is_module_address(addr)) where = "module"; else if (is_kernel_core_data(addr)) where = "kernel"; else continue; /* If it is writable and points to kernel/module global * data, then it's probably a netns leak. */ WARN(1, "sysctl %s/%s: data points to %s global data: %ps\n", path, ent->procname, where, ent->data); /* Make it "safe" by dropping writable perms */ ent->mode &= ~0222; } } struct ctl_table_header *register_net_sysctl(struct net *net, const char *path, struct ctl_table *table) { if (!net_eq(net, &init_net)) ensure_safe_net_sysctl(net, path, table); return __register_sysctl_table(&net->sysctls, path, table); } EXPORT_SYMBOL_GPL(register_net_sysctl); void unregister_net_sysctl_table(struct ctl_table_header *header) { unregister_sysctl_table(header); } EXPORT_SYMBOL_GPL(unregister_net_sysctl_table); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/userfaultfd_k.h * * Copyright (C) 2015 Red Hat, Inc. * */ #ifndef _LINUX_USERFAULTFD_K_H #define _LINUX_USERFAULTFD_K_H #ifdef CONFIG_USERFAULTFD #include <linux/userfaultfd.h> /* linux/include/uapi/linux/userfaultfd.h */ #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <asm-generic/pgtable_uffd.h> #include <linux/hugetlb_inline.h> /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want * to re-use O_* flags that couldn't possibly have a meaning * from userfaultfd, in order to leave a free define-space for * shared O_* flags. */ #define UFFD_CLOEXEC O_CLOEXEC #define UFFD_NONBLOCK O_NONBLOCK #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. * * Locking order: * fd_wqh.lock * fault_pending_wqh.lock * fault_wqh.lock * event_wqh.lock * * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's * also taken in IRQ context. */ /* * ANDROID: CRC fix for commit f91e6b41dd11 ("userfaultfd: move userfaultfd_ctx * struct to header file") */ #ifndef __GENKSYMS__ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ wait_queue_head_t fault_pending_wqh; /* waitqueue head for the userfaults */ wait_queue_head_t fault_wqh; /* waitqueue head for the pseudo fd to wakeup poll/read */ wait_queue_head_t fd_wqh; /* waitqueue head for events */ wait_queue_head_t event_wqh; /* a refile sequence protected by fault_pending_wqh lock */ seqcount_spinlock_t refile_seq; /* pseudo fd refcounting */ refcount_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* released */ bool released; /* * Prevents userfaultfd operations (fill/move/wp) from happening while * some non-cooperative event(s) is taking place. Increments are done * in write-mode. Whereas, userfaultfd operations, which includes * reading mmap_changing, is done under read-mode. */ struct rw_semaphore map_changing_lock; /* memory mappings are changing because of non-cooperative event */ atomic_t mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; ANDROID_KABI_RESERVE(1); }; #endif extern int sysctl_unprivileged_userfaultfd; extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); /* * The mode of operation for __mcopy_atomic and its helpers. * * This is almost an implementation detail (mcopy_atomic below doesn't take this * as a parameter), but it's exposed here because memory-kind-specific * implementations (e.g. hugetlbfs) need to know the mode of operation. */ enum mcopy_atomic_mode { /* A normal copy_from_user into the destination range. */ MCOPY_ATOMIC_NORMAL, /* Don't copy; map the destination range to the zero page. */ MCOPY_ATOMIC_ZEROPAGE, /* Just install pte(s) with the existing page(s) in the page cache. */ MCOPY_ATOMIC_CONTINUE, }; extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, bool newly_allocated, bool wp_copy); extern ssize_t mcopy_atomic(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, __u64 mode); extern ssize_t mfill_zeropage(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long len); extern ssize_t mcopy_continue(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long len); extern int mwriteprotect_range(struct userfaultfd_ctx *ctx, unsigned long start, unsigned long len, bool enable_wp); extern void uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* move_pages */ void double_pt_lock(spinlock_t *ptl1, spinlock_t *ptl2); void double_pt_unlock(spinlock_t *ptl1, spinlock_t *ptl2); ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, unsigned long src_start, unsigned long len, __u64 flags); int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr); /* mm helpers */ static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return vma->vm_userfaultfd_ctx.ctx == vm_ctx.ctx; } /* * Never enable huge pmd sharing on some uffd registered vmas: * * - VM_UFFD_WP VMAs, because write protect information is per pgtable entry. * * - VM_UFFD_MINOR VMAs, because otherwise we would never get minor faults for * VMAs which share huge pmds. (If you have two mappings to the same * underlying pages, and fault in the non-UFFD-registered one with a write, * with huge pmd sharing this would *also* setup the second UFFD-registered * mapping, and we'd not get minor faults.) */ static inline bool uffd_disable_huge_pmd_share(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } /* * Don't do fault around for either WP or MINOR registered uffd range. For * MINOR registered range, fault around will be a total disaster and ptes can * be installed without notifications; for WP it should mostly be fine as long * as the fault around checks for pte_none() before the installation, however * to be super safe we just forbid it. */ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return vma->vm_flags & (VM_UFFD_WP | VM_UFFD_MINOR); } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MISSING; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_WP; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return vma->vm_flags & VM_UFFD_MINOR; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return userfaultfd_wp(vma) && pte_uffd_wp(pte); } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return userfaultfd_wp(vma) && pmd_uffd_wp(pmd); } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return vma->vm_flags & __VM_UFFD_FLAGS; } static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; #ifndef CONFIG_PTE_MARKER_UFFD_WP /* * If user requested uffd-wp but not enabled pte markers for * uffd-wp, then shmem & hugetlbfs are not supported but only * anonymous. */ if ((vm_flags & VM_UFFD_WP) && !vma_is_anonymous(vma)) return false; #endif return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || vma_is_shmem(vma); } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *, unsigned long from, unsigned long to, unsigned long len); extern bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); #else /* CONFIG_USERFAULTFD */ /* mm helpers */ static inline vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { return VM_FAULT_SIGBUS; } static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma, struct vm_userfaultfd_ctx vm_ctx) { return true; } static inline bool userfaultfd_missing(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_wp(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_minor(struct vm_area_struct *vma) { return false; } static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { return false; } static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, pmd_t pmd) { return false; } static inline bool userfaultfd_armed(struct vm_area_struct *vma) { return false; } static inline int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *l) { return 0; } static inline void dup_userfaultfd_complete(struct list_head *l) { } static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { } static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx, unsigned long from, unsigned long to, unsigned long len) { } static inline bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return true; } static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf) { return 0; } static inline void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { } static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) { return false; } #endif /* CONFIG_USERFAULTFD */ static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP return is_pte_marker_entry(entry) && (pte_marker_get(entry) & PTE_MARKER_UFFD_WP); #else return false; #endif } static inline bool pte_marker_uffd_wp(pte_t pte) { #ifdef CONFIG_PTE_MARKER_UFFD_WP swp_entry_t entry; if (!is_swap_pte(pte)) return false; entry = pte_to_swp_entry(pte); return pte_marker_entry_uffd_wp(entry); #else return false; #endif } /* * Returns true if this is a swap pte and was uffd-wp wr-protected in either * forms (pte marker or a normal swap pte), false otherwise. */ static inline bool pte_swp_uffd_wp_any(pte_t pte) { #ifdef CONFIG_PTE_MARKER_UFFD_WP if (!is_swap_pte(pte)) return false; if (pte_swp_uffd_wp(pte)) return true; if (pte_marker_uffd_wp(pte)) return true; #endif return false; } #endif /* _LINUX_USERFAULTFD_K_H */ |
| 1741 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM bpf_test_run #if !defined(_TRACE_BPF_TEST_RUN_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BPF_TEST_RUN_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(bpf_test_finish, TP_PROTO(int *err), TP_ARGS(err), TP_STRUCT__entry( __field(int, err) ), TP_fast_assign( __entry->err = *err; ), TP_printk("bpf_test_finish with err=%d", __entry->err) ); #ifdef DEFINE_EVENT_WRITABLE #undef BPF_TEST_RUN_DEFINE_EVENT #define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size) \ DEFINE_EVENT_WRITABLE(template, call, PARAMS(proto), \ PARAMS(args), size) #else #undef BPF_TEST_RUN_DEFINE_EVENT #define BPF_TEST_RUN_DEFINE_EVENT(template, call, proto, args, size) \ DEFINE_EVENT(template, call, PARAMS(proto), PARAMS(args)) #endif BPF_TEST_RUN_DEFINE_EVENT(bpf_test_finish, bpf_test_finish, TP_PROTO(int *err), TP_ARGS(err), sizeof(int) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 94 94 94 94 94 94 94 94 92 88 89 89 89 87 89 87 87 87 87 90 1 87 2 5 5 5 5 5 5 5 5 9 5 5 5 5 8 9 8 5 1 4 5 4 4 2 3 39 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * kallsyms.c: in-kernel printing of symbolic oopses and stack traces. * * Rewritten and vastly simplified by Rusty Russell for in-kernel * module loader: * Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation * * ChangeLog: * * (25/Aug/2004) Paulo Marques <pmarques@grupopie.com> * Changed the compression method from stem compression to "table lookup" * compression (see scripts/kallsyms.c for a more complete description) */ #include <linux/kallsyms.h> #include <linux/init.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/kdb.h> #include <linux/err.h> #include <linux/proc_fs.h> #include <linux/sched.h> /* for cond_resched */ #include <linux/ctype.h> #include <linux/slab.h> #include <linux/filter.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include <linux/build_bug.h> #include <linux/compiler.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/bsearch.h> #include <linux/btf_ids.h> #include "kallsyms_internal.h" /* * Expand a compressed symbol data into the resulting uncompressed string, * if uncompressed string is too long (>= maxlen), it will be truncated, * given the offset to where the symbol is in the compressed stream. */ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result, size_t maxlen) { int len, skipped_first = 0; const char *tptr; const u8 *data; /* Get the compressed symbol length from the first symbol byte. */ data = &kallsyms_names[off]; len = *data; data++; off++; /* If MSB is 1, it is a "big" symbol, so needs an additional byte. */ if ((len & 0x80) != 0) { len = (len & 0x7F) | (*data << 7); data++; off++; } /* * Update the offset to return the offset for the next symbol on * the compressed stream. */ off += len; /* * For every byte on the compressed symbol data, copy the table * entry for that byte. */ while (len) { tptr = &kallsyms_token_table[kallsyms_token_index[*data]]; data++; len--; while (*tptr) { if (skipped_first) { if (maxlen <= 1) goto tail; *result = *tptr; result++; maxlen--; } else skipped_first = 1; tptr++; } } tail: if (maxlen) *result = '\0'; /* Return to offset to the next symbol. */ return off; } /* * Get symbol type information. This is encoded as a single char at the * beginning of the symbol name. */ static char kallsyms_get_symbol_type(unsigned int off) { /* * Get just the first code, look it up in the token table, * and return the first char from this token. */ return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]]; } /* * Find the offset on the compressed stream given and index in the * kallsyms array. */ static unsigned int get_symbol_offset(unsigned long pos) { const u8 *name; int i, len; /* * Use the closest marker we have. We have markers every 256 positions, * so that should be close enough. */ name = &kallsyms_names[kallsyms_markers[pos >> 8]]; /* * Sequentially scan all the symbols up to the point we're searching * for. Every symbol is stored in a [<len>][<len> bytes of data] format, * so we just need to add the len to the current pointer for every * symbol we wish to skip. */ for (i = 0; i < (pos & 0xFF); i++) { len = *name; /* * If MSB is 1, it is a "big" symbol, so we need to look into * the next byte (and skip it, too). */ if ((len & 0x80) != 0) len = ((len & 0x7F) | (name[1] << 7)) + 1; name = name + len + 1; } return name - kallsyms_names; } static unsigned long kallsyms_sym_address(int idx) { if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) return kallsyms_addresses[idx]; /* values are unsigned offsets if --absolute-percpu is not in effect */ if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU)) return kallsyms_relative_base + (u32)kallsyms_offsets[idx]; /* ...otherwise, positive offsets are absolute values */ if (kallsyms_offsets[idx] >= 0) return kallsyms_offsets[idx]; /* ...and negative offsets are relative to kallsyms_relative_base - 1 */ return kallsyms_relative_base - 1 - kallsyms_offsets[idx]; } static bool cleanup_symbol_name(char *s) { char *res; if (!IS_ENABLED(CONFIG_LTO_CLANG)) return false; /* * LLVM appends various suffixes for local functions and variables that * must be promoted to global scope as part of LTO. This can break * hooking of static functions with kprobes. '.' is not a valid * character in an identifier in C. Suffixes only in LLVM LTO observed: * - foo.llvm.[0-9a-f]+ */ res = strstr(s, ".llvm."); if (res) { *res = '\0'; return true; } return false; } static int compare_symbol_name(const char *name, char *namebuf) { /* The kallsyms_seqs_of_names is sorted based on names after * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled. * To ensure correct bisection in kallsyms_lookup_names(), do * cleanup_symbol_name(namebuf) before comparing name and namebuf. */ cleanup_symbol_name(namebuf); return strcmp(name, namebuf); } static unsigned int get_symbol_seq(int index) { unsigned int i, seq = 0; for (i = 0; i < 3; i++) seq = (seq << 8) | kallsyms_seqs_of_names[3 * index + i]; return seq; } static int kallsyms_lookup_names(const char *name, unsigned int *start, unsigned int *end) { int ret; int low, mid, high; unsigned int seq, off; char namebuf[KSYM_NAME_LEN]; low = 0; high = kallsyms_num_syms - 1; while (low <= high) { mid = low + (high - low) / 2; seq = get_symbol_seq(mid); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); ret = compare_symbol_name(name, namebuf); if (ret > 0) low = mid + 1; else if (ret < 0) high = mid - 1; else break; } if (low > high) return -ESRCH; low = mid; while (low) { seq = get_symbol_seq(low - 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); if (compare_symbol_name(name, namebuf)) break; low--; } *start = low; if (end) { high = mid; while (high < kallsyms_num_syms - 1) { seq = get_symbol_seq(high + 1); off = get_symbol_offset(seq); kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); if (compare_symbol_name(name, namebuf)) break; high++; } *end = high; } return 0; } /* Lookup the address for this symbol. Returns 0 if not found. */ unsigned long kallsyms_lookup_name(const char *name) { int ret; unsigned int i; /* Skip the search for empty string. */ if (!*name) return 0; ret = kallsyms_lookup_names(name, &i, NULL); if (!ret) return kallsyms_sym_address(get_symbol_seq(i)); return module_kallsyms_lookup_name(name); } /* * Iterate over all symbols in vmlinux. For symbols from modules use * module_kallsyms_on_each_symbol instead. */ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) { char namebuf[KSYM_NAME_LEN]; unsigned long i; unsigned int off; int ret; for (i = 0, off = 0; i < kallsyms_num_syms; i++) { off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf)); ret = fn(data, namebuf, NULL, kallsyms_sym_address(i)); if (ret != 0) return ret; cond_resched(); } return 0; } int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data) { int ret; unsigned int i, start, end; ret = kallsyms_lookup_names(name, &start, &end); if (ret) return 0; for (i = start; !ret && i <= end; i++) { ret = fn(data, kallsyms_sym_address(get_symbol_seq(i))); cond_resched(); } return ret; } static unsigned long get_symbol_pos(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { unsigned long symbol_start = 0, symbol_end = 0; unsigned long i, low, high, mid; /* This kernel should never had been booted. */ if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE)) BUG_ON(!kallsyms_addresses); else BUG_ON(!kallsyms_offsets); /* Do a binary search on the sorted kallsyms_addresses array. */ low = 0; high = kallsyms_num_syms; while (high - low > 1) { mid = low + (high - low) / 2; if (kallsyms_sym_address(mid) <= addr) low = mid; else high = mid; } /* * Search for the first aliased symbol. Aliased * symbols are symbols with the same address. */ while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low)) --low; symbol_start = kallsyms_sym_address(low); /* Search for next non-aliased symbol. */ for (i = low + 1; i < kallsyms_num_syms; i++) { if (kallsyms_sym_address(i) > symbol_start) { symbol_end = kallsyms_sym_address(i); break; } } /* If we found no next symbol, we use the end of the section. */ if (!symbol_end) { if (is_kernel_inittext(addr)) symbol_end = (unsigned long)_einittext; else if (IS_ENABLED(CONFIG_KALLSYMS_ALL)) symbol_end = (unsigned long)_end; else symbol_end = (unsigned long)_etext; } if (symbolsize) *symbolsize = symbol_end - symbol_start; if (offset) *offset = addr - symbol_start; return low; } /* * Lookup an address but don't bother to find any names. */ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, unsigned long *offset) { char namebuf[KSYM_NAME_LEN]; if (is_ksym_addr(addr)) { get_symbol_pos(addr, symbolsize, offset); return 1; } return !!module_address_lookup(addr, symbolsize, offset, NULL, NULL, namebuf) || !!__bpf_address_lookup(addr, symbolsize, offset, namebuf); } static const char *kallsyms_lookup_buildid(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { const char *ret; namebuf[KSYM_NAME_LEN - 1] = 0; namebuf[0] = 0; if (is_ksym_addr(addr)) { unsigned long pos; pos = get_symbol_pos(addr, symbolsize, offset); /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), namebuf, KSYM_NAME_LEN); if (modname) *modname = NULL; if (modbuildid) *modbuildid = NULL; ret = namebuf; goto found; } /* See if it's in a module or a BPF JITed image. */ ret = module_address_lookup(addr, symbolsize, offset, modname, modbuildid, namebuf); if (!ret) ret = bpf_address_lookup(addr, symbolsize, offset, modname, namebuf); if (!ret) ret = ftrace_mod_address_lookup(addr, symbolsize, offset, modname, namebuf); found: cleanup_symbol_name(namebuf); return ret; } /* * Lookup an address * - modname is set to NULL if it's in the kernel. * - We guarantee that the returned name is valid until we reschedule even if. * It resides in a module. * - We also guarantee that modname will be valid until rescheduled. */ const char *kallsyms_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, char *namebuf) { return kallsyms_lookup_buildid(addr, symbolsize, offset, modname, NULL, namebuf); } int lookup_symbol_name(unsigned long addr, char *symname) { int res; symname[0] = '\0'; symname[KSYM_NAME_LEN - 1] = '\0'; if (is_ksym_addr(addr)) { unsigned long pos; pos = get_symbol_pos(addr, NULL, NULL); /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), symname, KSYM_NAME_LEN); goto found; } /* See if it's in a module. */ res = lookup_module_symbol_name(addr, symname); if (res) return res; found: cleanup_symbol_name(symname); return 0; } int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) { int res; name[0] = '\0'; name[KSYM_NAME_LEN - 1] = '\0'; if (is_ksym_addr(addr)) { unsigned long pos; pos = get_symbol_pos(addr, size, offset); /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), name, KSYM_NAME_LEN); modname[0] = '\0'; goto found; } /* See if it's in a module. */ res = lookup_module_symbol_attrs(addr, size, offset, modname, name); if (res) return res; found: cleanup_symbol_name(name); return 0; } /* Look up a kernel symbol and return it in a text buffer. */ static int __sprint_symbol(char *buffer, unsigned long address, int symbol_offset, int add_offset, int add_buildid) { char *modname; const unsigned char *buildid; const char *name; unsigned long offset, size; int len; address += symbol_offset; name = kallsyms_lookup_buildid(address, &size, &offset, &modname, &buildid, buffer); if (!name) return sprintf(buffer, "0x%lx", address - symbol_offset); if (name != buffer) strcpy(buffer, name); len = strlen(buffer); offset -= symbol_offset; if (add_offset) len += sprintf(buffer + len, "+%#lx/%#lx", offset, size); if (modname) { len += sprintf(buffer + len, " [%s", modname); #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) if (add_buildid && buildid) { /* build ID should match length of sprintf */ #if IS_ENABLED(CONFIG_MODULES) static_assert(sizeof(typeof_member(struct module, build_id)) == 20); #endif len += sprintf(buffer + len, " %20phN", buildid); } #endif len += sprintf(buffer + len, "]"); } return len; } /** * sprint_symbol - Look up a kernel symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function looks up a kernel symbol with @address and stores its name, * offset, size and module name to @buffer if possible. If no symbol was found, * just saves its @address as is. * * This function returns the number of bytes stored in @buffer. */ int sprint_symbol(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, 0, 1, 0); } EXPORT_SYMBOL_GPL(sprint_symbol); /** * sprint_symbol_build_id - Look up a kernel symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function looks up a kernel symbol with @address and stores its name, * offset, size, module name and module build ID to @buffer if possible. If no * symbol was found, just saves its @address as is. * * This function returns the number of bytes stored in @buffer. */ int sprint_symbol_build_id(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, 0, 1, 1); } EXPORT_SYMBOL_GPL(sprint_symbol_build_id); /** * sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function looks up a kernel symbol with @address and stores its name * and module name to @buffer if possible. If no symbol was found, just saves * its @address as is. * * This function returns the number of bytes stored in @buffer. */ int sprint_symbol_no_offset(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, 0, 0, 0); } EXPORT_SYMBOL_GPL(sprint_symbol_no_offset); /** * sprint_backtrace - Look up a backtrace symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function is for stack backtrace and does the same thing as * sprint_symbol() but with modified/decreased @address. If there is a * tail-call to the function marked "noreturn", gcc optimized out code after * the call so that the stack-saved return address could point outside of the * caller. This function ensures that kallsyms will find the original caller * by decreasing @address. * * This function returns the number of bytes stored in @buffer. */ int sprint_backtrace(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, -1, 1, 0); } /** * sprint_backtrace_build_id - Look up a backtrace symbol and return it in a text buffer * @buffer: buffer to be stored * @address: address to lookup * * This function is for stack backtrace and does the same thing as * sprint_symbol() but with modified/decreased @address. If there is a * tail-call to the function marked "noreturn", gcc optimized out code after * the call so that the stack-saved return address could point outside of the * caller. This function ensures that kallsyms will find the original caller * by decreasing @address. This function also appends the module build ID to * the @buffer if @address is within a kernel module. * * This function returns the number of bytes stored in @buffer. */ int sprint_backtrace_build_id(char *buffer, unsigned long address) { return __sprint_symbol(buffer, address, -1, 1, 1); } /* To avoid using get_symbol_offset for every symbol, we carry prefix along. */ struct kallsym_iter { loff_t pos; loff_t pos_arch_end; loff_t pos_mod_end; loff_t pos_ftrace_mod_end; loff_t pos_bpf_end; unsigned long value; unsigned int nameoff; /* If iterating in core kernel symbols. */ char type; char name[KSYM_NAME_LEN]; char module_name[MODULE_NAME_LEN]; int exported; int show_value; }; int __weak arch_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name) { return -EINVAL; } static int get_ksymbol_arch(struct kallsym_iter *iter) { int ret = arch_get_kallsym(iter->pos - kallsyms_num_syms, &iter->value, &iter->type, iter->name); if (ret < 0) { iter->pos_arch_end = iter->pos; return 0; } return 1; } static int get_ksymbol_mod(struct kallsym_iter *iter) { int ret = module_get_kallsym(iter->pos - iter->pos_arch_end, &iter->value, &iter->type, iter->name, iter->module_name, &iter->exported); if (ret < 0) { iter->pos_mod_end = iter->pos; return 0; } return 1; } /* * ftrace_mod_get_kallsym() may also get symbols for pages allocated for ftrace * purposes. In that case "__builtin__ftrace" is used as a module name, even * though "__builtin__ftrace" is not a module. */ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter) { int ret = ftrace_mod_get_kallsym(iter->pos - iter->pos_mod_end, &iter->value, &iter->type, iter->name, iter->module_name, &iter->exported); if (ret < 0) { iter->pos_ftrace_mod_end = iter->pos; return 0; } return 1; } static int get_ksymbol_bpf(struct kallsym_iter *iter) { int ret; strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN); iter->exported = 0; ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end, &iter->value, &iter->type, iter->name); if (ret < 0) { iter->pos_bpf_end = iter->pos; return 0; } return 1; } /* * This uses "__builtin__kprobes" as a module name for symbols for pages * allocated for kprobes' purposes, even though "__builtin__kprobes" is not a * module. */ static int get_ksymbol_kprobe(struct kallsym_iter *iter) { strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN); iter->exported = 0; return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end, &iter->value, &iter->type, iter->name) < 0 ? 0 : 1; } /* Returns space to next name. */ static unsigned long get_ksymbol_core(struct kallsym_iter *iter) { unsigned off = iter->nameoff; iter->module_name[0] = '\0'; iter->value = kallsyms_sym_address(iter->pos); iter->type = kallsyms_get_symbol_type(off); off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name)); return off - iter->nameoff; } static void reset_iter(struct kallsym_iter *iter, loff_t new_pos) { iter->name[0] = '\0'; iter->nameoff = get_symbol_offset(new_pos); iter->pos = new_pos; if (new_pos == 0) { iter->pos_arch_end = 0; iter->pos_mod_end = 0; iter->pos_ftrace_mod_end = 0; iter->pos_bpf_end = 0; } } /* * The end position (last + 1) of each additional kallsyms section is recorded * in iter->pos_..._end as each section is added, and so can be used to * determine which get_ksymbol_...() function to call next. */ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos) { iter->pos = pos; if ((!iter->pos_arch_end || iter->pos_arch_end > pos) && get_ksymbol_arch(iter)) return 1; if ((!iter->pos_mod_end || iter->pos_mod_end > pos) && get_ksymbol_mod(iter)) return 1; if ((!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > pos) && get_ksymbol_ftrace_mod(iter)) return 1; if ((!iter->pos_bpf_end || iter->pos_bpf_end > pos) && get_ksymbol_bpf(iter)) return 1; return get_ksymbol_kprobe(iter); } /* Returns false if pos at or past end of file. */ static int update_iter(struct kallsym_iter *iter, loff_t pos) { /* Module symbols can be accessed randomly. */ if (pos >= kallsyms_num_syms) return update_iter_mod(iter, pos); /* If we're not on the desired position, reset to new position. */ if (pos != iter->pos) reset_iter(iter, pos); iter->nameoff += get_ksymbol_core(iter); iter->pos++; return 1; } static void *s_next(struct seq_file *m, void *p, loff_t *pos) { (*pos)++; if (!update_iter(m->private, *pos)) return NULL; return p; } static void *s_start(struct seq_file *m, loff_t *pos) { if (!update_iter(m->private, *pos)) return NULL; return m->private; } static void s_stop(struct seq_file *m, void *p) { } static int s_show(struct seq_file *m, void *p) { void *value; struct kallsym_iter *iter = m->private; /* Some debugging symbols have no name. Ignore them. */ if (!iter->name[0]) return 0; value = iter->show_value ? (void *)iter->value : NULL; if (iter->module_name[0]) { char type; /* * Label it "global" if it is exported, * "local" if not exported. */ type = iter->exported ? toupper(iter->type) : tolower(iter->type); seq_printf(m, "%px %c %s\t[%s]\n", value, type, iter->name, iter->module_name); } else seq_printf(m, "%px %c %s\n", value, iter->type, iter->name); return 0; } static const struct seq_operations kallsyms_op = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show }; #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__ksym { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct kallsym_iter *, ksym); }; static int ksym_prog_seq_show(struct seq_file *m, bool in_stop) { struct bpf_iter__ksym ctx; struct bpf_iter_meta meta; struct bpf_prog *prog; meta.seq = m; prog = bpf_iter_get_info(&meta, in_stop); if (!prog) return 0; ctx.meta = &meta; ctx.ksym = m ? m->private : NULL; return bpf_iter_run_prog(prog, &ctx); } static int bpf_iter_ksym_seq_show(struct seq_file *m, void *p) { return ksym_prog_seq_show(m, false); } static void bpf_iter_ksym_seq_stop(struct seq_file *m, void *p) { if (!p) (void) ksym_prog_seq_show(m, true); else s_stop(m, p); } static const struct seq_operations bpf_iter_ksym_ops = { .start = s_start, .next = s_next, .stop = bpf_iter_ksym_seq_stop, .show = bpf_iter_ksym_seq_show, }; static int bpf_iter_ksym_init(void *priv_data, struct bpf_iter_aux_info *aux) { struct kallsym_iter *iter = priv_data; reset_iter(iter, 0); /* cache here as in kallsyms_open() case; use current process * credentials to tell BPF iterators if values should be shown. */ iter->show_value = kallsyms_show_value(current_cred()); return 0; } DEFINE_BPF_ITER_FUNC(ksym, struct bpf_iter_meta *meta, struct kallsym_iter *ksym) static const struct bpf_iter_seq_info ksym_iter_seq_info = { .seq_ops = &bpf_iter_ksym_ops, .init_seq_private = bpf_iter_ksym_init, .fini_seq_private = NULL, .seq_priv_size = sizeof(struct kallsym_iter), }; static struct bpf_iter_reg ksym_iter_reg_info = { .target = "ksym", .feature = BPF_ITER_RESCHED, .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ksym, ksym), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ksym_iter_seq_info, }; BTF_ID_LIST(btf_ksym_iter_id) BTF_ID(struct, kallsym_iter) static int __init bpf_ksym_iter_register(void) { ksym_iter_reg_info.ctx_arg_info[0].btf_id = *btf_ksym_iter_id; return bpf_iter_reg_target(&ksym_iter_reg_info); } late_initcall(bpf_ksym_iter_register); #endif /* CONFIG_BPF_SYSCALL */ static inline int kallsyms_for_perf(void) { #ifdef CONFIG_PERF_EVENTS extern int sysctl_perf_event_paranoid; if (sysctl_perf_event_paranoid <= 1) return 1; #endif return 0; } /* * We show kallsyms information even to normal users if we've enabled * kernel profiling and are explicitly not paranoid (so kptr_restrict * is clear, and sysctl_perf_event_paranoid isn't set). * * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to * block even that). */ bool kallsyms_show_value(const struct cred *cred) { switch (kptr_restrict) { case 0: if (kallsyms_for_perf()) return true; fallthrough; case 1: if (security_capable(cred, &init_user_ns, CAP_SYSLOG, CAP_OPT_NOAUDIT) == 0) return true; fallthrough; default: return false; } } static int kallsyms_open(struct inode *inode, struct file *file) { /* * We keep iterator in m->private, since normal case is to * s_start from where we left off, so we avoid doing * using get_symbol_offset for every symbol. */ struct kallsym_iter *iter; iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter)); if (!iter) return -ENOMEM; reset_iter(iter, 0); /* * Instead of checking this on every s_show() call, cache * the result here at open time. */ iter->show_value = kallsyms_show_value(file->f_cred); return 0; } #ifdef CONFIG_KGDB_KDB const char *kdb_walk_kallsyms(loff_t *pos) { static struct kallsym_iter kdb_walk_kallsyms_iter; if (*pos == 0) { memset(&kdb_walk_kallsyms_iter, 0, sizeof(kdb_walk_kallsyms_iter)); reset_iter(&kdb_walk_kallsyms_iter, 0); } while (1) { if (!update_iter(&kdb_walk_kallsyms_iter, *pos)) return NULL; ++*pos; /* Some debugging symbols have no name. Ignore them. */ if (kdb_walk_kallsyms_iter.name[0]) return kdb_walk_kallsyms_iter.name; } } #endif /* CONFIG_KGDB_KDB */ static const struct proc_ops kallsyms_proc_ops = { .proc_open = kallsyms_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release_private, }; static int __init kallsyms_init(void) { proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops); return 0; } device_initcall(kallsyms_init); |
| 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PATH_H #define _LINUX_PATH_H struct dentry; struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; } __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); static inline int path_equal(const struct path *path1, const struct path *path2) { return path1->mnt == path2->mnt && path1->dentry == path2->dentry; } static inline void path_put_init(struct path *path) { path_put(path); *path = (struct path) { }; } #endif /* _LINUX_PATH_H */ |
| 3605 3402 754 2919 2919 754 3391 3390 3390 490 491 490 436 65 491 205 205 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) arch_irq_work_raise(); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack_noalloc(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } EXPORT_SYMBOL_GPL(irq_work_queue_on); bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 35 35 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Sysfs attributes of bridge * Linux ethernet bridge * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/times.h> #include <linux/sched/signal.h> #include "br_private.h" /* IMPORTANT: new bridge options must be added with netlink support only * please do not add new sysfs entries */ #define to_bridge(cd) ((struct net_bridge *)netdev_priv(to_net_dev(cd))) /* * Common code for storing bridge parameters. */ static ssize_t store_bridge_parm(struct device *d, const char *buf, size_t len, int (*set)(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack)) { struct net_bridge *br = to_bridge(d); struct netlink_ext_ack extack = {0}; unsigned long val; int err; if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; err = kstrtoul(buf, 0, &val); if (err != 0) return err; if (!rtnl_trylock()) return restart_syscall(); err = (*set)(br, val, &extack); if (!err) netdev_state_change(br->dev); if (extack._msg) { if (err) br_err(br, "%s\n", extack._msg); else br_warn(br, "%s\n", extack._msg); } rtnl_unlock(); return err ? err : len; } static ssize_t forward_delay_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->forward_delay)); } static int set_forward_delay(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_set_forward_delay(br, val); } static ssize_t forward_delay_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_forward_delay); } static DEVICE_ATTR_RW(forward_delay); static ssize_t hello_time_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%lu\n", jiffies_to_clock_t(to_bridge(d)->hello_time)); } static int set_hello_time(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_set_hello_time(br, val); } static ssize_t hello_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_hello_time); } static DEVICE_ATTR_RW(hello_time); static ssize_t max_age_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%lu\n", jiffies_to_clock_t(to_bridge(d)->max_age)); } static int set_max_age(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_set_max_age(br, val); } static ssize_t max_age_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_max_age); } static DEVICE_ATTR_RW(max_age); static ssize_t ageing_time_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->ageing_time)); } static int set_ageing_time(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_set_ageing_time(br, val); } static ssize_t ageing_time_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_ageing_time); } static DEVICE_ATTR_RW(ageing_time); static ssize_t stp_state_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->stp_enabled); } static int set_stp_state(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_stp_set_enabled(br, val, extack); } static ssize_t stp_state_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_stp_state); } static DEVICE_ATTR_RW(stp_state); static ssize_t group_fwd_mask_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%#x\n", br->group_fwd_mask); } static int set_group_fwd_mask(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { if (val & BR_GROUPFWD_RESTRICTED) return -EINVAL; br->group_fwd_mask = val; return 0; } static ssize_t group_fwd_mask_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_group_fwd_mask); } static DEVICE_ATTR_RW(group_fwd_mask); static ssize_t priority_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]); } static int set_priority(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_stp_set_bridge_priority(br, (u16) val); return 0; } static ssize_t priority_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_priority); } static DEVICE_ATTR_RW(priority); static ssize_t root_id_show(struct device *d, struct device_attribute *attr, char *buf) { return br_show_bridge_id(buf, &to_bridge(d)->designated_root); } static DEVICE_ATTR_RO(root_id); static ssize_t bridge_id_show(struct device *d, struct device_attribute *attr, char *buf) { return br_show_bridge_id(buf, &to_bridge(d)->bridge_id); } static DEVICE_ATTR_RO(bridge_id); static ssize_t root_port_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->root_port); } static DEVICE_ATTR_RO(root_port); static ssize_t root_path_cost_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->root_path_cost); } static DEVICE_ATTR_RO(root_path_cost); static ssize_t topology_change_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%d\n", to_bridge(d)->topology_change); } static DEVICE_ATTR_RO(topology_change); static ssize_t topology_change_detected_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->topology_change_detected); } static DEVICE_ATTR_RO(topology_change_detected); static ssize_t hello_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->hello_timer)); } static DEVICE_ATTR_RO(hello_timer); static ssize_t tcn_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->tcn_timer)); } static DEVICE_ATTR_RO(tcn_timer); static ssize_t topology_change_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->topology_change_timer)); } static DEVICE_ATTR_RO(topology_change_timer); static ssize_t gc_timer_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%ld\n", br_timer_value(&br->gc_work.timer)); } static DEVICE_ATTR_RO(gc_timer); static ssize_t group_addr_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%pM\n", br->group_addr); } static ssize_t group_addr_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { struct net_bridge *br = to_bridge(d); u8 new_addr[6]; if (!ns_capable(dev_net(br->dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!mac_pton(buf, new_addr)) return -EINVAL; if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ new_addr[5] == 2 || /* 802.3ad Slow protocols */ new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; if (!rtnl_trylock()) return restart_syscall(); spin_lock_bh(&br->lock); ether_addr_copy(br->group_addr, new_addr); spin_unlock_bh(&br->lock); br_opt_toggle(br, BROPT_GROUP_ADDR_SET, true); br_recalculate_fwd_mask(br); netdev_state_change(br->dev); rtnl_unlock(); return len; } static DEVICE_ATTR_RW(group_addr); static int set_flush(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct net_bridge_fdb_flush_desc desc = { .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); return 0; } static ssize_t flush_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_flush); } static DEVICE_ATTR_WO(flush); static ssize_t no_linklocal_learn_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br_boolopt_get(br, BR_BOOLOPT_NO_LL_LEARN)); } static int set_no_linklocal_learn(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_boolopt_toggle(br, BR_BOOLOPT_NO_LL_LEARN, !!val, extack); } static ssize_t no_linklocal_learn_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_no_linklocal_learn); } static DEVICE_ATTR_RW(no_linklocal_learn); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING static ssize_t multicast_router_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->multicast_ctx.multicast_router); } static int set_multicast_router(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_multicast_set_router(&br->multicast_ctx, val); } static ssize_t multicast_router_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_multicast_router); } static DEVICE_ATTR_RW(multicast_router); static ssize_t multicast_snooping_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br_opt_get(br, BROPT_MULTICAST_ENABLED)); } static ssize_t multicast_snooping_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_multicast_toggle); } static DEVICE_ATTR_RW(multicast_snooping); static ssize_t multicast_query_use_ifaddr_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)); } static int set_query_use_ifaddr(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); return 0; } static ssize_t multicast_query_use_ifaddr_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_query_use_ifaddr); } static DEVICE_ATTR_RW(multicast_query_use_ifaddr); static ssize_t multicast_querier_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->multicast_ctx.multicast_querier); } static int set_multicast_querier(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_multicast_set_querier(&br->multicast_ctx, val); } static ssize_t multicast_querier_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_multicast_querier); } static DEVICE_ATTR_RW(multicast_querier); static ssize_t hash_elasticity_show(struct device *d, struct device_attribute *attr, char *buf) { return sprintf(buf, "%u\n", RHT_ELASTICITY); } static int set_elasticity(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { /* 16 is RHT_ELASTICITY */ NL_SET_ERR_MSG_MOD(extack, "the hash_elasticity option has been deprecated and is always 16"); return 0; } static ssize_t hash_elasticity_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_elasticity); } static DEVICE_ATTR_RW(hash_elasticity); static ssize_t hash_max_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br->hash_max); } static int set_hash_max(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->hash_max = val; return 0; } static ssize_t hash_max_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_hash_max); } static DEVICE_ATTR_RW(hash_max); static ssize_t multicast_igmp_version_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br->multicast_ctx.multicast_igmp_version); } static int set_multicast_igmp_version(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_multicast_set_igmp_version(&br->multicast_ctx, val); } static ssize_t multicast_igmp_version_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_multicast_igmp_version); } static DEVICE_ATTR_RW(multicast_igmp_version); static ssize_t multicast_last_member_count_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br->multicast_ctx.multicast_last_member_count); } static int set_last_member_count(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->multicast_ctx.multicast_last_member_count = val; return 0; } static ssize_t multicast_last_member_count_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_last_member_count); } static DEVICE_ATTR_RW(multicast_last_member_count); static ssize_t multicast_startup_query_count_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br->multicast_ctx.multicast_startup_query_count); } static int set_startup_query_count(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->multicast_ctx.multicast_startup_query_count = val; return 0; } static ssize_t multicast_startup_query_count_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_startup_query_count); } static DEVICE_ATTR_RW(multicast_startup_query_count); static ssize_t multicast_last_member_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval)); } static int set_last_member_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); return 0; } static ssize_t multicast_last_member_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_last_member_interval); } static DEVICE_ATTR_RW(multicast_last_member_interval); static ssize_t multicast_membership_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval)); } static int set_membership_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); return 0; } static ssize_t multicast_membership_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_membership_interval); } static DEVICE_ATTR_RW(multicast_membership_interval); static ssize_t multicast_querier_interval_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval)); } static int set_querier_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); return 0; } static ssize_t multicast_querier_interval_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_querier_interval); } static DEVICE_ATTR_RW(multicast_querier_interval); static ssize_t multicast_query_interval_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%lu\n", jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval)); } static int set_query_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_multicast_set_query_intvl(&br->multicast_ctx, val); return 0; } static ssize_t multicast_query_interval_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_query_interval); } static DEVICE_ATTR_RW(multicast_query_interval); static ssize_t multicast_query_response_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf( buf, "%lu\n", jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval)); } static int set_query_response_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); return 0; } static ssize_t multicast_query_response_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_query_response_interval); } static DEVICE_ATTR_RW(multicast_query_response_interval); static ssize_t multicast_startup_query_interval_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf( buf, "%lu\n", jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval)); } static int set_startup_query_interval(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_multicast_set_startup_query_intvl(&br->multicast_ctx, val); return 0; } static ssize_t multicast_startup_query_interval_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_startup_query_interval); } static DEVICE_ATTR_RW(multicast_startup_query_interval); static ssize_t multicast_stats_enabled_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)); } static int set_stats_enabled(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!val); return 0; } static ssize_t multicast_stats_enabled_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_stats_enabled); } static DEVICE_ATTR_RW(multicast_stats_enabled); #if IS_ENABLED(CONFIG_IPV6) static ssize_t multicast_mld_version_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br->multicast_ctx.multicast_mld_version); } static int set_multicast_mld_version(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_multicast_set_mld_version(&br->multicast_ctx, val); } static ssize_t multicast_mld_version_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_multicast_mld_version); } static DEVICE_ATTR_RW(multicast_mld_version); #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static ssize_t nf_call_iptables_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br_opt_get(br, BROPT_NF_CALL_IPTABLES)); } static int set_nf_call_iptables(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); return 0; } static ssize_t nf_call_iptables_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_nf_call_iptables); } static DEVICE_ATTR_RW(nf_call_iptables); static ssize_t nf_call_ip6tables_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br_opt_get(br, BROPT_NF_CALL_IP6TABLES)); } static int set_nf_call_ip6tables(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); return 0; } static ssize_t nf_call_ip6tables_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_nf_call_ip6tables); } static DEVICE_ATTR_RW(nf_call_ip6tables); static ssize_t nf_call_arptables_show( struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br_opt_get(br, BROPT_NF_CALL_ARPTABLES)); } static int set_nf_call_arptables(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); return 0; } static ssize_t nf_call_arptables_store( struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_nf_call_arptables); } static DEVICE_ATTR_RW(nf_call_arptables); #endif #ifdef CONFIG_BRIDGE_VLAN_FILTERING static ssize_t vlan_filtering_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br_opt_get(br, BROPT_VLAN_ENABLED)); } static ssize_t vlan_filtering_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_vlan_filter_toggle); } static DEVICE_ATTR_RW(vlan_filtering); static ssize_t vlan_protocol_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%#06x\n", ntohs(br->vlan_proto)); } static ssize_t vlan_protocol_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_vlan_set_proto); } static DEVICE_ATTR_RW(vlan_protocol); static ssize_t default_pvid_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%d\n", br->default_pvid); } static ssize_t default_pvid_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, br_vlan_set_default_pvid); } static DEVICE_ATTR_RW(default_pvid); static ssize_t vlan_stats_enabled_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br_opt_get(br, BROPT_VLAN_STATS_ENABLED)); } static int set_vlan_stats_enabled(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_vlan_set_stats(br, val); } static ssize_t vlan_stats_enabled_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_vlan_stats_enabled); } static DEVICE_ATTR_RW(vlan_stats_enabled); static ssize_t vlan_stats_per_port_show(struct device *d, struct device_attribute *attr, char *buf) { struct net_bridge *br = to_bridge(d); return sprintf(buf, "%u\n", br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)); } static int set_vlan_stats_per_port(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { return br_vlan_set_stats_per_port(br, val); } static ssize_t vlan_stats_per_port_store(struct device *d, struct device_attribute *attr, const char *buf, size_t len) { return store_bridge_parm(d, buf, len, set_vlan_stats_per_port); } static DEVICE_ATTR_RW(vlan_stats_per_port); #endif static struct attribute *bridge_attrs[] = { &dev_attr_forward_delay.attr, &dev_attr_hello_time.attr, &dev_attr_max_age.attr, &dev_attr_ageing_time.attr, &dev_attr_stp_state.attr, &dev_attr_group_fwd_mask.attr, &dev_attr_priority.attr, &dev_attr_bridge_id.attr, &dev_attr_root_id.attr, &dev_attr_root_path_cost.attr, &dev_attr_root_port.attr, &dev_attr_topology_change.attr, &dev_attr_topology_change_detected.attr, &dev_attr_hello_timer.attr, &dev_attr_tcn_timer.attr, &dev_attr_topology_change_timer.attr, &dev_attr_gc_timer.attr, &dev_attr_group_addr.attr, &dev_attr_flush.attr, &dev_attr_no_linklocal_learn.attr, #ifdef CONFIG_BRIDGE_IGMP_SNOOPING &dev_attr_multicast_router.attr, &dev_attr_multicast_snooping.attr, &dev_attr_multicast_querier.attr, &dev_attr_multicast_query_use_ifaddr.attr, &dev_attr_hash_elasticity.attr, &dev_attr_hash_max.attr, &dev_attr_multicast_last_member_count.attr, &dev_attr_multicast_startup_query_count.attr, &dev_attr_multicast_last_member_interval.attr, &dev_attr_multicast_membership_interval.attr, &dev_attr_multicast_querier_interval.attr, &dev_attr_multicast_query_interval.attr, &dev_attr_multicast_query_response_interval.attr, &dev_attr_multicast_startup_query_interval.attr, &dev_attr_multicast_stats_enabled.attr, &dev_attr_multicast_igmp_version.attr, #if IS_ENABLED(CONFIG_IPV6) &dev_attr_multicast_mld_version.attr, #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) &dev_attr_nf_call_iptables.attr, &dev_attr_nf_call_ip6tables.attr, &dev_attr_nf_call_arptables.attr, #endif #ifdef CONFIG_BRIDGE_VLAN_FILTERING &dev_attr_vlan_filtering.attr, &dev_attr_vlan_protocol.attr, &dev_attr_default_pvid.attr, &dev_attr_vlan_stats_enabled.attr, &dev_attr_vlan_stats_per_port.attr, #endif NULL }; static const struct attribute_group bridge_group = { .name = SYSFS_BRIDGE_ATTR, .attrs = bridge_attrs, }; /* * Export the forwarding information table as a binary file * The records are struct __fdb_entry. * * Returns the number of bytes read. */ static ssize_t brforward_read(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); struct net_bridge *br = to_bridge(dev); int n; /* must read whole records */ if (off % sizeof(struct __fdb_entry) != 0) return -EINVAL; n = br_fdb_fillbuf(br, buf, count / sizeof(struct __fdb_entry), off / sizeof(struct __fdb_entry)); if (n > 0) n *= sizeof(struct __fdb_entry); return n; } static struct bin_attribute bridge_forward = { .attr = { .name = SYSFS_BRIDGE_FDB, .mode = 0444, }, .read = brforward_read, }; /* * Add entries in sysfs onto the existing network class device * for the bridge. * Adds a attribute group "bridge" containing tuning parameters. * Binary attribute containing the forward table * Sub directory to hold links to interfaces. * * Note: the ifobj exists only to be a subdirectory * to hold links. The ifobj exists in same data structure * as it's parent the bridge so reference counting works. */ int br_sysfs_addbr(struct net_device *dev) { struct kobject *brobj = &dev->dev.kobj; struct net_bridge *br = netdev_priv(dev); int err; err = sysfs_create_group(brobj, &bridge_group); if (err) { pr_info("%s: can't create group %s/%s\n", __func__, dev->name, bridge_group.name); goto out1; } err = sysfs_create_bin_file(brobj, &bridge_forward); if (err) { pr_info("%s: can't create attribute file %s/%s\n", __func__, dev->name, bridge_forward.attr.name); goto out2; } br->ifobj = kobject_create_and_add(SYSFS_BRIDGE_PORT_SUBDIR, brobj); if (!br->ifobj) { pr_info("%s: can't add kobject (directory) %s/%s\n", __func__, dev->name, SYSFS_BRIDGE_PORT_SUBDIR); err = -ENOMEM; goto out3; } return 0; out3: sysfs_remove_bin_file(&dev->dev.kobj, &bridge_forward); out2: sysfs_remove_group(&dev->dev.kobj, &bridge_group); out1: return err; } void br_sysfs_delbr(struct net_device *dev) { struct kobject *kobj = &dev->dev.kobj; struct net_bridge *br = netdev_priv(dev); kobject_put(br->ifobj); sysfs_remove_bin_file(kobj, &bridge_forward); sysfs_remove_group(kobj, &bridge_group); } |
| 287 287 285 287 287 287 1108 1108 1108 430 430 430 2127 2126 2012 1093 1093 18 18 18 412 412 288 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/core/fib_rules.c Generic Routing Rules * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/module.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> #include <linux/indirect_call_wrapper.h> #if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) #ifdef CONFIG_IP_MULTIPLE_TABLES #define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) #endif #elif defined(CONFIG_IP_MULTIPLE_TABLES) #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__) #endif static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(0), KUIDT_INIT(~0), }; bool fib_rule_matchall(const struct fib_rule *rule) { if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) return false; if (fib_rule_port_range_set(&rule->sport_range)) return false; if (fib_rule_port_range_set(&rule->dport_range)) return false; return true; } EXPORT_SYMBOL_GPL(fib_rule_matchall); int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table, u32 flags) { struct fib_rule *r; r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (r == NULL) return -ENOMEM; refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; r->flags = flags; r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; /* The lock is not required here, the list in unreacheable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; } EXPORT_SYMBOL(fib_default_rule_add); static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { struct list_head *pos; struct fib_rule *rule; if (!list_empty(&ops->rules_list)) { pos = ops->rules_list.next; if (pos->next != &ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; } } return 0; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family) { struct fib_rules_ops *ops; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (ops->family == family) { if (!try_module_get(ops->owner)) ops = NULL; rcu_read_unlock(); return ops; } } rcu_read_unlock(); return NULL; } static void rules_ops_put(struct fib_rules_ops *ops) { if (ops) module_put(ops->owner); } static void flush_route_cache(struct fib_rules_ops *ops) { if (ops->flush_cache) ops->flush_cache(ops); } static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; struct net *net; net = ops->fro_net; if (ops->rule_size < sizeof(struct fib_rule)) return -EINVAL; if (ops->match == NULL || ops->configure == NULL || ops->compare == NULL || ops->fill == NULL || ops->action == NULL) return -EINVAL; spin_lock(&net->rules_mod_lock); list_for_each_entry(o, &net->rules_ops, list) if (ops->family == o->family) goto errout; list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0; errout: spin_unlock(&net->rules_mod_lock); return err; } struct fib_rules_ops * fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) { struct fib_rules_ops *ops; int err; ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&ops->rules_list); ops->fro_net = net; err = __fib_rules_register(ops); if (err) { kfree(ops); ops = ERR_PTR(err); } return ops; } EXPORT_SYMBOL_GPL(fib_rules_register); static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { struct fib_rule *rule, *tmp; list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); if (ops->delete) ops->delete(rule); fib_rule_put(rule); } } void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; spin_lock(&net->rules_mod_lock); list_del_rcu(&ops->list); spin_unlock(&net->rules_mod_lock); fib_rules_cleanup_ops(ops); kfree_rcu(ops, rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); static int uid_range_set(struct fib_kuid_range *range) { return uid_valid(range->start) && uid_valid(range->end); } static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb) { struct fib_rule_uid_range *in; struct fib_kuid_range out; in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]); out.start = make_kuid(current_user_ns(), in->start); out.end = make_kuid(current_user_ns(), in->end); return out; } static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) { struct fib_rule_uid_range out = { from_kuid_munged(current_user_ns(), range->start), from_kuid_munged(current_user_ns(), range->end) }; return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); } static int nla_get_port_range(struct nlattr *pattr, struct fib_rule_port_range *port_range) { const struct fib_rule_port_range *pr = nla_data(pattr); if (!fib_rule_port_range_valid(pr)) return -EINVAL; port_range->start = pr->start; port_range->end = pr->end; return 0; } static int nla_put_port_range(struct sk_buff *skb, int attrtype, struct fib_rule_port_range *range) { return nla_put(skb, attrtype, sizeof(*range), range); } static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { int ret = 0; if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) goto out; if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) goto out; if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) goto out; if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) goto out; if (uid_lt(fl->flowi_uid, rule->uid_range.start) || uid_gt(fl->flowi_uid, rule->uid_range.end)) goto out; ret = INDIRECT_CALL_MT(ops->match, fib6_rule_match, fib4_rule_match, rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; } int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { struct fib_rule *rule; int err; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { jumped: if (!fib_rule_match(rule, ops, fl, flags, arg)) continue; if (rule->action == FR_ACT_GOTO) { struct fib_rule *target; target = rcu_dereference(rule->ctarget); if (target == NULL) { continue; } else { rule = target; goto jumped; } } else if (rule->action == FR_ACT_NOP) continue; else err = INDIRECT_CALL_MT(ops->action, fib6_rule_action, fib4_rule_action, rule, fl, flags, arg); if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, rule, flags, arg)) continue; if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(refcount_inc_not_zero(&rule->refcnt))) { arg->rule = rule; goto out; } break; } } err = -ESRCH; out: rcu_read_unlock(); return err; } EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, .info.extack = extack, .rule = rule, }; return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule, struct fib_rules_ops *ops, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = ops->family, .info.extack = extack, .rule = rule, }; ops->fib_rules_seq++; return call_fib_notifiers(net, event_type, &info.info); } /* Called with rcu_read_lock() */ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; int err = 0; ops = lookup_rules_ops(net, family); if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family, extack); if (err) break; } rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_rules_dump); unsigned int fib_rules_seq_read(struct net *net, int family) { unsigned int fib_rules_seq; struct fib_rules_ops *ops; ASSERT_RTNL(); ops = lookup_rules_ops(net, family); if (!ops) return 0; fib_rules_seq = ops->fib_rules_seq; rules_ops_put(ops); return fib_rules_seq; } EXPORT_SYMBOL_GPL(fib_rules_seq_read); static struct fib_rule *rule_find(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule, bool user_priority) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (rule->action && r->action != rule->action) continue; if (rule->table && r->table != rule->table) continue; if (user_priority && r->pref != rule->pref) continue; if (rule->iifname[0] && memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (rule->oifname[0] && memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (rule->mark && r->mark != rule->mark) continue; if (rule->suppress_ifgroup != -1 && r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (rule->suppress_prefixlen != -1 && r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; if (rule->tun_id && r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; if (uid_range_set(&rule->uid_range) && (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end))) continue; if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; if (rule->proto && r->proto != rule->proto) continue; if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return r; } return NULL; } #ifdef CONFIG_NET_L3_MASTER_DEV static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { nlrule->l3mdev = nla_get_u8(nla); if (nlrule->l3mdev != 1) { NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); return -1; } return 0; } #else static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); return -1; } #endif static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, struct nlattr *tb[], struct fib_rule **rule, bool *user_priority) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rule *nlrule = NULL; int err = -EINVAL; if (frh->src_len) if (!tb[FRA_SRC] || frh->src_len > (ops->addr_size * 8) || nla_len(tb[FRA_SRC]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid source address"); goto errout; } if (frh->dst_len) if (!tb[FRA_DST] || frh->dst_len > (ops->addr_size * 8) || nla_len(tb[FRA_DST]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid dst address"); goto errout; } nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (!nlrule) { err = -ENOMEM; goto errout; } refcount_set(&nlrule->refcnt, 1); nlrule->fr_net = net; if (tb[FRA_PRIORITY]) { nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); *user_priority = true; } else { nlrule->pref = fib_default_rule_pref(ops); } nlrule->proto = tb[FRA_PROTOCOL] ? nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; if (tb[FRA_IIFNAME]) { struct net_device *dev; nlrule->iifindex = -1; nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->iifname); if (dev) nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { struct net_device *dev; nlrule->oifindex = -1; nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->oifname); if (dev) nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ nlrule->mark_mask = 0xFFFFFFFF; } if (tb[FRA_FWMASK]) nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); if (tb[FRA_TUN_ID]) nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); err = -EINVAL; if (tb[FRA_L3MDEV] && fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) goto errout_free; nlrule->action = frh->action; nlrule->flags = frh->flags; nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else nlrule->suppress_prefixlen = -1; if (tb[FRA_SUPPRESS_IFGROUP]) nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else nlrule->suppress_ifgroup = -1; if (tb[FRA_GOTO]) { if (nlrule->action != FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; } nlrule->target = nla_get_u32(tb[FRA_GOTO]); /* Backward jumps are prohibited to avoid endless loops */ if (nlrule->target <= nlrule->pref) { NL_SET_ERR_MSG(extack, "Backward goto not supported"); goto errout_free; } } else if (nlrule->action == FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; } if (nlrule->l3mdev && nlrule->table) { NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; } if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; } nlrule->uid_range = nla_get_kuid_range(tb); if (!uid_range_set(&nlrule->uid_range) || !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; } } else { nlrule->uid_range = fib_kuid_range_unset; } if (tb[FRA_IP_PROTO]) nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], &nlrule->sport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } } if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], &nlrule->dport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } } *rule = nlrule; return 0; errout_free: kfree(nlrule); errout: return err; } static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (r->action != rule->action) continue; if (r->table != rule->table) continue; if (r->pref != rule->pref) continue; if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (r->mark != rule->mark) continue; if (r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (r->mark_mask != rule->mark_mask) continue; if (r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (r->l3mdev != rule->l3mdev) continue; if (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end)) continue; if (r->ip_proto != rule->ip_proto) continue; if (r->proto != rule->proto) continue; if (!fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return 1; } return 0; } static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FLOW] = { .type = NLA_U32 }, [FRA_TUN_ID] = { .type = NLA_U64 }, [FRA_FWMASK] = { .type = NLA_U32 }, [FRA_TABLE] = { .type = NLA_U32 }, [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, [FRA_GOTO] = { .type = NLA_U32 }, [FRA_L3MDEV] = { .type = NLA_U8 }, [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, [FRA_PROTOCOL] = { .type = NLA_U8 }, [FRA_IP_PROTO] = { .type = NLA_U8 }, [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } }; int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *last = NULL; struct nlattr *tb[FRA_MAX + 1]; int err = -EINVAL, unresolved = 0; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (!ops) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); if (err) goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free; err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack); if (err < 0) goto errout_free; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref == rule->target) { RCU_INIT_POINTER(rule->ctarget, r); break; } } if (rcu_dereference_protected(rule->ctarget, 1) == NULL) unresolved = 1; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; } if (last) list_add_rcu(&rule->list, &last->list); else list_add_rcu(&rule->list, &ops->rules_list); if (ops->unresolved_rules) { /* * There are unresolved goto rules in the list, check if * any of them are pointing to this new rule. */ list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref && rtnl_dereference(r->ctarget) == NULL) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; } } } if (rule->action == FR_ACT_GOTO) ops->nr_goto_rules++; if (unresolved) ops->unresolved_rules++; if (rule->tun_id) ip_tunnel_need_metadata(); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; errout_free: kfree(rule); errout: rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_newrule); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; int err = -EINVAL; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); if (err) goto errout; rule = rule_find(ops, frh, tb, nlrule, user_priority); if (!rule) { err = -ENOENT; goto errout; } if (rule->flags & FIB_RULE_PERMANENT) { err = -EPERM; goto errout; } if (ops->delete) { err = ops->delete(rule); if (err) goto errout; } if (rule->tun_id) ip_tunnel_unneed_metadata(); list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; if (rtnl_dereference(rule->ctarget) == NULL) ops->unresolved_rules--; } /* * Check if this rule is a target to any of them. If so, * adjust to the next one with the same preference or * disable them. As this operation is eventually very * expensive, it is only performed if goto rules, except * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { struct fib_rule *n; n = list_next_entry(rule, list); if (&n->list == &ops->rules_list || n->pref != rule->pref) n = NULL; list_for_each_entry(r, &ops->rules_list, list) { if (rtnl_dereference(r->ctarget) != rule) continue; rcu_assign_pointer(r->ctarget, n); if (!n) ops->unresolved_rules++; } } call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); kfree(nlrule); return 0; errout: kfree(nlrule); rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_delrule); static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ + nla_total_size(sizeof(struct fib_kuid_range)) + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); return payload; } static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, u32 pid, u32 seq, int type, int flags, struct fib_rules_ops *ops) { struct nlmsghdr *nlh; struct fib_rule_hdr *frh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); if (nlh == NULL) return -EMSGSIZE; frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; frh->flags = rule->flags; if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) goto nla_put_failure; if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; if (rule->iifindex == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; if (rule->oifindex == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } if ((rule->pref && nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || (rule->mark && nla_put_u32(skb, FRA_FWMARK, rule->mark)) || ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target)) || (rule->tun_id && nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || (rule->l3mdev && nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || (uid_range_set(&rule->uid_range) && nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) goto nla_put_failure; } if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, struct fib_rules_ops *ops) { int idx = 0; struct fib_rule *rule; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops); if (err) break; skip: idx++; } rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops); return err; } static int fib_valid_dumprule_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib_rule_hdr *frh; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request"); return -EINVAL; } frh = nlmsg_data(nlh); if (frh->dst_len || frh->src_len || frh->tos || frh->table || frh->res1 || frh->res2 || frh->action || frh->flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for fib rule dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request"); return -EINVAL; } return 0; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; int idx = 0, family; if (cb->strict_check) { int err = fib_valid_dumprule_req(nlh, cb->extack); if (err < 0) return err; } family = rtnl_msg_family(nlh); if (family != AF_UNSPEC) { /* Protocol specific dump request */ ops = lookup_rules_ops(net, family); if (ops == NULL) return -EAFNOSUPPORT; dump_rules(skb, cb, ops); return skb->len; } rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (idx < cb->args[0] || !try_module_get(ops->owner)) goto skip; if (dump_rules(skb, cb, ops) < 0) break; cb->args[1] = 0; skip: idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid) { struct net *net; struct sk_buff *skb; int err = -ENOMEM; net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); if (skb == NULL) goto errout; err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); if (err < 0) { /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: if (err < 0) rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) rule->iifindex = dev->ifindex; if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) rule->oifindex = dev->ifindex; } } static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) rule->iifindex = -1; if (rule->oifindex == dev->ifindex) rule->oifindex = -1; } } static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops; ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_CHANGENAME: list_for_each_entry(ops, &net->rules_ops, list) { detach_rules(&ops->rules_list, dev); attach_rules(&ops->rules_list, dev); } break; case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; } return NOTIFY_DONE; } static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event, }; static int __net_init fib_rules_net_init(struct net *net) { INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); return 0; } static void __net_exit fib_rules_net_exit(struct net *net) { WARN_ON_ONCE(!list_empty(&net->rules_ops)); } static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit, }; static int __init fib_rules_init(void) { int err; rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, 0); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) goto fail; err = register_netdevice_notifier(&fib_rules_notifier); if (err < 0) goto fail_unregister; return 0; fail_unregister: unregister_pernet_subsys(&fib_rules_net_ops); fail: rtnl_unregister(PF_UNSPEC, RTM_NEWRULE); rtnl_unregister(PF_UNSPEC, RTM_DELRULE); rtnl_unregister(PF_UNSPEC, RTM_GETRULE); return err; } subsys_initcall(fib_rules_init); |
| 1990 357 3 3 26 26 26 5 8 2558 2557 691 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /* * Convert jiffies to milliseconds and back. * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /* * mktime64 - Converts date to seconds. * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of * 0 <= tv_nsec < NSEC_PER_SEC * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see __msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * the _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /* * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundaries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } EXPORT_SYMBOL_GPL(nsec_to_clock_t); u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /* * Add two timespec64 values and do a safety check for overflow. * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 75 76 76 76 76 76 75 75 76 336 1 335 320 6 7 329 329 324 5 325 4 325 2 2 325 4 329 318 9 3 1 120 41 78 120 32 32 32 32 32 32 32 32 32 32 32 32 41 41 41 5 5 2 1 3 286 286 286 286 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PF_INET protocol family socket handler. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, <flla@stud.uni-sb.de> * Alan Cox, <A.Cox@swansea.ac.uk> * * Changes (see also sock.c) * * piggy, * Karl Knutson : Socket protocol table * A.N.Kuznetsov : Socket death error in accept(). * John Richardson : Fix non blocking error in connect() * so sockets that fail to connect * don't return -EINPROGRESS. * Alan Cox : Asynchronous I/O support * Alan Cox : Keep correct socket pointer on sock * structures * when accept() ed * Alan Cox : Semantics of SO_LINGER aren't state * moved to close when you look carefully. * With this fixed and the accept bug fixed * some RPC stuff seems happier. * Niibe Yutaka : 4.4BSD style write async I/O * Alan Cox, * Tony Gale : Fixed reuse semantics. * Alan Cox : bind() shouldn't abort existing but dead * sockets. Stops FTP netin:.. I hope. * Alan Cox : bind() works correctly for RAW sockets. * Note that FreeBSD at least was broken * in this respect so be careful with * compatibility tests... * Alan Cox : routing cache support * Alan Cox : memzero the socket structure for * compactness. * Matt Day : nonblock connect error handler * Alan Cox : Allow large numbers of pending sockets * (eg for big web sites), but only if * specifically application requested. * Alan Cox : New buffering throughout IP. Used * dumbly. * Alan Cox : New buffering now used smartly. * Alan Cox : BSD rather than common sense * interpretation of listen. * Germano Caronni : Assorted small races. * Alan Cox : sendmsg/recvmsg basic support. * Alan Cox : Only sendmsg/recvmsg now supported. * Alan Cox : Locked down bind (see security list). * Alan Cox : Loosened bind a little. * Mike McLagan : ADD/DEL DLCI Ioctls * Willy Konynenberg : Transparent proxying support. * David S. Miller : New socket lookup architecture. * Some other random speedups. * Cyrus Durgin : Cleaned up file for kmod hacks. * Andi Kleen : Fix inet_stream_connect TCP race. */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/sched.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <net/checksum.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/inet_connection_sock.h> #include <net/gro.h> #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> #include <net/ping.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #include <net/l3mdev.h> #include <net/compat.h> #include <trace/events/sock.h> /* The inetsw table contains everything that inet_create needs to * build a new socket. */ static struct list_head inetsw[SOCK_MAX]; static DEFINE_SPINLOCK(inetsw_lock); /* New destruction routine */ void inet_sock_destruct(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim_final(sk); if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) { pr_err("Attempt to release TCP socket in state %d %p\n", sk->sk_state, sk); return; } if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive inet socket %p\n", sk); return; } WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); WARN_ON_ONCE(sk_forward_alloc_get(sk)); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); /* * The routines beyond this point handle the behaviour of an AF_INET * socket object. Mostly it punts to the subprotocols of IP to do * the work. */ /* * Automatically bind an unbound socket. */ static int inet_autobind(struct sock *sk) { struct inet_sock *inet; /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; } /* * Move a socket into listening state. */ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; int err, tcp_fastopen; lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; old_state = sk->sk_state; if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) goto out; WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { /* Enable TFO w/o requiring TCP_FASTOPEN socket option. * Note that only TCP sockets (SOCK_STREAM) will reach here. * Also fastopen backlog may already been set via the option * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(sock_net(sk)); } err = inet_csk_listen_start(sk); if (err) goto out; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL); } err = 0; out: release_sock(sk); return err; } EXPORT_SYMBOL(inet_listen); /* * Create an inet socket. */ static int inet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct inet_protosw *answer; struct inet_sock *inet; struct proto *answer_prot; unsigned char answer_flags; int try_loading_module = 0; int err; if (protocol < 0 || protocol >= IPPROTO_MAX) return -EINVAL; sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; rcu_read_lock(); list_for_each_entry_rcu(answer, &inetsw[sock->type], list) { err = 0; /* Check the non-wild match. */ if (protocol == answer->protocol) { if (protocol != IPPROTO_IP) break; } else { /* Check for the two wild cases. */ if (IPPROTO_IP == protocol) { protocol = answer->protocol; break; } if (IPPROTO_IP == answer->protocol) break; } err = -EPROTONOSUPPORT; } if (unlikely(err)) { if (try_loading_module < 2) { rcu_read_unlock(); /* * Be more specific, e.g. net-pf-2-proto-132-type-1 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM) */ if (++try_loading_module == 1) request_module("net-pf-%d-proto-%d-type-%d", PF_INET, protocol, sock->type); /* * Fall back to generic, e.g. net-pf-2-proto-132 * (net-pf-PF_INET-proto-IPPROTO_SCTP) */ else request_module("net-pf-%d-proto-%d", PF_INET, protocol); goto lookup_protocol; } else goto out_rcu_unlock; } err = -EPERM; if (sock->type == SOCK_RAW && !kern && !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; answer_prot = answer->prot; answer_flags = answer->flags; rcu_read_unlock(); WARN_ON(!answer_prot->slab); err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; err = 0; if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; if (INET_PROTOSW_ICSK & answer_flags) inet_init_csk_locks(sk); inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; inet->nodefrag = 0; if (SOCK_RAW == sock->type) { inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; inet->inet_id = 0; sock_init_data(sock, sk); sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet->mc_loop = 1; inet->mc_ttl = 1; inet->mc_all = 1; inet->mc_index = 0; inet->mc_list = NULL; inet->rcv_tos = 0; sk_refcnt_debug_inc(sk); if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ err = sk->sk_prot->hash(sk); if (err) { sk_common_release(sk); goto out; } } if (sk->sk_prot->init) { err = sk->sk_prot->init(sk); if (err) { sk_common_release(sk); goto out; } } if (!kern) { err = BPF_CGROUP_RUN_PROG_INET_SOCK(sk); if (err) { sk_common_release(sk); goto out; } } out: return err; out_rcu_unlock: rcu_read_unlock(); goto out; } /* * The peer socket should always be NULL (or else). When we call this * function we are destroying the object and from then on nobody * should refer to it. */ int inet_release(struct socket *sock) { struct sock *sk = sock->sk; if (sk) { long timeout; if (!sk->sk_kern_sock) BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); /* If linger is set, we don't return until the close * is complete. Otherwise we return immediately. The * actually closing is done the same either way. * * If the close is due to the process exiting, we never * linger.. */ timeout = 0; if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) timeout = sk->sk_lingertime; sk->sk_prot->close(sk, timeout); sock->sk = NULL; } return 0; } EXPORT_SYMBOL(inet_release); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; u32 flags = BIND_WITH_LOCK; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { return sk->sk_prot->bind(sk, uaddr, addr_len); } if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, CGROUP_INET4_BIND, &flags); if (err) return err; return __inet_bind(sk, uaddr, addr_len, flags); } EXPORT_SYMBOL(inet_bind); int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; u32 tb_id = RT_TABLE_LOCAL; int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) * only if s_addr is INADDR_ANY. */ err = -EAFNOSUPPORT; if (addr->sin_family != AF_UNSPEC || addr->sin_addr.s_addr != htonl(INADDR_ANY)) goto out; } tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since * allowing applications to make a non-local bind solves * several problems with systems using dynamic addressing. * (ie. your servers still start up even if your ISDN link * is temporarily down) */ err = -EADDRNOTAVAIL; if (!inet_addr_valid_or_nonlocal(net, inet, addr->sin_addr.s_addr, chk_addr_ret)) goto out; snum = ntohs(addr->sin_port); err = -EACCES; if (!(flags & BIND_NO_CAP_NET_BIND_SERVICE) && snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; /* We keep a pair of addresses. rcv_saddr is the one * used by hash lookups, and saddr is used for transmit. * * In the BSD API these are the same except where it * would be illegal to use them (multicast/broadcast) in * which case the sending device address is used. */ if (flags & BIND_WITH_LOCK) lock_sock(sk); /* Check these errors (active socket, double bind). */ err = -EINVAL; if (sk->sk_state != TCP_CLOSE || inet->inet_num) goto out_release_sock; inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ if (snum || !(inet->bind_address_no_port || (flags & BIND_FORCE_ADDRESS_NO_PORT))) { err = sk->sk_prot->get_port(sk, snum); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; goto out_release_sock; } if (!(flags & BIND_FROM_BPF)) { err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); if (err) { inet->inet_saddr = inet->inet_rcv_saddr = 0; if (sk->sk_prot->put_port) sk->sk_prot->put_port(sk); goto out_release_sock; } } } if (inet->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; inet->inet_sport = htons(inet->inet_num); inet->inet_daddr = 0; inet->inet_dport = 0; sk_dst_reset(sk); err = 0; out_release_sock: if (flags & BIND_WITH_LOCK) release_sock(sk); out: return err; } int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; const struct proto *prot; int err; if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (uaddr->sa_family == AF_UNSPEC) return prot->disconnect(sk, flags); if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = prot->pre_connect(sk, uaddr, addr_len); if (err) return err; } if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return prot->connect(sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_dgram_connect); static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. * Connect() does not allow to get error notifications * without closing the socket. */ while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); if (signal_pending(current) || !timeo) break; } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; sk->sk_wait_pending--; return timeo; } /* * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg) { struct sock *sk = sock->sk; int err; long timeo; /* * uaddr can be NULL and addr_len can be 0 if: * sk is a TCP fastopen active socket and * TCP_FASTOPEN_CONNECT sockopt is set and * we already have a valid cookie for this socket. * In this case, user can call write() after connect(). * write() will invoke tcp_sendmsg_fastopen() which calls * __inet_stream_connect(). */ if (uaddr) { if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; } } switch (sock->state) { default: err = -EINVAL; goto out; case SS_CONNECTED: err = -EISCONN; goto out; case SS_CONNECTING: if (inet_sk(sk)->defer_connect) err = is_sendmsg ? -EINPROGRESS : -EISCONN; else err = -EALREADY; /* Fall out of switch with err, set for this state */ break; case SS_UNCONNECTED: err = -EISCONN; if (sk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); if (err) goto out; } err = sk->sk_prot->connect(sk, uaddr, addr_len); if (err < 0) goto out; sock->state = SS_CONNECTING; if (!err && inet_sk(sk)->defer_connect) goto out; /* Just entered SS_CONNECTING state; the only * difference is that return value in non-blocking * case is EINPROGRESS, rather than EALREADY. */ err = -EINPROGRESS; break; } timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) goto out; err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; } /* Connection was closed by RST, timeout, ICMP error * or another process disconnected us. */ if (sk->sk_state == TCP_CLOSE) goto sock_error; /* sk->sk_err may be not zero now, if RECVERR was ordered by user * and error was received after socket entered established state. * Hence, it is handled normally after connect() return successfully. */ sock->state = SS_CONNECTED; err = 0; out: return err; sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; } EXPORT_SYMBOL(__inet_stream_connect); int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { int err; lock_sock(sock->sk); err = __inet_stream_connect(sock, uaddr, addr_len, flags, 0); release_sock(sock->sk); return err; } EXPORT_SYMBOL(inet_stream_connect); /* * Accept a pending connection. The TCP layer now gives BSD semantics. */ int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk1 = sock->sk, *sk2; int err = -EINVAL; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern); if (!sk2) goto do_err; lock_sock(sk2); sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_CLOSE_WAIT | TCPF_CLOSE))); if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) set_bit(SOCK_SUPPORT_ZC, &newsock->flags); sock_graft(sk2, newsock); newsock->state = SS_CONNECTED; err = 0; release_sock(sk2); do_err: return err; } EXPORT_SYMBOL(inet_accept); /* * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); sin->sin_family = AF_INET; lock_sock(sk); if (peer) { if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) { release_sock(sk); return -ENOTCONN; } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sizeof(*sin); } EXPORT_SYMBOL(inet_getname); int inet_send_prepare(struct sock *sk) { sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; return 0; } EXPORT_SYMBOL_GPL(inet_send_prepare); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; return INDIRECT_CALL_2(sk->sk_prot->sendmsg, tcp_sendmsg, udp_sendmsg, sk, msg, size); } EXPORT_SYMBOL(inet_sendmsg); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { struct sock *sk = sock->sk; const struct proto *prot; if (unlikely(inet_send_prepare(sk))) return -EAGAIN; /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (prot->sendpage) return prot->sendpage(sk, page, offset, size, flags); return sock_no_sendpage(sock, page, offset, size, flags); } EXPORT_SYMBOL(inet_sendpage); INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *, size_t, int, int *)); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int addr_len = 0; int err; if (likely(!(flags & MSG_ERRQUEUE))) sock_rps_record_flow(sk); err = INDIRECT_CALL_2(sk->sk_prot->recvmsg, tcp_recvmsg, udp_recvmsg, sk, msg, size, flags, &addr_len); if (err >= 0) msg->msg_namelen = addr_len; return err; } EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; /* This should really check to make sure * the socket is a TCP socket. (WHY AC...) */ how++; /* maps 0->1 has the advantage of making bit 1 rcvs and 1->2 bit 2 snds. 2->3 */ if ((how & ~SHUTDOWN_MASK) || !how) /* MAXINT->0 */ return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTING) { if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE)) sock->state = SS_DISCONNECTING; else sock->state = SS_CONNECTED; } switch (sk->sk_state) { case TCP_CLOSE: err = -ENOTCONN; /* Hack to wake up other listeners, who can poll for EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ fallthrough; default: WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; /* Remaining two branches are temporary solution for missing * close() in multithreaded environment. It is _not_ a good idea, * but we have no choice until close() is repaired at VFS level. */ case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: err = sk->sk_prot->disconnect(sk, O_NONBLOCK); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; break; } /* Wake up anyone sleeping in poll. */ sk->sk_state_change(sk); release_sock(sk); return err; } EXPORT_SYMBOL(inet_shutdown); /* * ioctl() calls you can issue on an INET socket. Most of these are * device configuration and stuff and very rarely used. Some ioctls * pass on to the socket itself. * * NOTE: I like the idea of a module for the config stuff. ie ifconfig * loads the devconfigure module does its configuring and unloads it. * There's a good 20K of config code hanging around the kernel. */ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; int err = 0; struct net *net = sock_net(sk); void __user *p = (void __user *)arg; struct ifreq ifr; struct rtentry rt; switch (cmd) { case SIOCADDRT: case SIOCDELRT: if (copy_from_user(&rt, p, sizeof(struct rtentry))) return -EFAULT; err = ip_rt_ioctl(net, cmd, &rt); break; case SIOCRTMSG: err = -EINVAL; break; case SIOCDARP: case SIOCGARP: case SIOCSARP: err = arp_ioctl(net, cmd, (void __user *)arg); break; case SIOCGIFADDR: case SIOCGIFBRDADDR: case SIOCGIFNETMASK: case SIOCGIFDSTADDR: case SIOCGIFPFLAGS: if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); if (!err && put_user_ifreq(&ifr, p)) err = -EFAULT; break; case SIOCSIFADDR: case SIOCSIFBRDADDR: case SIOCSIFNETMASK: case SIOCSIFDSTADDR: case SIOCSIFPFLAGS: case SIOCSIFFLAGS: if (get_user_ifreq(&ifr, NULL, p)) return -EFAULT; err = devinet_ioctl(net, cmd, &ifr); break; default: if (sk->sk_prot->ioctl) err = sk->sk_prot->ioctl(sk, cmd, arg); else err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(inet_ioctl); #ifdef CONFIG_COMPAT static int inet_compat_routing_ioctl(struct sock *sk, unsigned int cmd, struct compat_rtentry __user *ur) { compat_uptr_t rtdev; struct rtentry rt; if (copy_from_user(&rt.rt_dst, &ur->rt_dst, 3 * sizeof(struct sockaddr)) || get_user(rt.rt_flags, &ur->rt_flags) || get_user(rt.rt_metric, &ur->rt_metric) || get_user(rt.rt_mtu, &ur->rt_mtu) || get_user(rt.rt_window, &ur->rt_window) || get_user(rt.rt_irtt, &ur->rt_irtt) || get_user(rtdev, &ur->rt_dev)) return -EFAULT; rt.rt_dev = compat_ptr(rtdev); return ip_rt_ioctl(sock_net(sk), cmd, &rt); } static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; switch (cmd) { case SIOCADDRT: case SIOCDELRT: return inet_compat_routing_ioctl(sk, cmd, argp); default: if (!sk->sk_prot->compat_ioctl) return -ENOIOCTLCMD; return sk->sk_prot->compat_ioctl(sk, cmd, arg); } } #endif /* CONFIG_COMPAT */ const struct proto_ops inet_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, .poll = tcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = inet_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif .set_rcvlowat = tcp_set_rcvlowat, }; EXPORT_SYMBOL(inet_stream_ops); const struct proto_ops inet_dgram_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = udp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; EXPORT_SYMBOL(inet_dgram_ops); /* * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without * udp_poll */ static const struct proto_ops inet_sockraw_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = inet_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif }; static const struct net_proto_family inet_family_ops = { .family = PF_INET, .create = inet_create, .owner = THIS_MODULE, }; /* Upon startup we insert all the elements in inetsw_array[] into * the linked list inetsw. */ static struct inet_protosw inetsw_array[] = { { .type = SOCK_STREAM, .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }, { .type = SOCK_DGRAM, .protocol = IPPROTO_ICMP, .prot = &ping_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, }, { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, .flags = INET_PROTOSW_REUSE, } }; #define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array) void inet_register_protosw(struct inet_protosw *p) { struct list_head *lh; struct inet_protosw *answer; int protocol = p->protocol; struct list_head *last_perm; spin_lock_bh(&inetsw_lock); if (p->type >= SOCK_MAX) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ last_perm = &inetsw[p->type]; list_for_each(lh, &inetsw[p->type]) { answer = list_entry(lh, struct inet_protosw, list); /* Check only the non-wild match. */ if ((INET_PROTOSW_PERMANENT & answer->flags) == 0) break; if (protocol == answer->protocol) goto out_permanent; last_perm = lh; } /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with * a wild-card protocol. But it is allowed to override any existing * non-permanent entry. This means that when we remove this entry, the * system automatically returns to the old behavior. */ list_add_rcu(&p->list, last_perm); out: spin_unlock_bh(&inetsw_lock); return; out_permanent: pr_err("Attempt to override permanent protocol %d\n", protocol); goto out; out_illegal: pr_err("Ignoring attempt to register invalid socket type %d\n", p->type); goto out; } EXPORT_SYMBOL(inet_register_protosw); void inet_unregister_protosw(struct inet_protosw *p) { if (INET_PROTOSW_PERMANENT & p->flags) { pr_err("Attempt to unregister permanent protocol %d\n", p->protocol); } else { spin_lock_bh(&inetsw_lock); list_del_rcu(&p->list); spin_unlock_bh(&inetsw_lock); synchronize_net(); } } EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; __be32 new_saddr; struct ip_options_rcu *inet_opt; int err; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* Query new route. */ fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, daddr, 0, sk->sk_bound_dev_if, sk->sk_protocol, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) return PTR_ERR(rt); new_saddr = fl4->saddr; if (new_saddr == old_saddr) { sk_setup_caps(sk, &rt->dst); return 0; } err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { ip_rt_put(rt); return err; } sk_setup_caps(sk, &rt->dst); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } /* * XXX The only one ugly spot where we need to * XXX really change the sockets identity after * XXX it has entered the hashes. -DaveM * * Besides that, it does not check for connection * uniqueness. Wait for troubles. */ return __sk_prot_rehash(sk); } int inet_sk_rebuild_header(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0); __be32 daddr; struct ip_options_rcu *inet_opt; struct flowi4 *fl4; int err; /* Route is OK, nothing to do. */ if (rt) return 0; /* Reroute. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; rcu_read_unlock(); fl4 = &inet->cork.fl.u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (!IS_ERR(rt)) { err = 0; sk_setup_caps(sk, &rt->dst); } else { err = PTR_ERR(rt); /* Routing failed... */ sk->sk_route_caps = 0; /* * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) sk->sk_err_soft = -err; } return err; } EXPORT_SYMBOL(inet_sk_rebuild_header); void inet_sk_set_state(struct sock *sk, int state) { trace_inet_sock_set_state(sk, sk->sk_state, state); sk->sk_state = state; } EXPORT_SYMBOL(inet_sk_set_state); void inet_sk_state_store(struct sock *sk, int newstate) { trace_inet_sock_set_state(sk, sk->sk_state, newstate); smp_store_release(&sk->sk_state, newstate); } struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features) { bool udpfrag = false, fixedid = false, gso_partial, encap; struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; unsigned int offset = 0; struct iphdr *iph; int proto, tot_len; int nhoff; int ihl; int id; skb_reset_network_header(skb); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) goto out; iph = ip_hdr(skb); ihl = iph->ihl * 4; if (ihl < sizeof(*iph)) goto out; id = ntohs(iph->id); proto = iph->protocol; /* Warning: after this point, iph might be no longer valid */ if (unlikely(!pskb_may_pull(skb, ihl))) goto out; __skb_pull(skb, ihl); encap = SKB_GSO_CB(skb)->encap_level > 0; if (encap) features &= skb->dev->hw_enc_features; SKB_GSO_CB(skb)->encap_level += ihl; skb_reset_transport_header(skb); segs = ERR_PTR(-EPROTONOSUPPORT); if (!skb->encapsulation || encap) { udpfrag = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP); fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); skb = segs; do { iph = (struct iphdr *)(skb_mac_header(skb) + nhoff); if (udpfrag) { iph->frag_off = htons(offset >> 3); if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; tot_len = skb->len - nhoff; } else if (skb_is_gso(skb)) { if (!fixedid) { iph->id = htons(id); id += skb_shinfo(skb)->gso_segs; } if (gso_partial) tot_len = skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)iph; else tot_len = skb->len - nhoff; } else { if (!fixedid) iph->id = htons(id++); tot_len = skb->len - nhoff; } iph->tot_len = htons(tot_len); ip_send_check(iph); if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; skb_reset_mac_len(skb); } while ((skb = skb->next)); out: return segs; } static struct sk_buff *ipip_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4)) return ERR_PTR(-EINVAL); return inet_gso_segment(skb, features); } struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; const struct iphdr *iph; struct sk_buff *p; unsigned int hlen; unsigned int off; unsigned int id; int flush = 1; int proto; off = skb_gro_offset(skb); hlen = off + sizeof(*iph); iph = skb_gro_header(skb, hlen, off); if (unlikely(!iph)) goto out; proto = iph->protocol; ops = rcu_dereference(inet_offloads[proto]); if (!ops || !ops->callbacks.gro_receive) goto out; if (*(u8 *)iph != 0x45) goto out; if (ip_is_fragment(iph)) goto out; if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out; id = ntohl(*(__be32 *)&iph->id); flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF)); id >>= 16; list_for_each_entry(p, head, list) { struct iphdr *iph2; u16 flush_id; if (!NAPI_GRO_CB(p)->same_flow) continue; iph2 = (struct iphdr *)(p->data + off); /* The above works because, with the exception of the top * (inner most) layer, we only aggregate pkts with the same * hdr length so all the hdrs we'll need to verify will start * at the same offset. */ if ((iph->protocol ^ iph2->protocol) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } /* All fields must match except length and checksum. */ NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)); NAPI_GRO_CB(p)->flush |= flush; /* We need to store of the IP ID check to be included later * when we can verify that this packet does in fact belong * to a given flow. */ flush_id = (u16)(id - ntohs(iph2->id)); /* This bit of code makes it much easier for us to identify * the cases where we are doing atomic vs non-atomic IP ID * checks. Specifically an atomic check can return IP ID * values 0 - 0xFFFF, while a non-atomic check can only * return 0 or 0xFFFF. */ if (!NAPI_GRO_CB(p)->is_atomic || !(iph->frag_off & htons(IP_DF))) { flush_id ^= NAPI_GRO_CB(p)->count; flush_id = flush_id ? 0xFFFF : 0; } /* If the previous IP ID value was based on an atomic * datagram we can overwrite the value and ignore it. */ if (NAPI_GRO_CB(skb)->is_atomic) NAPI_GRO_CB(p)->flush_id = flush_id; else NAPI_GRO_CB(p)->flush_id |= flush_id; } NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF)); NAPI_GRO_CB(skb)->flush |= flush; skb_set_network_header(skb, off); /* The above will be needed by the transport layer if there is one * immediately following this IP hdr. */ /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 */ skb_gro_pull(skb, sizeof(*iph)); skb_set_transport_header(skb, skb_gro_offset(skb)); pp = indirect_call_gro_receive(tcp4_gro_receive, udp4_gro_receive, ops->callbacks.gro_receive, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } static struct sk_buff *ipip_gro_receive(struct list_head *head, struct sk_buff *skb) { if (NAPI_GRO_CB(skb)->encap_mark) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } NAPI_GRO_CB(skb)->encap_mark = 1; return inet_gro_receive(head, skb); } #define SECONDS_PER_DAY 86400 /* inet_current_timestamp - Return IP network timestamp * * Return milliseconds since midnight in network byte order. */ __be32 inet_current_timestamp(void) { u32 secs; u32 msecs; struct timespec64 ts; ktime_get_real_ts64(&ts); /* Get secs since midnight. */ (void)div_u64_rem(ts.tv_sec, SECONDS_PER_DAY, &secs); /* Convert to msecs. */ msecs = secs * MSEC_PER_SEC; /* Convert nsec to msec. */ msecs += (u32)ts.tv_nsec / NSEC_PER_MSEC; /* Convert to network byte order. */ return htonl(msecs); } EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { unsigned int family = READ_ONCE(sk->sk_family); if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; } EXPORT_SYMBOL(inet_recv_error); int inet_gro_complete(struct sk_buff *skb, int nhoff) { __be16 newlen = htons(skb->len - nhoff); struct iphdr *iph = (struct iphdr *)(skb->data + nhoff); const struct net_offload *ops; int proto = iph->protocol; int err = -ENOSYS; if (skb->encapsulation) { skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP)); skb_set_inner_network_header(skb, nhoff); } csum_replace2(&iph->check, iph->tot_len, newlen); iph->tot_len = newlen; ops = rcu_dereference(inet_offloads[proto]); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; /* Only need to add sizeof(*iph) to get to the next hdr below * because any hdr with option will have been flushed in * inet_gro_receive(). */ err = INDIRECT_CALL_2(ops->callbacks.gro_complete, tcp4_gro_complete, udp4_gro_complete, skb, nhoff + sizeof(*iph)); out: return err; } static int ipip_gro_complete(struct sk_buff *skb, int nhoff) { skb->encapsulation = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; return inet_gro_complete(skb, nhoff); } int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) { struct socket *sock; int rc = sock_create_kern(net, family, type, protocol, &sock); if (rc == 0) { *sk = sock->sk; (*sk)->sk_allocation = GFP_ATOMIC; /* * Unhash it so that IP input processing does not even see it, * we do not wish this socket to see incoming packets. */ (*sk)->sk_prot->unhash(*sk); } return rc; } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; int i; for_each_possible_cpu(i) res += snmp_get_cpu_field(mib, i, offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, size_t syncp_offset) { void *bhptr; struct u64_stats_sync *syncp; u64 v; unsigned int start; bhptr = per_cpu_ptr(mib, cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { start = u64_stats_fetch_begin_irq(syncp); v = *(((u64 *)bhptr) + offt); } while (u64_stats_fetch_retry_irq(syncp, start)); return v; } EXPORT_SYMBOL_GPL(snmp_get_cpu_field64); u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; for_each_possible_cpu(cpu) { res += snmp_get_cpu_field64(mib, cpu, offt, syncp_offset); } return res; } EXPORT_SYMBOL_GPL(snmp_fold_field64); #endif #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, }; #endif static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, }; static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, .no_policy = 1, }; static __net_init int ipv4_mib_init_net(struct net *net) { int i; net->mib.tcp_statistics = alloc_percpu(struct tcp_mib); if (!net->mib.tcp_statistics) goto err_tcp_mib; net->mib.ip_statistics = alloc_percpu(struct ipstats_mib); if (!net->mib.ip_statistics) goto err_ip_mib; for_each_possible_cpu(i) { struct ipstats_mib *af_inet_stats; af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i); u64_stats_init(&af_inet_stats->syncp); } net->mib.net_statistics = alloc_percpu(struct linux_mib); if (!net->mib.net_statistics) goto err_net_mib; net->mib.udp_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udp_statistics) goto err_udp_mib; net->mib.udplite_statistics = alloc_percpu(struct udp_mib); if (!net->mib.udplite_statistics) goto err_udplite_mib; net->mib.icmp_statistics = alloc_percpu(struct icmp_mib); if (!net->mib.icmp_statistics) goto err_icmp_mib; net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), GFP_KERNEL); if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); return 0; err_icmpmsg_mib: free_percpu(net->mib.icmp_statistics); err_icmp_mib: free_percpu(net->mib.udplite_statistics); err_udplite_mib: free_percpu(net->mib.udp_statistics); err_udp_mib: free_percpu(net->mib.net_statistics); err_net_mib: free_percpu(net->mib.ip_statistics); err_ip_mib: free_percpu(net->mib.tcp_statistics); err_tcp_mib: return -ENOMEM; } static __net_exit void ipv4_mib_exit_net(struct net *net) { kfree(net->mib.icmpmsg_statistics); free_percpu(net->mib.icmp_statistics); free_percpu(net->mib.udplite_statistics); free_percpu(net->mib.udp_statistics); free_percpu(net->mib.net_statistics); free_percpu(net->mib.ip_statistics); free_percpu(net->mib.tcp_statistics); #ifdef CONFIG_MPTCP /* allocated on demand, see mptcp_init_sock() */ free_percpu(net->mib.mptcp_statistics); #endif } static __net_initdata struct pernet_operations ipv4_mib_ops = { .init = ipv4_mib_init_net, .exit = ipv4_mib_exit_net, }; static int __init init_ipv4_mibs(void) { return register_pernet_subsys(&ipv4_mib_ops); } static __net_init int inet_init_net(struct net *net) { /* * Set defaults for local port range */ seqlock_init(&net->ipv4.ip_local_ports.lock); net->ipv4.ip_local_ports.range[0] = 32768; net->ipv4.ip_local_ports.range[1] = 60999; seqlock_init(&net->ipv4.ping_group_range.lock); /* * Sane defaults - nobody may create ping sockets. * Boot scripts should set this to distro-specific group. */ net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1); net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0); /* Default values for sysctl-controlled parameters. * We set them here, in case sysctl is not compiled. */ net->ipv4.sysctl_ip_default_ttl = IPDEFTTL; net->ipv4.sysctl_ip_fwd_update_priority = 1; net->ipv4.sysctl_ip_dynaddr = 0; net->ipv4.sysctl_ip_early_demux = 1; net->ipv4.sysctl_udp_early_demux = 1; net->ipv4.sysctl_tcp_early_demux = 1; net->ipv4.sysctl_nexthop_compat_mode = 1; #ifdef CONFIG_SYSCTL net->ipv4.sysctl_ip_prot_sock = PROT_SOCK; #endif /* Some igmp sysctl, whose values are always used */ net->ipv4.sysctl_igmp_max_memberships = 20; net->ipv4.sysctl_igmp_max_msf = 10; /* IGMP reports for link-local multicast groups are enabled by default */ net->ipv4.sysctl_igmp_llm_reports = 1; net->ipv4.sysctl_igmp_qrv = 2; net->ipv4.sysctl_fib_notify_on_flag_change = 0; return 0; } static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, }; static int __init init_inet_pernet_ops(void) { return register_pernet_subsys(&af_inet_ops); } static int ipv4_proc_init(void); /* * IP protocol layer initialiser */ static struct packet_offload ip_packet_offload __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .callbacks = { .gso_segment = inet_gso_segment, .gro_receive = inet_gro_receive, .gro_complete = inet_gro_complete, }, }; static const struct net_offload ipip_offload = { .callbacks = { .gso_segment = ipip_gso_segment, .gro_receive = ipip_gro_receive, .gro_complete = ipip_gro_complete, }, }; static int __init ipip_offload_init(void) { return inet_add_offload(&ipip_offload, IPPROTO_IPIP); } static int __init ipv4_offload_init(void) { /* * Add offloads */ if (udpv4_offload_init() < 0) pr_crit("%s: Cannot add UDP protocol offload\n", __func__); if (tcpv4_offload_init() < 0) pr_crit("%s: Cannot add TCP protocol offload\n", __func__); if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); dev_add_offload(&ip_packet_offload); return 0; } fs_initcall(ipv4_offload_init); static struct packet_type ip_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_IP), .func = ip_rcv, .list_func = ip_list_rcv, }; static int __init inet_init(void) { struct inet_protosw *q; struct list_head *r; int rc; sock_skb_cb_check_size(sizeof(struct inet_skb_parm)); raw_hashinfo_init(&raw_v4_hashinfo); rc = proto_register(&tcp_prot, 1); if (rc) goto out; rc = proto_register(&udp_prot, 1); if (rc) goto out_unregister_tcp_proto; rc = proto_register(&raw_prot, 1); if (rc) goto out_unregister_udp_proto; rc = proto_register(&ping_prot, 1); if (rc) goto out_unregister_raw_proto; /* * Tell SOCKET that we are alive... */ (void)sock_register(&inet_family_ops); #ifdef CONFIG_SYSCTL ip_static_sysctl_init(); #endif /* * Add all the base protocols. */ if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) pr_crit("%s: Cannot add IGMP protocol\n", __func__); #endif /* Register the socket-side information for inet_create. */ for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r) INIT_LIST_HEAD(r); for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q) inet_register_protosw(q); /* * Set the ARP module up */ arp_init(); /* * Set the IP module up */ ip_init(); /* Initialise per-cpu ipv4 mibs */ if (init_ipv4_mibs()) panic("%s: Cannot init ipv4 mibs\n", __func__); /* Setup TCP slab cache for open requests. */ tcp_init(); /* Setup UDP memory threshold */ udp_init(); /* Add UDP-Lite (RFC 3828) */ udplite4_register(); raw_init(); ping_init(); /* * Set the ICMP layer up */ if (icmp_init() < 0) panic("Failed to create the ICMP control socket.\n"); /* * Initialise the multicast router */ #if defined(CONFIG_IP_MROUTE) if (ip_mr_init()) pr_crit("%s: Cannot init ipv4 mroute\n", __func__); #endif if (init_inet_pernet_ops()) pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); ipv4_proc_init(); ipfrag_init(); dev_add_pack(&ip_packet_type); ip_tunnel_core_init(); rc = 0; out: return rc; out_unregister_raw_proto: proto_unregister(&raw_prot); out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); goto out; } fs_initcall(inet_init); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS static int __init ipv4_proc_init(void) { int rc = 0; if (raw_proc_init()) goto out_raw; if (tcp4_proc_init()) goto out_tcp; if (udp4_proc_init()) goto out_udp; if (ping_proc_init()) goto out_ping; if (ip_misc_proc_init()) goto out_misc; out: return rc; out_misc: ping_proc_exit(); out_ping: udp4_proc_exit(); out_udp: tcp4_proc_exit(); out_tcp: raw_proc_exit(); out_raw: rc = -ENOMEM; goto out; } #else /* CONFIG_PROC_FS */ static int __init ipv4_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ |
| 4707 1731 4194 1014 270 778 854 96 219 2695 1794 52 52 52 184 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 18 52 449 50 50 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* include/net/xdp.h * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ #include <linux/skbuff.h> /* skb_shared_info */ /** * DOC: XDP RX-queue information * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how * the driver have configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. * * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally need to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; }; struct page_pool; struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; enum xdp_buff_flags { XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under * pressure */ }; struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; xdp->flags = 0; } static __always_inline void xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, int headroom, int data_len, const bool meta_valid) { unsigned char *data = hard_start + headroom; xdp->data_hard_start = hard_start; xdp->data = data; xdp->data_end = data + data_len; xdp->data_meta = meta_valid ? data : data + 1; } /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the * XDP/BPF data access to data_hard_end. Notice same area (and size) * is used for XDP_PASS, when constructing the SKB via build_skb(). */ #define xdp_data_hard_end(xdp) \ ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * xdp_get_shared_info_from_buff(struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); len += sinfo->xdp_frags_size; out: return len; } struct xdp_frame { void *data; u16 len; u16 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; void *xa; void *q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { /* bq->count will be zero'ed when bq->xa gets updated */ bq->xa = NULL; } static inline struct skb_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } struct xdp_cpumap_stats { unsigned int redirect; unsigned int pass; unsigned int drop; }; /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { frame->data = NULL; frame->dev_rx = NULL; } static inline void xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, bool pfmemalloc) { skb_shinfo(skb)->nr_frags = nr_frags; skb->len += size; skb->data_len += size; skb->truesize += truesize; skb->pfmemalloc |= pfmemalloc; } /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; xdp->flags = frame->flags; } static inline int xdp_update_frame_from_buff(struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); return -ENOSPC; } xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; xdp_frame->flags = xdp->flags; return 0; } /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ xdp_frame->mem = xdp->rxq->mem; return xdp_frame; } void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); /* When sending xdp_frame into the network stack, then there is no * return point callback, which is needed to release e.g. DMA-mapping * resources with page_pool. Thus, have explicit function to release * frame resources. */ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; struct skb_shared_info *sinfo; int i; /* Curr only page_pool needs this */ if (mem->type != MEM_TYPE_PAGE_POOL) return; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); for (i = 0; i < sinfo->nr_frags; i++) { struct page *page = skb_frag_page(&sinfo->frags[i]); __xdp_release_frame(page_address(page), mem); } out: __xdp_release_frame(xdpf->data, mem); } static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); len += sinfo->xdp_frags_size; out: return len; } int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); static inline int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id) { return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. */ static __always_inline void xdp_set_data_meta_invalid(struct xdp_buff *xdp) { xdp->data_meta = xdp->data + 1; } static __always_inline bool xdp_data_meta_unsupported(const struct xdp_buff *xdp) { return unlikely(xdp->data_meta > xdp->data); } static inline bool xdp_metalen_invalid(unsigned long metalen) { return (metalen & (sizeof(__u32) - 1)) || (metalen > 32); } struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; }; struct netdev_bpf; void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE #endif /* __LINUX_NET_XDP_H__ */ |
| 286 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 | // SPDX-License-Identifier: GPL-2.0-only /* Event cache for netfilter. */ /* * (C) 2005 Harald Welte <laforge@gnumonks.org> * (C) 2005 Patrick McHardy <kaber@trash.net> * (C) 2005-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2005 USAGI/WIDE Project <http://www.linux-ipv6.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/netfilter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/stddef.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/export.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> static DEFINE_MUTEX(nf_ct_ecache_mutex); #define DYING_NULLS_VAL ((1 << 30) + 1) #define ECACHE_MAX_JIFFIES msecs_to_jiffies(10) #define ECACHE_RETRY_JIFFIES msecs_to_jiffies(10) enum retry_state { STATE_CONGESTED, STATE_RESTART, STATE_DONE, }; struct nf_conntrack_net_ecache *nf_conn_pernet_ecache(const struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); return &cnet->ecache; } #if IS_MODULE(CONFIG_NF_CT_NETLINK) EXPORT_SYMBOL_GPL(nf_conn_pernet_ecache); #endif static enum retry_state ecache_work_evict_list(struct nf_conntrack_net *cnet) { unsigned long stop = jiffies + ECACHE_MAX_JIFFIES; struct hlist_nulls_head evicted_list; enum retry_state ret = STATE_DONE; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; unsigned int sent; INIT_HLIST_NULLS_HEAD(&evicted_list, DYING_NULLS_VAL); next: sent = 0; spin_lock_bh(&cnet->ecache.dying_lock); hlist_nulls_for_each_entry_safe(h, n, &cnet->ecache.dying_list, hnnode) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); /* The worker owns all entries, ct remains valid until nf_ct_put * in the loop below. */ if (nf_conntrack_event(IPCT_DESTROY, ct)) { ret = STATE_CONGESTED; break; } hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &evicted_list); if (time_after(stop, jiffies)) { ret = STATE_RESTART; break; } if (sent++ > 16) { spin_unlock_bh(&cnet->ecache.dying_lock); cond_resched(); goto next; } } spin_unlock_bh(&cnet->ecache.dying_lock); hlist_nulls_for_each_entry_safe(h, n, &evicted_list, hnnode) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode); nf_ct_put(ct); cond_resched(); } return ret; } static void ecache_work(struct work_struct *work) { struct nf_conntrack_net *cnet = container_of(work, struct nf_conntrack_net, ecache.dwork.work); int ret, delay = -1; ret = ecache_work_evict_list(cnet); switch (ret) { case STATE_CONGESTED: delay = ECACHE_RETRY_JIFFIES; break; case STATE_RESTART: delay = 0; break; case STATE_DONE: break; } if (delay >= 0) schedule_delayed_work(&cnet->ecache.dwork, delay); } static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e, const u32 events, const u32 missed, const struct nf_ct_event *item) { struct net *net = nf_ct_net(item->ct); struct nf_ct_event_notifier *notify; u32 old, want; int ret; if (!((events | missed) & e->ctmask)) return 0; rcu_read_lock(); notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (!notify) { rcu_read_unlock(); return 0; } ret = notify->ct_event(events | missed, item); rcu_read_unlock(); if (likely(ret >= 0 && missed == 0)) return 0; do { old = READ_ONCE(e->missed); if (ret < 0) want = old | events; else want = old & ~missed; } while (cmpxchg(&e->missed, old, want) != old); return ret; } int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, u32 portid, int report) { struct nf_conntrack_ecache *e; struct nf_ct_event item; unsigned int missed; int ret; if (!nf_ct_is_confirmed(ct)) return 0; e = nf_ct_ecache_find(ct); if (!e) return 0; memset(&item, 0, sizeof(item)); item.ct = ct; item.portid = e->portid ? e->portid : portid; item.report = report; /* This is a resent of a destroy event? If so, skip missed */ missed = e->portid ? 0 : e->missed; ret = __nf_conntrack_eventmask_report(e, events, missed, &item); if (unlikely(ret < 0 && (events & (1 << IPCT_DESTROY)))) { /* This is a destroy event that has been triggered by a process, * we store the PORTID to include it in the retransmission. */ if (e->portid == 0 && portid != 0) e->portid = portid; } return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_eventmask_report); /* deliver cached events and clear cache entry - must be called with locally * disabled softirqs */ void nf_ct_deliver_cached_events(struct nf_conn *ct) { struct nf_conntrack_ecache *e; struct nf_ct_event item; unsigned int events; if (!nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct)) return; e = nf_ct_ecache_find(ct); if (e == NULL) return; events = xchg(&e->cache, 0); item.ct = ct; item.portid = 0; item.report = 0; /* We make a copy of the missed event cache without taking * the lock, thus we may send missed events twice. However, * this does not harm and it happens very rarely. */ __nf_conntrack_eventmask_report(e, events, e->missed, &item); } EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events); void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, struct nf_conntrack_expect *exp, u32 portid, int report) { struct net *net = nf_ct_exp_net(exp); struct nf_ct_event_notifier *notify; struct nf_conntrack_ecache *e; rcu_read_lock(); notify = rcu_dereference(net->ct.nf_conntrack_event_cb); if (!notify) goto out_unlock; e = nf_ct_ecache_find(exp->master); if (!e) goto out_unlock; if (e->expmask & (1 << event)) { struct nf_exp_event item = { .exp = exp, .portid = portid, .report = report }; notify->exp_event(1 << event, &item); } out_unlock: rcu_read_unlock(); } void nf_conntrack_register_notifier(struct net *net, const struct nf_ct_event_notifier *new) { struct nf_ct_event_notifier *notify; mutex_lock(&nf_ct_ecache_mutex); notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb, lockdep_is_held(&nf_ct_ecache_mutex)); WARN_ON_ONCE(notify); rcu_assign_pointer(net->ct.nf_conntrack_event_cb, new); mutex_unlock(&nf_ct_ecache_mutex); } EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier); void nf_conntrack_unregister_notifier(struct net *net) { mutex_lock(&nf_ct_ecache_mutex); RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL); mutex_unlock(&nf_ct_ecache_mutex); /* synchronize_rcu() is called after netns pre_exit */ } EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier); void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (state == NFCT_ECACHE_DESTROY_FAIL && !delayed_work_pending(&cnet->ecache.dwork)) { schedule_delayed_work(&cnet->ecache.dwork, HZ); net->ct.ecache_dwork_pending = true; } else if (state == NFCT_ECACHE_DESTROY_SENT) { if (!hlist_nulls_empty(&cnet->ecache.dying_list)) mod_delayed_work(system_wq, &cnet->ecache.dwork, 0); else net->ct.ecache_dwork_pending = false; } } bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; switch (net->ct.sysctl_events) { case 0: /* assignment via template / ruleset? ignore sysctl. */ if (ctmask || expmask) break; return true; case 2: /* autodetect: no event listener, don't allocate extension. */ if (!READ_ONCE(nf_ctnetlink_has_listener)) return true; fallthrough; case 1: /* always allocate an extension. */ if (!ctmask && !expmask) { ctmask = ~0; expmask = ~0; } break; default: WARN_ON_ONCE(1); return true; } e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); if (e) { e->ctmask = ctmask; e->expmask = expmask; } return e != NULL; } EXPORT_SYMBOL_GPL(nf_ct_ecache_ext_add); #define NF_CT_EVENTS_DEFAULT 2 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT; void nf_conntrack_ecache_pernet_init(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); net->ct.sysctl_events = nf_ct_events; INIT_DELAYED_WORK(&cnet->ecache.dwork, ecache_work); INIT_HLIST_NULLS_HEAD(&cnet->ecache.dying_list, DYING_NULLS_VAL); spin_lock_init(&cnet->ecache.dying_lock); BUILD_BUG_ON(__IPCT_MAX >= 16); /* e->ctmask is u16 */ } void nf_conntrack_ecache_pernet_fini(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); cancel_delayed_work_sync(&cnet->ecache.dwork); } |
| 694 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KERNEL_EVENTS_INTERNAL_H #define _KERNEL_EVENTS_INTERNAL_H #include <linux/hardirq.h> #include <linux/uaccess.h> #include <linux/refcount.h> /* Buffer handling */ #define RING_BUFFER_WRITABLE 0x01 struct perf_buffer { refcount_t refcount; struct rcu_head rcu_head; #ifdef CONFIG_PERF_USE_VMALLOC struct work_struct work; int page_order; /* allocation order */ #endif int nr_pages; /* nr of data pages */ int overwrite; /* can overwrite itself */ int paused; /* can write into ring buffer */ atomic_t poll; /* POLL_ for wakeups */ local_t head; /* write position */ unsigned int nest; /* nested writers */ local_t events; /* event limit */ local_t wakeup; /* wakeup stamp */ local_t lost; /* nr records lost */ long watermark; /* wakeup watermark */ long aux_watermark; /* poll crap */ spinlock_t event_lock; struct list_head event_list; atomic_t mmap_count; unsigned long mmap_locked; struct user_struct *mmap_user; /* AUX area */ long aux_head; unsigned int aux_nest; long aux_wakeup; /* last aux_watermark boundary crossed by aux_head */ unsigned long aux_pgoff; int aux_nr_pages; int aux_overwrite; atomic_t aux_mmap_count; unsigned long aux_mmap_locked; void (*free_aux)(void *); refcount_t aux_refcount; int aux_in_sampling; void **aux_pages; void *aux_priv; struct perf_event_mmap_page *user_page; void *data_pages[]; }; extern void rb_free(struct perf_buffer *rb); static inline void rb_free_rcu(struct rcu_head *rcu_head) { struct perf_buffer *rb; rb = container_of(rcu_head, struct perf_buffer, rcu_head); rb_free(rb); } static inline void rb_toggle_paused(struct perf_buffer *rb, bool pause) { if (!pause && rb->nr_pages) rb->paused = 0; else rb->paused = 1; } extern struct perf_buffer * rb_alloc(int nr_pages, long watermark, int cpu, int flags); extern void perf_event_wakeup(struct perf_event *event); extern int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, pgoff_t pgoff, int nr_pages, long watermark, int flags); extern void rb_free_aux(struct perf_buffer *rb); extern struct perf_buffer *ring_buffer_get(struct perf_event *event); extern void ring_buffer_put(struct perf_buffer *rb); static inline bool rb_has_aux(struct perf_buffer *rb) { return !!rb->aux_nr_pages; } void perf_event_aux_event(struct perf_event *event, unsigned long head, unsigned long size, u64 flags); extern struct page * perf_mmap_to_page(struct perf_buffer *rb, unsigned long pgoff); #ifdef CONFIG_PERF_USE_VMALLOC /* * Back perf_mmap() with vmalloc memory. * * Required for architectures that have d-cache aliasing issues. */ static inline int page_order(struct perf_buffer *rb) { return rb->page_order; } #else static inline int page_order(struct perf_buffer *rb) { return 0; } #endif static inline int data_page_nr(struct perf_buffer *rb) { return rb->nr_pages << page_order(rb); } static inline unsigned long perf_data_size(struct perf_buffer *rb) { return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); } static inline unsigned long perf_aux_size(struct perf_buffer *rb) { return rb->aux_nr_pages << PAGE_SHIFT; } #define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \ { \ unsigned long size, written; \ \ do { \ size = min(handle->size, len); \ written = memcpy_func(__VA_ARGS__); \ written = size - written; \ \ len -= written; \ handle->addr += written; \ if (advance_buf) \ buf += written; \ handle->size -= written; \ if (!handle->size) { \ struct perf_buffer *rb = handle->rb; \ \ handle->page++; \ handle->page &= rb->nr_pages - 1; \ handle->addr = rb->data_pages[handle->page]; \ handle->size = PAGE_SIZE << page_order(rb); \ } \ } while (len && written == size); \ \ return len; \ } #define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ static inline unsigned long \ func_name(struct perf_output_handle *handle, \ const void *buf, unsigned long len) \ __DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size) static inline unsigned long __output_custom(struct perf_output_handle *handle, perf_copy_f copy_func, const void *buf, unsigned long len) { unsigned long orig_len = len; __DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf, orig_len - len, size) } static inline unsigned long memcpy_common(void *dst, const void *src, unsigned long n) { memcpy(dst, src, n); return 0; } DEFINE_OUTPUT_COPY(__output_copy, memcpy_common) static inline unsigned long memcpy_skip(void *dst, const void *src, unsigned long n) { return 0; } DEFINE_OUTPUT_COPY(__output_skip, memcpy_skip) #ifndef arch_perf_out_copy_user #define arch_perf_out_copy_user arch_perf_out_copy_user static inline unsigned long arch_perf_out_copy_user(void *dst, const void *src, unsigned long n) { unsigned long ret; pagefault_disable(); ret = __copy_from_user_inatomic(dst, src, n); pagefault_enable(); return ret; } #endif DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) static inline int get_recursion_context(int *recursion) { unsigned char rctx = interrupt_context_level(); if (recursion[rctx]) return -1; recursion[rctx]++; barrier(); return rctx; } static inline void put_recursion_context(int *recursion, int rctx) { barrier(); recursion[rctx]--; } #ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP static inline bool arch_perf_have_user_stack_dump(void) { return true; } #define perf_user_stack_pointer(regs) user_stack_pointer(regs) #else static inline bool arch_perf_have_user_stack_dump(void) { return false; } #define perf_user_stack_pointer(regs) 0 #endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */ #endif /* _KERNEL_EVENTS_INTERNAL_H */ |
| 932 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM signal #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH trace/hooks #if !defined(_TRACE_HOOK_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HOOK_SIGNAL_H #include <trace/hooks/vendor_hooks.h> struct task_struct; DECLARE_HOOK(android_vh_do_send_sig_info, TP_PROTO(int sig, struct task_struct *killer, struct task_struct *dst), TP_ARGS(sig, killer, dst)); DECLARE_HOOK(android_vh_exit_signal, TP_PROTO(struct task_struct *task), TP_ARGS(task)); DECLARE_HOOK(android_vh_killed_process, TP_PROTO(struct task_struct *killer, struct task_struct *dst, bool *reap), TP_ARGS(killer, dst, reap)); #endif /* _TRACE_HOOK_SIGNAL_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 492 493 492 493 493 493 493 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | /* * kmod - the kernel module loader */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <trace/events/module.h> /* * Assuming: * * threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE, * (u64) THREAD_SIZE * 8UL); * * If you need less than 50 threads would mean we're dealing with systems * smaller than 3200 pages. This assumes you are capable of having ~13M memory, * and this would only be an upper limit, after which the OOM killer would take * effect. Systems like these are very unlikely if modules are enabled. */ #define MAX_KMOD_CONCURRENT 50 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT); static DECLARE_WAIT_QUEUE_HEAD(kmod_wq); /* * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads * running at the same time without returning. When this happens we * believe you've somehow ended up with a recursive module dependency * creating a loop. * * We have no option but to fail. * * Userspace should proactively try to detect and prevent these. */ #define MAX_KMOD_ALL_BUSY_TIMEOUT 5 /* modprobe_path is set via /proc/sys. */ char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH; static void free_modprobe_argv(struct subprocess_info *info) { kfree(info->argv[3]); /* check call_modprobe() */ kfree(info->argv); } static int call_modprobe(char *module_name, int wait) { struct subprocess_info *info; static char *envp[] = { "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); if (!argv) goto out; module_name = kstrdup(module_name, GFP_KERNEL); if (!module_name) goto free_argv; argv[0] = modprobe_path; argv[1] = "-q"; argv[2] = "--"; argv[3] = module_name; /* check free_modprobe_argv() */ argv[4] = NULL; info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL, NULL, free_modprobe_argv, NULL); if (!info) goto free_module_name; return call_usermodehelper_exec(info, wait | UMH_KILLABLE); free_module_name: kfree(module_name); free_argv: kfree(argv); out: return -ENOMEM; } /** * __request_module - try to load a kernel module * @wait: wait (or not) for the operation to complete * @fmt: printf style format string for the name of the module * @...: arguments as specified in the format string * * Load a module using the user mode module loader. The function returns * zero on success or a negative errno code or positive exit code from * "modprobe" on failure. Note that a successful module load does not mean * the module did not then unload and exit on an error of its own. Callers * must check that the service they requested is now available not blindly * invoke it. * * If module auto-loading support is disabled then this function * simply returns -ENOENT. */ int __request_module(bool wait, const char *fmt, ...) { va_list args; char module_name[MODULE_NAME_LEN]; int ret; /* * We don't allow synchronous module loading from async. Module * init may invoke async_synchronize_full() which will end up * waiting for this task which already is waiting for the module * loading to complete, leading to a deadlock. */ WARN_ON_ONCE(wait && current_is_async()); if (!modprobe_path[0]) return -ENOENT; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return -ENAMETOOLONG; ret = security_kernel_module_request(module_name); if (ret) return ret; if (atomic_dec_if_positive(&kmod_concurrent_max) < 0) { pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...", atomic_read(&kmod_concurrent_max), MAX_KMOD_CONCURRENT, module_name); ret = wait_event_killable_timeout(kmod_wq, atomic_dec_if_positive(&kmod_concurrent_max) >= 0, MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); if (!ret) { pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); return -ETIME; } else if (ret == -ERESTARTSYS) { pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name); return ret; } } trace_module_request(module_name, wait, _RET_IP_); ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); atomic_inc(&kmod_concurrent_max); wake_up(&kmod_wq); return ret; } EXPORT_SYMBOL(__request_module); |
| 244 244 244 244 244 243 243 243 243 60 60 59 59 60 3705 2 3 2 2 2 2 2 2 2 2 2 2 2 2 2 337 337 337 244 244 244 243 243 243 243 243 243 2 243 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/pgsize_migration.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> #include <linux/mmdebug.h> #include <linux/perf_event.h> #include <linux/audit.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/notifier.h> #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #define CREATE_TRACE_POINTS #include <trace/events/mmap.h> #undef CREATE_TRACE_POINTS #include <trace/hooks/mm.h> #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, unsigned long start, unsigned long end, unsigned long start_t, unsigned long end_t, bool mm_wr_locked); static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { if (vma->vm_flags & VM_SHARED) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, file, mapping); i_mmap_unlock_write(mapping); } } /* * Close a vm structure and free it. */ static void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); if (unreachable) __vm_area_free(vma); else vm_area_free(vma); } /* * check_brk_limits() - Use platform specific check of range & verify mlock * limits. * @addr: The address to check * @len: The size of increase. * * Return: 0 on success. */ static int check_brk_limits(unsigned long addr, unsigned long len) { unsigned long mapped_addr; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; return mlock_future_check(current->mm, current->mm->def_flags, len); } static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma, unsigned long newbrk, unsigned long oldbrk, struct list_head *uf); static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *brkvma, unsigned long addr, unsigned long request, unsigned long flags); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *brkvma, *next = NULL; unsigned long min_brk; bool populate; bool downgraded = false; LIST_HEAD(uf); MA_STATE(mas, &mm->mm_mt, 0, 0); if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* * Always allow shrinking brk. * do_brk_munmap() may downgrade mmap_lock to read. */ if (brk <= mm->brk) { int ret; /* Search one past newbrk */ mas_set(&mas, newbrk); brkvma = mas_find(&mas, oldbrk); if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. * do_brk_munmap() may downgrade the lock, so update it * before calling do_brk_munmap(). */ mm->brk = brk; ret = do_brk_munmap(&mas, brkvma, newbrk, oldbrk, &uf); if (ret == 1) { downgraded = true; goto success; } else if (!ret) goto success; mm->brk = origbrk; goto out; } if (check_brk_limits(oldbrk, newbrk - oldbrk)) goto out; /* * Only check if the next VMA is within the stack_guard_gap of the * expansion area */ mas_set(&mas, oldbrk); next = mas_find(&mas, newbrk - 1 + PAGE_SIZE + stack_guard_gap); if (next) { vma_start_write(next); if (newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; } brkvma = mas_prev(&mas, mm->start_brk); /* Ok, looks good - let it rip. */ if (do_brk_flags(&mas, brkvma, oldbrk, newbrk - oldbrk, 0) < 0) goto out; mm->brk = brk; success: populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; if (downgraded) mmap_read_unlock(mm); else mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: mmap_write_unlock(mm); return origbrk; } #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) extern void mt_validate(struct maple_tree *mt); extern void mt_dump(const struct maple_tree *mt); /* Validate the maple tree */ static void validate_mm_mt(struct mm_struct *mm) { struct maple_tree *mt = &mm->mm_mt; struct vm_area_struct *vma_mt; MA_STATE(mas, mt, 0, 0); mt_validate(&mm->mm_mt); mas_for_each(&mas, vma_mt, ULONG_MAX) { if ((vma_mt->vm_start != mas.index) || (vma_mt->vm_end - 1 != mas.last)) { pr_emerg("issue in %s\n", current->comm); dump_stack(); dump_vma(vma_mt); pr_emerg("mt piv: %p %lu - %lu\n", vma_mt, mas.index, mas.last); pr_emerg("mt vma: %p %lu - %lu\n", vma_mt, vma_mt->vm_start, vma_mt->vm_end); mt_dump(mas.tree); if (vma_mt->vm_end != mas.last + 1) { pr_err("vma: %p vma_mt %lu-%lu\tmt %lu-%lu\n", mm, vma_mt->vm_start, vma_mt->vm_end, mas.index, mas.last); mt_dump(mas.tree); } VM_BUG_ON_MM(vma_mt->vm_end != mas.last + 1, mm); if (vma_mt->vm_start != mas.index) { pr_err("vma: %p vma_mt %p %lu - %lu doesn't match\n", mm, vma_mt, vma_mt->vm_start, vma_mt->vm_end); mt_dump(mas.tree); } VM_BUG_ON_MM(vma_mt->vm_start != mas.index, mm); } } } static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *vma; MA_STATE(mas, &mm->mm_mt, 0, 0); validate_mm_mt(mm); mas_for_each(&mas, vma, ULONG_MAX) { #ifdef CONFIG_DEBUG_VM_RB struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } #endif i++; } if (i != mm->map_count) { pr_emerg("map_count %d mas_for_each %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #else /* !CONFIG_DEBUG_VM_MAPLE_TREE */ #define validate_mm_mt(root) do { } while (0) #define validate_mm(mm) do { } while (0) #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static inline void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static inline void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { VMA_ITERATOR(vmi, mm, addr); struct vm_area_struct *vma; unsigned long nr_pages = 0; for_each_vma_range(vmi, vma, end) { unsigned long vm_start = max(addr, vma->vm_start); unsigned long vm_end = min(end, vma->vm_end); nr_pages += PHYS_PFN(vm_end - vm_start); } return nr_pages; } static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { if (vma->vm_flags & VM_SHARED) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * vma_mas_store() - Store a VMA in the maple tree. * @vma: The vm_area_struct * @mas: The maple state * * Efficient way to store a VMA in the maple tree when the @mas has already * walked to the correct location. * * Note: the end address is inclusive in the maple tree. */ void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas) { trace_vma_store(mas->tree, vma); mas_set_range(mas, vma->vm_start, vma->vm_end - 1); mas_store_prealloc(mas, vma); } /* * vma_mas_remove() - Remove a VMA from the maple tree. * @vma: The vm_area_struct * @mas: The maple state * * Efficient way to remove a VMA from the maple tree when the @mas has already * been established and points to the correct location. * Note: the end address is inclusive in the maple tree. */ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas) { trace_vma_mas_szero(mas->tree, vma->vm_start, vma->vm_end - 1); mas->index = vma->vm_start; mas->last = vma->vm_end - 1; mas_store_prealloc(mas, NULL); } /* * vma_mas_szero() - Set a given range to zero. Used when modifying a * vm_area_struct start or end. * * @mas: The maple tree ma_state * @start: The start address to zero * @end: The end address to zero. */ static inline void vma_mas_szero(struct ma_state *mas, unsigned long start, unsigned long end) { trace_vma_mas_szero(mas->tree, start, end - 1); mas_set_range(mas, start, end - 1); mas_store_prealloc(mas, NULL); } static int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_end - 1); struct address_space *mapping = NULL; if (mas_preallocate(&mas, vma, GFP_KERNEL)) return -ENOMEM; vma_start_write(vma); if (vma->vm_file) { mapping = vma->vm_file->f_mapping; i_mmap_lock_write(mapping); } vma_mas_store(vma, &mas); if (mapping) { __vma_link_file(vma, mapping); i_mmap_unlock_write(mapping); } mm->map_count++; validate_mm(mm); return 0; } /* * vma_expand - Expand an existing VMA * * @mas: The maple state * @vma: The vma to expand * @start: The start of the vma * @end: The exclusive end of the vma * @pgoff: The page offset of vma * @next: The current of next vma. * * Expand @vma to @start and @end. Can expand off the start and end. Will * expand over @next if it's different from @vma and @end == @next->vm_end. * Checking if the @vma can expand and merge with @next needs to be handled by * the caller. * * Returns: 0 on success */ inline int vma_expand(struct ma_state *mas, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *next) { struct mm_struct *mm = vma->vm_mm; struct address_space *mapping = NULL; struct rb_root_cached *root = NULL; struct anon_vma *anon_vma = vma->anon_vma; struct file *file = vma->vm_file; bool remove_next = false; struct vm_area_struct *anon_dup = NULL; vma_start_write(vma); if (next && (vma != next) && (end == next->vm_end)) { remove_next = true; /* Lock the VMA before removing it */ vma_start_write(next); if (next->anon_vma && !vma->anon_vma) { int error; anon_vma = next->anon_vma; vma->anon_vma = anon_vma; error = anon_vma_clone(vma, next); if (error) return error; anon_dup = vma; } } /* Not merging but overwriting any part of next is not handled. */ VM_BUG_ON(next && !remove_next && next != vma && end > next->vm_start); /* Only handles expanding */ VM_BUG_ON(vma->vm_start < start || vma->vm_end > end); mas_set_range(mas, start, end - 1); if (mas_preallocate(mas, vma, GFP_KERNEL)) goto nomem; vma_adjust_trans_huge(vma, start, end, 0); if (file) { mapping = file->f_mapping; root = &mapping->i_mmap; uprobe_munmap(vma, vma->vm_start, vma->vm_end); i_mmap_lock_write(mapping); } if (anon_vma) { anon_vma_lock_write(anon_vma); anon_vma_interval_tree_pre_update_vma(vma); } if (file) { flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, root); } vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; /* Note: mas must be pointing to the expanding VMA */ vma_mas_store(vma, mas); if (remove_next) vma_mark_detached(next, true); if (file) { vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } /* Expanding over the next vma */ if (remove_next && file) { __remove_shared_vm_struct(next, file, mapping); } if (anon_vma) { anon_vma_interval_tree_post_update_vma(vma); anon_vma_unlock_write(anon_vma); } if (file) { i_mmap_unlock_write(mapping); uprobe_mmap(vma); } if (remove_next) { if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); } if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); vm_area_free(next); } validate_mm(mm); return 0; nomem: if (anon_dup) unlink_anon_vmas(anon_dup); return -ENOMEM; } /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. * The following helper function should be used when such adjustments * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. * 'expand' vma is always locked before it's passed to __vma_adjust() * from vma_merge() because vma should not change from the moment * can_vma_merge_{before|after} decision is made. * 'insert' vma is used only by __split_vma() and it's always a brand * new vma which is not yet added into mm's vma tree, therefore no need * to lock it. */ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next_next = NULL; /* uninit var warning */ struct vm_area_struct *next = find_vma(mm, vma->vm_end); struct vm_area_struct *orig_vma = vma; struct address_space *mapping = NULL; struct rb_root_cached *root = NULL; struct anon_vma *anon_vma = NULL; struct file *file = vma->vm_file; bool vma_changed = false; long adjust_next = 0; int remove_next = 0; MA_STATE(mas, &mm->mm_mt, start, end - 1); struct vm_area_struct *exporter = NULL, *importer = NULL; struct vm_area_struct *anon_dup = NULL; vma_start_write(vma); if (next) vma_start_write(next); if (next && !insert) { if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). * The only other cases that gets here are * case 1, case 7 and case 8. */ if (next == expand) { /* * The only case where we don't expand "vma" * and we expand "next" instead is case 8. */ VM_WARN_ON(end != next->vm_end); /* * remove_next == 3 means we're * removing "vma" and that to do so we * swapped "vma" and "next". */ remove_next = 3; VM_WARN_ON(file != next->vm_file); swap(vma, next); } else { VM_WARN_ON(expand != vma); /* * case 1, 6, 7, remove_next == 2 is case 6, * remove_next == 1 is case 1 or 7. */ remove_next = 1 + (end > next->vm_end); if (remove_next == 2) { next_next = find_vma(mm, next->vm_end); if (next_next) vma_start_write(next_next); } VM_WARN_ON(remove_next == 2 && end != next_next->vm_end); } exporter = next; importer = vma; /* * If next doesn't have anon_vma, import from vma after * next, if the vma overlaps with it. */ if (remove_next == 2 && !next->anon_vma) exporter = next_next; } else if (end > next->vm_start) { /* * vma expands, overlapping part of the next: * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start); exporter = next; importer = vma; VM_WARN_ON(expand != importer); } else if (end < vma->vm_end) { /* * vma shrinks, and !insert tells it's not * split_vma inserting another: so it must be * mprotect case 4 shifting the boundary down. */ adjust_next = -(vma->vm_end - end); exporter = vma; importer = next; VM_WARN_ON(expand != importer); } /* * Easily overlooked: when mprotect shifts the boundary, * make sure the expanding vma has anon_vma set if the * shrinking vma had, to cover any anon pages imported. */ if (exporter && exporter->anon_vma && !importer->anon_vma) { int error; importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); if (error) return error; anon_dup = importer; } } if (adjust_next < 0) mas_set_range(&mas, next->vm_start + adjust_next, next->vm_end - 1); else if (insert) { vma_start_write(insert); mas_set_range(&mas, insert->vm_start, insert->vm_end - 1); } if (mas_preallocate(&mas, vma, GFP_KERNEL)) { if (anon_dup) unlink_anon_vmas(anon_dup); return -ENOMEM; } vma_adjust_trans_huge(orig_vma, start, end, adjust_next); if (file) { mapping = file->f_mapping; root = &mapping->i_mmap; uprobe_munmap(vma, vma->vm_start, vma->vm_end); if (adjust_next) uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert && insert->vm_file) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(insert, insert->vm_file->f_mapping); } } anon_vma = vma->anon_vma; if (!anon_vma && adjust_next) anon_vma = next->anon_vma; if (anon_vma) { VM_WARN_ON(adjust_next && next->anon_vma && anon_vma != next->anon_vma); anon_vma_lock_write(anon_vma); anon_vma_interval_tree_pre_update_vma(vma); if (adjust_next) anon_vma_interval_tree_pre_update_vma(next); } if (file) { flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, root); if (adjust_next) vma_interval_tree_remove(next, root); } if (start != vma->vm_start) { if ((vma->vm_start < start) && !insert) { vma_mas_szero(&mas, vma->vm_start, start); VM_WARN_ON(insert && insert->vm_start > vma->vm_start); } else if (!insert) { vma_changed = true; } vma->vm_start = start; } if (end != vma->vm_end) { if (vma->vm_end > end) { if ((vma->vm_end + adjust_next != end) && (!insert || (insert->vm_start != end))) { vma_mas_szero(&mas, end, vma->vm_end); mas_reset(&mas); VM_WARN_ON(insert && insert->vm_end < vma->vm_end); } } else if (!insert) { vma_changed = true; } vma->vm_end = end; } if (vma_changed) vma_mas_store(vma, &mas); vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; vma_mas_store(next, &mas); } if (file) { if (adjust_next) vma_interval_tree_insert(next, root); vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } if (remove_next && file) { __remove_shared_vm_struct(next, file, mapping); if (remove_next == 2) __remove_shared_vm_struct(next_next, file, mapping); } else if (insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ mas_reset(&mas); vma_start_write(insert); vma_mas_store(insert, &mas); mm->map_count++; } if (anon_vma) { anon_vma_interval_tree_post_update_vma(vma); if (adjust_next) anon_vma_interval_tree_post_update_vma(next); anon_vma_unlock_write(anon_vma); } if (file) { i_mmap_unlock_write(mapping); uprobe_mmap(vma); if (adjust_next) uprobe_mmap(next); } if (remove_next) { again: vma_mark_detached(next, true); if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); } if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); if (remove_next != 2) BUG_ON(vma->vm_end < next->vm_end); vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove next_next too. */ if (remove_next == 2) { remove_next = 1; next = next_next; goto again; } } if (insert && file) uprobe_mmap(insert); mas_destroy(&mas); validate_mm(mm); return 0; } /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those. */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return 0; if (vma->vm_file != file) return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) return 0; if (!is_mergable_pad_vma(vma, vm_flags)) return 0; return 1; } static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return 1; return anon_vma1 == anon_vma2; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. */ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; } return 0; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. */ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return 1; } return 0; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), * figure out whether that can be merged with its predecessor or its * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when * called for mprotect, it is certain to be already mapped (either at * an offset within prev, or at the start of next), and the flags of * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * * The following mprotect cases have to be considered, where AAAA is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: * * AAAA AAAA AAAA * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN * cannot merge might become might become * PPNNNNNNNNNN PPPPPPPPPPNN * mmap, brk or case 4 below case 5 below * mremap move: * AAAA AAAA * PPPP NNNN PPPPNNNNXXXX * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or * PPPPPPPPNNNN 2 or PPPPPPPPXXXX 7 or * PPPPNNNNNNNN 3 PPPPXXXXXXXX 8 * * It is important for case 8 that the vma NNNN overlapping the * region AAAA is never going to extended over XXXX. Instead XXXX must * be extended in region AAAA and NNNN must be removed. This way in * all cases where vma_merge succeeds, the moment vma_adjust drops the * rmap_locks, the properties of the merged vma will be already * correct for the whole merged range. Some of those properties like * vm_page_prot/vm_flags may be accessed by rmap_walks and they must * be correct for the whole merged range immediately after the * rmap_locks are released. Otherwise if XXXX would be removed and * NNNN would be extended over the XXXX range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, struct anon_vma_name *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *mid, *next, *res; int err = -1; bool merge_prev = false; bool merge_next = false; /* * We later require that vma->vm_flags == vm_flags, * so this tests vma->vm_flags & VM_SPECIAL, too. */ if (vm_flags & VM_SPECIAL) return NULL; if (prev) vma_start_write(prev); next = find_vma(mm, prev ? prev->vm_end : 0); if (next) vma_start_write(next); mid = next; if (next && next->vm_end == end) { /* cases 6, 7, 8 */ next = find_vma(mm, next->vm_end); if (next) vma_start_write(next); } /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(mid && end > mid->vm_end); VM_WARN_ON(addr >= end); /* Can we merge the predecessor? */ if (prev && prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, vm_userfaultfd_ctx, anon_name)) { merge_prev = true; } /* Can we merge the successor? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx, anon_name)) { merge_next = true; } /* Can we merge both the predecessor and the successor? */ if (merge_prev && merge_next && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ err = __vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, prev); res = prev; } else if (merge_prev) { /* cases 2, 5, 7 */ err = __vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL, prev); res = prev; } else if (merge_next) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); else /* cases 3, 8 */ err = __vma_adjust(mid, addr, next->vm_end, next->vm_pgoff - pglen, NULL, next); res = next; } /* * Cannot merge with predecessor or successor or error in __vma_adjust? */ if (err) return NULL; khugepaged_enter_vma(res, vm_flags); return res; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { MA_STATE(mas, &vma->vm_mm->mm_mt, vma->vm_end, vma->vm_end); struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; /* Try next first. */ next = mas_walk(&mas); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } prev = mas_prev(&mas, 0); VM_BUG_ON_VMA(prev != vma, vma); prev = mas_prev(&mas, 0); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } int mlock_future_check(struct mm_struct *mm, unsigned long flags, unsigned long len) { unsigned long locked, lock_limit; /* mlock MCL_FUTURE? */ if (flags & VM_LOCKED) { locked = len >> PAGE_SHIFT; locked += mm->locked_vm; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } return 0; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_mode & FMODE_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /* * The caller must write-lock current->mm->mmap_lock. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; vm_flags_t vm_flags; int pkey = 0; validate_mm(mm); *populate = 0; if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we dont add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = get_unmapped_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (mlock_future_check(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!file->f_op->mmap) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { vm_flags_t vm_flags = vma->vm_flags; const struct vm_operations_struct *vm_ops = vma->vm_ops; /* If it was private or non-writable, the write bit is already clear */ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) return 0; /* The backer wishes to know when pages are first written to? */ if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite)) return 1; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return 1; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) return 1; /* Specialty mapping? */ if (vm_flags & VM_PFNMAP) return 0; /* Can the mapping track the dirty pages? */ return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return 0; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } /** * unmapped_area() - Find an area between the low_limit and the high_limit with * the correct alignment and offset, all from @info. Note: current->mm is used * for the search. * * @info: The unmapped area information including the range (low_limit - * hight_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { unsigned long length, gap, low_limit; struct vm_area_struct *tmp; MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; low_limit = info->low_limit; retry: if (mas_empty_area(&mas, low_limit, info->high_limit - 1, length)) return -ENOMEM; gap = mas.index; gap += (info->align_offset - gap) & info->align_mask; tmp = mas_next(&mas, ULONG_MAX); if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) < gap + length - 1) { low_limit = tmp->vm_end; mas_reset(&mas); goto retry; } } else { tmp = mas_prev(&mas, 0); if (tmp && vm_end_gap(tmp) > gap) { low_limit = vm_end_gap(tmp); mas_reset(&mas); goto retry; } } return gap; } /** * unmapped_area_topdown() - Find an area between the low_limit and the * high_limit with * the correct alignment and offset at the highest available * address, all from @info. Note: current->mm is used for the search. * * @info: The unmapped area information including the range (low_limit - * hight_limit), the alignment offset and mask. * * Return: A memory address or -ENOMEM. */ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { unsigned long length, gap, high_limit, gap_end; struct vm_area_struct *tmp; MA_STATE(mas, ¤t->mm->mm_mt, 0, 0); /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; high_limit = info->high_limit; retry: if (mas_empty_area_rev(&mas, info->low_limit, high_limit - 1, length)) return -ENOMEM; gap = mas.last + 1 - info->length; gap -= (gap - info->align_offset) & info->align_mask; gap_end = mas.last; tmp = mas_next(&mas, ULONG_MAX); if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */ if (vm_start_gap(tmp) <= gap_end) { high_limit = vm_start_gap(tmp); mas_reset(&mas); goto retry; } } else { tmp = mas_prev(&mas, 0); if (tmp && vm_end_gap(tmp) > gap) { high_limit = tmp->vm_start; mas_reset(&mas); goto retry; } } return gap; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } EXPORT_SYMBOL_GPL(vm_unmapped_area); /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.align_mask = 0; info.align_offset = 0; return vm_unmapped_area(&info); } #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_get_unmapped_area(filp, addr, len, pgoff, flags); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ unsigned long generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info; const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.align_mask = 0; info.align_offset = 0; addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_get_unmapped_area_topdown(filp, addr, len, pgoff, flags); } #endif unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; get_area = current->mm->get_unmapped_area; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. * do_mmap() will clear pgoff, so match alignment. */ pgoff = 0; get_area = shmem_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } EXPORT_SYMBOL(get_unmapped_area); /** * find_vma_intersection() - Look up the first VMA which intersects the interval * @mm: The process address space. * @start_addr: The inclusive start user address. * @end_addr: The exclusive end user address. * * Returns: The first VMA within the provided range, %NULL otherwise. Assumes * start_addr < end_addr. */ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr) { unsigned long index = start_addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, end_addr - 1); } EXPORT_SYMBOL(find_vma_intersection); /** * find_vma() - Find the VMA for a given address, or the next VMA. * @mm: The mm_struct to check * @addr: The address * * Returns: The VMA associated with addr, or the next VMA. * May return %NULL in the case of no VMA at addr or above. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { unsigned long index = addr; mmap_assert_locked(mm); return mt_find(&mm->mm_mt, &index, ULONG_MAX); } EXPORT_SYMBOL(find_vma); /** * find_vma_prev() - Find the VMA for a given address, or the next vma and * set %pprev to the previous VMA, if any. * @mm: The mm_struct to check * @addr: The address * @pprev: The pointer to set to the previous VMA * * Note that RCU lock is missing here since the external mmap_lock() is used * instead. * * Returns: The VMA associated with @addr, or the next vma. * May return %NULL in the case of no vma at addr or above. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; MA_STATE(mas, &mm->mm_mt, addr, addr); vma = mas_walk(&mas); *pprev = mas_prev(&mas, 0); if (!vma) vma = mas_next(&mas, ULONG_MAX); return vma; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (mlock_future_check(mm, vma->vm_flags, grow << PAGE_SHIFT)) return -ENOMEM; /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) /* * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ static int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; MA_STATE(mas, &mm->mm_mt, vma->vm_start, address - 1); if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = find_vma_intersection(mm, vma->vm_end, gap_addr); if (next && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } mas->last = address - 1; if (mas_preallocate(&mas, vma, GFP_KERNEL)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { mas_destroy(&mas); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * We only hold a shared mmap_lock lock here, so * we need to protect against concurrent vma * expansions. anon_vma_lock_write() doesn't * help here, as we don't guarantee that all * growable vmas in a mm share the same root * anon vma. So, we reuse mm->page_table_lock * to guard against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; /* Overwrite old entry in mtree. */ vma_mas_store(vma, &mas); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma(vma, vma->vm_flags); mas_destroy(&mas); return error; } #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. * mmap_lock held for writing. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; MA_STATE(mas, &mm->mm_mt, vma->vm_start, vma->vm_start); struct vm_area_struct *prev; int error = 0; if (!(vma->vm_flags & VM_GROWSDOWN)) return -EFAULT; address &= PAGE_MASK; if (address < mmap_min_addr || address < FIRST_USER_ADDRESS) return -EPERM; /* Enforce stack_guard_gap */ prev = mas_prev(&mas, 0); /* Check that both stack segments have the same anon_vma? */ if (prev) { if (!(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev) && (address - prev->vm_end < stack_guard_gap)) return -ENOMEM; } mas_set_range(&mas, address, vma->vm_end - 1); if (mas_preallocate(&mas, vma, GFP_KERNEL)) return -ENOMEM; /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) { mas_destroy(&mas); return -ENOMEM; } /* Lock the VMA before expanding to prevent concurrent page faults */ vma_start_write(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * We only hold a shared mmap_lock lock here, so * we need to protect against concurrent vma * expansions. anon_vma_lock_write() doesn't * help here, as we don't guarantee that all * growable vmas in a mm share the same root * anon vma. So, we reuse mm->page_table_lock * to guard against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; /* Overwrite old entry in mtree. */ vma_mas_store(vma, &mas); anon_vma_interval_tree_post_update_vma(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma(vma, vma->vm_flags); mas_destroy(&mas); return error; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; static int __init cmdline_parse_stack_guard_gap(char *p) { unsigned long val; char *endptr; val = simple_strtoul(p, &endptr, 10); if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); #ifdef CONFIG_STACK_GROWSUP int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; if (!prev) return NULL; if (expand_stack_locked(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack_locked(struct vm_area_struct *vma, unsigned long address) { if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) return -EINVAL; return expand_downwards(vma, address); } struct vm_area_struct *find_extend_vma_locked(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm, addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; start = vma->vm_start; if (expand_stack_locked(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif /* * ANDROID: Reintroduce find_extend_vma() as it's still used by some external * modules. It was removed in commit 8d7071af8907 ("mm: always expand the * stack with the mmap write lock held") * In the future, everyone should just move to use the correct function instead * of this old, legacy one. */ struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) { return find_extend_vma_locked(mm, addr); } EXPORT_SYMBOL_GPL(find_extend_vma); /* * IA64 has some horrid mapping rules: it can expand both up and down, * but with various special rules. * * We'll get rid of this architecture eventually, so the ugliness is * temporary. */ #ifdef CONFIG_IA64 static inline bool vma_expand_ok(struct vm_area_struct *vma, unsigned long addr) { return REGION_NUMBER(addr) == REGION_NUMBER(vma->vm_start) && REGION_OFFSET(addr) < RGN_MAP_LIMIT; } /* * IA64 stacks grow down, but there's a special register backing store * that can grow up. Only sequentially, though, so the new address must * match vm_end. */ static inline int vma_expand_up(struct vm_area_struct *vma, unsigned long addr) { if (!vma_expand_ok(vma, addr)) return -EFAULT; if (vma->vm_end != (addr & PAGE_MASK)) return -EFAULT; return expand_upwards(vma, addr); } static inline bool vma_expand_down(struct vm_area_struct *vma, unsigned long addr) { if (!vma_expand_ok(vma, addr)) return -EFAULT; return expand_downwards(vma, addr); } #elif defined(CONFIG_STACK_GROWSUP) #define vma_expand_up(vma,addr) expand_upwards(vma, addr) #define vma_expand_down(vma, addr) (-EFAULT) #else #define vma_expand_up(vma,addr) (-EFAULT) #define vma_expand_down(vma, addr) expand_downwards(vma, addr) #endif /* * expand_stack(): legacy interface for page faulting. Don't use unless * you have to. * * This is called with the mm locked for reading, drops the lock, takes * the lock for writing, tries to look up a vma again, expands it if * necessary, and downgrades the lock to reading again. * * If no vma is found or it can't be expanded, it returns NULL and has * dropped the lock. */ struct vm_area_struct *expand_stack(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; mmap_read_unlock(mm); if (mmap_write_lock_killable(mm)) return NULL; vma = find_vma_prev(mm, addr, &prev); if (vma && vma->vm_start <= addr) goto success; if (prev && !vma_expand_up(prev, addr)) { vma = prev; goto success; } if (vma && !vma_expand_down(vma, addr)) goto success; mmap_write_unlock(mm); return NULL; success: mmap_write_downgrade(mm); return vma; } /* * Ok - we have the memory areas we should free on a maple tree so release them, * and do the vma updates. * * Called with the mm semaphore held. */ static inline void remove_mt(struct mm_struct *mm, struct ma_state *mas) { unsigned long nr_accounted = 0; struct vm_area_struct *vma; /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); mas_for_each(mas, vma, ULONG_MAX) { long nrpages = vma_pages(vma); if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; vm_stat_account(mm, vma->vm_flags, -nrpages); remove_vma(vma, false); } vm_unacct_memory(nr_accounted); validate_mm(mm); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ static void unmap_region(struct mm_struct *mm, struct maple_tree *mt, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next, unsigned long start, unsigned long end, unsigned long start_t, unsigned long end_t, bool mm_wr_locked) { struct mmu_gather tlb; lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); unmap_vmas(&tlb, mt, vma, start, end, start_t, end_t, mm_wr_locked); free_pgtables(&tlb, mt, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING, start_t, mm_wr_locked); tlb_finish_mmu(&tlb); } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. */ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vm_area_struct *new; int err; validate_mm_mt(mm); vma_start_write(vma); if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) new->vm_end = addr; else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = vma_dup_policy(vma, new); if (err) goto out_free_vma; err = anon_vma_clone(new, vma); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); vma_start_write(vma); vma_start_write(new); if (new_below) err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); /* Success. */ if (!err) { split_pad_vma(vma, new, addr, new_below); return 0; } /* Avoid vm accounting in close() operation */ new->vm_start = new->vm_end; new->vm_pgoff = 0; /* Clean everything up if vma_adjust failed. */ if (new->vm_ops && new->vm_ops->close) new->vm_ops->close(new); if (new->vm_file) fput(new->vm_file); unlink_anon_vmas(new); out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: vm_area_free(new); validate_mm_mt(mm); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(mm, vma, addr, new_below); } /* * do_mas_align_munmap() - munmap the aligned region from @start to @end. * @mas: The maple_state, ideally set up to alter the correct tree location. * @vma: The starting vm_area_struct * @mm: The mm_struct * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head * @downgrade: Set to true to attempt a write downgrade of the mmap_sem * * If @downgrade is true, check return code for potential release of the lock. */ static int do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool downgrade) { struct vm_area_struct *prev, *next = NULL; struct maple_tree mt_detach; int count = 0; int error = -ENOMEM; unsigned long locked_vm = 0; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, mas->tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); mas->last = end - 1; /* * If we need to split any vma, do it now to save pain later. * * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially * unmapped vm_area_struct will remain in use: so lower split_vma * places tmp vma above, and higher split_vma places tmp vma below. */ /* Does it split the first one? */ if (start > vma->vm_start) { /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) goto map_count_exceeded; /* * mas_pause() is not needed since mas->index needs to be set * differently than vma->vm_end anyways. */ error = __split_vma(mm, vma, start, 0); if (error) goto start_split_failed; mas_set(mas, start); vma = mas_walk(mas); } prev = mas_prev(mas, 0); if (unlikely((!prev))) mas_set(mas, start); /* * Detach a range of VMAs from the mm. Using next as a temp variable as * it is always overwritten. */ mas_for_each(mas, next, end - 1) { /* Does it split the end? */ if (next->vm_end > end) { struct vm_area_struct *split; error = __split_vma(mm, next, end, 1); if (error) goto end_split_failed; mas_set(mas, end); split = mas_prev(mas, 0); vma_start_write(split); mas_set(&mas_detach, count); error = mas_store_gfp(&mas_detach, split, GFP_KERNEL); if (error) goto munmap_gather_failed; vma_mark_detached(split, true); if (split->vm_flags & VM_LOCKED) locked_vm += vma_pages(split); count++; if (vma == next) vma = split; break; } vma_start_write(next); mas_set(&mas_detach, count); error = mas_store_gfp(&mas_detach, next, GFP_KERNEL); if (error) goto munmap_gather_failed; vma_mark_detached(next, true); if (next->vm_flags & VM_LOCKED) locked_vm += vma_pages(next); count++; if (unlikely(uf)) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain split, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ error = userfaultfd_unmap_prep(next, start, end, uf); if (error) goto userfaultfd_error; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE BUG_ON(next->vm_start < start); BUG_ON(next->vm_start > end); #endif } if (mas->last >= end) next = mas_walk(mas); if (!next) next = mas_next(mas, ULONG_MAX); #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) /* Make sure no VMAs are about to be lost. */ { MA_STATE(test, &mt_detach, 0, 0); struct vm_area_struct *vma_mas, *vma_test; int test_count = 0; unsigned long s, e; mas_set_range(mas, start, end - 1); rcu_read_lock(); vma_test = mas_find(&test, count - 1); mas_for_each(mas, vma_mas, end - 1) { if (!test_count) s = vma_mas->vm_start; BUG_ON(vma_mas != vma_test); test_count++; if (test_count == count) e = vma_mas->vm_end; vma_test = mas_next(&test, count - 1); } rcu_read_unlock(); BUG_ON(count != test_count); } #endif /* Point of no return */ mas_set_range(mas, start, end - 1); if (mas_store_gfp(mas, NULL, GFP_KERNEL)) return -ENOMEM; mm->locked_vm -= locked_vm; mm->map_count -= count; /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or * VM_GROWSUP VMA. Such VMAs can change their size under * down_read(mmap_lock) and collide with the VMA we are about to unmap. */ if (downgrade) { if (next && (next->vm_flags & VM_GROWSDOWN)) downgrade = false; else if (prev && (prev->vm_flags & VM_GROWSUP)) downgrade = false; else mmap_write_downgrade(mm); } /* * We can free page tables without write-locking mmap_lock because VMAs * were isolated before we downgraded mmap_lock. */ unmap_region(mm, &mt_detach, vma, prev, next, start, end, 1, count, !downgrade); /* Statistics and freeing VMAs */ mas_set(&mas_detach, 0); remove_mt(mm, &mas_detach); __mt_destroy(&mt_detach); validate_mm(mm); return downgrade ? 1 : 0; userfaultfd_error: munmap_gather_failed: end_split_failed: __mt_destroy(&mt_detach); start_split_failed: map_count_exceeded: return error; } /* * do_mas_munmap() - munmap a given range. * @mas: The maple state * @mm: The mm_struct * @start: The start address to munmap * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @downgrade: set to true if the user wants to attempt to write_downgrade the * mmap_sem * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be * aligned and any arch_unmap work will be preformed. * * Returns: -EINVAL on failure, 1 on success and unlock, 0 otherwise. */ int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; end = start + PAGE_ALIGN(len); if (end == start) return -EINVAL; /* arch_unmap() might do unmaps itself. */ arch_unmap(mm, start, end); /* Find the first overlapping VMA */ vma = mas_find(mas, end - 1); if (!vma) return 0; return do_mas_align_munmap(mas, vma, mm, start, end, uf, downgrade); } /* do_munmap() - Wrapper function for non-maple tree aware do_munmap() calls. * @mm: The mm_struct * @start: The start address to munmap * @len: The length to be munmapped. * @uf: The userfaultfd list_head */ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { MA_STATE(mas, &mm->mm_mt, start, start); return do_mas_munmap(&mas, mm, start, len, uf, false); } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct vm_area_struct *next, *prev, *merge; pgoff_t pglen = len >> PAGE_SHIFT; unsigned long charged = 0; unsigned long end = addr + len; unsigned long merge_start = addr, merge_end = end; pgoff_t vm_pgoff; int error; MA_STATE(mas, &mm->mm_mt, addr, end - 1); /* Check against address space limit. */ if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* * MAP_FIXED may remove pages of mappings that intersects with * requested mapping. Account for the pages it would unmap. */ nr_pages = count_vma_pages_range(mm, addr, end); if (!may_expand_vm(mm, vm_flags, (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } /* Unmap any existing mapping in the area */ if (do_mas_munmap(&mas, mm, addr, len, uf, false)) return -ENOMEM; /* * Private writable mapping: check memory availability */ if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; } next = mas_next(&mas, ULONG_MAX); prev = mas_prev(&mas, 0); if (vm_flags & VM_SPECIAL) goto cannot_expand; /* Attempt to expand an old mapping */ /* Check next */ if (next) vma_start_write(next); if (next && next->vm_start == end && !vma_policy(next) && can_vma_merge_before(next, vm_flags, NULL, file, pgoff+pglen, NULL_VM_UFFD_CTX, NULL)) { merge_end = next->vm_end; vma = next; vm_pgoff = next->vm_pgoff - pglen; } /* Check prev */ if (prev) vma_start_write(prev); if (prev && prev->vm_end == addr && !vma_policy(prev) && (vma ? can_vma_merge_after(prev, vm_flags, vma->anon_vma, file, pgoff, vma->vm_userfaultfd_ctx, NULL) : can_vma_merge_after(prev, vm_flags, NULL, file, pgoff, NULL_VM_UFFD_CTX, NULL))) { merge_start = prev->vm_start; vma = prev; vm_pgoff = prev->vm_pgoff; } /* Actually expand, if possible */ if (vma && !vma_expand(&mas, vma, merge_start, merge_end, vm_pgoff, next)) { khugepaged_enter_vma(vma, vm_flags); goto expanded; } cannot_expand: if (prev) mas_next_range(&mas, ULONG_MAX); BUG_ON(mas.last < addr); BUG_ON(mas.index > end - 1); mas.index = addr; mas.last = end - 1; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } vma->vm_start = addr; vma->vm_end = end; vm_flags_init(vma, vm_flags); vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; if (file) { if (vm_flags & VM_SHARED) { error = mapping_map_writable(file->f_mapping); if (error) goto free_vma; } vma->vm_file = get_file(file); error = call_mmap(file, vma); if (error) goto unmap_and_free_vma; /* * Expansion is handled above, merging is handled below. * Drivers should not alter the address of the VMA. */ if (WARN_ON((addr != vma->vm_start))) { error = -EINVAL; goto close_and_free_vma; } mas_reset(&mas); /* * If vm_flags changed after call_mmap(), we should try merge * vma again as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (merge) { /* * ->mmap() can change vma->vm_file and fput * the original file. So fput the vma->vm_file * here or we would add an extra fput for file * and cause general protection fault * ultimately. */ fput(vma->vm_file); vm_area_free(vma); vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } else { vma_set_anonymous(vma); } /* Allow architectures to sanity-check the vm_flags */ if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) goto close_and_free_vma; else if (vma->vm_file) goto unmap_and_free_vma; else goto free_vma; } if (mas_preallocate(&mas, vma, GFP_KERNEL)) { error = -ENOMEM; if (file) goto close_and_free_vma; else if (vma->vm_file) goto unmap_and_free_vma; else goto free_vma; } /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); mas_store_prealloc(&mas, vma); mm->map_count++; if (vma->vm_file) { if (vma->vm_flags & VM_SHARED) mapping_allow_writable(vma->vm_file->f_mapping); flush_dcache_mmap_lock(vma->vm_file->f_mapping); vma_interval_tree_insert(vma, &vma->vm_file->f_mapping->i_mmap); flush_dcache_mmap_unlock(vma->vm_file->f_mapping); i_mmap_unlock_write(vma->vm_file->f_mapping); } /* * vma_merge() calls khugepaged_enter_vma() either, the below * call covers the non-merge case. */ khugepaged_enter_vma(vma, vma->vm_flags); /* Once vma denies write, undo our temporary denial count */ unmap_writable: if (file && vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); file = vma->vm_file; expanded: perf_event_mmap(vma); vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) vm_flags_clear(vma, VM_LOCKED_MASK); else mm->locked_vm += (len >> PAGE_SHIFT); } if (file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vm_flags_set(vma, VM_SOFTDIRTY); vma_set_page_prot(vma); trace_android_vh_mmap_region(vma, addr); validate_mm(mm); return addr; close_and_free_vma: if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); unmap_and_free_vma: fput(vma->vm_file); vma->vm_file = NULL; /* Undo any partial mapping done by a device driver. */ unmap_region(mm, mas.tree, vma, prev, next, vma->vm_start, vma->vm_end, vma->vm_end, vma->vm_end, true); if (file && (vm_flags & VM_SHARED)) mapping_unmap_writable(file->f_mapping); free_vma: vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); validate_mm(mm); return error; } static int __vm_munmap(unsigned long start, size_t len, bool downgrade) { int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); MA_STATE(mas, &mm->mm_mt, start, start + len); if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mas_munmap(&mas, mm, start, len, &uf, downgrade); /* * Returning 1 indicates mmap_lock is downgraded. * But 1 is not legal return value of vm_munmap() and munmap(), reset * it to 0 before return. */ if (ret == 1) { mmap_read_unlock(mm); ret = 0; } else mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); return ret; } int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); profile_munmap(addr); return __vm_munmap(addr, len, true); } /* * Emulation of deprecated remap_file_pages() syscall. */ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/mm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_write_lock_killable(mm)) return -EINTR; vma = vma_lookup(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; if (start + size > vma->vm_end) { VMA_ITERATOR(vmi, mm, vma->vm_end); struct vm_area_struct *next, *prev = vma; for_each_vma_range(vmi, next, start + size) { /* hole between vmas ? */ if (next->vm_start != prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; prev = next; } if (!next) goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; file = get_file(vma->vm_file); ret = do_mmap(vma->vm_file, start, size, prot, flags, pgoff, &populate, NULL); fput(file); out: mmap_write_unlock(mm); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } /* * brk_munmap() - Unmap a parital vma. * @mas: The maple tree state. * @vma: The vma to be modified * @newbrk: the start of the address to unmap * @oldbrk: The end of the address to unmap * @uf: The userfaultfd list_head * * Returns: 1 on success. * unmaps a partial VMA mapping. Does not handle alignment, downgrades lock if * possible. */ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma, unsigned long newbrk, unsigned long oldbrk, struct list_head *uf) { struct mm_struct *mm = vma->vm_mm; int ret; arch_unmap(mm, newbrk, oldbrk); ret = do_mas_align_munmap(mas, vma, mm, newbrk, oldbrk, uf, true); validate_mm_mt(mm); return ret; } /* * do_brk_flags() - Increase the brk vma if the flags match. * @mas: The maple tree state. * @addr: The start address * @len: The length of the increase * @vma: The vma, * @flags: The VMA Flags * * Extend the brk VMA from addr to addr + len. If the VMA is NULL or the flags * do not match then create a new anonymous VMA. Eventually we may be able to * do some brk-specific accounting here. */ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, unsigned long addr, unsigned long len, unsigned long flags) { struct mm_struct *mm = current->mm; validate_mm_mt(mm); /* * Check against address space limits by the changed size * Note: This happens *after* clearing old mappings in some code paths. */ flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; if (vma) vma_start_write(vma); /* * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ if (vma && vma->vm_end == addr && !vma_policy(vma) && can_vma_merge_after(vma, flags, NULL, NULL, addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) { mas_set_range(mas, vma->vm_start, addr + len - 1); if (mas_preallocate(mas, vma, GFP_KERNEL)) return -ENOMEM; /* Set flags first to implicitly lock the VMA before updates */ vm_flags_set(vma, VM_SOFTDIRTY); vma_adjust_trans_huge(vma, vma->vm_start, addr + len, 0); if (vma->anon_vma) { anon_vma_lock_write(vma->anon_vma); anon_vma_interval_tree_pre_update_vma(vma); } vma->vm_end = addr + len; mas_store_prealloc(mas, vma); if (vma->anon_vma) { anon_vma_interval_tree_post_update_vma(vma); anon_vma_unlock_write(vma->anon_vma); } khugepaged_enter_vma(vma, flags); goto out; } /* create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) goto vma_alloc_fail; vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = addr >> PAGE_SHIFT; vm_flags_init(vma, flags); vma->vm_page_prot = vm_get_page_prot(flags); vma_start_write(vma); mas_set_range(mas, vma->vm_start, addr + len - 1); if (mas_store_gfp(mas, vma, GFP_KERNEL)) goto mas_store_fail; mm->map_count++; out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vm_flags_set(vma, VM_SOFTDIRTY); validate_mm(mm); return 0; mas_store_fail: vm_area_free(vma); vma_alloc_fail: vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; unsigned long len; int ret; bool populate; LIST_HEAD(uf); MA_STATE(mas, &mm->mm_mt, addr, addr); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; if (mmap_write_lock_killable(mm)) return -EINTR; ret = check_brk_limits(addr, len); if (ret) goto limits_failed; ret = do_mas_munmap(&mas, mm, addr, len, &uf, 0); if (ret) goto munmap_failed; vma = mas_prev(&mas, 0); ret = do_brk_flags(&mas, vma, addr, len, flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; munmap_failed: limits_failed: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(vm_brk_flags); int vm_brk(unsigned long addr, unsigned long len) { return vm_brk_flags(addr, len, 0); } EXPORT_SYMBOL(vm_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; MA_STATE(mas, &mm->mm_mt, 0, 0); int count = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); mmap_read_lock(mm); arch_exit_mmap(mm); vma = mas_find(&mas, ULONG_MAX); if (!vma || unlikely(xa_is_zero(vma))) { /* Can happen if dup_mmap() received an OOM */ mmap_read_unlock(mm); mmap_write_lock(mm); goto destroy; } lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu_fullmm(&tlb, mm); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use ULONG_MAX here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, &mm->mm_mt, vma, 0, ULONG_MAX, vma->vm_end, ULONG_MAX, false); mmap_read_unlock(mm); /* * Set MMF_OOM_SKIP to hide this task from the oom killer/reaper * because the memory has been already freed. */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mt_clear_in_rcu(&mm->mm_mt); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING, vma->vm_end, true); tlb_finish_mmu(&tlb); /* * Walk the list again, actually closing and freeing it, with preemption * enabled, without holding any MM locks besides the unreachable * mmap_write_lock. */ do { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); remove_vma(vma, true); count++; cond_resched(); vma = mas_find(&mas, ULONG_MAX); } while (vma && likely(!xa_is_zero(vma))); BUG_ON(count != mm->map_count); trace_exit_mmap(mm); destroy: __mt_destroy(&mm->mm_mt); mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { unsigned long charged = vma_pages(vma); if (find_vma_intersection(mm, vma->vm_start, vma->vm_end)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap and in do_brk_flags. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } if (vma_link(mm, vma)) { vm_unacct_memory(charged); return -ENOMEM; } return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; bool faulted_in_anon_vma = true; validate_mm_mt(mm); /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } new_vma = find_vma_prev(mm, addr, &prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; } validate_mm_mt(mm); return new_vma; out_vma_link: if (new_vma->vm_ops && new_vma->vm_ops->close) new_vma->vm_ops->close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: validate_mm_mt(mm); return NULL; } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages); if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static int special_mapping_split(struct vm_area_struct *vma, unsigned long addr) { /* * Forbid splitting special mappings - kernel has expectations over * the number of pages in mapping. Together with VM_DONTEXPAND * the size of vma should stay the same over the special mapping's * lifetime. */ return -EINVAL; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, .may_split = special_mapping_split, }; static const struct vm_operations_struct legacy_special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; if (vma->vm_ops == &legacy_special_mapping_vmops) { pages = vma->vm_private_data; } else { struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; } for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; validate_mm_mt(mm); vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma->vm_start = addr; vma->vm_end = addr + len; vm_flags_init(vma, (vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY) & ~VM_LOCKED_MASK); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); validate_mm_mt(mm); return vma; out: vm_area_free(vma); validate_mm_mt(mm); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && (vma->vm_ops == &special_mapping_vmops || vma->vm_ops == &legacy_special_mapping_vmops); } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { struct vm_area_struct *vma = __install_special_mapping( mm, addr, len, vm_flags, (void *)pages, &legacy_special_mapping_vmops); return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; MA_STATE(mas, &mm->mm_mt, 0, 0); mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); /* * vma_start_write() does not have a complement in mm_drop_all_locks() * because vma_start_write() is always asymmetrical; it marks a VMA as * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ mas_for_each(&mas, vma, ULONG_MAX) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } mas_set(&mas, 0); mas_for_each(&mas, vma, ULONG_MAX) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } mas_set(&mas, 0); mas_for_each(&mas, vma, ULONG_MAX) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } mas_set(&mas, 0); mas_for_each(&mas, vma, ULONG_MAX) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; MA_STATE(mas, &mm->mm_mt, 0, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); mas_for_each(&mas, vma, ULONG_MAX) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * initialise the percpu counter for VM */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (0 < tmp && tmp < (1UL << 17)) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (0 < tmp && tmp < (1UL << 13)) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static struct notifier_block reserve_mem_nb = { .notifier_call = reserve_mem_notifier, }; static int __meminit init_reserve_notifier(void) { if (register_hotmemory_notifier(&reserve_mem_nb)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier); |
| 895 894 895 339 339 339 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic Timer-queue * * Manages a simple queue of timers, ordered by expiration time. * Uses rbtrees for quick list adds and expiration. * * NOTE: All of the following functions need to be serialized * to avoid races. No locking is done by this library code. */ #include <linux/bug.h> #include <linux/timerqueue.h> #include <linux/rbtree.h> #include <linux/export.h> #define __node_2_tq(_n) \ rb_entry((_n), struct timerqueue_node, node) static inline bool __timerqueue_less(struct rb_node *a, const struct rb_node *b) { return __node_2_tq(a)->expires < __node_2_tq(b)->expires; } /** * timerqueue_add - Adds timer to timerqueue. * * @head: head of timerqueue * @node: timer node to be added * * Adds the timer node to the timerqueue, sorted by the node's expires * value. Returns true if the newly added timer is the first expiring timer in * the queue. */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { /* Make sure we don't add nodes that are already added */ WARN_ON_ONCE(!RB_EMPTY_NODE(&node->node)); return rb_add_cached(&node->node, &head->rb_root, __timerqueue_less); } EXPORT_SYMBOL_GPL(timerqueue_add); /** * timerqueue_del - Removes a timer from the timerqueue. * * @head: head of timerqueue * @node: timer node to be removed * * Removes the timer node from the timerqueue. Returns true if the queue is * not empty after the remove. */ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) { WARN_ON_ONCE(RB_EMPTY_NODE(&node->node)); rb_erase_cached(&node->node, &head->rb_root); RB_CLEAR_NODE(&node->node); return !RB_EMPTY_ROOT(&head->rb_root.rb_root); } EXPORT_SYMBOL_GPL(timerqueue_del); /** * timerqueue_iterate_next - Returns the timer after the provided timer * * @node: Pointer to a timer. * * Provides the timer that is after the given node. This is used, when * necessary, to iterate through the list of timers in a timer list * without modifying the list. */ struct timerqueue_node *timerqueue_iterate_next(struct timerqueue_node *node) { struct rb_node *next; if (!node) return NULL; next = rb_next(&node->node); if (!next) return NULL; return container_of(next, struct timerqueue_node, node); } EXPORT_SYMBOL_GPL(timerqueue_iterate_next); |
| 4 4 4 4 4 4 4 4 4 6 2 2 2 2 2 4 6 6 6 4 4 4 4 6 6 6 4 9 9 4 2 2 4 2 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware vSockets Driver * * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. */ /* Implementation notes: * * - There are two kinds of sockets: those created by user action (such as * calling socket(2)) and those created by incoming connection request packets. * * - There are two "global" tables, one for bound sockets (sockets that have * specified an address that they are responsible for) and one for connected * sockets (sockets that have established a connection with another socket). * These tables are "global" in that all sockets on the system are placed * within them. - Note, though, that the bound table contains an extra entry * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in * that list. The bound table is used solely for lookup of sockets when packets * are received and that's not necessary for SOCK_DGRAM sockets since we create * a datagram handle for each and need not perform a lookup. Keeping SOCK_DGRAM * sockets out of the bound hash buckets will reduce the chance of collisions * when looking for SOCK_STREAM sockets and prevents us from having to check the * socket type in the hash table lookups. * * - Sockets created by user action will either be "client" sockets that * initiate a connection or "server" sockets that listen for connections; we do * not support simultaneous connects (two "client" sockets connecting). * * - "Server" sockets are referred to as listener sockets throughout this * implementation because they are in the TCP_LISTEN state. When a * connection request is received (the second kind of socket mentioned above), * we create a new socket and refer to it as a pending socket. These pending * sockets are placed on the pending connection list of the listener socket. * When future packets are received for the address the listener socket is * bound to, we check if the source of the packet is from one that has an * existing pending connection. If it does, we process the packet for the * pending socket. When that socket reaches the connected state, it is removed * from the listener socket's pending list and enqueued in the listener * socket's accept queue. Callers of accept(2) will accept connected sockets * from the listener socket's accept queue. If the socket cannot be accepted * for some reason then it is marked rejected. Once the connection is * accepted, it is owned by the user process and the responsibility for cleanup * falls with that user process. * * - It is possible that these pending sockets will never reach the connected * state; in fact, we may never receive another packet after the connection * request. Because of this, we must schedule a cleanup function to run in the * future, after some amount of time passes where a connection should have been * established. This function ensures that the socket is off all lists so it * cannot be retrieved, then drops all references to the socket so it is cleaned * up (sock_put() -> sk_free() -> our sk_destruct implementation). Note this * function will also cleanup rejected sockets, those that reach the connected * state but leave it before they have been accepted. * * - Lock ordering for pending or accept queue sockets is: * * lock_sock(listener); * lock_sock_nested(pending, SINGLE_DEPTH_NESTING); * * Using explicit nested locking keeps lockdep happy since normally only one * lock of a given class may be taken at a time. * * - Sockets created by user action will be cleaned up when the user process * calls close(2), causing our release implementation to be called. Our release * implementation will perform some cleanup then drop the last reference so our * sk_destruct implementation is invoked. Our sk_destruct implementation will * perform additional cleanup that's common for both types of sockets. * * - A socket's reference count is what ensures that the structure won't be * freed. Each entry in a list (such as the "global" bound and connected tables * and the listener socket's pending list and connected queue) ensures a * reference. When we defer work until process context and pass a socket as our * argument, we must ensure the reference count is increased to ensure the * socket isn't freed before the function is run; the deferred function will * then drop the reference. * * - sk->sk_state uses the TCP state constants because they are widely used by * other address families and exposed to userspace tools like ss(8): * * TCP_CLOSE - unconnected * TCP_SYN_SENT - connecting * TCP_ESTABLISHED - connected * TCP_CLOSING - disconnecting * TCP_LISTEN - listening */ #include <linux/compat.h> #include <linux/types.h> #include <linux/bitops.h> #include <linux/cred.h> #ifndef __GENKSYMS__ #include <linux/errqueue.h> #endif #include <linux/init.h> #include <linux/io.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/net.h> #include <linux/poll.h> #include <linux/random.h> #include <linux/skbuff.h> #include <linux/smp.h> #include <linux/socket.h> #include <linux/stddef.h> #include <linux/unistd.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> #include <net/af_vsock.h> #include <uapi/linux/vm_sockets.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); /* Protocol family. */ static struct proto vsock_proto = { .name = "AF_VSOCK", .owner = THIS_MODULE, .obj_size = sizeof(struct vsock_sock), }; /* The default peer timeout indicates how long we will wait for a peer response * to a control message. */ #define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) #define VSOCK_DEFAULT_BUFFER_SIZE (1024 * 256) #define VSOCK_DEFAULT_BUFFER_MAX_SIZE (1024 * 256) #define VSOCK_DEFAULT_BUFFER_MIN_SIZE 128 /* Transport used for host->guest communication */ static const struct vsock_transport *transport_h2g; /* Transport used for guest->host communication */ static const struct vsock_transport *transport_g2h; /* Transport used for DGRAM communication */ static const struct vsock_transport *transport_dgram; /* Transport used for local communication */ static const struct vsock_transport *transport_local; static DEFINE_MUTEX(vsock_register_mutex); /**** UTILS ****/ /* Each bound VSocket is stored in the bind hash table and each connected * VSocket is stored in the connected hash table. * * Unbound sockets are all put on the same list attached to the end of the hash * table (vsock_unbound_sockets). Bound sockets are added to the hash table in * the bucket that their local address hashes to (vsock_bound_sockets(addr) * represents the list that addr hashes to). * * Specifically, we initialize the vsock_bind_table array to a size of * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function * mods with VSOCK_HASH_SIZE to ensure this. */ #define MAX_PORT_RETRIES 24 #define VSOCK_HASH(addr) ((addr)->svm_port % VSOCK_HASH_SIZE) #define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)]) #define vsock_unbound_sockets (&vsock_bind_table[VSOCK_HASH_SIZE]) /* XXX This can probably be implemented in a better way. */ #define VSOCK_CONN_HASH(src, dst) \ (((src)->svm_cid ^ (dst)->svm_port) % VSOCK_HASH_SIZE) #define vsock_connected_sockets(src, dst) \ (&vsock_connected_table[VSOCK_CONN_HASH(src, dst)]) #define vsock_connected_sockets_vsk(vsk) \ vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr) struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; EXPORT_SYMBOL_GPL(vsock_bind_table); struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; EXPORT_SYMBOL_GPL(vsock_connected_table); DEFINE_SPINLOCK(vsock_table_lock); EXPORT_SYMBOL_GPL(vsock_table_lock); /* Autobind this socket to the local address if necessary. */ static int vsock_auto_bind(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); struct sockaddr_vm local_addr; if (vsock_addr_bound(&vsk->local_addr)) return 0; vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); return __vsock_bind(sk, &local_addr); } static void vsock_init_tables(void) { int i; for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++) INIT_LIST_HEAD(&vsock_bind_table[i]); for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) INIT_LIST_HEAD(&vsock_connected_table[i]); } static void __vsock_insert_bound(struct list_head *list, struct vsock_sock *vsk) { sock_hold(&vsk->sk); list_add(&vsk->bound_table, list); } static void __vsock_insert_connected(struct list_head *list, struct vsock_sock *vsk) { sock_hold(&vsk->sk); list_add(&vsk->connected_table, list); } static void __vsock_remove_bound(struct vsock_sock *vsk) { list_del_init(&vsk->bound_table); sock_put(&vsk->sk); } static void __vsock_remove_connected(struct vsock_sock *vsk) { list_del_init(&vsk->connected_table); sock_put(&vsk->sk); } static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) { if (vsock_addr_equals_addr(addr, &vsk->local_addr)) return sk_vsock(vsk); if (addr->svm_port == vsk->local_addr.svm_port && (vsk->local_addr.svm_cid == VMADDR_CID_ANY || addr->svm_cid == VMADDR_CID_ANY)) return sk_vsock(vsk); } return NULL; } static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst) { struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { if (vsock_addr_equals_addr(src, &vsk->remote_addr) && dst->svm_port == vsk->local_addr.svm_port) { return sk_vsock(vsk); } } return NULL; } static void vsock_insert_unbound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); __vsock_insert_bound(vsock_unbound_sockets, vsk); spin_unlock_bh(&vsock_table_lock); } void vsock_insert_connected(struct vsock_sock *vsk) { struct list_head *list = vsock_connected_sockets( &vsk->remote_addr, &vsk->local_addr); spin_lock_bh(&vsock_table_lock); __vsock_insert_connected(list, vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_insert_connected); void vsock_remove_bound(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); if (__vsock_in_bound_table(vsk)) __vsock_remove_bound(vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_remove_bound); void vsock_remove_connected(struct vsock_sock *vsk) { spin_lock_bh(&vsock_table_lock); if (__vsock_in_connected_table(vsk)) __vsock_remove_connected(vsk); spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_remove_connected); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) { struct sock *sk; spin_lock_bh(&vsock_table_lock); sk = __vsock_find_bound_socket(addr); if (sk) sock_hold(sk); spin_unlock_bh(&vsock_table_lock); return sk; } EXPORT_SYMBOL_GPL(vsock_find_bound_socket); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst) { struct sock *sk; spin_lock_bh(&vsock_table_lock); sk = __vsock_find_connected_socket(src, dst); if (sk) sock_hold(sk); spin_unlock_bh(&vsock_table_lock); return sk; } EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) { vsock_remove_bound(vsk); vsock_remove_connected(vsk); } EXPORT_SYMBOL_GPL(vsock_remove_sock); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)) { int i; spin_lock_bh(&vsock_table_lock); for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { struct vsock_sock *vsk; list_for_each_entry(vsk, &vsock_connected_table[i], connected_table) { if (vsk->transport != transport) continue; fn(sk_vsock(vsk)); } } spin_unlock_bh(&vsock_table_lock); } EXPORT_SYMBOL_GPL(vsock_for_each_connected_socket); void vsock_add_pending(struct sock *listener, struct sock *pending) { struct vsock_sock *vlistener; struct vsock_sock *vpending; vlistener = vsock_sk(listener); vpending = vsock_sk(pending); sock_hold(pending); sock_hold(listener); list_add_tail(&vpending->pending_links, &vlistener->pending_links); } EXPORT_SYMBOL_GPL(vsock_add_pending); void vsock_remove_pending(struct sock *listener, struct sock *pending) { struct vsock_sock *vpending = vsock_sk(pending); list_del_init(&vpending->pending_links); sock_put(listener); sock_put(pending); } EXPORT_SYMBOL_GPL(vsock_remove_pending); void vsock_enqueue_accept(struct sock *listener, struct sock *connected) { struct vsock_sock *vlistener; struct vsock_sock *vconnected; vlistener = vsock_sk(listener); vconnected = vsock_sk(connected); sock_hold(connected); sock_hold(listener); list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue); } EXPORT_SYMBOL_GPL(vsock_enqueue_accept); static bool vsock_use_local_transport(unsigned int remote_cid) { if (!transport_local) return false; if (remote_cid == VMADDR_CID_LOCAL) return true; if (transport_g2h) { return remote_cid == transport_g2h->get_local_cid(); } else { return remote_cid == VMADDR_CID_HOST; } } static void vsock_deassign_transport(struct vsock_sock *vsk) { if (!vsk->transport) return; vsk->transport->destruct(vsk); module_put(vsk->transport->module); vsk->transport = NULL; } /* Assign a transport to a socket and call the .init transport callback. * * Note: for connection oriented socket this must be called when vsk->remote_addr * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if * g2h is not loaded, will use local transport; * - remote CID <= VMADDR_CID_HOST or h2g is not loaded or remote flags field * includes VMADDR_FLAG_TO_HOST flag value, will use guest->host transport; * - remote CID > VMADDR_CID_HOST will use host->guest transport; */ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) { const struct vsock_transport *new_transport; struct sock *sk = sk_vsock(vsk); unsigned int remote_cid = vsk->remote_addr.svm_cid; __u8 remote_flags; int ret; /* If the packet is coming with the source and destination CIDs higher * than VMADDR_CID_HOST, then a vsock channel where all the packets are * forwarded to the host should be established. Then the host will * need to forward the packets to the guest. * * The flag is set on the (listen) receive path (psk is not NULL). On * the connect path the flag can be set by the user space application. */ if (psk && vsk->local_addr.svm_cid > VMADDR_CID_HOST && vsk->remote_addr.svm_cid > VMADDR_CID_HOST) vsk->remote_addr.svm_flags |= VMADDR_FLAG_TO_HOST; remote_flags = vsk->remote_addr.svm_flags; switch (sk->sk_type) { case SOCK_DGRAM: new_transport = transport_dgram; break; case SOCK_STREAM: case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g || (remote_flags & VMADDR_FLAG_TO_HOST)) new_transport = transport_g2h; else new_transport = transport_h2g; break; default: return -ESOCKTNOSUPPORT; } if (vsk->transport) { if (vsk->transport == new_transport) return 0; /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we * have already held the sock lock. In the other cases, this * function is called on a new socket which is not assigned to * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); } /* We increase the module refcnt to prevent the transport unloading * while there are open sockets assigned to it. */ if (!new_transport || !try_module_get(new_transport->module)) return -ENODEV; if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || !new_transport->seqpacket_allow(remote_cid)) { module_put(new_transport->module); return -ESOCKTNOSUPPORT; } } ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); return ret; } vsk->transport = new_transport; return 0; } EXPORT_SYMBOL_GPL(vsock_assign_transport); bool vsock_find_cid(unsigned int cid) { if (transport_g2h && cid == transport_g2h->get_local_cid()) return true; if (transport_h2g && cid == VMADDR_CID_HOST) return true; if (transport_local && cid == VMADDR_CID_LOCAL) return true; return false; } EXPORT_SYMBOL_GPL(vsock_find_cid); static struct sock *vsock_dequeue_accept(struct sock *listener) { struct vsock_sock *vlistener; struct vsock_sock *vconnected; vlistener = vsock_sk(listener); if (list_empty(&vlistener->accept_queue)) return NULL; vconnected = list_entry(vlistener->accept_queue.next, struct vsock_sock, accept_queue); list_del_init(&vconnected->accept_queue); sock_put(listener); /* The caller will need a reference on the connected socket so we let * it call sock_put(). */ return sk_vsock(vconnected); } static bool vsock_is_accept_queue_empty(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); return list_empty(&vsk->accept_queue); } static bool vsock_is_pending(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); return !list_empty(&vsk->pending_links); } static int vsock_send_shutdown(struct sock *sk, int mode) { struct vsock_sock *vsk = vsock_sk(sk); if (!vsk->transport) return -ENODEV; return vsk->transport->shutdown(vsk, mode); } static void vsock_pending_work(struct work_struct *work) { struct sock *sk; struct sock *listener; struct vsock_sock *vsk; bool cleanup; vsk = container_of(work, struct vsock_sock, pending_work.work); sk = sk_vsock(vsk); listener = vsk->listener; cleanup = true; lock_sock(listener); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); if (vsock_is_pending(sk)) { vsock_remove_pending(listener, sk); sk_acceptq_removed(listener); } else if (!vsk->rejected) { /* We are not on the pending list and accept() did not reject * us, so we must have been accepted by our user process. We * just need to drop our references to the sockets and be on * our way. */ cleanup = false; goto out; } /* We need to remove ourself from the global connected sockets list so * incoming packets can't find this socket, and to reduce the reference * count. */ vsock_remove_connected(vsk); sk->sk_state = TCP_CLOSE; out: release_sock(sk); release_sock(listener); if (cleanup) sock_put(sk); sock_put(sk); sock_put(listener); } /**** SOCKET OPERATIONS ****/ static int __vsock_bind_connectible(struct vsock_sock *vsk, struct sockaddr_vm *addr) { static u32 port; struct sockaddr_vm new_addr; if (!port) port = LAST_RESERVED_PORT + 1 + prandom_u32_max(U32_MAX - LAST_RESERVED_PORT); vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); if (addr->svm_port == VMADDR_PORT_ANY) { bool found = false; unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { if (port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; if (!__vsock_find_bound_socket(&new_addr)) { found = true; break; } } if (!found) return -EADDRNOTAVAIL; } else { /* If port is in reserved range, ensure caller * has necessary privileges. */ if (addr->svm_port <= LAST_RESERVED_PORT && !capable(CAP_NET_BIND_SERVICE)) { return -EACCES; } if (__vsock_find_bound_socket(&new_addr)) return -EADDRINUSE; } vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); /* Remove connection oriented sockets from the unbound list and add them * to the hash table for easy lookup by its address. The unbound list * is simply an extra entry at the end of the hash table, a trick used * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); return 0; } static int __vsock_bind_dgram(struct vsock_sock *vsk, struct sockaddr_vm *addr) { return vsk->transport->dgram_bind(vsk, addr); } static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) { struct vsock_sock *vsk = vsock_sk(sk); int retval; /* First ensure this socket isn't already bound. */ if (vsock_addr_bound(&vsk->local_addr)) return -EINVAL; /* Now bind to the provided address or select appropriate values if * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY). Note that * like AF_INET prevents binding to a non-local IP address (in most * cases), we only allow binding to a local CID. */ if (addr->svm_cid != VMADDR_CID_ANY && !vsock_find_cid(addr->svm_cid)) return -EADDRNOTAVAIL; switch (sk->sk_socket->type) { case SOCK_STREAM: case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; case SOCK_DGRAM: retval = __vsock_bind_dgram(vsk, addr); break; default: retval = -EINVAL; break; } return retval; } static void vsock_connect_timeout(struct work_struct *work); static struct sock *__vsock_create(struct net *net, struct socket *sock, struct sock *parent, gfp_t priority, unsigned short type, int kern) { struct sock *sk; struct vsock_sock *psk; struct vsock_sock *vsk; sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto, kern); if (!sk) return NULL; sock_init_data(sock, sk); /* sk->sk_type is normally set in sock_init_data, but only if sock is * non-NULL. We make sure that our sockets always have a type by * setting it here if needed. */ if (!sock) sk->sk_type = type; vsk = vsock_sk(sk); vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); sk->sk_destruct = vsock_sk_destruct; sk->sk_backlog_rcv = vsock_queue_rcv_skb; sock_reset_flag(sk, SOCK_DONE); INIT_LIST_HEAD(&vsk->bound_table); INIT_LIST_HEAD(&vsk->connected_table); vsk->listener = NULL; INIT_LIST_HEAD(&vsk->pending_links); INIT_LIST_HEAD(&vsk->accept_queue); vsk->rejected = false; vsk->sent_request = false; vsk->ignore_connecting_rst = false; vsk->peer_shutdown = 0; INIT_DELAYED_WORK(&vsk->connect_work, vsock_connect_timeout); INIT_DELAYED_WORK(&vsk->pending_work, vsock_pending_work); psk = parent ? vsock_sk(parent) : NULL; if (parent) { vsk->trusted = psk->trusted; vsk->owner = get_cred(psk->owner); vsk->connect_timeout = psk->connect_timeout; vsk->buffer_size = psk->buffer_size; vsk->buffer_min_size = psk->buffer_min_size; vsk->buffer_max_size = psk->buffer_max_size; security_sk_clone(parent, sk); } else { vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE; vsk->buffer_min_size = VSOCK_DEFAULT_BUFFER_MIN_SIZE; vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE; } return sk; } static bool sock_type_connectible(u16 type) { return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); } static void __vsock_release(struct sock *sk, int level) { if (sk) { struct sock *pending; struct vsock_sock *vsk; vsk = vsock_sk(sk); pending = NULL; /* Compiler warning. */ /* When "level" is SINGLE_DEPTH_NESTING, use the nested * version to avoid the warning "possible recursive locking * detected". When "level" is 0, lock_sock_nested(sk, level) * is the same as lock_sock(sk). */ lock_sock_nested(sk, level); if (vsk->transport) vsk->transport->release(vsk); else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); sk->sk_shutdown = SHUTDOWN_MASK; skb_queue_purge(&sk->sk_receive_queue); /* Clean up any sockets that never were accepted. */ while ((pending = vsock_dequeue_accept(sk)) != NULL) { __vsock_release(pending, SINGLE_DEPTH_NESTING); sock_put(pending); } release_sock(sk); sock_put(sk); } } static void vsock_sk_destruct(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); vsock_deassign_transport(vsk); /* When clearing these addresses, there's no need to set the family and * possibly register the address family with the kernel. */ vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); put_cred(vsk->owner); } static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; err = sock_queue_rcv_skb(sk, skb); if (err) kfree_skb(skb); return err; } struct sock *vsock_create_connected(struct sock *parent) { return __vsock_create(sock_net(parent), NULL, parent, GFP_KERNEL, parent->sk_type, 0); } EXPORT_SYMBOL_GPL(vsock_create_connected); s64 vsock_stream_has_data(struct vsock_sock *vsk) { return vsk->transport->stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_data); static s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); if (sk->sk_type == SOCK_SEQPACKET) return vsk->transport->seqpacket_has_data(vsk); else return vsock_stream_has_data(vsk); } s64 vsock_stream_has_space(struct vsock_sock *vsk) { return vsk->transport->stream_has_space(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_space); void vsock_data_ready(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); if (vsock_stream_has_data(vsk) >= sk->sk_rcvlowat || sock_flag(sk, SOCK_DONE)) sk->sk_data_ready(sk); } EXPORT_SYMBOL_GPL(vsock_data_ready); static int vsock_release(struct socket *sock) { __vsock_release(sock->sk, 0); sock->sk = NULL; sock->state = SS_FREE; return 0; } static int vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { int err; struct sock *sk; struct sockaddr_vm *vm_addr; sk = sock->sk; if (vsock_addr_cast(addr, addr_len, &vm_addr) != 0) return -EINVAL; lock_sock(sk); err = __vsock_bind(sk, vm_addr); release_sock(sk); return err; } static int vsock_getname(struct socket *sock, struct sockaddr *addr, int peer) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *vm_addr; sk = sock->sk; vsk = vsock_sk(sk); err = 0; lock_sock(sk); if (peer) { if (sock->state != SS_CONNECTED) { err = -ENOTCONN; goto out; } vm_addr = &vsk->remote_addr; } else { vm_addr = &vsk->local_addr; } if (!vm_addr) { err = -EINVAL; goto out; } /* sys_getsockname() and sys_getpeername() pass us a * MAX_SOCK_ADDR-sized buffer and don't set addr_len. Unfortunately * that macro is defined in socket.c instead of .h, so we hardcode its * value here. */ BUILD_BUG_ON(sizeof(*vm_addr) > 128); memcpy(addr, vm_addr, sizeof(*vm_addr)); err = sizeof(*vm_addr); out: release_sock(sk); return err; } static int vsock_shutdown(struct socket *sock, int mode) { int err; struct sock *sk; /* User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode * here like the other address families do. Note also that the * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3), * which is what we want. */ mode++; if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; /* If this is a connection oriented socket and it is not connected then * bail out immediately. If it is a DGRAM socket then we must first * kick the socket so that it wakes up from any sleeping calls, for * example recv(), and then afterwards return the error. */ sk = sock->sk; lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; err = 0; } /* Receive and send shutdowns are treated alike. */ mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN); if (mode) { sk->sk_shutdown |= mode; sk->sk_state_change(sk); if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } } out: release_sock(sk); return err; } static __poll_t vsock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk; __poll_t mask; struct vsock_sock *vsk; sk = sock->sk; vsk = vsock_sk(sk); poll_wait(file, sk_sleep(sk), wait); mask = 0; if (sk->sk_err) /* Signify that there has been an error on this socket. */ mask |= EPOLLERR; /* INET sockets treat local write shutdown and peer write shutdown as a * case of EPOLLHUP set. */ if ((sk->sk_shutdown == SHUTDOWN_MASK) || ((sk->sk_shutdown & SEND_SHUTDOWN) && (vsk->peer_shutdown & SEND_SHUTDOWN))) { mask |= EPOLLHUP; } if (sk->sk_shutdown & RCV_SHUTDOWN || vsk->peer_shutdown & SEND_SHUTDOWN) { mask |= EPOLLRDHUP; } if (sock->type == SOCK_DGRAM) { /* For datagram sockets we can read if there is something in * the queue and write as long as the socket isn't shutdown for * sending. */ if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { mask |= EPOLLIN | EPOLLRDNORM; } if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; lock_sock(sk); transport = vsk->transport; /* Listening sockets that have connections in their accept * queue can be read. */ if (sk->sk_state == TCP_LISTEN && !vsock_is_accept_queue_empty(sk)) mask |= EPOLLIN | EPOLLRDNORM; /* If there is something in the queue then we can read. */ if (transport && transport->stream_is_active(vsk) && !(sk->sk_shutdown & RCV_SHUTDOWN)) { bool data_ready_now = false; int target = sock_rcvlowat(sk, 0, INT_MAX); int ret = transport->notify_poll_in( vsk, target, &data_ready_now); if (ret < 0) { mask |= EPOLLERR; } else { if (data_ready_now) mask |= EPOLLIN | EPOLLRDNORM; } } /* Sockets whose connections have been closed, reset, or * terminated should also be considered read, and we check the * shutdown flag for that. */ if (sk->sk_shutdown & RCV_SHUTDOWN || vsk->peer_shutdown & SEND_SHUTDOWN) { mask |= EPOLLIN | EPOLLRDNORM; } /* Connected sockets that can produce data can be written. */ if (transport && sk->sk_state == TCP_ESTABLISHED) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { bool space_avail_now = false; int ret = transport->notify_poll_out( vsk, 1, &space_avail_now); if (ret < 0) { mask |= EPOLLERR; } else { if (space_avail_now) /* Remove EPOLLWRBAND since INET * sockets are not setting it. */ mask |= EPOLLOUT | EPOLLWRNORM; } } } /* Simulate INET socket poll behaviors, which sets * EPOLLOUT|EPOLLWRNORM when peer is closed and nothing to read, * but local send is not shutdown. */ if (sk->sk_state == TCP_CLOSE || sk->sk_state == TCP_CLOSING) { if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM; } release_sock(sk); } return mask; } static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; const struct vsock_transport *transport; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* For now, MSG_DONTWAIT is always assumed... */ err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); transport = vsk->transport; err = vsock_auto_bind(vsk); if (err) goto out; /* If the provided message contains an address, use that. Otherwise * fall back on the socket's remote handle (if it has been connected). */ if (msg->msg_name && vsock_addr_cast(msg->msg_name, msg->msg_namelen, &remote_addr) == 0) { /* Ensure this address is of the right type and is a valid * destination. */ if (remote_addr->svm_cid == VMADDR_CID_ANY) remote_addr->svm_cid = transport->get_local_cid(); if (!vsock_addr_bound(remote_addr)) { err = -EINVAL; goto out; } } else if (sock->state == SS_CONNECTED) { remote_addr = &vsk->remote_addr; if (remote_addr->svm_cid == VMADDR_CID_ANY) remote_addr->svm_cid = transport->get_local_cid(); /* XXX Should connect() or this function ensure remote_addr is * bound? */ if (!vsock_addr_bound(&vsk->remote_addr)) { err = -EINVAL; goto out; } } else { err = -EINVAL; goto out; } if (!transport->dgram_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; } err = transport->dgram_enqueue(vsk, remote_addr, msg, len); out: release_sock(sk); return err; } static int vsock_dgram_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { int err; struct sock *sk; struct vsock_sock *vsk; struct sockaddr_vm *remote_addr; sk = sock->sk; vsk = vsock_sk(sk); err = vsock_addr_cast(addr, addr_len, &remote_addr); if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) { lock_sock(sk); vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); sock->state = SS_UNCONNECTED; release_sock(sk); return 0; } else if (err != 0) return -EINVAL; lock_sock(sk); err = vsock_auto_bind(vsk); if (err) goto out; if (!vsk->transport->dgram_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -EINVAL; goto out; } memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); sock->state = SS_CONNECTED; out: release_sock(sk); return err; } static int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct vsock_sock *vsk = vsock_sk(sock->sk); return vsk->transport->dgram_dequeue(vsk, msg, len, flags); } static const struct proto_ops vsock_dgram_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = vsock_shutdown, .sendmsg = vsock_dgram_sendmsg, .recvmsg = vsock_dgram_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static int vsock_transport_cancel_pkt(struct vsock_sock *vsk) { const struct vsock_transport *transport = vsk->transport; if (!transport || !transport->cancel_pkt) return -EOPNOTSUPP; return transport->cancel_pkt(vsk); } static void vsock_connect_timeout(struct work_struct *work) { struct sock *sk; struct vsock_sock *vsk; vsk = container_of(work, struct vsock_sock, connect_work.work); sk = sk_vsock(vsk); lock_sock(sk); if (sk->sk_state == TCP_SYN_SENT && (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_socket->state = SS_UNCONNECTED; sk->sk_err = ETIMEDOUT; sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); sock_put(sk); } static int vsock_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { int err; struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; struct sockaddr_vm *remote_addr; long timeout; DEFINE_WAIT(wait); err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); /* XXX AF_UNSPEC should make us disconnect like AF_INET. */ switch (sock->state) { case SS_CONNECTED: err = -EISCONN; goto out; case SS_DISCONNECTING: err = -EINVAL; goto out; case SS_CONNECTING: /* This continues on so we can move sock into the SS_CONNECTED * state once the connection has completed (at which point err * will be set to zero also). Otherwise, we will either wait * for the connection or return -EALREADY should this be a * non-blocking call. */ err = -EALREADY; if (flags & O_NONBLOCK) goto out; break; default: if ((sk->sk_state == TCP_LISTEN) || vsock_addr_cast(addr, addr_len, &remote_addr) != 0) { err = -EINVAL; goto out; } /* Set the remote address that we are connecting to. */ memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); err = vsock_assign_transport(vsk, NULL); if (err) goto out; transport = vsk->transport; /* The hypervisor and well-known contexts do not have socket * endpoints. */ if (!transport || !transport->stream_allow(remote_addr->svm_cid, remote_addr->svm_port)) { err = -ENETUNREACH; goto out; } err = vsock_auto_bind(vsk); if (err) goto out; sk->sk_state = TCP_SYN_SENT; err = transport->connect(vsk); if (err < 0) goto out; /* Mark sock as connecting and set the error code to in * progress in case this is a non-blocking connect. */ sock->state = SS_CONNECTING; err = -EINPROGRESS; } /* The receive path will handle all communication until we are able to * enter the connected state. Here we wait for the connection to be * completed or a notification of an error. */ timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection * attempt, in case the peer doesn't respond in a * timely manner. We hold on to the socket until the * timeout fires. */ sock_hold(sk); /* If the timeout function is already scheduled, * reschedule it, then ungrab the socket refcount to * keep it balanced. */ if (mod_delayed_work(system_wq, &vsk->connect_work, timeout)) sock_put(sk); /* Skip ahead to preserve error code set above. */ goto out_wait; } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); vsock_remove_connected(vsk); goto out_wait; } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } if (sk->sk_err) { err = -sk->sk_err; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; } else { err = 0; } out_wait: finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; } static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *listener; int err; struct sock *connected; struct vsock_sock *vconnected; long timeout; DEFINE_WAIT(wait); err = 0; listener = sock->sk; lock_sock(listener); if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } if (listener->sk_state != TCP_LISTEN) { err = -EINVAL; goto out; } /* Wait for children sockets to appear; these are the new sockets * created upon connection establishment. */ timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK); prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); while ((connected = vsock_dequeue_accept(listener)) == NULL && listener->sk_err == 0) { release_sock(listener); timeout = schedule_timeout(timeout); finish_wait(sk_sleep(listener), &wait); lock_sock(listener); if (signal_pending(current)) { err = sock_intr_errno(timeout); goto out; } else if (timeout == 0) { err = -EAGAIN; goto out; } prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(listener), &wait); if (listener->sk_err) err = -listener->sk_err; if (connected) { sk_acceptq_removed(listener); lock_sock_nested(connected, SINGLE_DEPTH_NESTING); vconnected = vsock_sk(connected); /* If the listener socket has received an error, then we should * reject this socket and return. Note that we simply mark the * socket rejected, drop our reference, and let the cleanup * function handle the cleanup; the fact that we found it in * the listener's accept queue guarantees that the cleanup * function hasn't run yet. */ if (err) { vconnected->rejected = true; } else { newsock->state = SS_CONNECTED; sock_graft(connected, newsock); } release_sock(connected); sock_put(connected); } out: release_sock(listener); return err; } static int vsock_listen(struct socket *sock, int backlog) { int err; struct sock *sk; struct vsock_sock *vsk; sk = sock->sk; lock_sock(sk); if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } if (sock->state != SS_UNCONNECTED) { err = -EINVAL; goto out; } vsk = vsock_sk(sk); if (!vsock_addr_bound(&vsk->local_addr)) { err = -EINVAL; goto out; } sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; err = 0; out: release_sock(sk); return err; } static void vsock_update_buffer_size(struct vsock_sock *vsk, const struct vsock_transport *transport, u64 val) { if (val > vsk->buffer_max_size) val = vsk->buffer_max_size; if (val < vsk->buffer_min_size) val = vsk->buffer_min_size; if (val != vsk->buffer_size && transport && transport->notify_buffer_size) transport->notify_buffer_size(vsk, &val); vsk->buffer_size = val; } static int vsock_connectible_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { int err; struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; u64 val; if (level != AF_VSOCK) return -ENOPROTOOPT; #define COPY_IN(_v) \ do { \ if (optlen < sizeof(_v)) { \ err = -EINVAL; \ goto exit; \ } \ if (copy_from_sockptr(&_v, optval, sizeof(_v)) != 0) { \ err = -EFAULT; \ goto exit; \ } \ } while (0) err = 0; sk = sock->sk; vsk = vsock_sk(sk); lock_sock(sk); transport = vsk->transport; switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: COPY_IN(val); vsock_update_buffer_size(vsk, transport, val); break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: COPY_IN(val); vsk->buffer_max_size = val; vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: COPY_IN(val); vsk->buffer_min_size = val; vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { struct __kernel_sock_timeval tv; err = sock_copy_user_timeval(&tv, optval, optlen, optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); if (err) break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; } else { err = -ERANGE; } break; } default: err = -ENOPROTOOPT; break; } #undef COPY_IN exit: release_sock(sk); return err; } static int vsock_connectible_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct vsock_sock *vsk = vsock_sk(sk); union { u64 val64; struct old_timeval32 tm32; struct __kernel_old_timeval tm; struct __kernel_sock_timeval stm; } v; int lv = sizeof(v.val64); int len; if (level != AF_VSOCK) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; memset(&v, 0, sizeof(v)); switch (optname) { case SO_VM_SOCKETS_BUFFER_SIZE: v.val64 = vsk->buffer_size; break; case SO_VM_SOCKETS_BUFFER_MAX_SIZE: v.val64 = vsk->buffer_max_size; break; case SO_VM_SOCKETS_BUFFER_MIN_SIZE: v.val64 = vsk->buffer_min_size; break; case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: lv = sock_get_timeout(vsk->connect_timeout, &v, optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; default: return -ENOPROTOOPT; } if (len < lv) return -EINVAL; if (len > lv) len = lv; if (copy_to_user(optval, &v, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; ssize_t total_written; long timeout; int err; struct vsock_transport_send_notify_data send_data; DEFINE_WAIT_FUNC(wait, woken_wake_function); sk = sock->sk; vsk = vsock_sk(sk); total_written = 0; err = 0; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; lock_sock(sk); transport = vsk->transport; /* Callers should not provide a destination with connection oriented * sockets. */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; } /* Send data only if both sides are not shutdown in the direction. */ if (sk->sk_shutdown & SEND_SHUTDOWN || vsk->peer_shutdown & RCV_SHUTDOWN) { err = -EPIPE; goto out; } if (!transport || sk->sk_state != TCP_ESTABLISHED || !vsock_addr_bound(&vsk->local_addr)) { err = -ENOTCONN; goto out; } if (!vsock_addr_bound(&vsk->remote_addr)) { err = -EDESTADDRREQ; goto out; } /* Wait for room in the produce queue to enqueue our user's data. */ timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = transport->notify_send_init(vsk, &send_data); if (err < 0) goto out; while (total_written < len) { ssize_t written; add_wait_queue(sk_sleep(sk), &wait); while (vsock_stream_has_space(vsk) == 0 && sk->sk_err == 0 && !(sk->sk_shutdown & SEND_SHUTDOWN) && !(vsk->peer_shutdown & RCV_SHUTDOWN)) { /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } err = transport->notify_send_pre_block(vsk, &send_data); if (err < 0) { remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } release_sock(sk); timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } else if (timeout == 0) { err = -EAGAIN; remove_wait_queue(sk_sleep(sk), &wait); goto out_err; } } remove_wait_queue(sk_sleep(sk), &wait); /* These checks occur both as part of and after the loop * conditional since we need to check before and after * sleeping. */ if (sk->sk_err) { err = -sk->sk_err; goto out_err; } else if ((sk->sk_shutdown & SEND_SHUTDOWN) || (vsk->peer_shutdown & RCV_SHUTDOWN)) { err = -EPIPE; goto out_err; } err = transport->notify_send_pre_enqueue(vsk, &send_data); if (err < 0) goto out_err; /* Note that enqueue will only write as many bytes as are free * in the produce queue, so we don't need to ensure len is * smaller than the queue size. It is the caller's * responsibility to check how many bytes we were able to send. */ if (sk->sk_type == SOCK_SEQPACKET) { written = transport->seqpacket_enqueue(vsk, msg, len - total_written); } else { written = transport->stream_enqueue(vsk, msg, len - total_written); } if (written < 0) { err = -ENOMEM; goto out_err; } total_written += written; err = transport->notify_send_post_enqueue( vsk, written, &send_data); if (err < 0) goto out_err; } out_err: if (total_written > 0) { /* Return number of written bytes only if: * 1) SOCK_STREAM socket. * 2) SOCK_SEQPACKET socket when whole buffer is sent. */ if (sk->sk_type == SOCK_STREAM || total_written == len) err = total_written; } out: release_sock(sk); return err; } static int vsock_connectible_wait_data(struct sock *sk, struct wait_queue_entry *wait, long timeout, struct vsock_transport_recv_notify_data *recv_data, size_t target) { const struct vsock_transport *transport; struct vsock_sock *vsk; s64 data; int err; vsk = vsock_sk(sk); err = 0; transport = vsk->transport; while (1) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); data = vsock_connectible_has_data(vsk); if (data != 0) break; if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) || (vsk->peer_shutdown & SEND_SHUTDOWN)) { break; } /* Don't wait for non-blocking sockets. */ if (timeout == 0) { err = -EAGAIN; break; } if (recv_data) { err = transport->notify_recv_pre_block(vsk, target, recv_data); if (err < 0) break; } release_sock(sk); timeout = schedule_timeout(timeout); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); break; } else if (timeout == 0) { err = -EAGAIN; break; } } finish_wait(sk_sleep(sk), wait); if (err) return err; /* Internal transport error when checking for available * data. XXX This should be changed to a connection * reset in a later change. */ if (data < 0) return -ENOMEM; return data; } static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { struct vsock_transport_recv_notify_data recv_data; const struct vsock_transport *transport; struct vsock_sock *vsk; ssize_t copied; size_t target; long timeout; int err; DEFINE_WAIT(wait); vsk = vsock_sk(sk); transport = vsk->transport; /* We must not copy less than target bytes into the user's buffer * before returning successfully, so we wait for the consume queue to * have that much data to consume before dequeueing. Note that this * makes it impossible to handle cases where target is greater than the * queue size. */ target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); if (target >= transport->stream_rcvhiwat(vsk)) { err = -ENOMEM; goto out; } timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); copied = 0; err = transport->notify_recv_init(vsk, target, &recv_data); if (err < 0) goto out; while (1) { ssize_t read; err = vsock_connectible_wait_data(sk, &wait, timeout, &recv_data, target); if (err <= 0) break; err = transport->notify_recv_pre_dequeue(vsk, target, &recv_data); if (err < 0) break; read = transport->stream_dequeue(vsk, msg, len - copied, flags); if (read < 0) { err = -ENOMEM; break; } copied += read; err = transport->notify_recv_post_dequeue(vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) goto out; if (read >= target || flags & MSG_PEEK) break; target -= read; } if (sk->sk_err) err = -sk->sk_err; else if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; if (copied > 0) err = copied; out: return err; } static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags) { const struct vsock_transport *transport; struct vsock_sock *vsk; ssize_t msg_len; long timeout; int err = 0; DEFINE_WAIT(wait); vsk = vsock_sk(sk); transport = vsk->transport; timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); if (err <= 0) goto out; msg_len = transport->seqpacket_dequeue(vsk, msg, flags); if (msg_len < 0) { err = -ENOMEM; goto out; } if (sk->sk_err) { err = -sk->sk_err; } else if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; } else { /* User sets MSG_TRUNC, so return real length of * packet. */ if (flags & MSG_TRUNC) err = msg_len; else err = len - msg_data_left(msg); /* Always set MSG_TRUNC if real length of packet is * bigger than user's buffer. */ if (msg_len > len) msg->msg_flags |= MSG_TRUNC; } out: return err; } static int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; int err; sk = sock->sk; if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_VSOCK, VSOCK_RECVERR); vsk = vsock_sk(sk); err = 0; lock_sock(sk); transport = vsk->transport; if (!transport || sk->sk_state != TCP_ESTABLISHED) { /* Recvmsg is supposed to return 0 if a peer performs an * orderly shutdown. Differentiate between that case and when a * peer has not connected or a local shutdown occurred with the * SOCK_DONE flag. */ if (sock_flag(sk, SOCK_DONE)) err = 0; else err = -ENOTCONN; goto out; } if (flags & MSG_OOB) { err = -EOPNOTSUPP; goto out; } /* We don't check peer_shutdown flag here since peer may actually shut * down, but there can be data in the queue that a local socket can * receive. */ if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; goto out; } /* It is valid on Linux to pass in a zero-length receive buffer. This * is not an error. We may as well bail out now. */ if (!len) { err = 0; goto out; } if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); return err; } static int vsock_set_rcvlowat(struct sock *sk, int val) { const struct vsock_transport *transport; struct vsock_sock *vsk; vsk = vsock_sk(sk); if (val > vsk->buffer_size) return -EINVAL; transport = vsk->transport; if (transport && transport->set_rcvlowat) return transport->set_rcvlowat(vsk, val); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); return 0; } static const struct proto_ops vsock_stream_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = sock_no_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, .getsockopt = vsock_connectible_getsockopt, .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, .set_rcvlowat = vsock_set_rcvlowat, }; static const struct proto_ops vsock_seqpacket_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, .ioctl = sock_no_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, .getsockopt = vsock_connectible_getsockopt, .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static int vsock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct vsock_sock *vsk; struct sock *sk; int ret; if (!sock) return -EINVAL; if (protocol && protocol != PF_VSOCK) return -EPROTONOSUPPORT; switch (sock->type) { case SOCK_DGRAM: sock->ops = &vsock_dgram_ops; break; case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; case SOCK_SEQPACKET: sock->ops = &vsock_seqpacket_ops; break; default: return -ESOCKTNOSUPPORT; } sock->state = SS_UNCONNECTED; sk = __vsock_create(net, sock, NULL, GFP_KERNEL, 0, kern); if (!sk) return -ENOMEM; vsk = vsock_sk(sk); if (sock->type == SOCK_DGRAM) { ret = vsock_assign_transport(vsk, NULL); if (ret < 0) { sock_put(sk); return ret; } } vsock_insert_unbound(vsk); return 0; } static const struct net_proto_family vsock_family_ops = { .family = AF_VSOCK, .create = vsock_create, .owner = THIS_MODULE, }; static long vsock_dev_do_ioctl(struct file *filp, unsigned int cmd, void __user *ptr) { u32 __user *p = ptr; u32 cid = VMADDR_CID_ANY; int retval = 0; switch (cmd) { case IOCTL_VM_SOCKETS_GET_LOCAL_CID: /* To be compatible with the VMCI behavior, we prioritize the * guest CID instead of well-know host CID (VMADDR_CID_HOST). */ if (transport_g2h) cid = transport_g2h->get_local_cid(); else if (transport_h2g) cid = transport_h2g->get_local_cid(); if (put_user(cid, p) != 0) retval = -EFAULT; break; default: retval = -ENOIOCTLCMD; } return retval; } static long vsock_dev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return vsock_dev_do_ioctl(filp, cmd, (void __user *)arg); } #ifdef CONFIG_COMPAT static long vsock_dev_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return vsock_dev_do_ioctl(filp, cmd, compat_ptr(arg)); } #endif static const struct file_operations vsock_device_ops = { .owner = THIS_MODULE, .unlocked_ioctl = vsock_dev_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = vsock_dev_compat_ioctl, #endif .open = nonseekable_open, }; static struct miscdevice vsock_device = { .name = "vsock", .fops = &vsock_device_ops, }; static int __init vsock_init(void) { int err = 0; vsock_init_tables(); vsock_proto.owner = THIS_MODULE; vsock_device.minor = MISC_DYNAMIC_MINOR; err = misc_register(&vsock_device); if (err) { pr_err("Failed to register misc device\n"); goto err_reset_transport; } err = proto_register(&vsock_proto, 1); /* we want our slab */ if (err) { pr_err("Cannot register vsock protocol\n"); goto err_deregister_misc; } err = sock_register(&vsock_family_ops); if (err) { pr_err("could not register af_vsock (%d) address family: %d\n", AF_VSOCK, err); goto err_unregister_proto; } return 0; err_unregister_proto: proto_unregister(&vsock_proto); err_deregister_misc: misc_deregister(&vsock_device); err_reset_transport: return err; } static void __exit vsock_exit(void) { misc_deregister(&vsock_device); sock_unregister(AF_VSOCK); proto_unregister(&vsock_proto); } const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk) { return vsk->transport; } EXPORT_SYMBOL_GPL(vsock_core_get_transport); int vsock_core_register(const struct vsock_transport *t, int features) { const struct vsock_transport *t_h2g, *t_g2h, *t_dgram, *t_local; int err = mutex_lock_interruptible(&vsock_register_mutex); if (err) return err; t_h2g = transport_h2g; t_g2h = transport_g2h; t_dgram = transport_dgram; t_local = transport_local; if (features & VSOCK_TRANSPORT_F_H2G) { if (t_h2g) { err = -EBUSY; goto err_busy; } t_h2g = t; } if (features & VSOCK_TRANSPORT_F_G2H) { if (t_g2h) { err = -EBUSY; goto err_busy; } t_g2h = t; } if (features & VSOCK_TRANSPORT_F_DGRAM) { if (t_dgram) { err = -EBUSY; goto err_busy; } t_dgram = t; } if (features & VSOCK_TRANSPORT_F_LOCAL) { if (t_local) { err = -EBUSY; goto err_busy; } t_local = t; } transport_h2g = t_h2g; transport_g2h = t_g2h; transport_dgram = t_dgram; transport_local = t_local; err_busy: mutex_unlock(&vsock_register_mutex); return err; } EXPORT_SYMBOL_GPL(vsock_core_register); void vsock_core_unregister(const struct vsock_transport *t) { mutex_lock(&vsock_register_mutex); if (transport_h2g == t) transport_h2g = NULL; if (transport_g2h == t) transport_g2h = NULL; if (transport_dgram == t) transport_dgram = NULL; if (transport_local == t) transport_local = NULL; mutex_unlock(&vsock_register_mutex); } EXPORT_SYMBOL_GPL(vsock_core_unregister); module_init(vsock_init); module_exit(vsock_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Socket Family"); MODULE_VERSION("1.0.2.0-k"); MODULE_LICENSE("GPL v2"); |
| 903 903 546 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implement CPU time clocks for the POSIX clock interface. */ #include <linux/sched/signal.h> #include <linux/sched/cputime.h> #include <linux/posix-timers.h> #include <linux/errno.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/kernel_stat.h> #include <trace/events/timer.h> #include <linux/tick.h> #include <linux/workqueue.h> #include <linux/compat.h> #include <linux/sched/deadline.h> #include <linux/task_work.h> #include "posix-timers.h" static void posix_cpu_timer_rearm(struct k_itimer *timer); void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { posix_cputimers_init(pct); if (cpu_limit != RLIM_INFINITY) { pct->bases[CPUCLOCK_PROF].nextevt = cpu_limit * NSEC_PER_SEC; pct->timers_active = true; } } /* * Called after updating RLIMIT_CPU to run cpu timer and update * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if * necessary. Needs siglock protection since other code may update the * expiration cache as well. * * Returns 0 on success, -ESRCH on failure. Can fail if the task is exiting and * we cannot lock_task_sighand. Cannot fail if task is current. */ int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new) { u64 nsecs = rlim_new * NSEC_PER_SEC; unsigned long irq_fl; if (!lock_task_sighand(task, &irq_fl)) return -ESRCH; set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL); unlock_task_sighand(task, &irq_fl); return 0; } /* * Functions for validating access to tasks. */ static struct pid *pid_for_clock(const clockid_t clock, bool gettime) { const bool thread = !!CPUCLOCK_PERTHREAD(clock); const pid_t upid = CPUCLOCK_PID(clock); struct pid *pid; if (CPUCLOCK_WHICH(clock) >= CPUCLOCK_MAX) return NULL; /* * If the encoded PID is 0, then the timer is targeted at current * or the process to which current belongs. */ if (upid == 0) return thread ? task_pid(current) : task_tgid(current); pid = find_vpid(upid); if (!pid) return NULL; if (thread) { struct task_struct *tsk = pid_task(pid, PIDTYPE_PID); return (tsk && same_thread_group(tsk, current)) ? pid : NULL; } /* * For clock_gettime(PROCESS) allow finding the process by * with the pid of the current task. The code needs the tgid * of the process so that pid_task(pid, PIDTYPE_TGID) can be * used to find the process. */ if (gettime && (pid == task_pid(current))) return task_tgid(current); /* * For processes require that pid identifies a process. */ return pid_has_task(pid, PIDTYPE_TGID) ? pid : NULL; } static inline int validate_clock_permissions(const clockid_t clock) { int ret; rcu_read_lock(); ret = pid_for_clock(clock, false) ? 0 : -EINVAL; rcu_read_unlock(); return ret; } static inline enum pid_type clock_pid_type(const clockid_t clock) { return CPUCLOCK_PERTHREAD(clock) ? PIDTYPE_PID : PIDTYPE_TGID; } static inline struct task_struct *cpu_timer_task_rcu(struct k_itimer *timer) { return pid_task(timer->it.cpu.pid, clock_pid_type(timer->it_clock)); } /* * Update expiry time from increment, and increase overrun count, * given the current clock sample. */ static u64 bump_cpu_timer(struct k_itimer *timer, u64 now) { u64 delta, incr, expires = timer->it.cpu.node.expires; int i; if (!timer->it_interval) return expires; if (now < expires) return expires; incr = timer->it_interval; delta = now + incr - expires; /* Don't use (incr*2 < delta), incr*2 might overflow. */ for (i = 0; incr < delta - incr; i++) incr = incr << 1; for (; i >= 0; incr >>= 1, i--) { if (delta < incr) continue; timer->it.cpu.node.expires += incr; timer->it_overrun += 1LL << i; delta -= incr; } return timer->it.cpu.node.expires; } /* Check whether all cache entries contain U64_MAX, i.e. eternal expiry time */ static inline bool expiry_cache_is_inactive(const struct posix_cputimers *pct) { return !(~pct->bases[CPUCLOCK_PROF].nextevt | ~pct->bases[CPUCLOCK_VIRT].nextevt | ~pct->bases[CPUCLOCK_SCHED].nextevt); } static int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { int error = validate_clock_permissions(which_clock); if (!error) { tp->tv_sec = 0; tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ); if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { /* * If sched_clock is using a cycle counter, we * don't have any idea of its true resolution * exported, but it is much more than 1s/HZ. */ tp->tv_nsec = 1; } } return error; } static int posix_cpu_clock_set(const clockid_t clock, const struct timespec64 *tp) { int error = validate_clock_permissions(clock); /* * You can never reset a CPU clock, but we check for other errors * in the call before failing with EPERM. */ return error ? : -EPERM; } /* * Sample a per-thread clock for the given task. clkid is validated. */ static u64 cpu_clock_sample(const clockid_t clkid, struct task_struct *p) { u64 utime, stime; if (clkid == CPUCLOCK_SCHED) return task_sched_runtime(p); task_cputime(p, &utime, &stime); switch (clkid) { case CPUCLOCK_PROF: return utime + stime; case CPUCLOCK_VIRT: return utime; default: WARN_ON_ONCE(1); } return 0; } static inline void store_samples(u64 *samples, u64 stime, u64 utime, u64 rtime) { samples[CPUCLOCK_PROF] = stime + utime; samples[CPUCLOCK_VIRT] = utime; samples[CPUCLOCK_SCHED] = rtime; } static void task_sample_cputime(struct task_struct *p, u64 *samples) { u64 stime, utime; task_cputime(p, &utime, &stime); store_samples(samples, stime, utime, p->se.sum_exec_runtime); } static void proc_sample_cputime_atomic(struct task_cputime_atomic *at, u64 *samples) { u64 stime, utime, rtime; utime = atomic64_read(&at->utime); stime = atomic64_read(&at->stime); rtime = atomic64_read(&at->sum_exec_runtime); store_samples(samples, stime, utime, rtime); } /* * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg * to avoid race conditions with concurrent updates to cputime. */ static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime) { u64 curr_cputime; retry: curr_cputime = atomic64_read(cputime); if (sum_cputime > curr_cputime) { if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime) goto retry; } } static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum) { __update_gt_cputime(&cputime_atomic->utime, sum->utime); __update_gt_cputime(&cputime_atomic->stime, sum->stime); __update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime); } /** * thread_group_sample_cputime - Sample cputime for a given task * @tsk: Task for which cputime needs to be started * @samples: Storage for time samples * * Called from sys_getitimer() to calculate the expiry time of an active * timer. That means group cputime accounting is already active. Called * with task sighand lock held. * * Updates @times with an uptodate sample of the thread group cputimes. */ void thread_group_sample_cputime(struct task_struct *tsk, u64 *samples) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers; WARN_ON_ONCE(!pct->timers_active); proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } /** * thread_group_start_cputime - Start cputime and return a sample * @tsk: Task for which cputime needs to be started * @samples: Storage for time samples * * The thread group cputime accounting is avoided when there are no posix * CPU timers armed. Before starting a timer it's required to check whether * the time accounting is active. If not, a full update of the atomic * accounting store needs to be done and the accounting enabled. * * Updates @times with an uptodate sample of the thread group cputimes. */ static void thread_group_start_cputime(struct task_struct *tsk, u64 *samples) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct posix_cputimers *pct = &tsk->signal->posix_cputimers; lockdep_assert_task_sighand_held(tsk); /* Check if cputimer isn't running. This is accessed without locking. */ if (!READ_ONCE(pct->timers_active)) { struct task_cputime sum; /* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have * to synchronize the timer to the clock every time we start it. */ thread_group_cputime(tsk, &sum); update_gt_cputime(&cputimer->cputime_atomic, &sum); /* * We're setting timers_active without a lock. Ensure this * only gets written to in one operation. We set it after * update_gt_cputime() as a small optimization, but * barriers are not required because update_gt_cputime() * can handle concurrent updates. */ WRITE_ONCE(pct->timers_active, true); } proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } static void __thread_group_cputime(struct task_struct *tsk, u64 *samples) { struct task_cputime ct; thread_group_cputime(tsk, &ct); store_samples(samples, ct.stime, ct.utime, ct.sum_exec_runtime); } /* * Sample a process (thread group) clock for the given task clkid. If the * group's cputime accounting is already enabled, read the atomic * store. Otherwise a full update is required. clkid is already validated. */ static u64 cpu_clock_sample_group(const clockid_t clkid, struct task_struct *p, bool start) { struct thread_group_cputimer *cputimer = &p->signal->cputimer; struct posix_cputimers *pct = &p->signal->posix_cputimers; u64 samples[CPUCLOCK_MAX]; if (!READ_ONCE(pct->timers_active)) { if (start) thread_group_start_cputime(p, samples); else __thread_group_cputime(p, samples); } else { proc_sample_cputime_atomic(&cputimer->cputime_atomic, samples); } return samples[clkid]; } static int posix_cpu_clock_get(const clockid_t clock, struct timespec64 *tp) { const clockid_t clkid = CPUCLOCK_WHICH(clock); struct task_struct *tsk; u64 t; rcu_read_lock(); tsk = pid_task(pid_for_clock(clock, true), clock_pid_type(clock)); if (!tsk) { rcu_read_unlock(); return -EINVAL; } if (CPUCLOCK_PERTHREAD(clock)) t = cpu_clock_sample(clkid, tsk); else t = cpu_clock_sample_group(clkid, tsk, false); rcu_read_unlock(); *tp = ns_to_timespec64(t); return 0; } /* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. * This is called from sys_timer_create() and do_cpu_nanosleep() with the * new timer already all-zeros initialized. */ static int posix_cpu_timer_create(struct k_itimer *new_timer) { static struct lock_class_key posix_cpu_timers_key; struct pid *pid; rcu_read_lock(); pid = pid_for_clock(new_timer->it_clock, false); if (!pid) { rcu_read_unlock(); return -EINVAL; } /* * If posix timer expiry is handled in task work context then * timer::it_lock can be taken without disabling interrupts as all * other locking happens in task context. This requires a separate * lock class key otherwise regular posix timer expiry would record * the lock class being taken in interrupt context and generate a * false positive warning. */ if (IS_ENABLED(CONFIG_POSIX_CPU_TIMERS_TASK_WORK)) lockdep_set_class(&new_timer->it_lock, &posix_cpu_timers_key); new_timer->kclock = &clock_posix_cpu; timerqueue_init(&new_timer->it.cpu.node); new_timer->it.cpu.pid = get_pid(pid); rcu_read_unlock(); return 0; } static struct posix_cputimer_base *timer_base(struct k_itimer *timer, struct task_struct *tsk) { int clkidx = CPUCLOCK_WHICH(timer->it_clock); if (CPUCLOCK_PERTHREAD(timer->it_clock)) return tsk->posix_cputimers.bases + clkidx; else return tsk->signal->posix_cputimers.bases + clkidx; } /* * Force recalculating the base earliest expiration on the next tick. * This will also re-evaluate the need to keep around the process wide * cputime counter and tick dependency and eventually shut these down * if necessary. */ static void trigger_base_recalc_expires(struct k_itimer *timer, struct task_struct *tsk) { struct posix_cputimer_base *base = timer_base(timer, tsk); base->nextevt = 0; } /* * Dequeue the timer and reset the base if it was its earliest expiration. * It makes sure the next tick recalculates the base next expiration so we * don't keep the costly process wide cputime counter around for a random * amount of time, along with the tick dependency. * * If another timer gets queued between this and the next tick, its * expiration will update the base next event if necessary on the next * tick. */ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) { struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base; if (!cpu_timer_dequeue(ctmr)) return; base = timer_base(timer, p); if (cpu_timer_getexpires(ctmr) == base->nextevt) trigger_base_recalc_expires(timer, p); } /* * Clean up a CPU-clock timer that is about to be destroyed. * This is called from timer deletion with the timer already locked. * If we return TIMER_RETRY, it's necessary to release the timer's lock * and try again. (This happens when the timer is in the middle of firing.) */ static int posix_cpu_timer_del(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) goto out; /* * Protect against sighand release/switch in exit/exec and process/ * thread timer list entry concurrent read/writes. */ sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) { /* * This raced with the reaping of the task. The exit cleanup * should have removed this timer from the timer queue. */ WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); } else { if (timer->it.cpu.firing) ret = TIMER_RETRY; else disarm_timer(timer, p); unlock_task_sighand(p, &flags); } out: rcu_read_unlock(); if (!ret) put_pid(ctmr->pid); return ret; } static void cleanup_timerqueue(struct timerqueue_head *head) { struct timerqueue_node *node; struct cpu_timer *ctmr; while ((node = timerqueue_getnext(head))) { timerqueue_del(head, node); ctmr = container_of(node, struct cpu_timer, node); ctmr->head = NULL; } } /* * Clean out CPU timers which are still armed when a thread exits. The * timers are only removed from the list. No other updates are done. The * corresponding posix timers are still accessible, but cannot be rearmed. * * This must be called with the siglock held. */ static void cleanup_timers(struct posix_cputimers *pct) { cleanup_timerqueue(&pct->bases[CPUCLOCK_PROF].tqhead); cleanup_timerqueue(&pct->bases[CPUCLOCK_VIRT].tqhead); cleanup_timerqueue(&pct->bases[CPUCLOCK_SCHED].tqhead); } /* * These are both called with the siglock held, when the current thread * is being reaped. When the final (leader) thread in the group is reaped, * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit. */ void posix_cpu_timers_exit(struct task_struct *tsk) { cleanup_timers(&tsk->posix_cputimers); } void posix_cpu_timers_exit_group(struct task_struct *tsk) { cleanup_timers(&tsk->signal->posix_cputimers); } /* * Insert the timer on the appropriate list before any timers that * expire later. This must be called with the sighand lock held. */ static void arm_timer(struct k_itimer *timer, struct task_struct *p) { struct posix_cputimer_base *base = timer_base(timer, p); struct cpu_timer *ctmr = &timer->it.cpu; u64 newexp = cpu_timer_getexpires(ctmr); if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return; /* * We are the new earliest-expiring POSIX 1.b timer, hence * need to update expiration cache. Take into account that * for process timers we share expiration cache with itimers * and RLIMIT_CPU and for thread timers with RLIMIT_RTTIME. */ if (newexp < base->nextevt) base->nextevt = newexp; if (CPUCLOCK_PERTHREAD(timer->it_clock)) tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); else tick_dep_set_signal(p, TICK_DEP_BIT_POSIX_TIMER); } /* * The timer is locked, fire it and arrange for its reload. */ static void cpu_timer_fire(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { /* * User don't want any signal. */ cpu_timer_setexpires(ctmr, 0); } else if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. */ wake_up_process(timer->it_process); cpu_timer_setexpires(ctmr, 0); } else if (!timer->it_interval) { /* * One-shot timer. Clear it as soon as it's fired. */ posix_timer_event(timer, 0); cpu_timer_setexpires(ctmr, 0); } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { /* * The signal did not get queued because the signal * was ignored, so we won't get any callback to * reload the timer. But we need to keep it * ticking in case the signal is deliverable next time. */ posix_cpu_timer_rearm(timer); ++timer->it_requeue_pending; } } /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. * If we return TIMER_RETRY, it's necessary to release the timer's lock * and try again. (This happens when the timer is in the middle of firing.) */ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, struct itimerspec64 *new, struct itimerspec64 *old) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); u64 old_expires, new_expires, old_incr, val; struct cpu_timer *ctmr = &timer->it.cpu; struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; int ret = 0; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) { /* * If p has just been reaped, we can no * longer get any information about it at all. */ rcu_read_unlock(); return -ESRCH; } /* * Use the to_ktime conversion because that clamps the maximum * value to KTIME_MAX and avoid multiplication overflows. */ new_expires = ktime_to_ns(timespec64_to_ktime(new->it_value)); /* * Protect against sighand release/switch in exit/exec and p->cpu_timers * and p->signal->cpu_timers read/write in arm_timer() */ sighand = lock_task_sighand(p, &flags); /* * If p has just been reaped, we can no * longer get any information about it at all. */ if (unlikely(sighand == NULL)) { rcu_read_unlock(); return -ESRCH; } /* * Disarm any old timer after extracting its expiry time. */ old_incr = timer->it_interval; old_expires = cpu_timer_getexpires(ctmr); if (unlikely(timer->it.cpu.firing)) { timer->it.cpu.firing = -1; ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); } /* * We need to sample the current value to convert the new * value from to relative and absolute, and to convert the * old value from absolute to relative. To set a process * timer, we need a sample to balance the thread expiry * times (in arm_timer). With an absolute time, we must * check if it's already passed. In short, we need a sample. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) val = cpu_clock_sample(clkid, p); else val = cpu_clock_sample_group(clkid, p, true); if (old) { if (old_expires == 0) { old->it_value.tv_sec = 0; old->it_value.tv_nsec = 0; } else { /* * Update the timer in case it has overrun already. * If it has, we'll report it as having overrun and * with the next reloaded timer already ticking, * though we are swallowing that pending * notification here to install the new setting. */ u64 exp = bump_cpu_timer(timer, val); if (val < exp) { old_expires = exp - val; old->it_value = ns_to_timespec64(old_expires); } else { old->it_value.tv_nsec = 1; old->it_value.tv_sec = 0; } } } if (unlikely(ret)) { /* * We are colliding with the timer actually firing. * Punt after filling in the timer's old value, and * disable this firing since we are already reporting * it as an overrun (thanks to bump_cpu_timer above). */ unlock_task_sighand(p, &flags); goto out; } if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) { new_expires += val; } /* * Install the new expiry time (or zero). * For a timer with no notification action, we don't actually * arm the timer (we'll just fake it for timer_gettime). */ cpu_timer_setexpires(ctmr, new_expires); if (new_expires != 0 && val < new_expires) { arm_timer(timer, p); } unlock_task_sighand(p, &flags); /* * Install the new reload setting, and * set up the signal and overrun bookkeeping. */ timer->it_interval = timespec64_to_ktime(new->it_interval); /* * This acts as a modification timestamp for the timer, * so any automatic reload attempt will punt on seeing * that we have reset the timer manually. */ timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING; timer->it_overrun_last = 0; timer->it_overrun = -1; if (val >= new_expires) { if (new_expires != 0) { /* * The designated time already passed, so we notify * immediately, even if the thread never runs to * accumulate more time on this clock. */ cpu_timer_fire(timer); } /* * Make sure we don't keep around the process wide cputime * counter or the tick dependency if they are not necessary. */ sighand = lock_task_sighand(p, &flags); if (!sighand) goto out; if (!cpu_timer_queued(ctmr)) trigger_base_recalc_expires(timer, p); unlock_task_sighand(p, &flags); } out: rcu_read_unlock(); if (old) old->it_interval = ns_to_timespec64(old_incr); return ret; } static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct cpu_timer *ctmr = &timer->it.cpu; u64 now, expires = cpu_timer_getexpires(ctmr); struct task_struct *p; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) goto out; /* * Easy part: convert the reload time. */ itp->it_interval = ktime_to_timespec64(timer->it_interval); if (!expires) goto out; /* * Sample the clock to take the difference with the expiry time. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) now = cpu_clock_sample(clkid, p); else now = cpu_clock_sample_group(clkid, p, false); if (now < expires) { itp->it_value = ns_to_timespec64(expires - now); } else { /* * The timer should have expired already, but the firing * hasn't taken place yet. Say it's just about to expire. */ itp->it_value.tv_nsec = 1; itp->it_value.tv_sec = 0; } out: rcu_read_unlock(); } #define MAX_COLLECTED 20 static u64 collect_timerqueue(struct timerqueue_head *head, struct list_head *firing, u64 now) { struct timerqueue_node *next; int i = 0; while ((next = timerqueue_getnext(head))) { struct cpu_timer *ctmr; u64 expires; ctmr = container_of(next, struct cpu_timer, node); expires = cpu_timer_getexpires(ctmr); /* Limit the number of timers to expire at once */ if (++i == MAX_COLLECTED || now < expires) return expires; ctmr->firing = 1; /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(ctmr->handling, current); cpu_timer_dequeue(ctmr); list_add_tail(&ctmr->elist, firing); } return U64_MAX; } static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples, struct list_head *firing) { struct posix_cputimer_base *base = pct->bases; int i; for (i = 0; i < CPUCLOCK_MAX; i++, base++) { base->nextevt = collect_timerqueue(&base->tqhead, firing, samples[i]); } } static inline void check_dl_overrun(struct task_struct *tsk) { if (tsk->dl.dl_overrun) { tsk->dl.dl_overrun = 0; send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID); } } static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard) { if (time < limit) return false; if (print_fatal_signals) { pr_info("%s Watchdog Timeout (%s): %s[%d]\n", rt ? "RT" : "CPU", hard ? "hard" : "soft", current->comm, task_pid_nr(current)); } send_signal_locked(signo, SEND_SIG_PRIV, current, PIDTYPE_TGID); return true; } /* * Check for any per-thread CPU timers that have fired and move them off * the tsk->cpu_timers[N] list onto the firing list. Here we update the * tsk->it_*_expires values to reflect the remaining thread CPU timers. */ static void check_thread_timers(struct task_struct *tsk, struct list_head *firing) { struct posix_cputimers *pct = &tsk->posix_cputimers; u64 samples[CPUCLOCK_MAX]; unsigned long soft; if (dl_task(tsk)) check_dl_overrun(tsk); if (expiry_cache_is_inactive(pct)) return; task_sample_cputime(tsk, samples); collect_posix_cputimers(pct, samples, firing); /* * Check for the special case thread timers. */ soft = task_rlimit(tsk, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { /* Task RT timeout is accounted in jiffies. RTTIME is usec */ unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ); unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME); /* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY && check_rlimit(rttime, hard, SIGKILL, true, true)) return; /* At the soft limit, send a SIGXCPU every second */ if (check_rlimit(rttime, soft, SIGXCPU, true, false)) { soft += USEC_PER_SEC; tsk->signal->rlim[RLIMIT_RTTIME].rlim_cur = soft; } } if (expiry_cache_is_inactive(pct)) tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER); } static inline void stop_process_timers(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; /* Turn off the active flag. This is done without locking. */ WRITE_ONCE(pct->timers_active, false); tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, u64 *expires, u64 cur_time, int signo) { if (!it->expires) return; if (cur_time >= it->expires) { if (it->incr) it->expires += it->incr; else it->expires = 0; trace_itimer_expire(signo == SIGPROF ? ITIMER_PROF : ITIMER_VIRTUAL, task_tgid(tsk), cur_time); send_signal_locked(signo, SEND_SIG_PRIV, tsk, PIDTYPE_TGID); } if (it->expires && it->expires < *expires) *expires = it->expires; } /* * Check for any per-thread CPU timers that have fired and move them * off the tsk->*_timers list onto the firing list. Per-thread timers * have already been taken off. */ static void check_process_timers(struct task_struct *tsk, struct list_head *firing) { struct signal_struct *const sig = tsk->signal; struct posix_cputimers *pct = &sig->posix_cputimers; u64 samples[CPUCLOCK_MAX]; unsigned long soft; /* * If there are no active process wide timers (POSIX 1.b, itimers, * RLIMIT_CPU) nothing to check. Also skip the process wide timer * processing when there is already another task handling them. */ if (!READ_ONCE(pct->timers_active) || pct->expiry_active) return; /* * Signify that a thread is checking for process timers. * Write access to this field is protected by the sighand lock. */ pct->expiry_active = true; /* * Collect the current process totals. Group accounting is active * so the sample can be taken directly. */ proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, samples); collect_posix_cputimers(pct, samples, firing); /* * Check for the special case process timers. */ check_cpu_itimer(tsk, &sig->it[CPUCLOCK_PROF], &pct->bases[CPUCLOCK_PROF].nextevt, samples[CPUCLOCK_PROF], SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &pct->bases[CPUCLOCK_VIRT].nextevt, samples[CPUCLOCK_VIRT], SIGVTALRM); soft = task_rlimit(tsk, RLIMIT_CPU); if (soft != RLIM_INFINITY) { /* RLIMIT_CPU is in seconds. Samples are nanoseconds */ unsigned long hard = task_rlimit_max(tsk, RLIMIT_CPU); u64 ptime = samples[CPUCLOCK_PROF]; u64 softns = (u64)soft * NSEC_PER_SEC; u64 hardns = (u64)hard * NSEC_PER_SEC; /* At the hard limit, send SIGKILL. No further action. */ if (hard != RLIM_INFINITY && check_rlimit(ptime, hardns, SIGKILL, false, true)) return; /* At the soft limit, send a SIGXCPU every second */ if (check_rlimit(ptime, softns, SIGXCPU, false, false)) { sig->rlim[RLIMIT_CPU].rlim_cur = soft + 1; softns += NSEC_PER_SEC; } /* Update the expiry cache */ if (softns < pct->bases[CPUCLOCK_PROF].nextevt) pct->bases[CPUCLOCK_PROF].nextevt = softns; } if (expiry_cache_is_inactive(pct)) stop_process_timers(sig); pct->expiry_active = false; } /* * This is called from the signal code (via posixtimer_rearm) * when the last timer signal was delivered and we have to reload the timer. */ static void posix_cpu_timer_rearm(struct k_itimer *timer) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); struct task_struct *p; struct sighand_struct *sighand; unsigned long flags; u64 now; rcu_read_lock(); p = cpu_timer_task_rcu(timer); if (!p) goto out; /* Protect timer list r/w in arm_timer() */ sighand = lock_task_sighand(p, &flags); if (unlikely(sighand == NULL)) goto out; /* * Fetch the current sample and update the timer's expiry time. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) now = cpu_clock_sample(clkid, p); else now = cpu_clock_sample_group(clkid, p, true); bump_cpu_timer(timer, now); /* * Now re-arm for the new expiry time. */ arm_timer(timer, p); unlock_task_sighand(p, &flags); out: rcu_read_unlock(); } /** * task_cputimers_expired - Check whether posix CPU timers are expired * * @samples: Array of current samples for the CPUCLOCK clocks * @pct: Pointer to a posix_cputimers container * * Returns true if any member of @samples is greater than the corresponding * member of @pct->bases[CLK].nextevt. False otherwise */ static inline bool task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct) { int i; for (i = 0; i < CPUCLOCK_MAX; i++) { if (samples[i] >= pct->bases[i].nextevt) return true; } return false; } /** * fastpath_timer_check - POSIX CPU timers fast path. * * @tsk: The task (thread) being checked. * * Check the task and thread group timers. If both are zero (there are no * timers set) return false. Otherwise snapshot the task and thread group * timers and compare them with the corresponding expiration times. Return * true if a timer has expired, else return false. */ static inline bool fastpath_timer_check(struct task_struct *tsk) { struct posix_cputimers *pct = &tsk->posix_cputimers; struct signal_struct *sig; if (!expiry_cache_is_inactive(pct)) { u64 samples[CPUCLOCK_MAX]; task_sample_cputime(tsk, samples); if (task_cputimers_expired(samples, pct)) return true; } sig = tsk->signal; pct = &sig->posix_cputimers; /* * Check if thread group timers expired when timers are active and * no other thread in the group is already handling expiry for * thread group cputimers. These fields are read without the * sighand lock. However, this is fine because this is meant to be * a fastpath heuristic to determine whether we should try to * acquire the sighand lock to handle timer expiry. * * In the worst case scenario, if concurrently timers_active is set * or expiry_active is cleared, but the current thread doesn't see * the change yet, the timer checks are delayed until the next * thread in the group gets a scheduler interrupt to handle the * timer. This isn't an issue in practice because these types of * delays with signals actually getting sent are expected. */ if (READ_ONCE(pct->timers_active) && !READ_ONCE(pct->expiry_active)) { u64 samples[CPUCLOCK_MAX]; proc_sample_cputime_atomic(&sig->cputimer.cputime_atomic, samples); if (task_cputimers_expired(samples, pct)) return true; } if (dl_task(tsk) && tsk->dl.dl_overrun) return true; return false; } static void handle_posix_cpu_timers(struct task_struct *tsk); #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK static void posix_cpu_timers_work(struct callback_head *work) { struct posix_cputimers_work *cw = container_of(work, typeof(*cw), work); mutex_lock(&cw->mutex); handle_posix_cpu_timers(current); mutex_unlock(&cw->mutex); } /* * Invoked from the posix-timer core when a cancel operation failed because * the timer is marked firing. The caller holds rcu_read_lock(), which * protects the timer and the task which is expiring it from being freed. */ static void posix_cpu_timer_wait_running(struct k_itimer *timr) { struct task_struct *tsk = rcu_dereference(timr->it.cpu.handling); /* Has the handling task completed expiry already? */ if (!tsk) return; /* Ensure that the task cannot go away */ get_task_struct(tsk); /* Now drop the RCU protection so the mutex can be locked */ rcu_read_unlock(); /* Wait on the expiry mutex */ mutex_lock(&tsk->posix_cputimers_work.mutex); /* Release it immediately again. */ mutex_unlock(&tsk->posix_cputimers_work.mutex); /* Drop the task reference. */ put_task_struct(tsk); /* Relock RCU so the callsite is balanced */ rcu_read_lock(); } static void posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr) { /* Ensure that timr->it.cpu.handling task cannot go away */ rcu_read_lock(); spin_unlock_irq(&timr->it_lock); posix_cpu_timer_wait_running(timr); rcu_read_unlock(); /* @timr is on stack and is valid */ spin_lock_irq(&timr->it_lock); } /* * Clear existing posix CPU timers task work. */ void clear_posix_cputimers_work(struct task_struct *p) { /* * A copied work entry from the old task is not meaningful, clear it. * N.B. init_task_work will not do this. */ memset(&p->posix_cputimers_work.work, 0, sizeof(p->posix_cputimers_work.work)); init_task_work(&p->posix_cputimers_work.work, posix_cpu_timers_work); mutex_init(&p->posix_cputimers_work.mutex); p->posix_cputimers_work.scheduled = false; } /* * Initialize posix CPU timers task work in init task. Out of line to * keep the callback static and to avoid header recursion hell. */ void __init posix_cputimers_init_work(void) { clear_posix_cputimers_work(current); } /* * Note: All operations on tsk->posix_cputimer_work.scheduled happen either * in hard interrupt context or in task context with interrupts * disabled. Aside of that the writer/reader interaction is always in the * context of the current task, which means they are strict per CPU. */ static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk) { return tsk->posix_cputimers_work.scheduled; } static inline void __run_posix_cpu_timers(struct task_struct *tsk) { if (WARN_ON_ONCE(tsk->posix_cputimers_work.scheduled)) return; /* Schedule task work to actually expire the timers */ tsk->posix_cputimers_work.scheduled = true; task_work_add(tsk, &tsk->posix_cputimers_work.work, TWA_RESUME); } static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk, unsigned long start) { bool ret = true; /* * On !RT kernels interrupts are disabled while collecting expired * timers, so no tick can happen and the fast path check can be * reenabled without further checks. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { tsk->posix_cputimers_work.scheduled = false; return true; } /* * On RT enabled kernels ticks can happen while the expired timers * are collected under sighand lock. But any tick which observes * the CPUTIMERS_WORK_SCHEDULED bit set, does not run the fastpath * checks. So reenabling the tick work has do be done carefully: * * Disable interrupts and run the fast path check if jiffies have * advanced since the collecting of expired timers started. If * jiffies have not advanced or the fast path check did not find * newly expired timers, reenable the fast path check in the timer * interrupt. If there are newly expired timers, return false and * let the collection loop repeat. */ local_irq_disable(); if (start != jiffies && fastpath_timer_check(tsk)) ret = false; else tsk->posix_cputimers_work.scheduled = false; local_irq_enable(); return ret; } #else /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */ static inline void __run_posix_cpu_timers(struct task_struct *tsk) { lockdep_posixtimer_enter(); handle_posix_cpu_timers(tsk); lockdep_posixtimer_exit(); } static void posix_cpu_timer_wait_running(struct k_itimer *timr) { cpu_relax(); } static void posix_cpu_timer_wait_running_nsleep(struct k_itimer *timr) { spin_unlock_irq(&timr->it_lock); cpu_relax(); spin_lock_irq(&timr->it_lock); } static inline bool posix_cpu_timers_work_scheduled(struct task_struct *tsk) { return false; } static inline bool posix_cpu_timers_enable_work(struct task_struct *tsk, unsigned long start) { return true; } #endif /* CONFIG_POSIX_CPU_TIMERS_TASK_WORK */ static void handle_posix_cpu_timers(struct task_struct *tsk) { struct k_itimer *timer, *next; unsigned long flags, start; LIST_HEAD(firing); if (!lock_task_sighand(tsk, &flags)) return; do { /* * On RT locking sighand lock does not disable interrupts, * so this needs to be careful vs. ticks. Store the current * jiffies value. */ start = READ_ONCE(jiffies); barrier(); /* * Here we take off tsk->signal->cpu_timers[N] and * tsk->cpu_timers[N] all the timers that are firing, and * put them on the firing list. */ check_thread_timers(tsk, &firing); check_process_timers(tsk, &firing); /* * The above timer checks have updated the expiry cache and * because nothing can have queued or modified timers after * sighand lock was taken above it is guaranteed to be * consistent. So the next timer interrupt fastpath check * will find valid data. * * If timer expiry runs in the timer interrupt context then * the loop is not relevant as timers will be directly * expired in interrupt context. The stub function below * returns always true which allows the compiler to * optimize the loop out. * * If timer expiry is deferred to task work context then * the following rules apply: * * - On !RT kernels no tick can have happened on this CPU * after sighand lock was acquired because interrupts are * disabled. So reenabling task work before dropping * sighand lock and reenabling interrupts is race free. * * - On RT kernels ticks might have happened but the tick * work ignored posix CPU timer handling because the * CPUTIMERS_WORK_SCHEDULED bit is set. Reenabling work * must be done very carefully including a check whether * ticks have happened since the start of the timer * expiry checks. posix_cpu_timers_enable_work() takes * care of that and eventually lets the expiry checks * run again. */ } while (!posix_cpu_timers_enable_work(tsk, start)); /* * We must release sighand lock before taking any timer's lock. * There is a potential race with timer deletion here, as the * siglock now protects our private firing list. We have set * the firing flag in each timer, so that a deletion attempt * that gets the timer lock before we do will give it up and * spin until we've taken care of that timer below. */ unlock_task_sighand(tsk, &flags); /* * Now that all the timers on our list have the firing flag, * no one will touch their list entries but us. We'll take * each timer's lock before clearing its firing flag, so no * timer call will interfere. */ list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) { int cpu_firing; /* * spin_lock() is sufficient here even independent of the * expiry context. If expiry happens in hard interrupt * context it's obvious. For task work context it's safe * because all other operations on timer::it_lock happen in * task context (syscall or exit). */ spin_lock(&timer->it_lock); list_del_init(&timer->it.cpu.elist); cpu_firing = timer->it.cpu.firing; timer->it.cpu.firing = 0; /* * The firing flag is -1 if we collided with a reset * of the timer, which already reported this * almost-firing as an overrun. So don't generate an event. */ if (likely(cpu_firing >= 0)) cpu_timer_fire(timer); /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(timer->it.cpu.handling, NULL); spin_unlock(&timer->it_lock); } } /* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. * Interrupts are disabled. */ void run_posix_cpu_timers(void) { struct task_struct *tsk = current; lockdep_assert_irqs_disabled(); /* * If the actual expiry is deferred to task work context and the * work is already scheduled there is no point to do anything here. */ if (posix_cpu_timers_work_scheduled(tsk)) return; /* * The fast path checks that there are no expired thread or thread * group timers. If that's so, just return. */ if (!fastpath_timer_check(tsk)) return; __run_posix_cpu_timers(tsk); } /* * Set one of the process-wide special case CPU timers or RLIMIT_CPU. * The tsk->sighand->siglock must be held by the caller. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clkid, u64 *newval, u64 *oldval) { u64 now, *nextevt; if (WARN_ON_ONCE(clkid >= CPUCLOCK_SCHED)) return; nextevt = &tsk->signal->posix_cputimers.bases[clkid].nextevt; now = cpu_clock_sample_group(clkid, tsk, true); if (oldval) { /* * We are setting itimer. The *oldval is absolute and we update * it to be relative, *newval argument is relative and we update * it to be absolute. */ if (*oldval) { if (*oldval <= now) { /* Just about to fire. */ *oldval = TICK_NSEC; } else { *oldval -= now; } } if (*newval) *newval += now; } /* * Update expiration cache if this is the earliest timer. CPUCLOCK_PROF * expiry cache is also used by RLIMIT_CPU!. */ if (*newval < *nextevt) *nextevt = *newval; tick_dep_set_signal(tsk, TICK_DEP_BIT_POSIX_TIMER); } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { struct itimerspec64 it; struct k_itimer timer; u64 expires; int error; /* * Set up a temporary timer and then wait for it to go off. */ memset(&timer, 0, sizeof timer); spin_lock_init(&timer.it_lock); timer.it_clock = which_clock; timer.it_overrun = -1; error = posix_cpu_timer_create(&timer); timer.it_process = current; if (!error) { static struct itimerspec64 zero_it; struct restart_block *restart; memset(&it, 0, sizeof(it)); it.it_value = *rqtp; spin_lock_irq(&timer.it_lock); error = posix_cpu_timer_set(&timer, flags, &it, NULL); if (error) { spin_unlock_irq(&timer.it_lock); return error; } while (!signal_pending(current)) { if (!cpu_timer_getexpires(&timer.it.cpu)) { /* * Our timer fired and was reset, below * deletion can not fail. */ posix_cpu_timer_del(&timer); spin_unlock_irq(&timer.it_lock); return 0; } /* * Block until cpu_timer_fire (or a signal) wakes us. */ __set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irq(&timer.it_lock); schedule(); spin_lock_irq(&timer.it_lock); } /* * We were interrupted by a signal. */ expires = cpu_timer_getexpires(&timer.it.cpu); error = posix_cpu_timer_set(&timer, 0, &zero_it, &it); if (!error) { /* Timer is now unarmed, deletion can not fail. */ posix_cpu_timer_del(&timer); } else { while (error == TIMER_RETRY) { posix_cpu_timer_wait_running_nsleep(&timer); error = posix_cpu_timer_del(&timer); } } spin_unlock_irq(&timer.it_lock); if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { /* * It actually did fire already. */ return 0; } error = -ERESTART_RESTARTBLOCK; /* * Report back to the user the time still remaining. */ restart = ¤t->restart_block; restart->nanosleep.expires = expires; if (restart->nanosleep.type != TT_NONE) error = nanosleep_copyout(restart, &it.it_value); } return error; } static long posix_cpu_nsleep_restart(struct restart_block *restart_block); static int posix_cpu_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { struct restart_block *restart_block = ¤t->restart_block; int error; /* * Diagnose required errors first. */ if (CPUCLOCK_PERTHREAD(which_clock) && (CPUCLOCK_PID(which_clock) == 0 || CPUCLOCK_PID(which_clock) == task_pid_vnr(current))) return -EINVAL; error = do_cpu_nanosleep(which_clock, flags, rqtp); if (error == -ERESTART_RESTARTBLOCK) { if (flags & TIMER_ABSTIME) return -ERESTARTNOHAND; restart_block->nanosleep.clockid = which_clock; set_restart_fn(restart_block, posix_cpu_nsleep_restart); } return error; } static long posix_cpu_nsleep_restart(struct restart_block *restart_block) { clockid_t which_clock = restart_block->nanosleep.clockid; struct timespec64 t; t = ns_to_timespec64(restart_block->nanosleep.expires); return do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t); } #define PROCESS_CLOCK make_process_cpuclock(0, CPUCLOCK_SCHED) #define THREAD_CLOCK make_thread_cpuclock(0, CPUCLOCK_SCHED) static int process_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_getres(PROCESS_CLOCK, tp); } static int process_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_get(PROCESS_CLOCK, tp); } static int process_cpu_timer_create(struct k_itimer *timer) { timer->it_clock = PROCESS_CLOCK; return posix_cpu_timer_create(timer); } static int process_cpu_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp); } static int thread_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_getres(THREAD_CLOCK, tp); } static int thread_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp) { return posix_cpu_clock_get(THREAD_CLOCK, tp); } static int thread_cpu_timer_create(struct k_itimer *timer) { timer->it_clock = THREAD_CLOCK; return posix_cpu_timer_create(timer); } const struct k_clock clock_posix_cpu = { .clock_getres = posix_cpu_clock_getres, .clock_set = posix_cpu_clock_set, .clock_get_timespec = posix_cpu_clock_get, .timer_create = posix_cpu_timer_create, .nsleep = posix_cpu_nsleep, .timer_set = posix_cpu_timer_set, .timer_del = posix_cpu_timer_del, .timer_get = posix_cpu_timer_get, .timer_rearm = posix_cpu_timer_rearm, .timer_wait_running = posix_cpu_timer_wait_running, }; const struct k_clock clock_process = { .clock_getres = process_cpu_clock_getres, .clock_get_timespec = process_cpu_clock_get, .timer_create = process_cpu_timer_create, .nsleep = process_cpu_nsleep, }; const struct k_clock clock_thread = { .clock_getres = thread_cpu_clock_getres, .clock_get_timespec = thread_cpu_clock_get, .timer_create = thread_cpu_timer_create, }; |
| 439 438 431 9 235 | 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 | // SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) /* Copyright (C) 2016-2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * SipHash: a fast short-input PRF * https://131002.net/siphash/ * * This implementation is specifically for SipHash2-4 for a secure PRF * and HalfSipHash1-3/SipHash1-3 for an insecure PRF only suitable for * hashtables. */ #include <linux/siphash.h> #include <asm/unaligned.h> #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 #include <linux/dcache.h> #include <asm/word-at-a-time.h> #endif #define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3) #define PREAMBLE(len) \ u64 v0 = SIPHASH_CONST_0; \ u64 v1 = SIPHASH_CONST_1; \ u64 v2 = SIPHASH_CONST_2; \ u64 v3 = SIPHASH_CONST_3; \ u64 b = ((u64)(len)) << 56; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ v1 ^= key->key[1]; \ v0 ^= key->key[0]; #define POSTAMBLE \ v3 ^= b; \ SIPROUND; \ SIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ SIPROUND; \ SIPROUND; \ SIPROUND; \ SIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; PREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = le64_to_cpup(data); v3 ^= m; SIPROUND; SIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= le32_to_cpup(data); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } #endif POSTAMBLE } EXPORT_SYMBOL(__siphash_aligned); #endif u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; PREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = get_unaligned_le64(data); v3 ^= m; SIPROUND; SIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= get_unaligned_le32(end); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } #endif POSTAMBLE } EXPORT_SYMBOL(__siphash_unaligned); /** * siphash_1u64 - compute 64-bit siphash PRF value of a u64 * @first: first u64 * @key: the siphash key */ u64 siphash_1u64(const u64 first, const siphash_key_t *key) { PREAMBLE(8) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; POSTAMBLE } EXPORT_SYMBOL(siphash_1u64); /** * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64 * @first: first u64 * @second: second u64 * @key: the siphash key */ u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key) { PREAMBLE(16) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; POSTAMBLE } EXPORT_SYMBOL(siphash_2u64); /** * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64 * @first: first u64 * @second: second u64 * @third: third u64 * @key: the siphash key */ u64 siphash_3u64(const u64 first, const u64 second, const u64 third, const siphash_key_t *key) { PREAMBLE(24) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; v3 ^= third; SIPROUND; SIPROUND; v0 ^= third; POSTAMBLE } EXPORT_SYMBOL(siphash_3u64); /** * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64 * @first: first u64 * @second: second u64 * @third: third u64 * @forth: forth u64 * @key: the siphash key */ u64 siphash_4u64(const u64 first, const u64 second, const u64 third, const u64 forth, const siphash_key_t *key) { PREAMBLE(32) v3 ^= first; SIPROUND; SIPROUND; v0 ^= first; v3 ^= second; SIPROUND; SIPROUND; v0 ^= second; v3 ^= third; SIPROUND; SIPROUND; v0 ^= third; v3 ^= forth; SIPROUND; SIPROUND; v0 ^= forth; POSTAMBLE } EXPORT_SYMBOL(siphash_4u64); u64 siphash_1u32(const u32 first, const siphash_key_t *key) { PREAMBLE(4) b |= first; POSTAMBLE } EXPORT_SYMBOL(siphash_1u32); u64 siphash_3u32(const u32 first, const u32 second, const u32 third, const siphash_key_t *key) { u64 combined = (u64)second << 32 | first; PREAMBLE(12) v3 ^= combined; SIPROUND; SIPROUND; v0 ^= combined; b |= third; POSTAMBLE } EXPORT_SYMBOL(siphash_3u32); #if BITS_PER_LONG == 64 /* Note that on 64-bit, we make HalfSipHash1-3 actually be SipHash1-3, for * performance reasons. On 32-bit, below, we actually implement HalfSipHash1-3. */ #define HSIPROUND SIPROUND #define HPREAMBLE(len) PREAMBLE(len) #define HPOSTAMBLE \ v3 ^= b; \ HSIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ HSIPROUND; \ HSIPROUND; \ HSIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; HPREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = le64_to_cpup(data); v3 ^= m; HSIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= le32_to_cpup(data); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } #endif HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); #endif u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); const u8 left = len & (sizeof(u64) - 1); u64 m; HPREAMBLE(len) for (; data != end; data += sizeof(u64)) { m = get_unaligned_le64(data); v3 ^= m; HSIPROUND; v0 ^= m; } #if defined(CONFIG_DCACHE_WORD_ACCESS) && BITS_PER_LONG == 64 if (left) b |= le64_to_cpu((__force __le64)(load_unaligned_zeropad(data) & bytemask_from_count(left))); #else switch (left) { case 7: b |= ((u64)end[6]) << 48; fallthrough; case 6: b |= ((u64)end[5]) << 40; fallthrough; case 5: b |= ((u64)end[4]) << 32; fallthrough; case 4: b |= get_unaligned_le32(end); break; case 3: b |= ((u64)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } #endif HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); /** * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32 * @first: first u32 * @key: the hsiphash key */ u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key) { HPREAMBLE(4) b |= first; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_1u32); /** * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32 * @first: first u32 * @second: second u32 * @key: the hsiphash key */ u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(8) v3 ^= combined; HSIPROUND; v0 ^= combined; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_2u32); /** * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @key: the hsiphash key */ u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(12) v3 ^= combined; HSIPROUND; v0 ^= combined; b |= third; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_3u32); /** * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @forth: forth u32 * @key: the hsiphash key */ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, const u32 forth, const hsiphash_key_t *key) { u64 combined = (u64)second << 32 | first; HPREAMBLE(16) v3 ^= combined; HSIPROUND; v0 ^= combined; combined = (u64)forth << 32 | third; v3 ^= combined; HSIPROUND; v0 ^= combined; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_4u32); #else #define HSIPROUND HSIPHASH_PERMUTATION(v0, v1, v2, v3) #define HPREAMBLE(len) \ u32 v0 = HSIPHASH_CONST_0; \ u32 v1 = HSIPHASH_CONST_1; \ u32 v2 = HSIPHASH_CONST_2; \ u32 v3 = HSIPHASH_CONST_3; \ u32 b = ((u32)(len)) << 24; \ v3 ^= key->key[1]; \ v2 ^= key->key[0]; \ v1 ^= key->key[1]; \ v0 ^= key->key[0]; #define HPOSTAMBLE \ v3 ^= b; \ HSIPROUND; \ v0 ^= b; \ v2 ^= 0xff; \ HSIPROUND; \ HSIPROUND; \ HSIPROUND; \ return v1 ^ v3; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); const u8 left = len & (sizeof(u32) - 1); u32 m; HPREAMBLE(len) for (; data != end; data += sizeof(u32)) { m = le32_to_cpup(data); v3 ^= m; HSIPROUND; v0 ^= m; } switch (left) { case 3: b |= ((u32)end[2]) << 16; fallthrough; case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); #endif u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); const u8 left = len & (sizeof(u32) - 1); u32 m; HPREAMBLE(len) for (; data != end; data += sizeof(u32)) { m = get_unaligned_le32(data); v3 ^= m; HSIPROUND; v0 ^= m; } switch (left) { case 3: b |= ((u32)end[2]) << 16; fallthrough; case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); /** * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32 * @first: first u32 * @key: the hsiphash key */ u32 hsiphash_1u32(const u32 first, const hsiphash_key_t *key) { HPREAMBLE(4) v3 ^= first; HSIPROUND; v0 ^= first; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_1u32); /** * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32 * @first: first u32 * @second: second u32 * @key: the hsiphash key */ u32 hsiphash_2u32(const u32 first, const u32 second, const hsiphash_key_t *key) { HPREAMBLE(8) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_2u32); /** * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @key: the hsiphash key */ u32 hsiphash_3u32(const u32 first, const u32 second, const u32 third, const hsiphash_key_t *key) { HPREAMBLE(12) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; v3 ^= third; HSIPROUND; v0 ^= third; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_3u32); /** * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32 * @first: first u32 * @second: second u32 * @third: third u32 * @forth: forth u32 * @key: the hsiphash key */ u32 hsiphash_4u32(const u32 first, const u32 second, const u32 third, const u32 forth, const hsiphash_key_t *key) { HPREAMBLE(16) v3 ^= first; HSIPROUND; v0 ^= first; v3 ^= second; HSIPROUND; v0 ^= second; v3 ^= third; HSIPROUND; v0 ^= third; v3 ^= forth; HSIPROUND; v0 ^= forth; HPOSTAMBLE } EXPORT_SYMBOL(hsiphash_4u32); #endif |
| 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 41 43 5 5 5 5 5 5 2 320 331 291 41 41 41 41 43 43 43 2 41 2 41 286 286 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The User Datagram Protocol (UDP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Hirokazu Takahashi, <taka@valinux.co.jp> * * Fixes: * Alan Cox : verify_area() calls * Alan Cox : stopped close while in use off icmp * messages. Not a fix but a botch that * for udp at least is 'valid'. * Alan Cox : Fixed icmp handling properly * Alan Cox : Correct error for oversized datagrams * Alan Cox : Tidied select() semantics. * Alan Cox : udp_err() fixed properly, also now * select and read wake correctly on errors * Alan Cox : udp_send verify_area moved to avoid mem leak * Alan Cox : UDP can count its memory * Alan Cox : send to an unknown connection causes * an ECONNREFUSED off the icmp, but * does NOT close. * Alan Cox : Switched to new sk_buff handlers. No more backlog! * Alan Cox : Using generic datagram code. Even smaller and the PEEK * bug no longer crashes it. * Fred Van Kempen : Net2e support for sk->broadcast. * Alan Cox : Uses skb_free_datagram * Alan Cox : Added get/set sockopt support. * Alan Cox : Broadcasting without option set returns EACCES. * Alan Cox : No wakeup calls. Instead we now use the callbacks. * Alan Cox : Use ip_tos and ip_ttl * Alan Cox : SNMP Mibs * Alan Cox : MSG_DONTROUTE, and 0.0.0.0 support. * Matt Dillon : UDP length checks. * Alan Cox : Smarter af_inet used properly. * Alan Cox : Use new kernel side addressing. * Alan Cox : Incorrect return on truncated datagram receive. * Arnt Gulbrandsen : New udp_send and stuff * Alan Cox : Cache last socket * Alan Cox : Route cache * Jon Peatfield : Minor efficiency fix to sendto(). * Mike Shaver : RFC1122 checks. * Alan Cox : Nonblocking error fix. * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * David S. Miller : New socket lookup architecture. * Last socket cache retained as it * does have a high hit rate. * Olaf Kirch : Don't linearise iovec on sendmsg. * Andi Kleen : Some cleanups, cache destination entry * for connect. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Melvin Smith : Check msg_name not msg_namelen in sendto(), * return ENOTCONN for unconnected sockets (POSIX) * Janos Farkas : don't deliver multi/broadcasts to a different * bound-to-device socket * Hirokazu Takahashi : HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi : sendfile() on UDP works now. * Arnaldo C. Melo : convert /proc/net/udp to seq_file * 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. * Derek Atkins <derek@ihtfp.com>: Add Encapulation Support * James Chapman : Add L2TP encapsulation type. */ #define pr_fmt(fmt) "UDP: " fmt #include <linux/bpf-cgroup.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/tcp_states.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/ip_tunnels.h> #include <net/route.h> #include <net/checksum.h> #include <net/xfrm.h> #include <trace/events/udp.h> #include <linux/static_key.h> #include <linux/btf_ids.h> #include <trace/events/skb.h> #include <net/busy_poll.h> #include "udp_impl.h" #include <net/sock_reuseport.h> #include <net/addrconf.h> #include <net/udp_tunnel.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(udp_memory_allocated); DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, unsigned long *bitmap, struct sock *sk, unsigned int log) { struct sock *sk2; kuid_t uid = sock_i_uid(sk); sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && (bitmap || udp_sk(sk2)->udp_port_hash == num) && (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && inet_rcv_saddr_equal(sk, sk2, true)) { if (sk2->sk_reuseport && sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(uid, sock_i_uid(sk2))) { if (!bitmap) return 0; } else { if (!bitmap) return 1; __set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap); } } } return 0; } /* * Note: we still hold spinlock of primary hash chain, so no other writer * can insert/delete a socket with local_port == num */ static int udp_lib_lport_inuse2(struct net *net, __u16 num, struct udp_hslot *hslot2, struct sock *sk) { struct sock *sk2; kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); udp_portaddr_for_each_entry(sk2, &hslot2->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && (udp_sk(sk2)->udp_port_hash == num) && (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && inet_rcv_saddr_equal(sk, sk2, true)) { if (sk2->sk_reuseport && sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(uid, sock_i_uid(sk2))) { res = 0; } else { res = 1; } break; } } spin_unlock(&hslot2->lock); return res; } static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) { struct net *net = sock_net(sk); kuid_t uid = sock_i_uid(sk); struct sock *sk2; sk_for_each(sk2, &hslot->head) { if (net_eq(sock_net(sk2), net) && sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) && (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && inet_rcv_saddr_equal(sk, sk2, false)) { return reuseport_add_sock(sk, sk2, inet_rcv_saddr_any(sk)); } } return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); } /** * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * * @sk: socket struct in question * @snum: port number to look up * @hash2_nulladdr: AF-dependent hash value in secondary hash chains, * with NULL address */ int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr) { struct udp_table *udptable = sk->sk_prot->h.udp_table; struct udp_hslot *hslot, *hslot2; struct net *net = sock_net(sk); int error = -EADDRINUSE; if (!snum) { DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); unsigned short first, last; int low, high, remaining; unsigned int rand; inet_sk_get_local_port_range(sk, &low, &high); remaining = (high - low) + 1; rand = get_random_u32(); first = reciprocal_scale(rand, remaining) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE */ rand = (rand | 1) * (udptable->mask + 1); last = first + udptable->mask + 1; do { hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, udptable->log); snum = first; /* * Iterate on all possible values of snum for this hash. * Using steps of an odd multiple of UDP_HTABLE_SIZE * give us randomization and full range coverage. */ do { if (low <= snum && snum <= high && !test_bit(snum >> udptable->log, bitmap) && !inet_is_local_reserved_port(net, snum)) goto found; snum += rand; } while (snum != first); spin_unlock_bh(&hslot->lock); cond_resched(); } while (++first != last); goto fail; } else { hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); if (hslot->count > 10) { int exist; unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum; slot2 &= udptable->mask; hash2_nulladdr &= udptable->mask; hslot2 = udp_hashslot2(udptable, slot2); if (hslot->count < hslot2->count) goto scan_primary_hash; exist = udp_lib_lport_inuse2(net, snum, hslot2, sk); if (!exist && (hash2_nulladdr != slot2)) { hslot2 = udp_hashslot2(udptable, hash2_nulladdr); exist = udp_lib_lport_inuse2(net, snum, hslot2, sk); } if (exist) goto fail_unlock; else goto found; } scan_primary_hash: if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0)) goto fail_unlock; } found: inet_sk(sk)->inet_num = snum; udp_sk(sk)->udp_port_hash = snum; udp_sk(sk)->udp_portaddr_hash ^= snum; if (sk_unhashed(sk)) { if (sk->sk_reuseport && udp_reuseport_add_sock(sk, hslot)) { inet_sk(sk)->inet_num = 0; udp_sk(sk)->udp_port_hash = 0; udp_sk(sk)->udp_portaddr_hash ^= snum; goto fail_unlock; } sk_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock(&hslot2->lock); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node, &hslot2->head); else hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, &hslot2->head); hslot2->count++; spin_unlock(&hslot2->lock); } sock_set_flag(sk, SOCK_RCU_FREE); error = 0; fail_unlock: spin_unlock_bh(&hslot->lock); fail: return error; } EXPORT_SYMBOL(udp_lib_get_port); int udp_v4_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); unsigned int hash2_partial = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); /* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; return udp_lib_get_port(sk, snum, hash2_nulladdr); } static int compute_score(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, int dif, int sdif) { int score; struct inet_sock *inet; bool dev_match; if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || ipv6_only_sock(sk)) return -1; if (sk->sk_rcv_saddr != daddr) return -1; score = (sk->sk_family == PF_INET) ? 2 : 1; inet = inet_sk(sk); if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; score += 4; } dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif); if (!dev_match) return -1; if (sk->sk_bound_dev_if) score += 4; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } static u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { static u32 udp_ehash_secret __read_mostly; net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, udp_ehash_secret + net_hash_mix(net)); } static struct sock *lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum) { struct sock *reuse_sk = NULL; u32 hash; if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); } return reuse_sk; } /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, struct sk_buff *skb) { struct sock *sk, *result; int score, badness; result = NULL; badness = 0; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { badness = score; result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); if (!result) { result = sk; continue; } /* Fall back to scoring if group has connections */ if (!reuseport_has_conns(sk)) return result; /* Reuseport logic returned an error, keep original score. */ if (IS_ERR(result)) continue; badness = compute_score(result, net, saddr, sport, daddr, hnum, dif, sdif); } } return result; } static struct sock *udp4_lookup_run_bpf(struct net *net, struct udp_table *udptable, struct sk_buff *skb, __be32 saddr, __be16 sport, __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; if (udptable != &udp_table) return NULL; /* only UDP is supported */ no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); if (reuse_sk) sk = reuse_sk; return sk; } /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; struct sock *result, *sk; hash2 = ipv4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; /* Lookup connected or non-wildcard socket */ result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) goto done; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp4_lookup_run_bpf(net, udptable, skb, saddr, sport, daddr, hnum, dif); if (sk) { result = sk; goto done; } } /* Got non-wildcard socket or error on first lookup */ if (result) goto done; /* Lookup wildcard sockets */ hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; result = udp4_lib_lookup2(net, saddr, sport, htonl(INADDR_ANY), hnum, dif, sdif, hslot2, skb); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(__udp4_lib_lookup); static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { const struct iphdr *iph = ip_hdr(skb); return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), udptable, skb); } struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = ip_hdr(skb); return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), &udp_table, NULL); } /* Must be called under rcu_read_lock(). * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { struct sock *sk; sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, 0, &udp_table, NULL); if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(udp4_lib_lookup); #endif static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif, unsigned short hnum) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net) || udp_sk(sk)->udp_port_hash != hnum || (inet->inet_daddr && inet->inet_daddr != rmt_addr) || (inet->inet_dport != rmt_port && inet->inet_dport) || (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) || ipv6_only_sock(sk) || !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return false; if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif)) return false; return true; } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); EXPORT_SYMBOL(udp_encap_needed_key); #if IS_ENABLED(CONFIG_IPV6) DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); EXPORT_SYMBOL(udpv6_encap_needed_key); #endif void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); } EXPORT_SYMBOL(udp_encap_enable); void udp_encap_disable(void) { static_branch_dec(&udp_encap_needed_key); } EXPORT_SYMBOL(udp_encap_disable); /* Handler for tunnels with arbitrary destination ports: no socket lookup, go * through error handlers in encapsulations looking for a match. */ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, u32 info); const struct ip_tunnel_encap_ops *encap; encap = rcu_dereference(iptun_encaps[i]); if (!encap) continue; handler = encap->err_handler; if (handler && !handler(skb, info)) return 0; } return -ENOENT; } /* Try to match ICMP errors to UDP tunnels by looking up a socket without * reversing source and destination port: this will match tunnels that force the * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that * lwtunnels might actually break this assumption by being configured with * different destination ports on endpoints, in this case we won't be able to * trace ICMP messages back to them. * * If this doesn't match any socket, probe tunnels with arbitrary destination * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port * we've sent packets to won't necessarily match the local destination port. * * Then ask the tunnel implementation to match the error against a valid * association. * * Return an error if we can't find a match, the socket if we need further * processing, zero otherwise. */ static struct sock *__udp4_lib_err_encap(struct net *net, const struct iphdr *iph, struct udphdr *uh, struct udp_table *udptable, struct sock *sk, struct sk_buff *skb, u32 info) { int (*lookup)(struct sock *sk, struct sk_buff *skb); int network_offset, transport_offset; struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); /* Network header needs to point to the outer IPv4 header inside ICMP */ skb_reset_network_header(skb); /* Transport header needs to point to the UDP header */ skb_set_transport_header(skb, iph->ihl << 2); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (lookup && lookup(sk, skb)) sk = NULL; goto out; } sk = __udp4_lib_lookup(net, iph->daddr, uh->source, iph->saddr, uh->dest, skb->dev->ifindex, 0, udptable, NULL); if (sk) { up = udp_sk(sk); lookup = READ_ONCE(up->encap_err_lookup); if (!lookup || lookup(sk, skb)) sk = NULL; } out: if (!sk) sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info)); skb_set_transport_header(skb, transport_offset); skb_set_network_header(skb, network_offset); return sk; } /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. * Header points to the ip header of the error packet. We move * on past this. Then (as it used to claim before adjustment) * header points to the first 8 bytes of the udp header. We need * to find the appropriate port. */ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; const struct iphdr *iph = (const struct iphdr *)skb->data; struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2)); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; bool tunnel = false; struct sock *sk; int harderr; int err; struct net *net = dev_net(skb->dev); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udp_encap_needed_key)) { sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, info); if (!sk) return 0; } else sk = ERR_PTR(-ENOENT); if (IS_ERR(sk)) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return PTR_ERR(sk); } tunnel = true; } err = 0; harderr = 0; inet = inet_sk(sk); switch (type) { default: case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; case ICMP_SOURCE_QUENCH: goto out; case ICMP_PARAMETERPROB: err = EPROTO; harderr = 1; break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ ipv4_sk_update_pmtu(skb, sk, info); if (inet->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; } goto out; } err = EHOSTUNREACH; if (code <= NR_ICMP_UNREACH) { harderr = icmp_err_convert[code].fatal; err = icmp_err_convert[code].errno; } break; case ICMP_REDIRECT: ipv4_sk_redirect(skb, sk); goto out; } /* * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ if (udp_sk(sk)->encap_err_rcv) udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); goto out; } if (!inet->recverr) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); sk->sk_err = err; sk_error_report(sk); out: return 0; } int udp_err(struct sk_buff *skb, u32 info) { return __udp4_lib_err(skb, info, &udp_table); } /* * Throw away all pending data and cancel the corking. Socket is locked. */ void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); if (up->pending) { up->len = 0; WRITE_ONCE(up->pending, 0); ip_flush_pending_frames(sk); } } EXPORT_SYMBOL(udp_flush_pending_frames); /** * udp4_hwcsum - handle outgoing HW checksumming * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) * @src: source IP address * @dst: destination IP address */ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { struct udphdr *uh = udp_hdr(skb); int offset = skb_transport_offset(skb); int len = skb->len - offset; int hlen = len; __wsum csum = 0; if (!skb_has_frag_list(skb)) { /* * Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0); } else { struct sk_buff *frags; /* * HW-checksum won't work as there are two or more * fragments on the socket so that all csums of sk_buffs * should be together */ skb_walk_frags(skb, frags) { csum = csum_add(csum, frags->csum); hlen -= frags->len; } csum = skb_checksum(skb, offset, hlen, csum); skb->ip_summed = CHECKSUM_NONE; uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } } EXPORT_SYMBOL_GPL(udp4_hwcsum); /* Function to set UDP checksum for an IPv4 UDP packet. This is intended * for the simple case like when setting the checksum for a UDP tunnel. */ void udp_set_csum(bool nocheck, struct sk_buff *skb, __be32 saddr, __be32 daddr, int len) { struct udphdr *uh = udp_hdr(skb); if (nocheck) { uh->check = 0; } else if (skb_is_gso(skb)) { uh->check = ~udp_v4_check(len, saddr, daddr, 0); } else if (skb->ip_summed == CHECKSUM_PARTIAL) { uh->check = 0; uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb)); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); uh->check = ~udp_v4_check(len, saddr, daddr, 0); } } EXPORT_SYMBOL(udp_set_csum); static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, struct inet_cork *cork) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct udphdr *uh; int err; int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; int datalen = len - sizeof(*uh); __wsum csum = 0; /* * Create a UDP header */ uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = fl4->fl4_dport; uh->len = htons(len); uh->check = 0; if (cork->gso_size) { const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); if (hlen + cork->gso_size > cork->fragsize) { kfree_skb(skb); return -EINVAL; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } if (sk->sk_no_check_tx) { kfree_skb(skb); return -EINVAL; } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } if (datalen > cork->gso_size) { skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, cork->gso_size); } goto csum_partial; } if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); else if (sk->sk_no_check_tx) { /* UDP csum off */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ csum_partial: udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; } else csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len, sk->sk_protocol, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: err = ip_send_skb(sock_net(sk), skb); if (err) { if (err == -ENOBUFS && !inet->recverr) { UDP_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; } } else UDP_INC_STATS(sock_net(sk), UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } /* * Push out all pending data as one UDP datagram. Socket is locked. */ int udp_push_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct flowi4 *fl4 = &inet->cork.fl.u.ip4; struct sk_buff *skb; int err = 0; skb = ip_finish_skb(sk, fl4); if (!skb) goto out; err = udp_send_skb(skb, fl4, &inet->cork.base); out: up->len = 0; WRITE_ONCE(up->pending, 0); return err; } EXPORT_SYMBOL(udp_push_pending_frames); static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) { switch (cmsg->cmsg_type) { case UDP_SEGMENT: if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16))) return -EINVAL; *gso_size = *(__u16 *)CMSG_DATA(cmsg); return 0; default: return -EINVAL; } } int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) { struct cmsghdr *cmsg; bool need_ip = false; int err; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_UDP) { need_ip = true; continue; } err = __udp_cmsg_send(cmsg, gso_size); if (err) return err; } return need_ip; } EXPORT_SYMBOL_GPL(udp_cmsg_send); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; struct ipcm_cookie ipc; struct rtable *rt = NULL; int free = 0; int connected = 0; __be32 daddr, faddr, saddr; __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; if (len > 0xFFFF) return -EMSGSIZE; /* * Check the flags. */ if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; if (READ_ONCE(up->pending)) { /* * There are pending frames. * The socket lock must be held while it's corked. */ lock_sock(sk); if (likely(up->pending)) { if (unlikely(up->pending != AF_INET)) { release_sock(sk); return -EINVAL; } goto do_append_data; } release_sock(sk); } ulen += sizeof(struct udphdr); /* * Get and verify the address. */ if (usin) { if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { if (usin->sin_family != AF_UNSPEC) return -EAFNOSUPPORT; } daddr = usin->sin_addr.s_addr; dport = usin->sin_port; if (dport == 0) return -EINVAL; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = inet->inet_daddr; dport = inet->inet_dport; /* Open fast path for connected socket. Route will not be used, if at least one option is set. */ connected = 1; } ipcm_init_sk(&ipc, inet); ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); connected = 0; } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { memcpy(&opt_copy, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); ipc.opt = &opt_copy.opt; } rcu_read_unlock(); } if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, (struct sockaddr *)usin, &ipc.addr); if (err) goto out_free; if (usin) { if (usin->sin_port == 0) { /* BPF program set invalid port. Reject it. */ err = -EINVAL; goto out_free; } daddr = usin->sin_addr.s_addr; dport = usin->sin_port; } } saddr = ipc.addr; ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) { err = -EINVAL; goto out_free; } faddr = ipc.opt->opt.faddr; connected = 0; } tos = get_rttos(&ipc, inet); if (sock_flag(sk, SOCK_LOCALROUTE) || (msg->msg_flags & MSG_DONTROUTE) || (ipc.opt && ipc.opt->opt.is_strictroute)) { tos |= RTO_ONLINK; connected = 0; } if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; connected = 0; } else if (!ipc.oif) { ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and * uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. * If so, we want to allow the send using the uc_index. */ if (ipc.oif != inet->uc_index && ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk), inet->uc_index)) { ipc.oif = inet->uc_index; } } if (connected) rt = (struct rtable *)sk_dst_check(sk, 0); if (!rt) { struct net *net = sock_net(sk); __u8 flow_flags = inet_sk_flowi_flags(sk); fl4 = &fl4_stack; flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, flow_flags, faddr, saddr, dport, inet->inet_sport, sk->sk_uid); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } err = -EACCES; if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) goto out; if (connected) sk_dst_set(sk, dst_clone(&rt->dst)); } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: saddr = fl4->saddr; if (!ipc.addr) daddr = ipc.addr = fl4->daddr; /* Lockless fast path for the non-corking case. */ if (!corkreq) { struct inet_cork cork; skb = ip_make_skb(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, &cork, msg->msg_flags); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) err = udp_send_skb(skb, fl4, &cork); goto out; } lock_sock(sk); if (unlikely(up->pending)) { /* The socket is already corked while preparing it. */ /* ... which is an evident application bug. --ANK */ release_sock(sk); net_dbg_ratelimited("socket already corked\n"); err = -EINVAL; goto out; } /* * Now cork the socket to pend data. */ fl4 = &inet->cork.fl.u.ip4; fl4->daddr = daddr; fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = inet->inet_sport; WRITE_ONCE(up->pending, AF_INET); do_append_data: up->len += ulen; err = ip_append_data(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_flush_pending_frames(sk); else if (!corkreq) err = udp_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) WRITE_ONCE(up->pending, 0); release_sock(sk); out: ip_rt_put(rt); out_free: if (free) kfree(ipc.opt); if (!err) return len; /* * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting * ENOBUFS might not be good (it's not tunable per se), but otherwise * we don't have a good statistic (IpOutDiscards but it can be too many * things). We could add another new stat but at least for now that * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(&rt->dst, &fl4->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } EXPORT_SYMBOL(udp_sendmsg); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct bio_vec bvec; struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; if (flags & MSG_SENDPAGE_NOTLAST) msg.msg_flags |= MSG_MORE; bvec_set_page(&bvec, page, size, offset); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); return udp_sendmsg(sk, &msg, size); } #define UDP_SKB_IS_STATELESS 0x80000000 /* all head states (dst, sk, nf conntrack) except skb extensions are * cleared by udp_rcv(). * * We need to preserve secpath, if present, to eventually process * IP_CMSG_PASSSEC at recvmsg() time. * * Other extensions can be cleared. */ static bool udp_try_make_stateless(struct sk_buff *skb) { if (!skb_has_extensions(skb)) return true; if (!secpath_exists(skb)) { skb_ext_reset(skb); return true; } return false; } static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch = udp_skb_scratch(skb); BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long)); scratch->_tsize_state = skb->truesize; #if BITS_PER_LONG == 64 scratch->len = skb->len; scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif if (udp_try_make_stateless(skb)) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) { /* We come here after udp_lib_checksum_complete() returned 0. * This means that __skb_checksum_complete() might have * set skb->csum_valid to 1. * On 64bit platforms, we can set csum_unnecessary * to true, but only if the skb is not shared. */ #if BITS_PER_LONG == 64 if (!skb_shared(skb)) udp_skb_scratch(skb)->csum_unnecessary = true; #endif } static int udp_skb_truesize(struct sk_buff *skb) { return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; } static bool udp_skb_has_head_state(struct sk_buff *skb) { return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS); } /* fully reclaim rmem/fwd memory allocated for skb */ static void udp_rmem_release(struct sock *sk, int size, int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; int amt; if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; if (size < (sk->sk_rcvbuf >> 2) && !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; } up->forward_deficit = 0; /* acquire the sk_receive_queue for fwd allocated memory scheduling, * if the called don't held it already */ sk_queue = &sk->sk_receive_queue; if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); sk_forward_alloc_add(sk, size); amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); sk_forward_alloc_add(sk, -amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); /* this can save us from acquiring the rx queue lock on next receive */ skb_queue_splice_tail_init(sk_queue, &up->reader_queue); if (!rx_queue_lock_held) spin_unlock(&sk_queue->lock); } /* Note: called with reader_queue.lock held. * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch * This avoids a cache line miss while receive_queue lock is held. * Look at __udp_enqueue_schedule_skb() to find where this copy is done. */ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) { prefetch(&skb->data); udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); } EXPORT_SYMBOL(udp_skb_destructor); /* as above, but the caller held the rx queue lock, too */ static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) { prefetch(&skb->data); udp_rmem_release(sk, udp_skb_truesize(skb), 1, true); } /* Idea of busylocks is to let producers grab an extra spinlock * to relieve pressure on the receive_queue spinlock shared by consumer. * Under flood, this means that only one producer can be in line * trying to acquire the receive_queue spinlock. * These busylock can be allocated on a per cpu manner, instead of a * per socket one (that would consume a cache line per socket) */ static int udp_busylocks_log __read_mostly; static spinlock_t *udp_busylocks __read_mostly; static spinlock_t *busylock_acquire(void *ptr) { spinlock_t *busy; busy = udp_busylocks + hash_ptr(ptr, udp_busylocks_log); spin_lock(busy); return busy; } static void busylock_release(spinlock_t *busy) { if (busy) spin_unlock(busy); } int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; int rmem, delta, amt, err = -ENOMEM; spinlock_t *busy = NULL; int size; /* try to avoid the costly atomic add/sub pair when the receive * queue is full; always allow at least a packet */ rmem = atomic_read(&sk->sk_rmem_alloc); if (rmem > sk->sk_rcvbuf) goto drop; /* Under mem pressure, it might be helpful to help udp_recvmsg() * having linear skbs : * - Reduce memory overhead and thus increase receive queue capacity * - Less cache line misses at copyout() time * - Less work at consume_skb() (less alien page frag freeing) */ if (rmem > (sk->sk_rcvbuf >> 1)) { skb_condense(skb); busy = busylock_acquire(sk); } size = skb->truesize; udp_set_dev_scratch(skb); /* we drop only if the receive buf is full and the receive * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); if (size >= sk->sk_forward_alloc) { amt = sk_mem_pages(size); delta = amt << PAGE_SHIFT; if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) { err = -ENOBUFS; spin_unlock(&list->lock); goto uncharge_drop; } sk->sk_forward_alloc += delta; } sk_forward_alloc_add(sk, -size); /* no need to setup a destructor, we will explicitly release the * forward allocated memory on dequeue */ sock_skb_set_dropcount(sk, skb); __skb_queue_tail(list, skb); spin_unlock(&list->lock); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); busylock_release(busy); return 0; uncharge_drop: atomic_sub(skb->truesize, &sk->sk_rmem_alloc); drop: atomic_inc(&sk->sk_drops); busylock_release(busy); return err; } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); unsigned int total = 0; struct sk_buff *skb; skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue); while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) { total += skb->truesize; kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); } EXPORT_SYMBOL_GPL(udp_destruct_common); static void udp_destruct_sock(struct sock *sk) { udp_destruct_common(sk); inet_sock_destruct(sk); } int udp_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) { bool slow = lock_sock_fast(sk); sk_peek_offset_bwd(sk, len); unlock_sock_fast(sk, slow); } if (!skb_unref(skb)) return; /* In the more common cases we cleared the head states previously, * see __udp_queue_rcv_skb(). */ if (unlikely(udp_skb_has_head_state(skb))) skb_release_head_state(skb); __consume_stateless_skb(skb); } EXPORT_SYMBOL_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, int *total) { struct sk_buff *skb; while ((skb = skb_peek(rcvq)) != NULL) { if (udp_lib_checksum_complete(skb)) { __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, IS_UDPLITE(sk)); __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, IS_UDPLITE(sk)); atomic_inc(&sk->sk_drops); __skb_unlink(skb, rcvq); *total += skb->truesize; kfree_skb(skb); } else { udp_skb_csum_unnecessary_set(skb); break; } } return skb; } /** * first_packet_length - return length of first packet in receive queue * @sk: socket * * Drops all bad checksum frames, until a valid one is found. * Returns the length of found skb, or -1 if none is found. */ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff *skb; int total = 0; int res; spin_lock_bh(&rcvq->lock); skb = __first_packet_length(sk, rcvq, &total); if (!skb && !skb_queue_empty_lockless(sk_queue)) { spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, rcvq); spin_unlock(&sk_queue->lock); skb = __first_packet_length(sk, rcvq, &total); } res = skb ? skb->len : -1; if (total) udp_rmem_release(sk, total, 1, false); spin_unlock_bh(&rcvq->lock); return res; } /* * IOCTL requests applicable to the UDP protocol */ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { int amount = max_t(int, 0, first_packet_length(sk)); return put_user(amount, (int __user *)arg); } default: return -ENOIOCTLCMD; } return 0; } EXPORT_SYMBOL(udp_ioctl); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, int *err) { struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff_head *queue; struct sk_buff *last; long timeo; int error; queue = &udp_sk(sk)->reader_queue; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb; error = sock_error(sk); if (error) break; error = -EAGAIN; do { spin_lock_bh(&queue->lock); skb = __skb_try_recv_from_queue(sk, queue, flags, off, err, &last); if (skb) { if (!(flags & MSG_PEEK)) udp_skb_destructor(sk, skb); spin_unlock_bh(&queue->lock); return skb; } if (skb_queue_empty_lockless(sk_queue)) { spin_unlock_bh(&queue->lock); goto busy_check; } /* refill the reader queue and walk it again * keep both queues locked to avoid re-acquiring * the sk_receive_queue lock if fwd memory scheduling * is needed. */ spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, queue); skb = __skb_try_recv_from_queue(sk, queue, flags, off, err, &last); if (skb && !(flags & MSG_PEEK)) udp_skb_dtor_locked(sk, skb); spin_unlock(&sk_queue->lock); spin_unlock_bh(&queue->lock); if (skb) return skb; busy_check: if (!sk_can_busy_loop(sk)) break; sk_busy_loop(sk, flags & MSG_DONTWAIT); } while (!skb_queue_empty_lockless(sk_queue)); /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, &error, &timeo, (struct sk_buff *)sk_queue)); *err = error; return NULL; } EXPORT_SYMBOL(__skb_recv_udp); int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; int err; try_again: skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); if (!skb) return err; if (udp_lib_checksum_complete(skb)) { int is_udplite = IS_UDPLITE(sk); struct net *net = sock_net(sk); __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, is_udplite); __UDP_INC_STATS(net, UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); kfree_skb(skb); goto try_again; } WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); return recv_actor(sk, skb); } EXPORT_SYMBOL(udp_read_skb); /* * This should be easy, if there is something there we * return it, otherwise we block. */ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; unsigned int ulen, copied; int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); bool checksum_valid = false; if (flags & MSG_ERRQUEUE) return ip_recv_error(sk, msg, len, addr_len); try_again: off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, &off, &err); if (!skb) return err; ulen = udp_skb_len(skb); copied = len; if (copied > ulen - off) copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial * coverage checksum (UDP-Lite), do it before the copy. */ if (copied < ulen || peeking || (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { checksum_valid = udp_skb_csum_unnecessary(skb) || !__udp_lib_checksum_complete(skb); if (!checksum_valid) goto csum_copy_err; } if (checksum_valid || udp_skb_csum_unnecessary(skb)) { if (udp_skb_is_linear(skb)) err = copy_linear_skb(skb, copied, off, &msg->msg_iter); else err = skb_copy_datagram_msg(skb, off, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_err; } if (unlikely(err)) { if (!peeking) { atomic_inc(&sk->sk_drops); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } kfree_skb(skb); return err; } if (!peeking) UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); sock_recv_cmsgs(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, (struct sockaddr *)sin); } if (udp_sk(sk)->gro_enabled) udp_cmsg_recv(msg, sk, skb); if (inet->cmsg_flags) ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); err = copied; if (flags & MSG_TRUNC) err = ulen; skb_consume_udp(sk, skb, peeking ? -err : err); return err; csum_copy_err: if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, udp_skb_destructor)) { UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } kfree_skb(skb); /* starting over for a new packet, but check if we need to yield */ cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from __ip4_datagram_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 < sizeof(struct sockaddr_in)) return -EINVAL; return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); } EXPORT_SYMBOL(udp_pre_connect); int __udp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); /* * 1003.1g - break association. */ sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); if (sk->sk_prot->rehash && (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) sk->sk_prot->rehash(sk); } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); inet->inet_sport = 0; } sk_dst_reset(sk); return 0; } EXPORT_SYMBOL(__udp_disconnect); int udp_disconnect(struct sock *sk, int flags) { lock_sock(sk); __udp_disconnect(sk, flags); release_sock(sk); return 0; } EXPORT_SYMBOL(udp_disconnect); void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; struct udp_hslot *hslot, *hslot2; hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); if (sk_del_node_init_rcu(sk)) { hslot->count--; inet_sk(sk)->inet_num = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); spin_lock(&hslot2->lock); hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); } spin_unlock_bh(&hslot->lock); } } EXPORT_SYMBOL(udp_lib_unhash); /* * inet_rcv_saddr was changed, we must rehash secondary hash */ void udp_lib_rehash(struct sock *sk, u16 newhash) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; struct udp_hslot *hslot, *hslot2, *nhslot2; hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { hslot = udp_hashslot(udptable, sock_net(sk), udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); if (hslot2 != nhslot2) { spin_lock(&hslot2->lock); hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); spin_lock(&nhslot2->lock); hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, &nhslot2->head); nhslot2->count++; spin_unlock(&nhslot2->lock); } spin_unlock_bh(&hslot->lock); } } } EXPORT_SYMBOL(udp_lib_rehash); void udp_v4_rehash(struct sock *sk) { u16 new_hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); } static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; if (inet_sk(sk)->inet_daddr) { sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); sk_incoming_cpu_update(sk); } else { sk_mark_napi_id_once(sk, skb); } rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); int drop_reason; /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) { UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; } else { UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, is_udplite); drop_reason = SKB_DROP_REASON_PROTO_MEM; } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb_reason(skb, drop_reason); trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } return 0; } /* returns: * -1: error * 0: success * >0: "udp encap" protocol resubmission * * Note that in the success and error cases, the skb is assumed to * have either been requeued or freed. */ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); /* * Charge it to the socket, dropping if the queue is full. */ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; } nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* * This is an encapsulation socket so pass the skb to * the socket's udp_encap_rcv() hook. Otherwise, just * fall through and pass this up the UDP socket. * up->encap_rcv() returns the following value: * =0 if skb was successfully passed to the encap * handler or was discarded by it. * >0 if skb should be passed on to UDP. * <0 if skb should be resubmitted as proto -N */ /* if we're overly short, let UDP handle it */ encap_rcv = READ_ONCE(up->encap_rcv); if (encap_rcv) { int ret; /* Verify checksum before giving to encap */ if (udp_lib_checksum_complete(skb)) goto csum_error; ret = encap_rcv(sk, skb); if (ret <= 0) { __UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); return -ret; } } /* FALLTHROUGH -- it's a UDP Packet */ } /* * UDP-Lite specific tests, ignored on UDP sockets */ if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are * disabled for the following two types of errors: these depend * on the application settings, not on the functioning of the * protocol stack as such. * * RFC 3828 here recommends (sec 3.3): "There should also be a * way ... to ... at least let the receiving application block * delivery of packets with coverage values less than a value * provided by the application." */ if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLite: partial coverage %d while full coverage %d requested\n", UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } /* The next case involves violating the min. coverage requested * by the receiver. This is subtle: if receiver wants x and x is * greater than the buffersize/MTU then receiver will complain * that it wants x while sender emits packets of smaller size y. * Therefore the above ...()->partial_cov statement is essential. */ if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n", UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) goto csum_error; if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto drop; } udp_csum_pull_header(skb); ipv4_pktinfo_prepare(sk, skb, true); return __udp_queue_rcv_skb(sk, skb); csum_error: drop_reason = SKB_DROP_REASON_UDP_CSUM; __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); kfree_skb_reason(skb, drop_reason); return -1; } static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff *next, *segs; int ret; if (likely(!udp_unexpected_gso(sk, skb))) return udp_queue_rcv_one_skb(sk, skb); BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_GSO_CB_OFFSET); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, true); skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); udp_post_segment_fix_csum(skb); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } return 0; } /* For TCP sockets, sk_rx_dst is protected by socket lock * For UDP, we use xchg() to guard against concurrent changes. */ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; if (dst_hold_safe(dst)) { old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } return false; } EXPORT_SYMBOL(udp_sk_rx_dst_set); /* * Multicasts and broadcasts go to each listener. * * Note: called only from the BH handler context. */ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udphdr *uh, __be32 saddr, __be32 daddr, struct udp_table *udptable, int proto) { struct sock *sk, *first = NULL; unsigned short hnum = ntohs(uh->dest); struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); unsigned int offset = offsetof(typeof(*sk), sk_node); int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); struct hlist_node *node; struct sk_buff *nskb; if (use_hash2) { hash2_any = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & udptable->mask; hash2 = ipv4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr, uh->source, saddr, dif, sdif, hnum)) continue; if (!first) { first = sk; continue; } nskb = skb_clone(skb, GFP_ATOMIC); if (unlikely(!nskb)) { atomic_inc(&sk->sk_drops); __UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); __UDP_INC_STATS(net, UDP_MIB_INERRORS, IS_UDPLITE(sk)); continue; } if (udp_queue_rcv_skb(sk, nskb) > 0) consume_skb(nskb); } /* Also lookup *:port if we are using hash2 and haven't done so yet. */ if (use_hash2 && hash2 != hash2_any) { hash2 = hash2_any; goto start_lookup; } if (first) { if (udp_queue_rcv_skb(first, skb) > 0) consume_skb(skb); } else { kfree_skb(skb); __UDP_INC_STATS(net, UDP_MIB_IGNOREDMULTI, proto == IPPROTO_UDPLITE); } return 0; } /* Initialize UDP checksum. If exited with zero value (success), * CHECKSUM_UNNECESSARY means, that no more checks are required. * Otherwise, csum completion requires checksumming packet body, * including udp header and folding it to skb->csum. */ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) { int err; UDP_SKB_CB(skb)->partial_cov = 0; UDP_SKB_CB(skb)->cscov = skb->len; if (proto == IPPROTO_UDPLITE) { err = udplite_checksum_init(skb, uh); if (err) return err; if (UDP_SKB_CB(skb)->partial_cov) { skb->csum = inet_compute_pseudo(skb, proto); return 0; } } /* Note, we are only interested in != 0 or == 0, thus the * force to int. */ err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, inet_compute_pseudo); if (err) return err; if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) { /* If SW calculated the value, we know it's bad */ if (skb->csum_complete_sw) return 1; /* HW says the value is bad. Let's validate that. * skb->csum is no longer the full packet checksum, * so don't treat it as such. */ skb_checksum_complete_unset(skb); } return 0; } /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and * return code conversion for ip layer consumption */ static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, struct udphdr *uh) { int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) skb_checksum_try_convert(skb, IPPROTO_UDP, inet_compute_pseudo); ret = udp_queue_rcv_skb(sk, skb); /* a return value > 0 means to resubmit the input, but * it wants the return to be -protocol, or 0 */ if (ret > 0) return -ret; return 0; } /* * All we need to do is get the socket, and then do a checksum. */ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { struct sock *sk; struct udphdr *uh; unsigned short ulen; struct rtable *rt = skb_rtable(skb); __be32 saddr, daddr; struct net *net = dev_net(skb->dev); bool refcounted; int drop_reason; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; /* * Validate the packet. */ if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto drop; /* No space for header. */ uh = udp_hdr(skb); ulen = ntohs(uh->len); saddr = ip_hdr(skb)->saddr; daddr = ip_hdr(skb)->daddr; if (ulen > skb->len) goto short_packet; if (proto == IPPROTO_UDP) { /* UDP validates ulen. */ if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen)) goto short_packet; uh = udp_hdr(skb); } if (udp4_csum_init(skb, uh, proto)) goto csum_error; sk = skb_steal_sock(skb, &refcounted); if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); if (refcounted) sock_put(sk); return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; nf_reset_ct(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_lib_checksum_complete(skb)) goto csum_error; drop_reason = SKB_DROP_REASON_NO_SOCKET; __UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); /* * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ kfree_skb_reason(skb, drop_reason); return 0; short_packet: drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), ulen, skb->len, &daddr, ntohs(uh->dest)); goto drop; csum_error: /* * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ drop_reason = SKB_DROP_REASON_UDP_CSUM; net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), ulen); __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb_reason(skb, drop_reason); return 0; } /* We can only early demux multicast if there is a single matching socket. * If more than one socket found returns NULL */ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { unsigned short hnum = ntohs(loc_port); struct sock *sk, *result; struct udp_hslot *hslot; unsigned int slot; slot = udp_hashfn(net, hnum, udp_table.mask); hslot = &udp_table.hash[slot]; /* Do not bother scanning a too big list */ if (hslot->count > 10) return NULL; result = NULL; sk_for_each_rcu(sk, &hslot->head) { if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr, rmt_port, rmt_addr, dif, sdif, hnum)) { if (result) return NULL; result = sk; } } return result; } /* For unicast we should only early demux connected sockets or we can * break forwarding setups. The chains here can be long so only check * if the first socket is an exact match and if not move on. */ static struct sock *__udp4_lib_demux_lookup(struct net *net, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif, int sdif) { INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); unsigned short hnum = ntohs(loc_port); unsigned int hash2, slot2; struct udp_hslot *hslot2; __portpair ports; struct sock *sk; hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); slot2 = hash2 & udp_table.mask; hslot2 = &udp_table.hash2[slot2]; ports = INET_COMBINED_PORTS(rmt_port, hnum); udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { if (inet_match(net, sk, acookie, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; } return NULL; } int udp_v4_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct in_device *in_dev = NULL; const struct iphdr *iph; const struct udphdr *uh; struct sock *sk = NULL; struct dst_entry *dst; int dif = skb->dev->ifindex; int sdif = inet_sdif(skb); int ours; /* validate the packet */ if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) return 0; iph = ip_hdr(skb); uh = udp_hdr(skb); if (skb->pkt_type == PACKET_MULTICAST) { in_dev = __in_dev_get_rcu(skb->dev); if (!in_dev) return 0; ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, iph->protocol); if (!ours) return 0; sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif, sdif); } else if (skb->pkt_type == PACKET_HOST) { sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif, sdif); } if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) return 0; skb->sk = sk; skb->destructor = sock_efree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst) { u32 itag = 0; /* set noref for now. * any place which wants to hold dst has to call * dst_hold_safe() */ skb_dst_set_noref(skb, dst); /* for unconnected multicast sockets we need to validate * the source on each packet */ if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, iph->saddr, iph->tos & IPTOS_RT_MASK, skb->dev, in_dev, &itag); } return 0; } int udp_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); } void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); /* protects from races with udp_abort() */ sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key)) { if (up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) encap_destroy(sk); } if (up->encap_enabled) static_branch_dec(&udp_encap_needed_key); } } /* * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); int val, valbool; int err = 0; int is_udplite = IS_UDPLITE(sk); if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; valbool = val ? 1 : 0; switch (optname) { case UDP_CORK: if (val != 0) { WRITE_ONCE(up->corkflag, 1); } else { WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); } break; case UDP_ENCAP: switch (val) { case 0: #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: case UDP_ENCAP_ESPINUDP_NON_IKE: #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) WRITE_ONCE(up->encap_rcv, ipv6_stub->xfrm6_udp_encap_rcv); else #endif WRITE_ONCE(up->encap_rcv, xfrm4_udp_encap_rcv); #endif fallthrough; case UDP_ENCAP_L2TPINUDP: up->encap_type = val; lock_sock(sk); udp_tunnel_encap_enable(sk->sk_socket); release_sock(sk); break; default: err = -ENOPROTOOPT; break; } break; case UDP_NO_CHECK6_TX: up->no_check6_tx = valbool; break; case UDP_NO_CHECK6_RX: up->no_check6_rx = valbool; break; case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; WRITE_ONCE(up->gso_size, val); break; case UDP_GRO: lock_sock(sk); /* when enabling GRO, accept the related GSO packet type */ if (valbool) udp_tunnel_encap_enable(sk->sk_socket); up->gro_enabled = valbool; up->accept_udp_l4 = valbool; release_sock(sk); break; /* * UDP-Lite's partial checksum coverage (RFC 3828). */ /* The sender sets actual checksum coverage length via this option. * The case coverage > packet length is handled by send module. */ case UDPLITE_SEND_CSCOV: if (!is_udplite) /* Disable the option on UDP sockets */ return -ENOPROTOOPT; if (val != 0 && val < 8) /* Illegal coverage: use default (8) */ val = 8; else if (val > USHRT_MAX) val = USHRT_MAX; up->pcslen = val; up->pcflag |= UDPLITE_SEND_CC; break; /* The receiver specifies a minimum checksum coverage value. To make * sense, this should be set to at least 8 (as done below). If zero is * used, this again means full checksum coverage. */ case UDPLITE_RECV_CSCOV: if (!is_udplite) /* Disable the option on UDP sockets */ return -ENOPROTOOPT; if (val != 0 && val < 8) /* Avoid silly minimal values. */ val = 8; else if (val > USHRT_MAX) val = USHRT_MAX; up->pcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; default: err = -ENOPROTOOPT; break; } return err; } EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_push_pending_frames); return ip_setsockopt(sk, level, optname, optval, optlen); } int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct udp_sock *up = udp_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case UDP_CORK: val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: val = up->encap_type; break; case UDP_NO_CHECK6_TX: val = up->no_check6_tx; break; case UDP_NO_CHECK6_RX: val = up->no_check6_rx; break; case UDP_SEGMENT: val = READ_ONCE(up->gso_size); break; case UDP_GRO: val = up->gro_enabled; break; /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: val = up->pcslen; break; case UDPLITE_RECV_CSCOV: val = up->pcrlen; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } EXPORT_SYMBOL(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_getsockopt(sk, level, optname, optval, optlen); return ip_getsockopt(sk, level, optname, optval, optlen); } /** * udp_poll - wait for a UDP event. * @file: - file struct * @sock: - socket * @wait: - poll table * * This is same as datagram poll, except for the special case of * blocking sockets. If application is using a blocking fd * and a packet with checksum error is in the queue; * then it could get return from select indicating data available * but then block when reading it. Add special case code * to work around these arguably broken applications. */ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) && !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) mask &= ~(EPOLLIN | EPOLLRDNORM); /* psock ingress_msg queue should not contain any bad checksum frames */ if (sk_is_readable(sk)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } EXPORT_SYMBOL(udp_poll); int udp_abort(struct sock *sk, int err) { lock_sock(sk); /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing * with close() */ if (sock_flag(sk, SOCK_DEAD)) goto out; sk->sk_err = err; sk_error_report(sk); __udp_disconnect(sk, 0); out: release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(udp_abort); struct proto udp_prot = { .name = "UDP", .owner = THIS_MODULE, .close = udp_lib_close, .pre_connect = udp_pre_connect, .connect = ip4_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udp_init_sock, .destroy = udp_destroy_sock, .setsockopt = udp_setsockopt, .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .put_port = udp_lib_unhash, #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif .memory_allocated = &udp_memory_allocated, .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udp_table, .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS static struct sock *udp_get_first(struct seq_file *seq, int start) { struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); struct udp_seq_afinfo *afinfo; struct sock *sk; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); sk_for_each(sk, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; if (afinfo->family == AF_UNSPEC || sk->sk_family == afinfo->family) goto found; } spin_unlock_bh(&hslot->lock); } sk = NULL; found: return sk; } static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); struct udp_seq_afinfo *afinfo; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); do { sk = sk_next(sk); } while (sk && (!net_eq(sock_net(sk), net) || (afinfo->family != AF_UNSPEC && sk->sk_family != afinfo->family))); if (!sk) { if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); return udp_get_first(seq, state->bucket + 1); } return sk; } static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) { struct sock *sk = udp_get_first(seq, 0); if (sk) while (pos && (sk = udp_get_next(seq, sk)) != NULL) --pos; return pos ? NULL : sk; } void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } EXPORT_SYMBOL(udp_seq_start); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; if (v == SEQ_START_TOKEN) sk = udp_get_idx(seq, 0); else sk = udp_get_next(seq, v); ++*pos; return sk; } EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; struct udp_seq_afinfo *afinfo; if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else afinfo = pde_data(file_inode(seq->file)); if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); } EXPORT_SYMBOL(udp_seq_stop); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, int bucket) { struct inet_sock *inet = inet_sk(sp); __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), udp_rqueue_get(sp), 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } int udp4_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode ref pointer drops"); else { struct udp_iter_state *state = seq->private; udp4_format_sock(v, seq, state->bucket); } seq_pad(seq, '\n'); return 0; } #ifdef CONFIG_BPF_SYSCALL struct bpf_iter__udp { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct udp_sock *, udp_sk); uid_t uid __aligned(8); int bucket __aligned(8); }; static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) { struct bpf_iter__udp ctx; meta->seq_num--; /* skip SEQ_START_TOKEN */ ctx.meta = meta; ctx.udp_sk = udp_sk; ctx.uid = uid; ctx.bucket = bucket; return bpf_iter_run_prog(prog, &ctx); } static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; if (v == SEQ_START_TOKEN) return 0; uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); return udp_prog_seq_show(prog, &meta, v, uid, state->bucket); } static void bpf_iter_udp_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)udp_prog_seq_show(prog, &meta, v, 0, 0); } udp_seq_stop(seq, v); } static const struct seq_operations bpf_iter_udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, .stop = bpf_iter_udp_seq_stop, .show = bpf_iter_udp_seq_show, }; #endif const struct seq_operations udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, .stop = udp_seq_stop, .show = udp4_seq_show, }; EXPORT_SYMBOL(udp_seq_ops); static struct udp_seq_afinfo udp4_seq_afinfo = { .family = AF_INET, .udp_table = &udp_table, }; static int __net_init udp4_proc_init_net(struct net *net) { if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops, sizeof(struct udp_iter_state), &udp4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit udp4_proc_exit_net(struct net *net) { remove_proc_entry("udp", net->proc_net); } static struct pernet_operations udp4_net_ops = { .init = udp4_proc_init_net, .exit = udp4_proc_exit_net, }; int __init udp4_proc_init(void) { return register_pernet_subsys(&udp4_net_ops); } void udp4_proc_exit(void) { unregister_pernet_subsys(&udp4_net_ops); } #endif /* CONFIG_PROC_FS */ static __initdata unsigned long uhash_entries; static int __init set_uhash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &uhash_entries); if (ret) return 0; if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) uhash_entries = UDP_HTABLE_SIZE_MIN; return 1; } __setup("uhash_entries=", set_uhash_entries); void __init udp_table_init(struct udp_table *table, const char *name) { unsigned int i; table->hash = alloc_large_system_hash(name, 2 * sizeof(struct udp_hslot), uhash_entries, 21, /* one slot per 2 MB */ 0, &table->log, &table->mask, UDP_HTABLE_SIZE_MIN, 64 * 1024); table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { INIT_HLIST_HEAD(&table->hash[i].head); table->hash[i].count = 0; spin_lock_init(&table->hash[i].lock); } for (i = 0; i <= table->mask; i++) { INIT_HLIST_HEAD(&table->hash2[i].head); table->hash2[i].count = 0; spin_lock_init(&table->hash2[i].lock); } } u32 udp_flow_hashrnd(void) { static u32 hashrnd __read_mostly; net_get_random_once(&hashrnd, sizeof(hashrnd)); return hashrnd; } EXPORT_SYMBOL(udp_flow_hashrnd); static int __net_init udp_sysctl_init(struct net *net) { net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; #endif return 0; } static struct pernet_operations __net_initdata udp_sysctl_ops = { .init = udp_sysctl_init, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta, struct udp_sock *udp_sk, uid_t uid, int bucket) static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) { struct udp_iter_state *st = priv_data; struct udp_seq_afinfo *afinfo; int ret; afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); if (!afinfo) return -ENOMEM; afinfo->family = AF_UNSPEC; afinfo->udp_table = &udp_table; st->bpf_seq_afinfo = afinfo; ret = bpf_iter_init_seq_net(priv_data, aux); if (ret) kfree(afinfo); return ret; } static void bpf_iter_fini_udp(void *priv_data) { struct udp_iter_state *st = priv_data; kfree(st->bpf_seq_afinfo); bpf_iter_fini_seq_net(priv_data); } static const struct bpf_iter_seq_info udp_seq_info = { .seq_ops = &bpf_iter_udp_seq_ops, .init_seq_private = bpf_iter_init_udp, .fini_seq_private = bpf_iter_fini_udp, .seq_priv_size = sizeof(struct udp_iter_state), }; static struct bpf_iter_reg udp_reg_info = { .target = "udp", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__udp, udp_sk), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &udp_seq_info, }; static void __init bpf_iter_register(void) { udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP]; if (bpf_iter_reg_target(&udp_reg_info)) pr_warn("Warning: could not register bpf iterator udp\n"); } #endif void __init udp_init(void) { unsigned long limit; unsigned int i; udp_table_init(&udp_table, "UDP"); limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; /* 16 spinlocks per cpu */ udp_busylocks_log = ilog2(nr_cpu_ids) + 4; udp_busylocks = kmalloc(sizeof(spinlock_t) << udp_busylocks_log, GFP_KERNEL); if (!udp_busylocks) panic("UDP: failed to alloc udp_busylocks\n"); for (i = 0; i < (1U << udp_busylocks_log); i++) spin_lock_init(udp_busylocks + i); if (register_pernet_subsys(&udp_sysctl_ops)) panic("UDP: failed to init sysctl parameters.\n"); #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_register(); #endif } |
| 9083 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_X86_XSAVE_H #define __ASM_X86_XSAVE_H #include <linux/uaccess.h> #include <linux/types.h> #include <asm/processor.h> #include <asm/fpu/api.h> #include <asm/user.h> /* Bit 63 of XCR0 is reserved for future expansion */ #define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) #define XSTATE_CPUID 0x0000000d #define TILE_CPUID 0x0000001d #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 #define XSAVE_HDR_OFFSET FXSAVE_SIZE #define XSAVE_YMM_SIZE 256 #define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) #define XSAVE_ALIGNMENT 64 /* All currently supported user features */ #define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM | \ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_XTILE) /* * Features which are restored when returning to user space. * PKRU is not restored on return to user space because PKRU * is switched eagerly in switch_to() and flush_thread() */ #define XFEATURE_MASK_USER_RESTORE \ (XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU) /* Features which are dynamically enabled for a process on request */ #define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA /* All currently supported supervisor features */ #define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID) /* * A supervisor state component may not always contain valuable information, * and its size may be huge. Saving/restoring such supervisor state components * at each context switch can cause high CPU and space overhead, which should * be avoided. Such supervisor state components should only be saved/restored * on demand. The on-demand supervisor features are set in this mask. * * Unlike the existing supported supervisor features, an independent supervisor * feature does not allocate a buffer in task->fpu, and the corresponding * supervisor state component cannot be saved/restored at each context switch. * * To support an independent supervisor feature, a developer should follow the * dos and don'ts as below: * - Do dynamically allocate a buffer for the supervisor state component. * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the * state component to/from the buffer. * - Don't set the bit corresponding to the independent supervisor feature in * IA32_XSS at run time, since it has been set at boot time. */ #define XFEATURE_MASK_INDEPENDENT (XFEATURE_MASK_LBR) /* * Unsupported supervisor features. When a supervisor feature in this mask is * supported in the future, move it to the supported supervisor feature mask. */ #define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT) /* All supervisor states including supported and unsupported states. */ #define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \ XFEATURE_MASK_INDEPENDENT | \ XFEATURE_MASK_SUPERVISOR_UNSUPPORTED) /* * The feature mask required to restore FPU state: * - All user states which are not eagerly switched in switch_to()/exec() * - The suporvisor states */ #define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \ XFEATURE_MASK_SUPERVISOR_SUPPORTED) /* * Features in this mask have space allocated in the signal frame, but may not * have that space initialized when the feature is in its init state. */ #define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \ XFEATURE_MASK_USER_DYNAMIC) extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; extern void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask); int xfeature_size(int xfeature_nr); void xsaves(struct xregs_state *xsave, u64 mask); void xrstors(struct xregs_state *xsave, u64 mask); int xfd_enable_feature(u64 xfd_err); #ifdef CONFIG_X86_64 DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); #endif #ifdef CONFIG_X86_64 DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); static __always_inline __pure bool fpu_state_size_dynamic(void) { return static_branch_unlikely(&__fpu_state_size_dynamic); } #else static __always_inline __pure bool fpu_state_size_dynamic(void) { return false; } #endif #endif |
| 12678 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); if (IS_ERR(dir)) return PTR_ERR(dir); return 0; } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 3 3 3 1 2 3 1 2 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" /* LINKMODES_GET */ struct linkmodes_req_info { struct ethnl_req_info base; }; struct linkmodes_reply_data { struct ethnl_reply_data base; struct ethtool_link_ksettings ksettings; struct ethtool_link_settings *lsettings; bool peer_empty; }; #define LINKMODES_REPDATA(__reply_base) \ container_of(__reply_base, struct linkmodes_reply_data, base) const struct nla_policy ethnl_linkmodes_get_policy[] = { [ETHTOOL_A_LINKMODES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, struct genl_info *info) { struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; data->lsettings = &data->ksettings.base; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); if (ret < 0 && info) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out; } if (!dev->ethtool_ops->cap_link_lanes_supported) data->ksettings.lanes = 0; data->peer_empty = bitmap_empty(data->ksettings.link_modes.lp_advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); out: ethnl_ops_complete(dev); return ret; } static int linkmodes_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int len, ret; len = nla_total_size(sizeof(u8)) /* LINKMODES_AUTONEG */ + nla_total_size(sizeof(u32)) /* LINKMODES_SPEED */ + nla_total_size(sizeof(u32)) /* LINKMODES_LANES */ + nla_total_size(sizeof(u8)) /* LINKMODES_DUPLEX */ + nla_total_size(sizeof(u8)) /* LINKMODES_RATE_MATCHING */ + 0; ret = ethnl_bitset_size(ksettings->link_modes.advertising, ksettings->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; if (!data->peer_empty) { ret = ethnl_bitset_size(ksettings->link_modes.lp_advertising, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; } if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED) len += nla_total_size(sizeof(u8)); if (lsettings->master_slave_state != MASTER_SLAVE_STATE_UNSUPPORTED) len += nla_total_size(sizeof(u8)); return len; } static int linkmodes_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkmodes_reply_data *data = LINKMODES_REPDATA(reply_base); const struct ethtool_link_ksettings *ksettings = &data->ksettings; const struct ethtool_link_settings *lsettings = &ksettings->base; bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; int ret; if (nla_put_u8(skb, ETHTOOL_A_LINKMODES_AUTONEG, lsettings->autoneg)) return -EMSGSIZE; ret = ethnl_put_bitset(skb, ETHTOOL_A_LINKMODES_OURS, ksettings->link_modes.advertising, ksettings->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return -EMSGSIZE; if (!data->peer_empty) { ret = ethnl_put_bitset(skb, ETHTOOL_A_LINKMODES_PEER, ksettings->link_modes.lp_advertising, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return -EMSGSIZE; } if (nla_put_u32(skb, ETHTOOL_A_LINKMODES_SPEED, lsettings->speed) || nla_put_u8(skb, ETHTOOL_A_LINKMODES_DUPLEX, lsettings->duplex)) return -EMSGSIZE; if (ksettings->lanes && nla_put_u32(skb, ETHTOOL_A_LINKMODES_LANES, ksettings->lanes)) return -EMSGSIZE; if (lsettings->master_slave_cfg != MASTER_SLAVE_CFG_UNSUPPORTED && nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, lsettings->master_slave_cfg)) return -EMSGSIZE; if (lsettings->master_slave_state != MASTER_SLAVE_STATE_UNSUPPORTED && nla_put_u8(skb, ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, lsettings->master_slave_state)) return -EMSGSIZE; if (nla_put_u8(skb, ETHTOOL_A_LINKMODES_RATE_MATCHING, lsettings->rate_matching)) return -EMSGSIZE; return 0; } const struct ethnl_request_ops ethnl_linkmodes_request_ops = { .request_cmd = ETHTOOL_MSG_LINKMODES_GET, .reply_cmd = ETHTOOL_MSG_LINKMODES_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKMODES_HEADER, .req_info_size = sizeof(struct linkmodes_req_info), .reply_data_size = sizeof(struct linkmodes_reply_data), .prepare_data = linkmodes_prepare_data, .reply_size = linkmodes_reply_size, .fill_reply = linkmodes_fill_reply, }; /* LINKMODES_SET */ const struct nla_policy ethnl_linkmodes_set_policy[] = { [ETHTOOL_A_LINKMODES_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKMODES_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_OURS] = { .type = NLA_NESTED }, [ETHTOOL_A_LINKMODES_SPEED] = { .type = NLA_U32 }, [ETHTOOL_A_LINKMODES_DUPLEX] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG] = { .type = NLA_U8 }, [ETHTOOL_A_LINKMODES_LANES] = NLA_POLICY_RANGE(NLA_U32, 1, 8), }; /* Set advertised link modes to all supported modes matching requested speed, * lanes and duplex values. Called when autonegotiation is on, speed, lanes or * duplex is requested but no link mode change. This is done in userspace with * ioctl() interface, move it into kernel for netlink. * Returns true if advertised modes bitmap was modified. */ static bool ethnl_auto_linkmodes(struct ethtool_link_ksettings *ksettings, bool req_speed, bool req_lanes, bool req_duplex) { unsigned long *advertising = ksettings->link_modes.advertising; unsigned long *supported = ksettings->link_modes.supported; DECLARE_BITMAP(old_adv, __ETHTOOL_LINK_MODE_MASK_NBITS); unsigned int i; bitmap_copy(old_adv, advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) { const struct link_mode_info *info = &link_mode_params[i]; if (info->speed == SPEED_UNKNOWN) continue; if (test_bit(i, supported) && (!req_speed || info->speed == ksettings->base.speed) && (!req_lanes || info->lanes == ksettings->lanes) && (!req_duplex || info->duplex == ksettings->base.duplex)) set_bit(i, advertising); else clear_bit(i, advertising); } return !bitmap_equal(old_adv, advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); } static bool ethnl_validate_master_slave_cfg(u8 cfg) { switch (cfg) { case MASTER_SLAVE_CFG_MASTER_PREFERRED: case MASTER_SLAVE_CFG_SLAVE_PREFERRED: case MASTER_SLAVE_CFG_MASTER_FORCE: case MASTER_SLAVE_CFG_SLAVE_FORCE: return true; } return false; } static int ethnl_check_linkmodes(struct genl_info *info, struct nlattr **tb) { const struct nlattr *master_slave_cfg, *lanes_cfg; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; if (master_slave_cfg && !ethnl_validate_master_slave_cfg(nla_get_u8(master_slave_cfg))) { NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, "master/slave value is invalid"); return -EOPNOTSUPP; } lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; if (lanes_cfg && !is_power_of_2(nla_get_u32(lanes_cfg))) { NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, "lanes value is invalid"); return -EINVAL; } return 0; } static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb, struct ethtool_link_ksettings *ksettings, bool *mod, const struct net_device *dev) { struct ethtool_link_settings *lsettings = &ksettings->base; bool req_speed, req_lanes, req_duplex; const struct nlattr *master_slave_cfg, *lanes_cfg; int ret; master_slave_cfg = tb[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]; if (master_slave_cfg) { if (lsettings->master_slave_cfg == MASTER_SLAVE_CFG_UNSUPPORTED) { NL_SET_ERR_MSG_ATTR(info->extack, master_slave_cfg, "master/slave configuration not supported by device"); return -EOPNOTSUPP; } } *mod = false; req_speed = tb[ETHTOOL_A_LINKMODES_SPEED]; req_lanes = tb[ETHTOOL_A_LINKMODES_LANES]; req_duplex = tb[ETHTOOL_A_LINKMODES_DUPLEX]; ethnl_update_u8(&lsettings->autoneg, tb[ETHTOOL_A_LINKMODES_AUTONEG], mod); lanes_cfg = tb[ETHTOOL_A_LINKMODES_LANES]; if (lanes_cfg) { /* If autoneg is off and lanes parameter is not supported by the * driver, return an error. */ if (!lsettings->autoneg && !dev->ethtool_ops->cap_link_lanes_supported) { NL_SET_ERR_MSG_ATTR(info->extack, lanes_cfg, "lanes configuration not supported by device"); return -EOPNOTSUPP; } } else if (!lsettings->autoneg && ksettings->lanes) { /* If autoneg is off and lanes parameter is not passed from user but * it was defined previously then set the lanes parameter to 0. */ ksettings->lanes = 0; *mod = true; } ret = ethnl_update_bitset(ksettings->link_modes.advertising, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_LINKMODES_OURS], link_mode_names, info->extack, mod); if (ret < 0) return ret; ethnl_update_u32(&lsettings->speed, tb[ETHTOOL_A_LINKMODES_SPEED], mod); ethnl_update_u32(&ksettings->lanes, lanes_cfg, mod); ethnl_update_u8(&lsettings->duplex, tb[ETHTOOL_A_LINKMODES_DUPLEX], mod); ethnl_update_u8(&lsettings->master_slave_cfg, master_slave_cfg, mod); if (!tb[ETHTOOL_A_LINKMODES_OURS] && lsettings->autoneg && (req_speed || req_lanes || req_duplex) && ethnl_auto_linkmodes(ksettings, req_speed, req_lanes, req_duplex)) *mod = true; return 0; } int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info) { struct ethtool_link_ksettings ksettings = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; struct net_device *dev; bool mod = false; int ret; ret = ethnl_check_linkmodes(info, tb); if (ret < 0) return ret; ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_LINKMODES_HEADER], genl_info_net(info), info->extack, true); if (ret < 0) return ret; dev = req_info.dev; ret = -EOPNOTSUPP; if (!dev->ethtool_ops->get_link_ksettings || !dev->ethtool_ops->set_link_ksettings) goto out_dev; rtnl_lock(); ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; ret = __ethtool_get_link_ksettings(dev, &ksettings); if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out_ops; } ret = ethnl_update_linkmodes(info, tb, &ksettings, &mod, dev); if (ret < 0) goto out_ops; if (mod) { ret = dev->ethtool_ops->set_link_ksettings(dev, &ksettings); if (ret < 0) GENL_SET_ERR_MSG(info, "link settings update failed"); else ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL); } out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(&req_info); return ret; } |
| 18 3 12 4 3 39 18 18 60 67 67 20 60 17 17 9 3 10 4 10 7 7 278 277 276 270 275 275 275 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: IP/IP protocol decoder modified to support * virtual tunnel interface * * Authors: * Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012 */ /* This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c For comments look at net/ipv4/ip_gre.c --ANK */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> static struct rtnl_link_ops vti_link_ops __read_mostly; static unsigned int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type, bool update_skb_dev) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; if (update_skb_dev) skb->dev = tunnel->dev; return xfrm_input(skb, nexthdr, spi, encap_type); } return -EINVAL; drop: kfree_skb(skb); return 0; } static int vti_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { return vti_input(skb, nexthdr, spi, encap_type, false); } static int vti_rcv(struct sk_buff *skb, __be32 spi, bool update_skb_dev) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return vti_input(skb, ip_hdr(skb)->protocol, spi, 0, update_skb_dev); } static int vti_rcv_proto(struct sk_buff *skb) { return vti_rcv(skb, 0, false); } static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; u32 orig_mark = skb->mark; int ret; if (!tunnel) return 1; dev = tunnel->dev; if (err) { dev->stats.rx_errors++; dev->stats.rx_dropped++; return 0; } x = xfrm_input_state(skb); inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } family = inner_mode->family; skb->mark = be32_to_cpu(tunnel->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); skb->mark = orig_mark; if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); return 0; } static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) { xfrm_address_t *daddr = (xfrm_address_t *)&dst; xfrm_address_t *saddr = (xfrm_address_t *)&src; /* if there is no transform then this tunnel is not functional. * Or if the xfrm is not mode tunnel. */ if (!x || x->props.mode != XFRM_MODE_TUNNEL || x->props.family != AF_INET) return false; if (!dst) return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) return false; return true; } static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; int err; int mtu; if (!dst) { switch (skb->protocol) { case htons(ETH_P_IP): { struct rtable *rt; fl->u.ip4.flowi4_oif = dev->ifindex; fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } dst = &rt->dst; skb_dst_set(skb, dst); break; } #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): fl->u.ip6.flowi6_oif = dev->ifindex; fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); if (dst->error) { dst_release(dst); dst = NULL; dev->stats.tx_carrier_errors++; goto tx_error_icmp; } skb_dst_set(skb, dst); break; #endif default: dev->stats.tx_carrier_errors++; goto tx_error_icmp; } } dst_hold(dst); dst = xfrm_lookup_route(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } if (dst->flags & DST_XFRM_QUEUE) goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; dst_release(dst); goto tx_error_icmp; } tdev = dst->dev; if (tdev == dev) { dst_release(dst); dev->stats.collisions++; goto tx_error; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } else { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } dst_release(dst); goto tx_error; } xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: dev->stats.tx_errors++; kfree_skb(skb); return NETDEV_TX_OK; } /* This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct flowi fl; if (!pskb_inet_may_pull(skb)) goto tx_err; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(skb, &fl, AF_INET6); break; default: goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); return vti_xmit(skb, dev, &fl); tx_err: dev->stats.tx_errors++; kfree_skb(skb); return NETDEV_TX_OK; } static int vti4_err(struct sk_buff *skb, u32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip_tunnel *tunnel; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; mark = be32_to_cpu(tunnel->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; break; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; } static int vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) { int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_IPIP || p->iph.ihl != 5) return -EINVAL; } if (!(p->i_flags & GRE_KEY)) p->i_key = 0; if (!(p->o_flags & GRE_KEY)) p->o_key = 0; p->i_flags = VTI_ISVTI; err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { p->i_flags |= GRE_KEY; p->o_flags |= GRE_KEY; } return 0; } static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = vti_tunnel_ctl, }; static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } static int vti_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); return ip_tunnel_init(dev); } static void __net_init vti_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; iph->version = 4; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; } static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) static int vti_rcv_tunnel(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return vti_input(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr, 0, false); } static struct xfrm_tunnel vti_ipip_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; #if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; #endif #endif static int __net_init vti_init_net(struct net *net) { int err; struct ip_tunnel_net *itn; err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0"); if (err) return err; itn = net_generic(net, vti_net_id); if (itn->fb_tunnel_dev) vti_fb_tunnel_init(itn->fb_tunnel_dev); return 0; } static void __net_exit vti_exit_batch_net(struct list_head *list_net) { ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, .exit_batch = vti_exit_batch_net, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void vti_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_IPIP; if (!data) return; parms->i_flags = VTI_ISVTI; if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); if (data[IFLA_VTI_OKEY]) parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_FWMARK]) *fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm parms; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); return ip_tunnel_newlink(dev, tb, &parms, fwmark); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; vti_netlink_parms(data, &p, &fwmark); return ip_tunnel_changelink(dev, tb, &p, fwmark); } static size_t vti_get_size(const struct net_device *dev) { return /* IFLA_VTI_LINK */ nla_total_size(4) + /* IFLA_VTI_IKEY */ nla_total_size(4) + /* IFLA_VTI_OKEY */ nla_total_size(4) + /* IFLA_VTI_LOCAL */ nla_total_size(4) + /* IFLA_VTI_REMOTE */ nla_total_size(4) + /* IFLA_VTI_FWMARK */ nla_total_size(4) + 0; } static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) || nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark)) return -EMSGSIZE; return 0; } static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vti_link_ops __read_mostly = { .kind = "vti", .maxtype = IFLA_VTI_MAX, .policy = vti_policy, .priv_size = sizeof(struct ip_tunnel), .setup = vti_tunnel_setup, .validate = vti_tunnel_validate, .newlink = vti_newlink, .changelink = vti_changelink, .dellink = ip_tunnel_dellink, .get_size = vti_get_size, .fill_info = vti_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static int __init vti_init(void) { const char *msg; int err; pr_info("IPv4 over IPsec tunneling driver\n"); msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) goto pernet_dev_failed; msg = "tunnel protocols"; err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) msg = "ipip tunnel"; err = xfrm4_tunnel_register(&vti_ipip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ipip_failed; #if IS_ENABLED(CONFIG_IPV6) err = xfrm4_tunnel_register(&vti_ipip6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipip6_failed; #endif #endif msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) goto rtnl_link_failed; return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) #if IS_ENABLED(CONFIG_IPV6) xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); xfrm_tunnel_ipip6_failed: #endif xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: #endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: pr_err("vti init: failed to register %s\n", msg); return err; } static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) #if IS_ENABLED(CONFIG_IPV6) xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); #endif xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); #endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); } module_init(vti_init); module_exit(vti_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti"); MODULE_ALIAS_NETDEV("ip_vti0"); |
| 10 11 10 4 8 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H #include <linux/icmpv6.h> #include <linux/kernel.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/inet_frag.h> enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP6_DEFRAG_CONNTRACK_OUT, __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP6_DEFRAG_CONNTRACK_BRIDGE_IN, __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, }; /* * Equivalent of ipv4 struct ip */ struct frag_queue { struct inet_frag_queue q; int iif; __u16 nhoffset; u8 ecn; }; #if IS_ENABLED(CONFIG_IPV6) static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); const struct frag_v6_compare_key *key = a; q->key.v6 = *key; fq->ecn = 0; } static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v6, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline int ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v6_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static inline void ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) { struct net_device *dev = NULL; struct sk_buff *head; rcu_read_lock(); /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(fq->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) goto out; __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); /* Don't send error if the first segment did not arrive. */ if (!(fq->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&fq->q); if (!head) goto out; head->dev = dev; spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); kfree_skb(head); goto out_rcu_unlock; out: spin_unlock(&fq->q.lock); out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } /* Check if the upper layer header is truncated in the first fragment. */ static inline bool ipv6frag_thdr_truncated(struct sk_buff *skb, int start, u8 *nexthdrp) { u8 nexthdr = *nexthdrp; __be16 frag_off; int offset; offset = ipv6_skip_exthdr(skb, start, &nexthdr, &frag_off); if (offset < 0 || (frag_off & htons(IP6_OFFSET))) return false; switch (nexthdr) { case NEXTHDR_TCP: offset += sizeof(struct tcphdr); break; case NEXTHDR_UDP: offset += sizeof(struct udphdr); break; case NEXTHDR_ICMP: offset += sizeof(struct icmp6hdr); break; default: offset += 1; } if (offset > skb->len) return true; return false; } #endif #endif |
| 3094 485 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKRU_H #define _ASM_X86_PKRU_H #include <asm/cpufeature.h> #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #define pkru_get_init_value() READ_ONCE(init_pkru_value) #else #define init_pkru_value 0 #define pkru_get_init_value() 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u32 read_pkru(void) { if (cpu_feature_enabled(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru != rdpkru()) wrpkru(pkru); } static inline void pkru_write_default(void) { if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; wrpkru(pkru_get_init_value()); } #endif |
| 707 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Global definitions for the ARP (RFC 826) protocol. * * Version: @(#)if_arp.h 1.0.1 04/16/93 * * Authors: Original taken from Berkeley UNIX 4.3, (c) UCB 1986-1988 * Portions taken from the KA9Q/NOS (v2.00m PA0GRI) source. * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Florian La Roche, * Jonathan Layes <layes@loran.com> * Arnaldo Carvalho de Melo <acme@conectiva.com.br> ARPHRD_HWX25 */ #ifndef _LINUX_IF_ARP_H #define _LINUX_IF_ARP_H #include <linux/skbuff.h> #include <uapi/linux/if_arp.h> static inline struct arphdr *arp_hdr(const struct sk_buff *skb) { return (struct arphdr *)skb_network_header(skb); } static inline unsigned int arp_hdr_len(const struct net_device *dev) { switch (dev->type) { #if IS_ENABLED(CONFIG_FIREWIRE_NET) case ARPHRD_IEEE1394: /* ARP header, device address and 2 IP addresses */ return sizeof(struct arphdr) + dev->addr_len + sizeof(u32) * 2; #endif default: /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ return sizeof(struct arphdr) + (dev->addr_len + sizeof(u32)) * 2; } } static inline bool dev_is_mac_header_xmit(const struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: case ARPHRD_PIMREG: /* PPP adds its l2 header automatically in ppp_start_xmit(). * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init(). */ case ARPHRD_PPP: return false; default: return true; } } #endif /* _LINUX_IF_ARP_H */ |
| 2016 2014 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <linux/completion.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "swap.h" #include <trace/hooks/bl_hib.h> static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 /* returns 1 if swap entry is freed */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct folio *folio; int ret = 0; folio = filemap_get_folio(swap_address_space(entry), offset); if (!folio) return 0; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (folio_trylock(folio)) { if ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))) ret = folio_free_swap(folio); folio_unlock(folio); } folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_page_sector(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = __page_file_index(page); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_size(size) (size) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_size() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_size(size) 1 #endif #define LATENCY_LIMIT 256 static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; } static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; } static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; } static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; } static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; } static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; } static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; } static inline bool cluster_is_huge(struct swap_cluster_info *info) { if (IS_ENABLED(CONFIG_THP_SWAP)) return info->flags & CLUSTER_FLAG_HUGE; return false; } static inline void cluster_clear_huge(struct swap_cluster_info *info) { info->flags &= ~CLUSTER_FLAG_HUGE; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); } static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); } static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); cluster_list_add_tail(&si->free_clusters, ci, idx); } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); __free_cluster(si, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); cluster_list_del_first(&si->free_clusters, ci); cluster_set_count_flag(ci + idx, 0, 0); } static void free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info + idx; VM_BUG_ON(cluster_count(ci) != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, idx); return; } __free_cluster(si, idx); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. */ static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + 1); } /* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) free_cluster(p, idx); } /* * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); cluster_set_null(&percpu_cluster->index); return true; } /* * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { if (!cluster_list_empty(&si->free_clusters)) { cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them, then * reread cluster_next_cpu since we dropped si->lock */ swap_do_scheduled_discard(si); *scan_base = this_cpu_read(*si->cluster_next_cpu); *offset = *scan_base; goto new_cluster; } else return false; } /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { if (!si->swap_map[tmp]) break; tmp++; } unlock_cluster(ci); } if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; return true; } static void __del_from_avail_list(struct swap_info_struct *p) { int nid; assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *p) { spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) WRITE_ONCE(si->highest_bit, si->highest_bit - nr_entries); WRITE_ONCE(si->inuse_pages, si->inuse_pages + nr_entries); if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *p) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) { WARN_ON(!plist_node_empty(&p->avail_lists[nid])); plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); } spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; WRITE_ONCE(si->highest_bit, end); if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); WRITE_ONCE(si->inuse_pages, si->inuse_pages - nr_entries); if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); frontswap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } clear_shadow_from_swap_cache(si->type, begin, end); } static void set_cluster_next(struct swap_info_struct *si, unsigned long next) { unsigned long prev; if (!(si->flags & SWP_SOLIDSTATE)) { si->cluster_next = next; return; } prev = this_cpu_read(*si->cluster_next_cpu); /* * Cross the swap address space size aligned trunk, choose * another trunk randomly to avoid lock contention on swap * address space if possible. */ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) != (next >> SWAP_ADDRESS_SPACE_SHIFT)) { /* No free swap slots available */ if (si->highest_bit <= si->lowest_bit) return; next = si->lowest_bit + prandom_u32_max(si->highest_bit - si->lowest_bit + 1); next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES); next = max_t(unsigned int, next, si->lowest_bit); } this_cpu_write(*si->cluster_next_cpu, next); } static bool swap_offset_available_and_locked(struct swap_info_struct *si, unsigned long offset) { if (data_race(!si->swap_map[offset])) { spin_lock(&si->lock); return true; } if (vm_swap_full() && READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { spin_lock(&si->lock); return true; } return false; } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; bool scanned_many = false; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ si->flags += SWP_SCANNING; /* * Use percpu scan base for SSD to reduce lock contention on * cluster and swap cache. For HDD, sequential access is more * important. */ if (si->flags & SWP_SOLIDSTATE) scan_base = this_cpu_read(*si->cluster_next_cpu); else scan_base = si->cluster_next; offset = scan_base; /* SSD algorithm */ if (si->cluster_info) { if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } else if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= si->highest_bit; offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } WRITE_ONCE(si->swap_map[offset], usage); inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); swap_range_alloc(si, offset, 1); slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; } else if (si->cluster_nr && !si->swap_map[++offset]) { /* non-ssd case, still more slots in cluster? */ --si->cluster_nr; goto checks; } /* * Even if there's no free clusters available (fragmented), * try to scan a little more quickly with lock held unless we * have scanned too many slots already. */ if (!scanned_many) { unsigned long scan_limit; if (offset < scan_base) scan_limit = scan_base; else scan_limit = si->highest_bit; for (; offset <= scan_limit && --latency_ration > 0; offset++) { if (!si->swap_map[offset]) goto checks; } } done: set_cluster_next(si, offset + 1); si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); while (++offset <= READ_ONCE(si->highest_bit)) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; } offset = si->lowest_bit; while (offset < scan_base) { if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; scanned_many = true; } if (swap_offset_available_and_locked(si, offset)) goto checks; offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) { unsigned long idx; struct swap_cluster_info *ci; unsigned long offset; /* * Should not even be attempting cluster allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) { VM_WARN_ON_ONCE(1); return 0; } if (cluster_list_empty(&si->free_clusters)) return 0; idx = cluster_list_first(&si->free_clusters); offset = idx * SWAPFILE_CLUSTER; ci = lock_cluster(si, offset); alloc_cluster(si, idx); cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER); unlock_cluster(ci); swap_range_alloc(si, offset, SWAPFILE_CLUSTER); *slot = swp_entry(si->type, offset); return 1; } static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); spin_lock(&swap_avail_lock); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) { spin_unlock(&swap_avail_lock); goto noswap; } n_goal = min3((long)n_goal, (long)SWAP_BATCH, avail_pgs); atomic_long_sub(n_goal * size, &nr_swap_pages); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } if (size == SWAPFILE_CLUSTER) { if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); if (n_ret || size == SWAPFILE_CLUSTER) goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; if (!entry.val) goto out; p = swp_swap_info(entry); if (!p) goto bad_nofile; if (data_race(!(p->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; if (data_race(!p->swap_map[swp_offset(entry)])) goto bad_free; return p; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(p->swap_map[offset], usage); else WRITE_ONCE(p->swap_map[offset], SWAP_HAS_CACHE); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, page * table lock is held, etc., the swap entry may become invalid because * of swapoff. Then, we need to enclose all swap related functions * with get_swap_device() and put_swap_device(), unless the swap * functions call get/put_swap_device() by themselves. * * Note that when only holding the PTL, swapoff might succeed immediately * after freeing a swap entry. Therefore, immediately after * __swap_entry_free(), the swap info might become stale and should not * be touched without a prior get_swap_device(). * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; if (!percpu_ref_tryget_live(&si->users)) goto out; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(). */ smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, 1); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); return usage; } static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); swap_range_free(p, offset, 1); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) __swap_entry_free(p, entry); } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; int size = swap_entry_size(folio_nr_pages(folio)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; VM_BUG_ON(!(val & SWAP_HAS_CACHE)); if (val == SWAP_HAS_CACHE) free_entries++; } cluster_clear_huge(ci); if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); return; } } for (i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } #ifdef CONFIG_THP_SWAP int split_swap_cluster(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); si = _swap_info_get(entry); if (!si) return -EBUSY; ci = lock_cluster(si, offset); cluster_clear_huge(ci); unlock_cluster(ci); return 0; } #endif static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); prev = p; } if (p) spin_unlock(&p->lock); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); int count = 0; si = get_swap_device(entry); if (si) { count = swap_count(si->swap_map[offset]); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int __swp_swapcount(swp_entry_t entry) { int count = 0; struct swap_info_struct *si; si = get_swap_device(entry); if (si) { count = swap_swapcount(si, entry); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || !cluster_is_huge(ci)) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < SWAPFILE_CLUSTER; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio_swap_entry(folio); struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_swapcount(si, entry) != 0; return swap_page_trans_huge_swapped(si, entry); } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; if (folio_swapped(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; delete_from_swap_cache(folio); folio_set_dirty(folio); return true; } /* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */ int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; unsigned char count; if (non_swap_entry(entry)) return 1; p = get_swap_device(entry); if (p) { if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) { put_swap_device(p); return 0; } count = __swap_entry_free(p, entry); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); put_swap_device(p); } return p != NULL; } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ spin_lock(&si->lock); if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) atomic_long_dec(&nr_swap_pages); spin_unlock(&si->lock); fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_swap_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page = folio_file_page(folio, swp_offset(entry)); struct page *swapcache; spinlock_t *ptl; pte_t *pte, new_pte; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { ret = 0; goto out; } if (unlikely(!PageUptodate(page))) { pte_t pteval; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); pteval = swp_entry_to_pte(make_swapin_error_entry(page)); set_pte_at(vma->vm_mm, addr, pte, pteval); swap_free(entry); ret = 0; goto out; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(entry, page_folio(page)); /* See do_swap_page() */ BUG_ON(!PageAnon(page) && PageMappedToDisk(page)); BUG_ON(PageAnon(page) && PageAnonExclusive(page)); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); if (page == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): PageWriteback() would be problematic. * However, we do a wait_on_page_writeback() just before this * call and have the page locked. */ VM_BUG_ON_PAGE(PageWriteback(page), page); if (pte_swp_exclusive(*pte)) rmap_flags |= RMAP_EXCLUSIVE; page_add_anon_rmap(page, vma, addr, rmap_flags); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr); lru_cache_add_inactive_or_unevictable(page, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(*pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(*pte)) new_pte = pte_mkuffd_wp(new_pte); set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: pte_unmap_unlock(pte, ptl); if (page != swapcache) { unlock_page(page); put_page(page); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { swp_entry_t entry; pte_t *pte; struct swap_info_struct *si; int ret = 0; volatile unsigned char *swap_map; si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { struct folio *folio; unsigned long offset; if (!is_swap_pte(*pte)) continue; entry = pte_to_swp_entry(*pte); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); swap_map = &si->swap_map[offset]; folio = swap_cache_get_folio(entry, vma, addr); if (!folio) { struct page *page; struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); if (page) folio = page_folio(page); } if (!folio) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); goto out; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); ret = 0; out: return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (vma->anon_vma) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) return 0; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = filemap_get_folio(swap_address_space(entry), i); if (!folio) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writepage() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; return -EINTR; } return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *p) { struct block_device *bdev; if (p->bdev) bdev = p->bdev; else bdev = p->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { int i; if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; for_each_node(i) { if (p->prio >= 0) p->avail_lists[i].prio = -p->prio; else { if (swap_node(p) == i) p->avail_lists[i].prio = 1; else p->avail_lists[i].prio = -p->prio; } } p->swap_map = swap_map; p->cluster_info = cluster_info; } static void _enable_swap_info(struct swap_info_struct *p) { p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } bool has_usable_swap(void) { bool ret = true; spin_lock(&swap_lock); if (plist_head_empty(&swap_active_head)) ret = false; spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; unsigned int old_block_size; bool hibernation_swap = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); /* * Wait for swap operations protected by get/put_swap_device() * to complete. * * We need synchronize_rcu() here to protect the accessing to * the swap cache data structure. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); destroy_swap_extents(p); trace_android_vh_check_hibernation_swap(p->bdev, &hibernation_swap); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || hibernation_swap || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = si->pages << (PAGE_SHIFT - 10); inuse = READ_ONCE(si->inuse_pages) << (PAGE_SHIFT - 10); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { int error; if (S_ISBLK(inode->i_mode)) { p->bdev = blkdev_get_by_dev(inode->i_rdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); if (IS_ERR(p->bdev)) { error = PTR_ERR(p->bdev); p->bdev = NULL; return error; } p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(p->bdev)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; bool hibernation_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } trace_android_vh_check_hibernation_swap(p->bdev, &hibernation_swap); if (p->bdev && bdev_stable_writes(p->bdev)) p->flags |= SWP_STABLE_WRITES; if (p->bdev && p->bdev->bd_disk->fops->rw_page) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && !hibernation_swap && bdev_nonrot(p->bdev)) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; p->cluster_next_cpu = alloc_percpu(unsigned int); if (!p->cluster_next_cpu) { error = -ENOMEM; goto bad_swap_unlock_inode; } /* * select a random position to start with to help wear leveling * SSD */ for_each_possible_cpu(cpu) { per_cpu(*p->cluster_next_cpu, cpu) = 1 + prandom_u32_max(p->highest_bit); } nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL); if ((swap_flags & SWAP_FLAG_DISCARD) && p->bdev && bdev_max_discard_sectors(p->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_address_space; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_address_space: exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; free_percpu(p->cluster_next_cpu); p->cluster_next_cpu = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += READ_ONCE(si->inuse_pages); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } EXPORT_SYMBOL_NS_GPL(si_swapinfo, MINIDUMP); /* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err; p = get_swap_device(entry); if (!p) return -EINVAL; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; if (usage == SWAP_HAS_CACHE) { /* set SWAP_HAS_CACHE if there is no cache and entry is used */ if (!has_cache && count) has_cache = SWAP_HAS_CACHE; else if (has_cache) /* someone else added cache */ err = -EEXIST; else /* no users remaining */ err = -ENOENT; } else if (count || has_cache) { if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) err = -EINVAL; else if (swap_count_continued(p, offset, count)) count = COUNT_CONTINUED; else err = -ENOMEM; } else err = -ENOENT; /* unused swap entry */ WRITE_ONCE(p->swap_map[offset], count | has_cache); unlock_out: unlock_cluster_or_swap_info(p, ci); put_swap_device(p); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry) { __swap_duplicate(entry, SWAP_MAP_SHMEM); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: swap entry for which we allocate swap cache. * * Called when allocating swap cache for existing swap entry, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry) { return __swap_duplicate(entry, SWAP_HAS_CACHE); } void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char usage; ci = lock_cluster_or_swap_info(si, offset); usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE); unlock_cluster_or_swap_info(si, ci); if (!usage) free_swap_slot(entry); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } struct swap_info_struct *page_swap_info(struct page *page) { swp_entry_t entry = { .val = page_private(page) }; return swp_swap_info(entry); } /* * out-of-line methods to avoid include hell. */ struct address_space *swapcache_mapping(struct folio *folio) { return page_swap_info(&folio->page)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; return swp_offset(swap); } EXPORT_SYMBOL_GPL(__page_file_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, * no architecture is using highmem pages for kernel page tables: so it * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_atomic(list_page) + offset; count = *map; kunmap_atomic(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_atomic(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_atomic(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_atomic(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_atomic(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; kunmap_atomic(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_atomic(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_atomic(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_atomic(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) { struct swap_info_struct *si, *next; int nid = page_to_nid(page); if (!(gfp_mask & __GFP_IO)) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_queue) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 9079 9090 9079 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xsave/xrstor support. * * Author: Suresh Siddha <suresh.b.siddha@intel.com> */ #include <linux/bitops.h> #include <linux/compat.h> #include <linux/cpu.h> #include <linux/mman.h> #include <linux/nospec.h> #include <linux/pkeys.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> #include <asm/fpu/api.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/xcr.h> #include <asm/tlbflush.h> #include <asm/prctl.h> #include <asm/elf.h> #include "context.h" #include "internal.h" #include "legacy.h" #include "xstate.h" #define for_each_extended_xfeature(bit, mask) \ (bit) = FIRST_EXTENDED_XFEATURE; \ for_each_set_bit_from(bit, (unsigned long *)&(mask), 8 * sizeof(mask)) /* * Although we spell it out in here, the Processor Trace * xfeature is completely unused. We use other mechanisms * to save/restore PT state in Linux. */ static const char *xfeature_names[] = { "x87 floating point registers" , "SSE registers" , "AVX registers" , "MPX bounds registers" , "MPX CSR" , "AVX-512 opmask" , "AVX-512 Hi256" , "AVX-512 ZMM_Hi256" , "Processor Trace (unused)" , "Protection Keys User registers", "PASID state", "unknown xstate feature" , "unknown xstate feature" , "unknown xstate feature" , "unknown xstate feature" , "unknown xstate feature" , "unknown xstate feature" , "AMX Tile config" , "AMX Tile data" , "unknown xstate feature" , }; static unsigned short xsave_cpuid_features[] __initdata = { [XFEATURE_FP] = X86_FEATURE_FPU, [XFEATURE_SSE] = X86_FEATURE_XMM, [XFEATURE_YMM] = X86_FEATURE_AVX, [XFEATURE_BNDREGS] = X86_FEATURE_MPX, [XFEATURE_BNDCSR] = X86_FEATURE_MPX, [XFEATURE_OPMASK] = X86_FEATURE_AVX512F, [XFEATURE_ZMM_Hi256] = X86_FEATURE_AVX512F, [XFEATURE_Hi16_ZMM] = X86_FEATURE_AVX512F, [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT, [XFEATURE_PKRU] = X86_FEATURE_PKU, [XFEATURE_PASID] = X86_FEATURE_ENQCMD, [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE, [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE, }; static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init; #define XSTATE_FLAG_SUPERVISOR BIT(0) #define XSTATE_FLAG_ALIGNED64 BIT(1) /* * Return whether the system supports a given xfeature. * * Also return the name of the (most advanced) feature that the caller requested: */ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) { u64 xfeatures_missing = xfeatures_needed & ~fpu_kernel_cfg.max_features; if (unlikely(feature_name)) { long xfeature_idx, max_idx; u64 xfeatures_print; /* * So we use FLS here to be able to print the most advanced * feature that was requested but is missing. So if a driver * asks about "XFEATURE_MASK_SSE | XFEATURE_MASK_YMM" we'll print the * missing AVX feature - this is the most informative message * to users: */ if (xfeatures_missing) xfeatures_print = xfeatures_missing; else xfeatures_print = xfeatures_needed; xfeature_idx = fls64(xfeatures_print)-1; max_idx = ARRAY_SIZE(xfeature_names)-1; xfeature_idx = min(xfeature_idx, max_idx); *feature_name = xfeature_names[xfeature_idx]; } if (xfeatures_missing) return 0; return 1; } EXPORT_SYMBOL_GPL(cpu_has_xfeatures); static bool xfeature_is_aligned64(int xfeature_nr) { return xstate_flags[xfeature_nr] & XSTATE_FLAG_ALIGNED64; } static bool xfeature_is_supervisor(int xfeature_nr) { return xstate_flags[xfeature_nr] & XSTATE_FLAG_SUPERVISOR; } static unsigned int xfeature_get_offset(u64 xcomp_bv, int xfeature) { unsigned int offs, i; /* * Non-compacted format and legacy features use the cached fixed * offsets. */ if (!cpu_feature_enabled(X86_FEATURE_XCOMPACTED) || xfeature <= XFEATURE_SSE) return xstate_offsets[xfeature]; /* * Compacted format offsets depend on the actual content of the * compacted xsave area which is determined by the xcomp_bv header * field. */ offs = FXSAVE_SIZE + XSAVE_HDR_SIZE; for_each_extended_xfeature(i, xcomp_bv) { if (xfeature_is_aligned64(i)) offs = ALIGN(offs, 64); if (i == xfeature) break; offs += xstate_sizes[i]; } return offs; } /* * Enable the extended processor state save/restore feature. * Called once per CPU onlining. */ void fpu__init_cpu_xstate(void) { if (!boot_cpu_has(X86_FEATURE_XSAVE) || !fpu_kernel_cfg.max_features) return; cr4_set_bits(X86_CR4_OSXSAVE); /* * Must happen after CR4 setup and before xsetbv() to allow KVM * lazy passthrough. Write independent of the dynamic state static * key as that does not work on the boot CPU. This also ensures * that any stale state is wiped out from XFD. Reset the per CPU * xfd cache too. */ if (cpu_feature_enabled(X86_FEATURE_XFD)) xfd_set_state(init_fpstate.xfd); /* * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user * states can be set here. */ xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * MSR_IA32_XSS sets supervisor states managed by XSAVES. */ if (boot_cpu_has(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } } static bool xfeature_enabled(enum xfeature xfeature) { return fpu_kernel_cfg.max_features & BIT_ULL(xfeature); } /* * Record the offsets and sizes of various xstates contained * in the XSAVE state memory layout. */ static void __init setup_xstate_cache(void) { u32 eax, ebx, ecx, edx, i; /* start at the beginning of the "extended state" */ unsigned int last_good_offset = offsetof(struct xregs_state, extended_state_area); /* * The FP xstates and SSE xstates are legacy states. They are always * in the fixed offsets in the xsave area in either compacted form * or standard form. */ xstate_offsets[XFEATURE_FP] = 0; xstate_sizes[XFEATURE_FP] = offsetof(struct fxregs_state, xmm_space); xstate_offsets[XFEATURE_SSE] = xstate_sizes[XFEATURE_FP]; xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state, xmm_space); for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); xstate_sizes[i] = eax; xstate_flags[i] = ecx; /* * If an xfeature is supervisor state, the offset in EBX is * invalid, leave it to -1. */ if (xfeature_is_supervisor(i)) continue; xstate_offsets[i] = ebx; /* * In our xstate size checks, we assume that the highest-numbered * xstate feature has the highest offset in the buffer. Ensure * it does. */ WARN_ONCE(last_good_offset > xstate_offsets[i], "x86/fpu: misordered xstate at %d\n", last_good_offset); last_good_offset = xstate_offsets[i]; } } static void __init print_xstate_feature(u64 xstate_mask) { const char *feature_name; if (cpu_has_xfeatures(xstate_mask, &feature_name)) pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name); } /* * Print out all the supported xstate features: */ static void __init print_xstate_features(void) { print_xstate_feature(XFEATURE_MASK_FP); print_xstate_feature(XFEATURE_MASK_SSE); print_xstate_feature(XFEATURE_MASK_YMM); print_xstate_feature(XFEATURE_MASK_BNDREGS); print_xstate_feature(XFEATURE_MASK_BNDCSR); print_xstate_feature(XFEATURE_MASK_OPMASK); print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); print_xstate_feature(XFEATURE_MASK_PKRU); print_xstate_feature(XFEATURE_MASK_PASID); print_xstate_feature(XFEATURE_MASK_XTILE_CFG); print_xstate_feature(XFEATURE_MASK_XTILE_DATA); } /* * This check is important because it is easy to get XSTATE_* * confused with XSTATE_BIT_*. */ #define CHECK_XFEATURE(nr) do { \ WARN_ON(nr < FIRST_EXTENDED_XFEATURE); \ WARN_ON(nr >= XFEATURE_MAX); \ } while (0) /* * Print out xstate component offsets and sizes */ static void __init print_xstate_offset_size(void) { int i; for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { pr_info("x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, xfeature_get_offset(fpu_kernel_cfg.max_features, i), i, xstate_sizes[i]); } } /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static __init void os_xrstor_booting(struct xregs_state *xstate) { u64 mask = fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSTATE; u32 lmask = mask; u32 hmask = mask >> 32; int err; if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * All supported features have either init state all zeros or are * handled in setup_init_fpu() individually. This is an explicit * feature list and does not use XFEATURE_MASK*SUPPORTED to catch * newly added supported features at build time and make people * actually look at the init state for the new feature. */ #define XFEATURES_INIT_FPSTATE_HANDLED \ (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM | \ XFEATURE_MASK_PKRU | \ XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_PASID | \ XFEATURE_MASK_XTILE) /* * setup the xstate image representing the init state */ static void __init setup_init_fpu_buf(void) { BUILD_BUG_ON((XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED) != XFEATURES_INIT_FPSTATE_HANDLED); if (!boot_cpu_has(X86_FEATURE_XSAVE)) return; print_xstate_features(); xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures); /* * Init all the features state with header.xfeatures being 0x0 */ os_xrstor_booting(&init_fpstate.regs.xsave); /* * All components are now in init state. Read the state back so * that init_fpstate contains all non-zero init state. This only * works with XSAVE, but not with XSAVEOPT and XSAVEC/S because * those use the init optimization which skips writing data for * components in init state. * * XSAVE could be used, but that would require to reshuffle the * data when XSAVEC/S is available because XSAVEC/S uses xstate * compaction. But doing so is a pointless exercise because most * components have an all zeros init state except for the legacy * ones (FP and SSE). Those can be saved with FXSAVE into the * legacy area. Adding new features requires to ensure that init * state is all zeroes or if not to add the necessary handling * here. */ fxsave(&init_fpstate.regs.fxsave); } int xfeature_size(int xfeature_nr) { u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); return eax; } /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ static int validate_user_xstate_header(const struct xstate_header *hdr, struct fpstate *fpstate) { /* No unknown or supervisor features may be set */ if (hdr->xfeatures & ~fpstate->user_xfeatures) return -EINVAL; /* Userspace must use the uncompacted format */ if (hdr->xcomp_bv) return -EINVAL; /* * If 'reserved' is shrunken to add a new field, make sure to validate * that new field here! */ BUILD_BUG_ON(sizeof(hdr->reserved) != 48); /* No reserved bits may be set */ if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) return -EINVAL; return 0; } static void __init __xstate_dump_leaves(void) { int i; u32 eax, ebx, ecx, edx; static int should_dump = 1; if (!should_dump) return; should_dump = 0; /* * Dump out a few leaves past the ones that we support * just in case there are some goodies up there */ for (i = 0; i < XFEATURE_MAX + 10; i++) { cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", XSTATE_CPUID, i, eax, ebx, ecx, edx); } } #define XSTATE_WARN_ON(x, fmt, ...) do { \ if (WARN_ONCE(x, "XSAVE consistency problem: " fmt, ##__VA_ARGS__)) { \ __xstate_dump_leaves(); \ } \ } while (0) #define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \ if ((nr == nr_macro) && \ WARN_ONCE(sz != sizeof(__struct), \ "%s: struct is %zu bytes, cpu state %d bytes\n", \ __stringify(nr_macro), sizeof(__struct), sz)) { \ __xstate_dump_leaves(); \ } \ } while (0) /** * check_xtile_data_against_struct - Check tile data state size. * * Calculate the state size by multiplying the single tile size which is * recorded in a C struct, and the number of tiles that the CPU informs. * Compare the provided size with the calculation. * * @size: The tile data state size * * Returns: 0 on success, -EINVAL on mismatch. */ static int __init check_xtile_data_against_struct(int size) { u32 max_palid, palid, state_size; u32 eax, ebx, ecx, edx; u16 max_tile; /* * Check the maximum palette id: * eax: the highest numbered palette subleaf. */ cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx); /* * Cross-check each tile size and find the maximum number of * supported tiles. */ for (palid = 1, max_tile = 0; palid <= max_palid; palid++) { u16 tile_size, max; /* * Check the tile size info: * eax[31:16]: bytes per title * ebx[31:16]: the max names (or max number of tiles) */ cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx); tile_size = eax >> 16; max = ebx >> 16; if (tile_size != sizeof(struct xtile_data)) { pr_err("%s: struct is %zu bytes, cpu xtile %d bytes\n", __stringify(XFEATURE_XTILE_DATA), sizeof(struct xtile_data), tile_size); __xstate_dump_leaves(); return -EINVAL; } if (max > max_tile) max_tile = max; } state_size = sizeof(struct xtile_data) * max_tile; if (size != state_size) { pr_err("%s: calculated size is %u bytes, cpu state %d bytes\n", __stringify(XFEATURE_XTILE_DATA), state_size, size); __xstate_dump_leaves(); return -EINVAL; } return 0; } /* * We have a C struct for each 'xstate'. We need to ensure * that our software representation matches what the CPU * tells us about the state's size. */ static bool __init check_xstate_against_struct(int nr) { /* * Ask the CPU for the size of the state. */ int sz = xfeature_size(nr); /* * Match each CPU state with the corresponding software * structure. */ XCHECK_SZ(sz, nr, XFEATURE_YMM, struct ymmh_struct); XCHECK_SZ(sz, nr, XFEATURE_BNDREGS, struct mpx_bndreg_state); XCHECK_SZ(sz, nr, XFEATURE_BNDCSR, struct mpx_bndcsr_state); XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state); XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state); XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state); XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg); /* The tile data size varies between implementations. */ if (nr == XFEATURE_XTILE_DATA) check_xtile_data_against_struct(sz); /* * Make *SURE* to add any feature numbers in below if * there are "holes" in the xsave state component * numbers. */ if ((nr < XFEATURE_YMM) || (nr >= XFEATURE_MAX) || (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) || ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) { XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr); return false; } return true; } static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted) { unsigned int topmost = fls64(xfeatures) - 1; unsigned int offset = xstate_offsets[topmost]; if (topmost <= XFEATURE_SSE) return sizeof(struct xregs_state); if (compacted) offset = xfeature_get_offset(xfeatures, topmost); return offset + xstate_sizes[topmost]; } /* * This essentially double-checks what the cpu told us about * how large the XSAVE buffer needs to be. We are recalculating * it to be safe. * * Independent XSAVE features allocate their own buffers and are not * covered by these checks. Only the size of the buffer for task->fpu * is checked here. */ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) { bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); bool xsaves = cpu_feature_enabled(X86_FEATURE_XSAVES); unsigned int size = FXSAVE_SIZE + XSAVE_HDR_SIZE; int i; for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { if (!check_xstate_against_struct(i)) return false; /* * Supervisor state components can be managed only by * XSAVES. */ if (!xsaves && xfeature_is_supervisor(i)) { XSTATE_WARN_ON(1, "Got supervisor feature %d, but XSAVES not advertised\n", i); return false; } } size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted); XSTATE_WARN_ON(size != kernel_size, "size %u != kernel_size %u\n", size, kernel_size); return size == kernel_size; } /* * Get total size of enabled xstates in XCR0 | IA32_XSS. * * Note the SDM's wording here. "sub-function 0" only enumerates * the size of the *user* states. If we use it to size a buffer * that we use 'XSAVES' on, we could potentially overflow the * buffer because 'XSAVES' saves system states too. * * This also takes compaction into account. So this works for * XSAVEC as well. */ static unsigned int __init get_compacted_size(void) { unsigned int eax, ebx, ecx, edx; /* * - CPUID function 0DH, sub-function 1: * EBX enumerates the size (in bytes) required by * the XSAVES instruction for an XSAVE area * containing all the state components * corresponding to bits currently set in * XCR0 | IA32_XSS. * * When XSAVES is not available but XSAVEC is (virt), then there * are no supervisor states, but XSAVEC still uses compacted * format. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); return ebx; } /* * Get the total size of the enabled xstates without the independent supervisor * features. */ static unsigned int __init get_xsave_compacted_size(void) { u64 mask = xfeatures_mask_independent(); unsigned int size; if (!mask) return get_compacted_size(); /* Disable independent features. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); /* * Ask the hardware what size is required of the buffer. * This is the size required for the task->fpu buffer. */ size = get_compacted_size(); /* Re-enable independent features so XSAVES will work on them again. */ wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); return size; } static unsigned int __init get_xsave_size_user(void) { unsigned int eax, ebx, ecx, edx; /* * - CPUID function 0DH, sub-function 0: * EBX enumerates the size (in bytes) required by * the XSAVE instruction for an XSAVE area * containing all the *user* state components * corresponding to bits currently set in XCR0. */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); return ebx; } static int __init init_xstate_size(void) { /* Recompute the context size for enabled features: */ unsigned int user_size, kernel_size, kernel_default_size; bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); /* Uncompacted user space size */ user_size = get_xsave_size_user(); /* * XSAVES kernel size includes supervisor states and uses compacted * format. XSAVEC uses compacted format, but does not save * supervisor states. * * XSAVE[OPT] do not support supervisor states so kernel and user * size is identical. */ if (compacted) kernel_size = get_xsave_compacted_size(); else kernel_size = user_size; kernel_default_size = xstate_calculate_size(fpu_kernel_cfg.default_features, compacted); if (!paranoid_xstate_size_valid(kernel_size)) return -EINVAL; fpu_kernel_cfg.max_size = kernel_size; fpu_user_cfg.max_size = user_size; fpu_kernel_cfg.default_size = kernel_default_size; fpu_user_cfg.default_size = xstate_calculate_size(fpu_user_cfg.default_features, false); return 0; } /* * We enabled the XSAVE hardware, but something went wrong and * we can not use it. Disable it. */ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size) { fpu_kernel_cfg.max_features = 0; cr4_clear_bits(X86_CR4_OSXSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVE); /* Restore the legacy size.*/ fpu_kernel_cfg.max_size = legacy_size; fpu_kernel_cfg.default_size = legacy_size; fpu_user_cfg.max_size = legacy_size; fpu_user_cfg.default_size = legacy_size; /* * Prevent enabling the static branch which enables writes to the * XFD MSR. */ init_fpstate.xfd = 0; fpstate_reset(¤t->thread.fpu); } /* * Enable and initialize the xsave feature. * Called once per system bootup. */ void __init fpu__init_system_xstate(unsigned int legacy_size) { unsigned int eax, ebx, ecx, edx; u64 xfeatures; int err; int i; if (!boot_cpu_has(X86_FEATURE_FPU)) { pr_info("x86/fpu: No FPU detected\n"); return; } if (!boot_cpu_has(X86_FEATURE_XSAVE)) { pr_info("x86/fpu: x87 FPU will use %s\n", boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE"); return; } if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { WARN_ON_FPU(1); return; } /* * Find user xstates supported by the processor. */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { /* * This indicates that something really unexpected happened * with the enumeration. Disable XSAVE and try to continue * booting without it. This is too early to BUG(). */ pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", fpu_kernel_cfg.max_features); goto out_disable; } /* * Clear XSAVE features that are disabled in the normal CPUID. */ for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { unsigned short cid = xsave_cpuid_features[i]; /* Careful: X86_FEATURE_FPU is 0! */ if ((i != XFEATURE_FP && !cid) || !boot_cpu_has(cid)) fpu_kernel_cfg.max_features &= ~BIT_ULL(i); } if (!cpu_feature_enabled(X86_FEATURE_XFD)) fpu_kernel_cfg.max_features &= ~XFEATURE_MASK_USER_DYNAMIC; if (!cpu_feature_enabled(X86_FEATURE_XSAVES)) fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; else fpu_kernel_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED | XFEATURE_MASK_SUPERVISOR_SUPPORTED; fpu_user_cfg.max_features = fpu_kernel_cfg.max_features; fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED; /* Clean out dynamic features from default */ fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features; fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; fpu_user_cfg.default_features = fpu_user_cfg.max_features; fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC; /* Store it for paranoia check at the end */ xfeatures = fpu_kernel_cfg.max_features; /* * Initialize the default XFD state in initfp_state and enable the * dynamic sizing mechanism if dynamic states are available. The * static key cannot be enabled here because this runs before * jump_label_init(). This is delayed to an initcall. */ init_fpstate.xfd = fpu_user_cfg.max_features & XFEATURE_MASK_USER_DYNAMIC; /* Set up compaction feature bit */ if (cpu_feature_enabled(X86_FEATURE_XSAVEC) || cpu_feature_enabled(X86_FEATURE_XSAVES)) setup_force_cpu_cap(X86_FEATURE_XCOMPACTED); /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); /* Cache size, offset and flags for initialization */ setup_xstate_cache(); err = init_xstate_size(); if (err) goto out_disable; /* Reset the state for the current task */ fpstate_reset(¤t->thread.fpu); /* * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: */ update_regset_xstate_info(fpu_user_cfg.max_size, fpu_user_cfg.max_features); /* * init_fpstate excludes dynamic states as they are large but init * state is zero. */ init_fpstate.size = fpu_kernel_cfg.default_size; init_fpstate.xfeatures = fpu_kernel_cfg.default_features; if (init_fpstate.size > sizeof(init_fpstate.regs)) { pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n", sizeof(init_fpstate.regs), init_fpstate.size); goto out_disable; } setup_init_fpu_buf(); /* * Paranoia check whether something in the setup modified the * xfeatures mask. */ if (xfeatures != fpu_kernel_cfg.max_features) { pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n", xfeatures, fpu_kernel_cfg.max_features); goto out_disable; } /* * CPU capabilities initialization runs before FPU init. So * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely * functional, set the feature bit so depending code works. */ setup_force_cpu_cap(X86_FEATURE_OSXSAVE); print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", fpu_kernel_cfg.max_features, fpu_kernel_cfg.max_size, boot_cpu_has(X86_FEATURE_XCOMPACTED) ? "compacted" : "standard"); return; out_disable: /* something went wrong, try to boot without any XSAVE support */ fpu__init_disable_system_xstate(legacy_size); } /* * Restore minimal FPU state after suspend: */ void fpu__resume_cpu(void) { /* * Restore XCR0 on xsave capable CPUs: */ if (cpu_feature_enabled(X86_FEATURE_XSAVE)) xsetbv(XCR_XFEATURE_ENABLED_MASK, fpu_user_cfg.max_features); /* * Restore IA32_XSS. The same CPUID bit enumerates support * of XSAVES and MSR_IA32_XSS. */ if (cpu_feature_enabled(X86_FEATURE_XSAVES)) { wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | xfeatures_mask_independent()); } if (fpu_state_size_dynamic()) wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd); } /* * Given an xstate feature nr, calculate where in the xsave * buffer the state is. Callers should ensure that the buffer * is valid. */ static void *__raw_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { u64 xcomp_bv = xsave->header.xcomp_bv; if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) { if (WARN_ON_ONCE(!(xcomp_bv & BIT_ULL(xfeature_nr)))) return NULL; } return (void *)xsave + xfeature_get_offset(xcomp_bv, xfeature_nr); } /* * Given the xsave area and a state inside, this function returns the * address of the state. * * This is the API that is called to get xstate address in either * standard format or compacted format of xsave area. * * Note that if there is no data for the field in the xsave buffer * this will return NULL. * * Inputs: * xstate: the thread's storage area for all FPU data * xfeature_nr: state which is defined in xsave.h (e.g. XFEATURE_FP, * XFEATURE_SSE, etc...) * Output: * address of the state in the xsave area, or NULL if the * field is not present in the xsave buffer. */ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) { /* * Do we even *have* xsave state? */ if (!boot_cpu_has(X86_FEATURE_XSAVE)) return NULL; /* * We should not ever be requesting features that we * have not enabled. */ if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr))) return NULL; /* * This assumes the last 'xsave*' instruction to * have requested that 'xfeature_nr' be saved. * If it did not, we might be seeing and old value * of the field in the buffer. * * This can happen because the last 'xsave' did not * request that this feature be saved (unlikely) * or because the "init optimization" caused it * to not be saved. */ if (!(xsave->header.xfeatures & BIT_ULL(xfeature_nr))) return NULL; return __raw_xsave_addr(xsave, xfeature_nr); } #ifdef CONFIG_ARCH_HAS_PKEYS /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { u32 old_pkru, new_pkru_bits = 0; int pkey_shift; /* * This check implies XSAVE support. OSPKE only gets * set if we enable XSAVE and we enable PKU in XCR0. */ if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return -EINVAL; /* * This code should only be called with valid 'pkey' * values originating from in-kernel users. Complain * if a bad value is observed. */ if (WARN_ON_ONCE(pkey >= arch_max_pkey())) return -EINVAL; /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; if (init_val & PKEY_DISABLE_WRITE) new_pkru_bits |= PKRU_WD_BIT; /* Shift the bits in to the correct place in PKRU for pkey: */ pkey_shift = pkey * PKRU_BITS_PER_PKEY; new_pkru_bits <<= pkey_shift; /* Get old PKRU and mask off any old bits in place: */ old_pkru = read_pkru(); old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); /* Write old part along with new part: */ write_pkru(old_pkru | new_pkru_bits); return 0; } #endif /* ! CONFIG_ARCH_HAS_PKEYS */ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, void *init_xstate, unsigned int size) { membuf_write(to, from_xstate ? xstate : init_xstate, size); } /** * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming * format, i.e. from the kernel internal hardware dependent storage format * to the requested @mode. UABI XSTATE is always uncompacted! * * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u64 xfeatures, u32 pkru_val, enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; struct xregs_state *xsave = &fpstate->regs.xsave; struct xstate_header header; unsigned int zerofrom; u64 mask; int i; memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; /* Mask out the feature bits depending on copy mode */ switch (copy_mode) { case XSTATE_COPY_FP: header.xfeatures &= XFEATURE_MASK_FP; break; case XSTATE_COPY_FX: header.xfeatures &= XFEATURE_MASK_FP | XFEATURE_MASK_SSE; break; case XSTATE_COPY_XSAVE: header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } /* Copy FP state up to MXCSR */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387, &xinit->i387, off_mxcsr); /* Copy MXCSR when SSE or YMM are set in the feature mask */ copy_feature(header.xfeatures & (XFEATURE_MASK_SSE | XFEATURE_MASK_YMM), &to, &xsave->i387.mxcsr, &xinit->i387.mxcsr, MXCSR_AND_FLAGS_SIZE); /* Copy the remaining FP state */ copy_feature(header.xfeatures & XFEATURE_MASK_FP, &to, &xsave->i387.st_space, &xinit->i387.st_space, sizeof(xsave->i387.st_space)); /* Copy the SSE state - shared with YMM, but independently managed */ copy_feature(header.xfeatures & XFEATURE_MASK_SSE, &to, &xsave->i387.xmm_space, &xinit->i387.xmm_space, sizeof(xsave->i387.xmm_space)); if (copy_mode != XSTATE_COPY_XSAVE) goto out; /* Zero the padding area */ membuf_zero(&to, sizeof(xsave->i387.padding)); /* Copy xsave->i387.sw_reserved */ membuf_write(&to, xstate_fx_sw_bytes, sizeof(xsave->i387.sw_reserved)); /* Copy the user space relevant state of @xsave->header */ membuf_write(&to, &header, sizeof(header)); zerofrom = offsetof(struct xregs_state, extended_state_area); /* * This 'mask' indicates which states to copy from fpstate. * Those extended states that are not present in fpstate are * either disabled or initialized: * * In non-compacted format, disabled features still occupy * state space but there is no state to copy from in the * compacted init_fpstate. The gap tracking will zero these * states. * * The extended features have an all zeroes init state. Thus, * remove them from 'mask' to zero those features in the user * buffer instead of retrieving them from init_fpstate. */ mask = header.xfeatures; for_each_extended_xfeature(i, mask) { /* * If there was a feature or alignment gap, zero the space * in the destination buffer. */ if (zerofrom < xstate_offsets[i]) membuf_zero(&to, xstate_offsets[i] - zerofrom); if (i == XFEATURE_PKRU) { struct pkru_state pkru = {0}; /* * PKRU is not necessarily up to date in the * XSAVE buffer. Use the provided value. */ pkru.pkru = pkru_val; membuf_write(&to, &pkru, sizeof(pkru)); } else { membuf_write(&to, __raw_xsave_addr(xsave, i), xstate_sizes[i]); } /* * Keep track of the last copied state in the non-compacted * target buffer for gap zeroing. */ zerofrom = xstate_offsets[i] + xstate_sizes[i]; } out: if (to.left) membuf_zero(&to, to.left); } /** * copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @tsk: The task from which to copy the saved xstate * @copy_mode: The requested copy mode * * Converts from kernel XSAVE or XSAVES compacted format to UABI conforming * format, i.e. from the kernel internal hardware dependent storage format * to the requested @mode. UABI XSTATE is always uncompacted! * * It supports partial copy but @to.pos always starts from zero. */ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, tsk->thread.fpu.fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, const void *kbuf, const void __user *ubuf) { if (kbuf) { memcpy(dst, kbuf + offset, size); } else { if (copy_from_user(dst, ubuf + offset, size)) return -EFAULT; } return 0; } /** * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate * @fpstate: The fpstate buffer to copy to * @kbuf: The UABI format buffer, if it comes from the kernel * @ubuf: The UABI format buffer, if it comes from userspace * @pkru: The location to write the PKRU value to * * Converts from the UABI format into the kernel internal hardware * dependent format. * * This function ultimately has three different callers with distinct PKRU * behavior. * 1. When called from sigreturn the PKRU register will be restored from * @fpstate via an XRSTOR. Correctly copying the UABI format buffer to * @fpstate is sufficient to cover this case, but the caller will also * pass a pointer to the thread_struct's pkru field in @pkru and updating * it is harmless. * 2. When called from ptrace the PKRU register will be restored from the * thread_struct's pkru field. A pointer to that is passed in @pkru. * The kernel will restore it manually, so the XRSTOR behavior that resets * the PKRU register to the hardware init value (0) if the corresponding * xfeatures bit is not set is emulated here. * 3. When called from KVM the PKRU register will be restored from the vcpu's * pkru field. A pointer to that is passed in @pkru. KVM hasn't used * XRSTOR and hasn't had the PKRU resetting behavior described above. To * preserve that KVM behavior, it passes NULL for @pkru if the xfeatures * bit is not set. */ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, const void __user *ubuf, u32 *pkru) { struct xregs_state *xsave = &fpstate->regs.xsave; unsigned int offset, size; struct xstate_header hdr; u64 mask; int i; offset = offsetof(struct xregs_state, header); if (copy_from_buffer(&hdr, offset, sizeof(hdr), kbuf, ubuf)) return -EFAULT; if (validate_user_xstate_header(&hdr, fpstate)) return -EINVAL; /* Validate MXCSR when any of the related features is in use */ mask = XFEATURE_MASK_FP | XFEATURE_MASK_SSE | XFEATURE_MASK_YMM; if (hdr.xfeatures & mask) { u32 mxcsr[2]; offset = offsetof(struct fxregs_state, mxcsr); if (copy_from_buffer(mxcsr, offset, sizeof(mxcsr), kbuf, ubuf)) return -EFAULT; /* Reserved bits in MXCSR must be zero. */ if (mxcsr[0] & ~mxcsr_feature_mask) return -EINVAL; /* SSE and YMM require MXCSR even when FP is not in use. */ if (!(hdr.xfeatures & XFEATURE_MASK_FP)) { xsave->i387.mxcsr = mxcsr[0]; xsave->i387.mxcsr_mask = mxcsr[1]; } } for (i = 0; i < XFEATURE_MAX; i++) { mask = BIT_ULL(i); if (hdr.xfeatures & mask) { void *dst = __raw_xsave_addr(xsave, i); offset = xstate_offsets[i]; size = xstate_sizes[i]; if (copy_from_buffer(dst, offset, size, kbuf, ubuf)) return -EFAULT; } } if (hdr.xfeatures & XFEATURE_MASK_PKRU) { struct pkru_state *xpkru; xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU); *pkru = xpkru->pkru; } else { /* * KVM may pass NULL here to indicate that it does not need * PKRU updated. */ if (pkru) *pkru = 0; } /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': */ xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL; /* * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= hdr.xfeatures; return 0; } /* * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S] * format and copy to the target thread. Used by ptrace and KVM. */ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru) { return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru); } /* * Convert from a sigreturn standard-format user-space buffer to kernel * XSAVE[S] format and copy to the target thread. This is called from the * sigreturn() and rt_sigreturn() system calls. */ int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf) { return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru); } static bool validate_independent_components(u64 mask) { u64 xchk; if (WARN_ON_FPU(!cpu_feature_enabled(X86_FEATURE_XSAVES))) return false; xchk = ~xfeatures_mask_independent(); if (WARN_ON_ONCE(!mask || mask & xchk)) return false; return true; } /** * xsaves - Save selected components to a kernel xstate buffer * @xstate: Pointer to the buffer * @mask: Feature mask to select the components to save * * The @xstate buffer must be 64 byte aligned and correctly initialized as * XSAVES does not write the full xstate header. Before first use the * buffer should be zeroed otherwise a consecutive XRSTORS from that buffer * can #GP. * * The feature mask must be a subset of the independent features. */ void xsaves(struct xregs_state *xstate, u64 mask) { int err; if (!validate_independent_components(mask)) return; XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } /** * xrstors - Restore selected components from a kernel xstate buffer * @xstate: Pointer to the buffer * @mask: Feature mask to select the components to restore * * The @xstate buffer must be 64 byte aligned and correctly initialized * otherwise XRSTORS from that buffer can #GP. * * Proper usage is to restore the state which was saved with * xsaves() into @xstate. * * The feature mask must be a subset of the independent features. */ void xrstors(struct xregs_state *xstate, u64 mask) { int err; if (!validate_independent_components(mask)) return; XSTATE_OP(XRSTORS, xstate, (u32)mask, (u32)(mask >> 32), err); WARN_ON_ONCE(err); } #if IS_ENABLED(CONFIG_KVM) void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature) { void *addr = get_xsave_addr(&fps->regs.xsave, xfeature); if (addr) memset(addr, 0, xstate_sizes[xfeature]); } EXPORT_SYMBOL_GPL(fpstate_clear_xstate_component); #endif #ifdef CONFIG_X86_64 #ifdef CONFIG_X86_DEBUG_FPU /* * Ensure that a subsequent XSAVE* or XRSTOR* instruction with RFBM=@mask * can safely operate on the @fpstate buffer. */ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor) { u64 xfd = __this_cpu_read(xfd_state); if (fpstate->xfd == xfd) return true; /* * The XFD MSR does not match fpstate->xfd. That's invalid when * the passed in fpstate is current's fpstate. */ if (fpstate->xfd == current->thread.fpu.fpstate->xfd) return false; /* * XRSTOR(S) from init_fpstate are always correct as it will just * bring all components into init state and not read from the * buffer. XSAVE(S) raises #PF after init. */ if (fpstate == &init_fpstate) return rstor; /* * XSAVE(S): clone(), fpu_swap_kvm_fpu() * XRSTORS(S): fpu_swap_kvm_fpu() */ /* * No XSAVE/XRSTOR instructions (except XSAVE itself) touch * the buffer area for XFD-disabled state components. */ mask &= ~xfd; /* * Remove features which are valid in fpstate. They * have space allocated in fpstate. */ mask &= ~fpstate->xfeatures; /* * Any remaining state components in 'mask' might be written * by XSAVE/XRSTOR. Fail validation it found. */ return !mask; } void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { WARN_ON_ONCE(!xstate_op_valid(fpstate, mask, rstor)); } #endif /* CONFIG_X86_DEBUG_FPU */ static int __init xfd_update_static_branch(void) { /* * If init_fpstate.xfd has bits set then dynamic features are * available and the dynamic sizing must be enabled. */ if (init_fpstate.xfd) static_branch_enable(&__fpu_state_size_dynamic); return 0; } arch_initcall(xfd_update_static_branch) void fpstate_free(struct fpu *fpu) { if (fpu->fpstate && fpu->fpstate != &fpu->__fpstate) vfree(fpu->fpstate); } /** * fpstate_realloc - Reallocate struct fpstate for the requested new features * * @xfeatures: A bitmap of xstate features which extend the enabled features * of that task * @ksize: The required size for the kernel buffer * @usize: The required size for user space buffers * @guest_fpu: Pointer to a guest FPU container. NULL for host allocations * * Note vs. vmalloc(): If the task with a vzalloc()-allocated buffer * terminates quickly, vfree()-induced IPIs may be a concern, but tasks * with large states are likely to live longer. * * Returns: 0 on success, -ENOMEM on allocation error. */ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, unsigned int usize, struct fpu_guest *guest_fpu) { struct fpu *fpu = ¤t->thread.fpu; struct fpstate *curfps, *newfps = NULL; unsigned int fpsize; bool in_use; fpsize = ksize + ALIGN(offsetof(struct fpstate, regs), 64); newfps = vzalloc(fpsize); if (!newfps) return -ENOMEM; newfps->size = ksize; newfps->user_size = usize; newfps->is_valloc = true; /* * When a guest FPU is supplied, use @guest_fpu->fpstate * as reference independent whether it is in use or not. */ curfps = guest_fpu ? guest_fpu->fpstate : fpu->fpstate; /* Determine whether @curfps is the active fpstate */ in_use = fpu->fpstate == curfps; if (guest_fpu) { newfps->is_guest = true; newfps->is_confidential = curfps->is_confidential; newfps->in_use = curfps->in_use; guest_fpu->xfeatures |= xfeatures; guest_fpu->uabi_size = usize; } fpregs_lock(); /* * If @curfps is in use, ensure that the current state is in the * registers before swapping fpstate as that might invalidate it * due to layout changes. */ if (in_use && test_thread_flag(TIF_NEED_FPU_LOAD)) fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ xstate_init_xcomp_bv(&newfps->regs.xsave, newfps->xfeatures); if (guest_fpu) { guest_fpu->fpstate = newfps; /* If curfps is active, update the FPU fpstate pointer */ if (in_use) fpu->fpstate = newfps; } else { fpu->fpstate = newfps; } if (in_use) xfd_update_state(fpu->fpstate); fpregs_unlock(); /* Only free valloc'ed state */ if (curfps && curfps->is_valloc) vfree(curfps); return 0; } static int validate_sigaltstack(unsigned int usize) { struct task_struct *thread, *leader = current->group_leader; unsigned long framesize = get_sigframe_size(); lockdep_assert_held(¤t->sighand->siglock); /* get_sigframe_size() is based on fpu_user_cfg.max_size */ framesize -= fpu_user_cfg.max_size; framesize += usize; for_each_thread(leader, thread) { if (thread->sas_ss_size && thread->sas_ss_size < framesize) return -ENOSPC; } return 0; } static int __xstate_request_perm(u64 permitted, u64 requested, bool guest) { /* * This deliberately does not exclude !XSAVES as we still might * decide to optionally context switch XCR0 or talk the silicon * vendors into extending XFD for the pre AMX states, especially * AVX512. */ bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED); struct fpu *fpu = ¤t->group_leader->thread.fpu; struct fpu_state_perm *perm; unsigned int ksize, usize; u64 mask; int ret = 0; /* Check whether fully enabled */ if ((permitted & requested) == requested) return 0; /* Calculate the resulting kernel state size */ mask = permitted | requested; /* Take supervisor states into account on the host */ if (!guest) mask |= xfeatures_mask_supervisor(); ksize = xstate_calculate_size(mask, compacted); /* Calculate the resulting user state size */ mask &= XFEATURE_MASK_USER_SUPPORTED; usize = xstate_calculate_size(mask, false); if (!guest) { ret = validate_sigaltstack(usize); if (ret) return ret; } perm = guest ? &fpu->guest_perm : &fpu->perm; /* Pairs with the READ_ONCE() in xstate_get_group_perm() */ WRITE_ONCE(perm->__state_perm, mask); /* Protected by sighand lock */ perm->__state_size = ksize; perm->__user_state_size = usize; return ret; } /* * Permissions array to map facilities with more than one component */ static const u64 xstate_prctl_req[XFEATURE_MAX] = { [XFEATURE_XTILE_DATA] = XFEATURE_MASK_XTILE_DATA, }; static int xstate_request_perm(unsigned long idx, bool guest) { u64 permitted, requested; int ret; if (idx >= XFEATURE_MAX) return -EINVAL; /* * Look up the facility mask which can require more than * one xstate component. */ idx = array_index_nospec(idx, ARRAY_SIZE(xstate_prctl_req)); requested = xstate_prctl_req[idx]; if (!requested) return -EOPNOTSUPP; if ((fpu_user_cfg.max_features & requested) != requested) return -EOPNOTSUPP; /* Lockless quick check */ permitted = xstate_get_group_perm(guest); if ((permitted & requested) == requested) return 0; /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); permitted = xstate_get_group_perm(guest); /* First vCPU allocation locks the permissions. */ if (guest && (permitted & FPU_GUEST_PERM_LOCKED)) ret = -EBUSY; else ret = __xstate_request_perm(permitted, requested, guest); spin_unlock_irq(¤t->sighand->siglock); return ret; } int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu) { u64 xfd_event = xfd_err & XFEATURE_MASK_USER_DYNAMIC; struct fpu_state_perm *perm; unsigned int ksize, usize; struct fpu *fpu; if (!xfd_event) { if (!guest_fpu) pr_err_once("XFD: Invalid xfd error: %016llx\n", xfd_err); return 0; } /* Protect against concurrent modifications */ spin_lock_irq(¤t->sighand->siglock); /* If not permitted let it die */ if ((xstate_get_group_perm(!!guest_fpu) & xfd_event) != xfd_event) { spin_unlock_irq(¤t->sighand->siglock); return -EPERM; } fpu = ¤t->group_leader->thread.fpu; perm = guest_fpu ? &fpu->guest_perm : &fpu->perm; ksize = perm->__state_size; usize = perm->__user_state_size; /* * The feature is permitted. State size is sufficient. Dropping * the lock is safe here even if more features are added from * another task, the retrieved buffer sizes are valid for the * currently requested feature(s). */ spin_unlock_irq(¤t->sighand->siglock); /* * Try to allocate a new fpstate. If that fails there is no way * out. */ if (fpstate_realloc(xfd_event, ksize, usize, guest_fpu)) return -EFAULT; return 0; } int xfd_enable_feature(u64 xfd_err) { return __xfd_enable_feature(xfd_err, NULL); } #else /* CONFIG_X86_64 */ static inline int xstate_request_perm(unsigned long idx, bool guest) { return -EPERM; } #endif /* !CONFIG_X86_64 */ u64 xstate_get_guest_group_perm(void) { return xstate_get_group_perm(true); } EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); /** * fpu_xstate_prctl - xstate permission operations * @tsk: Redundant pointer to current * @option: A subfunction of arch_prctl() * @arg2: option argument * Return: 0 if successful; otherwise, an error code * * Option arguments: * * ARCH_GET_XCOMP_SUPP: Pointer to user space u64 to store the info * ARCH_GET_XCOMP_PERM: Pointer to user space u64 to store the info * ARCH_REQ_XCOMP_PERM: Facility number requested * * For facilities which require more than one XSTATE component, the request * must be the highest state component number related to that facility, * e.g. for AMX which requires XFEATURE_XTILE_CFG(17) and * XFEATURE_XTILE_DATA(18) this would be XFEATURE_XTILE_DATA(18). */ long fpu_xstate_prctl(int option, unsigned long arg2) { u64 __user *uptr = (u64 __user *)arg2; u64 permitted, supported; unsigned long idx = arg2; bool guest = false; switch (option) { case ARCH_GET_XCOMP_SUPP: supported = fpu_user_cfg.max_features | fpu_user_cfg.legacy_features; return put_user(supported, uptr); case ARCH_GET_XCOMP_PERM: /* * Lockless snapshot as it can also change right after the * dropping the lock. */ permitted = xstate_get_host_group_perm(); permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); case ARCH_GET_XCOMP_GUEST_PERM: permitted = xstate_get_guest_group_perm(); permitted &= XFEATURE_MASK_USER_SUPPORTED; return put_user(permitted, uptr); case ARCH_REQ_XCOMP_GUEST_PERM: guest = true; fallthrough; case ARCH_REQ_XCOMP_PERM: if (!IS_ENABLED(CONFIG_X86_64)) return -EOPNOTSUPP; return xstate_request_perm(idx, guest); default: return -EINVAL; } } #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 * use in the task. */ static void avx512_status(struct seq_file *m, struct task_struct *task) { unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp); long delta; if (!timestamp) { /* * Report -1 if no AVX512 usage */ delta = -1; } else { delta = (long)(jiffies - timestamp); /* * Cap to LONG_MAX if time difference > LONG_MAX */ if (delta < 0) delta = LONG_MAX; delta = jiffies_to_msecs(delta); } seq_put_decimal_ll(m, "AVX512_elapsed_ms:\t", delta); seq_putc(m, '\n'); } /* * Report architecture specific information */ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { /* * Report AVX512 state if the processor and build option supported. */ if (cpu_feature_enabled(X86_FEATURE_AVX512F)) avx512_status(m, task); return 0; } #endif /* CONFIG_PROC_PID_ARCH_STATUS */ |
| 280 380 11 184 36 221 99 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/thread_info.h> #include <linux/mm_types.h> #include <uapi/linux/uio.h> struct page; struct pipe_inode_info; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_IOVEC, ITER_KVEC, ITER_BVEC, ITER_PIPE, ITER_XARRAY, ITER_DISCARD, ITER_UBUF, }; #define ITER_SOURCE 1 // == WRITE #define ITER_DEST 0 // == READ struct iov_iter_state { size_t iov_offset; size_t count; unsigned long nr_segs; }; struct iov_iter { u8 iter_type; bool nofault; bool data_source; bool user_backed; union { size_t iov_offset; int last_offset; }; size_t count; union { const struct iovec *iov; const struct kvec *kvec; const struct bio_vec *bvec; struct xarray *xarray; struct pipe_inode_info *pipe; void __user *ubuf; }; union { unsigned long nr_segs; struct { unsigned int head; unsigned int start_head; }; loff_t xarray_start; }; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; } static inline void iov_iter_save_state(struct iov_iter *iter, struct iov_iter_state *state) { state->iov_offset = iter->iov_offset; state->count = iter->count; state->nr_segs = iter->nr_segs; } static inline bool iter_is_ubuf(const struct iov_iter *i) { return iov_iter_type(i) == ITER_UBUF; } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_pipe(const struct iov_iter *i) { return iov_iter_type(i) == ITER_PIPE; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->data_source ? WRITE : READ; } static inline bool user_backed_iter(const struct iov_iter *i) { return i->user_backed; } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) { return (struct iovec) { .iov_base = iter->iov->iov_base + iter->iov_offset, .iov_len = min(iter->count, iter->iov->iov_len - iter->iov_offset), }; } size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_to_iter(&folio->page, offset, bytes, i); } static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, true)) return _copy_to_iter(addr, bytes, i); return 0; } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter_nocache(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter_nocache(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_mc_to_iter _copy_to_iter #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } static inline int iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) { size_t shorted = 0; int npages; if (iov_iter_count(i) > max_bytes) { shorted = iov_iter_count(i) - max_bytes; iov_iter_truncate(i, max_bytes); } npages = iov_iter_npages(i, maxpages); if (shorted) iov_iter_reexpand(i, iov_iter_count(i) + shorted); return npages; } struct csum_state { __wsum csum; size_t off; }; size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); static __always_inline __must_check bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { size_t copied = csum_and_copy_from_iter(addr, bytes, csum, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, void __user *buf, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, .user_backed = true, .data_source = direction, .ubuf = buf, .count = count }; } #endif |
| 391 391 391 411 41 27 53 44 44 53 53 53 53 265 197 217 174 41 41 41 41 41 458 458 25 458 25 25 25 417 417 19 19 19 417 391 391 391 391 41 41 41 41 458 458 458 458 25 25 25 458 391 458 457 458 458 458 458 458 458 25 7 7 1 1 1 1 2 2 1 1 7 7 5 2 1 667 667 412 41 391 391 391 5 386 38 38 38 38 38 38 667 667 667 637 41 666 1092 1092 458 458 458 417 417 417 399 399 120 120 407 399 10 2 8 286 286 2128 2127 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = prandom_u32_max(max_delay); im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = prandom_u32_max(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = prandom_u32_max(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (del_timer(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); if (mr_ifc_count) { if (cmpxchg(&in_dev->mr_ifc_count, mr_ifc_count, mr_ifc_count - 1) != mr_ifc_count) goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = from_timer(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list *im; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } } im = kzalloc(sizeof(*im), gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist_flex, flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen) { int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; msf_size = IP_MSFILTER_SIZE(copycount); if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_sockptr_offset(optval, offsetof(struct ip_msfilter, imsf_slist_flex), psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet->mc_all; if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } if (!state->im) break; spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 288 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | /* * This file implement the Wireless Extensions proc API. * * Authors : Jean Tourrilhes - HPL - <jt@hpl.hp.com> * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ /* * The /proc/net/wireless file is a human readable user-space interface * exporting various wireless specific statistics from the wireless devices. * This is the most popular part of the Wireless Extensions ;-) * * This interface is a pure clone of /proc/net/dev (in net/core/dev.c). * The content of the file is basically the content of "struct iw_statistics". */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/wireless.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <net/iw_handler.h> #include <net/wext.h> static void wireless_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = get_wireless_stats(dev); static struct iw_statistics nullstats = {}; /* show device if it's wireless regardless of current stats */ if (!stats) { #ifdef CONFIG_WIRELESS_EXT if (dev->wireless_handlers) stats = &nullstats; #endif #ifdef CONFIG_CFG80211 if (dev->ieee80211_ptr) stats = &nullstats; #endif } if (stats) { seq_printf(seq, "%6s: %04x %3d%c %3d%c %3d%c %6d %6d %6d " "%6d %6d %6d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & IW_QUAL_QUAL_UPDATED ? '.' : ' ', ((__s32) stats->qual.level) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_LEVEL_UPDATED ? '.' : ' ', ((__s32) stats->qual.noise) - ((stats->qual.updated & IW_QUAL_DBM) ? 0x100 : 0), stats->qual.updated & IW_QUAL_NOISE_UPDATED ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.fragment, stats->discard.retries, stats->discard.misc, stats->miss.beacon); if (stats != &nullstats) stats->qual.updated &= ~IW_QUAL_ALL_UPDATED; } } /* ---------------------------------------------------------------- */ /* * Print info for /proc/net/wireless (print all entries) */ static int wireless_dev_seq_show(struct seq_file *seq, void *v) { might_sleep(); if (v == SEQ_START_TOKEN) seq_printf(seq, "Inter-| sta-| Quality | Discarded " "packets | Missed | WE\n" " face | tus | link level noise | nwid " "crypt frag retry misc | beacon | %d\n", WIRELESS_EXT); else wireless_seq_printf_stats(seq, v); return 0; } static void *wireless_dev_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; rtnl_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; for_each_netdev(net, dev) if (off++ == *pos) return dev; return NULL; } static void *wireless_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); ++*pos; return v == SEQ_START_TOKEN ? first_net_device(net) : next_net_device(v); } static void wireless_dev_seq_stop(struct seq_file *seq, void *v) { rtnl_unlock(); } static const struct seq_operations wireless_seq_ops = { .start = wireless_dev_seq_start, .next = wireless_dev_seq_next, .stop = wireless_dev_seq_stop, .show = wireless_dev_seq_show, }; int __net_init wext_proc_init(struct net *net) { /* Create /proc/net/wireless entry */ if (!proc_create_net("wireless", 0444, net->proc_net, &wireless_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } void __net_exit wext_proc_exit(struct net *net) { remove_proc_entry("wireless", net->proc_net); } |
| 46 81 325 325 81 81 473 473 473 55 337 81 324 325 325 326 325 324 325 324 324 325 325 95 127 123 4 127 111 111 111 110 110 2 94 85 12 12 12 95 89 75 14 14 8 87 1 1 1 1 1 1 97 49 54 54 54 9 46 9 46 6 49 6 19 25 6 19 55 55 55 55 55 325 324 325 325 325 325 347 347 346 347 24 34 46 12 325 324 40 324 325 325 325 291 11 11 11 473 473 472 423 53 308 308 308 308 21 296 308 292 292 276 307 130 1 8 67 76 5 48 11 41 48 4 2 2 48 24 40 48 16 4 91 473 473 473 53 53 423 55 55 40 35 35 5 21 473 473 309 473 55 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Resizable virtual memory filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. * Copyright (C) 2002-2011 Hugh Dickins. * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * * Extended attribute support for tmpfs: * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net> * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> * * tiny-shmem: * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com> * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> #include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/fileattr.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/fs_parser.h> #include <linux/swapfile.h> #include <linux/iversion.h> #include <linux/mm_inline.h> #include "swap.h" #undef CREATE_TRACE_POINTS #include <trace/hooks/mm.h> static struct vfsmount *shm_mnt; #ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/shmem_fs.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/percpu_counter.h> #include <linux/falloc.h> #include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/migrate.h> #include <linux/highmem.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <uapi/linux/memfd.h> #include <linux/userfaultfd_k.h> #include <linux/rmap.h> #include <linux/uuid.h> #include <linux/android_vendor.h> #include <linux/uaccess.h> #include "internal.h" #define BLOCKS_PER_PAGE (PAGE_SIZE/512) #define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 /* Symlink up to this size is kmalloc'ed instead of using a swappable page */ #define SHORT_SYMLINK_LEN 128 /* * shmem_fallocate communicates with shmem_fault or shmem_writepage via * inode->i_private (with i_rwsem making sure that it has only one user at * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ pgoff_t nr_unswapped; /* how often writepage refused to swap out */ }; struct shmem_options { unsigned long long blocks; unsigned long long inodes; struct mempolicy *mpol; kuid_t uid; kgid_t gid; umode_t mode; bool full_inums; int huge; int seen; #define SHMEM_SEEN_BLOCKS 1 #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 #define SHMEM_SEEN_INUMS 8 }; #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { return totalram_pages() / 2; } static unsigned long shmem_default_max_inodes(void) { unsigned long nr_pages = totalram_pages(); return min(nr_pages - totalhigh_pages(), nr_pages / 2); } #endif static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type); static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { return sb->s_fs_info; } /* * shmem_file_setup pre-accounts the whole fixed size of a VM object, * for shared memory and for shared anonymous (/dev/zero) mappings * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1), * consistent with the pre-accounting of private mappings ... */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { return (flags & VM_NORESERVE) ? 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } static inline int shmem_reacct_size(unsigned long flags, loff_t oldsize, loff_t newsize) { if (!(flags & VM_NORESERVE)) { if (VM_ACCT(newsize) > VM_ACCT(oldsize)) return security_vm_enough_memory_mm(current->mm, VM_ACCT(newsize) - VM_ACCT(oldsize)); else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); } return 0; } /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. * shmem_get_folio reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ static inline int shmem_acct_block(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; return security_vm_enough_memory_mm(current->mm, pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static inline bool shmem_inode_acct_block(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (shmem_acct_block(info->flags, pages)) return false; if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks - pages) > 0) goto unacct; percpu_counter_add(&sbinfo->used_blocks, pages); } return true; unacct: shmem_unacct_blocks(info->flags, pages); return false; } static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_sub(&sbinfo->used_blocks, pages); shmem_unacct_blocks(info->flags, pages); } static const struct super_operations shmem_ops; const struct address_space_operations shmem_aops; static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; static struct file_system_type shmem_fs_type; bool vma_is_shmem(struct vm_area_struct *vma) { return vma->vm_ops == &shmem_vm_ops; } static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); /* * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and * produces a novel ino for the newly allocated inode. * * It may also be called when making a hard link to permit the space needed by * each dentry. However, in that case, no new inode number is needed since that * internally draws from another pool of inode numbers (currently global * get_next_ino()). This case is indicated by passing NULL as inop. */ #define SHMEM_INO_BATCH 1024 static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; if (!(sb->s_flags & SB_KERNMOUNT)) { raw_spin_lock(&sbinfo->stat_lock); if (sbinfo->max_inodes) { if (!sbinfo->free_inodes) { raw_spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_inodes--; } if (inop) { ino = sbinfo->next_ino++; if (unlikely(is_zero_ino(ino))) ino = sbinfo->next_ino++; if (unlikely(!sbinfo->full_inums && ino > UINT_MAX)) { /* * Emulate get_next_ino uint wraparound for * compatibility */ if (IS_ENABLED(CONFIG_64BIT)) pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n", __func__, MINOR(sb->s_dev)); sbinfo->next_ino = 1; ino = sbinfo->next_ino++; } *inop = ino; } raw_spin_unlock(&sbinfo->stat_lock); } else if (inop) { /* * __shmem_file_setup, one of our callers, is lock-free: it * doesn't hold stat_lock in shmem_reserve_inode since * max_inodes is always 0, and is called from potentially * unknown contexts. As such, use a per-cpu batched allocator * which doesn't require the per-sb stat_lock unless we are at * the batch boundary. * * We don't need to worry about inode{32,64} since SB_KERNMOUNT * shmem mounts are not exposed to userspace, so we don't need * to worry about things like glibc compatibility. */ ino_t *next_ino; next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); ino = *next_ino; if (unlikely(ino % SHMEM_INO_BATCH == 0)) { raw_spin_lock(&sbinfo->stat_lock); ino = sbinfo->next_ino; sbinfo->next_ino += SHMEM_INO_BATCH; raw_spin_unlock(&sbinfo->stat_lock); if (unlikely(is_zero_ino(ino))) ino++; } *inop = ino; *next_ino = ++ino; put_cpu(); } return 0; } static void shmem_free_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { raw_spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; raw_spin_unlock(&sbinfo->stat_lock); } } /** * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop * undirtied hole pages behind our back. * * But normally info->alloced == inode->i_mapping->nrpages + info->swapped * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped) * * It has to be called with the spinlock held. */ static void shmem_recalc_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); long freed; freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { info->alloced -= freed; inode->i_blocks -= freed * BLOCKS_PER_PAGE; shmem_inode_unacct_blocks(inode, freed); } } bool shmem_charge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; if (!shmem_inode_acct_block(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ inode->i_mapping->nrpages += pages; spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); return true; } void shmem_uncharge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; /* nrpages adjustment done by __filemap_remove_folio() or caller */ spin_lock_irqsave(&info->lock, flags); info->alloced -= pages; inode->i_blocks -= pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); shmem_inode_unacct_blocks(inode, pages); } /* * Replace item expected in xarray by a new item, while holding xa_lock. */ static int shmem_replace_entry(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { XA_STATE(xas, &mapping->i_pages, index); void *item; VM_BUG_ON(!expected); VM_BUG_ON(!replacement); item = xas_load(&xas); if (item != expected) return -ENOENT; xas_store(&xas, replacement); return 0; } /* * Sometimes, before we decide whether to proceed or to fail, we must check * that an entry was not already brought back from swap by a racing thread. * * Checking page is not enough: by the time a SwapCache page is locked, it * might be reused, and again be SwapCache, using the same swap as before. */ static bool shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) { return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap); } /* * Definitions for "huge tmpfs": tmpfs mounted with the huge= option * * SHMEM_HUGE_NEVER: * disables huge pages for the mount; * SHMEM_HUGE_ALWAYS: * enables huge pages for the mount; * SHMEM_HUGE_WITHIN_SIZE: * only allocate huge pages if the page will be fully within i_size, * also respect fadvise()/madvise() hints; * SHMEM_HUGE_ADVISE: * only allocate huge pages if requested with fadvise()/madvise(); */ #define SHMEM_HUGE_NEVER 0 #define SHMEM_HUGE_ALWAYS 1 #define SHMEM_HUGE_WITHIN_SIZE 2 #define SHMEM_HUGE_ADVISE 3 /* * Special values. * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: * * SHMEM_HUGE_DENY: * disables huge on shm_mnt and all mounts, for emergency use; * SHMEM_HUGE_FORCE: * enables huge on shm_mnt and all mounts, w/o needing option, for testing; * */ #define SHMEM_HUGE_DENY (-1) #define SHMEM_HUGE_FORCE (-2) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* ifdef here to avoid bloating shmem.o when not necessary */ static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, pgoff_t index, bool shmem_huge_force) { loff_t i_size; if (!S_ISREG(inode->i_mode)) return false; if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) return false; if (shmem_huge == SHMEM_HUGE_DENY) return false; if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE) return true; switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: return true; case SHMEM_HUGE_WITHIN_SIZE: index = round_up(index + 1, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); if (i_size >> PAGE_SHIFT >= index) return true; fallthrough; case SHMEM_HUGE_ADVISE: if (vma && (vma->vm_flags & VM_HUGEPAGE)) return true; fallthrough; default: return false; } } #if defined(CONFIG_SYSFS) static int shmem_parse_huge(const char *str) { if (!strcmp(str, "never")) return SHMEM_HUGE_NEVER; if (!strcmp(str, "always")) return SHMEM_HUGE_ALWAYS; if (!strcmp(str, "within_size")) return SHMEM_HUGE_WITHIN_SIZE; if (!strcmp(str, "advise")) return SHMEM_HUGE_ADVISE; if (!strcmp(str, "deny")) return SHMEM_HUGE_DENY; if (!strcmp(str, "force")) return SHMEM_HUGE_FORCE; return -EINVAL; } #endif #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) static const char *shmem_format_huge(int huge) { switch (huge) { case SHMEM_HUGE_NEVER: return "never"; case SHMEM_HUGE_ALWAYS: return "always"; case SHMEM_HUGE_WITHIN_SIZE: return "within_size"; case SHMEM_HUGE_ADVISE: return "advise"; case SHMEM_HUGE_DENY: return "deny"; case SHMEM_HUGE_FORCE: return "force"; default: VM_BUG_ON(1); return "bad_val"; } } #endif static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { LIST_HEAD(list), *pos, *next; LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; struct folio *folio; unsigned long batch = sc ? sc->nr_to_scan : 128; int split = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; spin_lock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &sbinfo->shrinklist) { info = list_entry(pos, struct shmem_inode_info, shrinklist); /* pin the inode */ inode = igrab(&info->vfs_inode); /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); goto next; } /* Check if there's anything to gain */ if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { list_move(&info->shrinklist, &to_remove); goto next; } list_move(&info->shrinklist, &list); next: sbinfo->shrinklist_len--; if (!--batch) break; } spin_unlock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &to_remove) { info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; list_del_init(&info->shrinklist); iput(inode); } list_for_each_safe(pos, next, &list) { int ret; pgoff_t index; info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; if (nr_to_split && split >= nr_to_split) goto move_back; index = (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT; folio = filemap_get_folio(inode->i_mapping, index); if (!folio) goto drop; /* No huge page at the end of the file: nothing to split */ if (!folio_test_large(folio)) { folio_put(folio); goto drop; } /* * Move the inode on the list back to shrinklist if we failed * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!folio_trylock(folio)) { folio_put(folio); goto move_back; } ret = split_folio(folio); folio_unlock(folio); folio_put(folio); /* If split failed move the inode on the list back to shrinklist */ if (ret) goto move_back; split++; drop: list_del_init(&info->shrinklist); goto put; move_back: /* * Make sure the inode is either on the global list or deleted * from any local list before iput() since it could be deleted * in another thread once we put the inode (then the local list * is corrupted). */ spin_lock(&sbinfo->shrinklist_lock); list_move(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; spin_unlock(&sbinfo->shrinklist_lock); put: iput(inode); } return split; } static long shmem_unused_huge_scan(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (!READ_ONCE(sbinfo->shrinklist_len)) return SHRINK_STOP; return shmem_unused_huge_shrink(sbinfo, sc, 0); } static long shmem_unused_huge_count(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); return READ_ONCE(sbinfo->shrinklist_len); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ #define shmem_huge SHMEM_HUGE_DENY bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, pgoff_t index, bool shmem_huge_force) { return false; } static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Like filemap_add_folio, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp, struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); long nr = folio_nr_pages(folio); int error; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio); VM_BUG_ON(expected && folio_test_large(folio)); folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = index; if (!folio_test_swapcache(folio)) { error = mem_cgroup_charge(folio, charge_mm, gfp); if (error) { if (folio_test_pmd_mappable(folio)) { count_vm_event(THP_FILE_FALLBACK); count_vm_event(THP_FILE_FALLBACK_CHARGE); } goto error; } } folio_throttle_swaprate(folio, gfp); do { xas_lock_irq(&xas); if (expected != xas_find_conflict(&xas)) { xas_set_err(&xas, -EEXIST); goto unlock; } if (expected && xas_find_conflict(&xas)) { xas_set_err(&xas, -EEXIST); goto unlock; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; if (folio_test_pmd_mappable(folio)) { count_vm_event(THP_FILE_ALLOC); __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); } mapping->nrpages += nr; __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); goto error; } return 0; error: folio->mapping = NULL; folio_ref_sub(folio, nr); return error; } /* * Like delete_from_page_cache, but substitutes swap for @folio. */ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); int error; xa_lock_irq(&mapping->i_pages); error = shmem_replace_entry(mapping, folio->index, folio, radswap); folio->mapping = NULL; mapping->nrpages -= nr; __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); xa_unlock_irq(&mapping->i_pages); folio_put(folio); BUG_ON(error); } /* * Remove swap entry from page cache, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { void *old; old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); if (old != radswap) return -ENOENT; free_swap_and_cache(radix_to_swp_entry(radswap)); return 0; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given offsets are swapped out. * * This is safe to call without i_rwsem or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; unsigned long max = end - 1; rcu_read_lock(); xas_for_each(&xas, page, max) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; if (xas.xa_index == max) break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return swapped << PAGE_SHIFT; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given vma is swapped out. * * This is safe to call without i_rwsem or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_swap_usage(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; unsigned long swapped; /* Be careful as we don't hold info->lock */ swapped = READ_ONCE(info->swapped); /* * The easier cases are when the shmem object has nothing in swap, or * the vma maps it whole. Then we can simply use the stats that we * already track. */ if (!swapped) return 0; if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) return swapped << PAGE_SHIFT; /* Here comes the more involved part */ return shmem_partial_swap_usage(mapping, vma->vm_pgoff, vma->vm_pgoff + vma_pages(vma)); } /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ void shmem_unlock_mapping(struct address_space *mapping) { struct folio_batch fbatch; pgoff_t index = 0; folio_batch_init(&fbatch); /* * Minor point, but we might as well stop if someone else SHM_LOCKs it. */ while (!mapping_unevictable(mapping) && filemap_get_folios(mapping, &index, ~0UL, &fbatch)) { check_move_unevictable_folios(&fbatch); folio_batch_release(&fbatch); cond_resched(); } } static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) { struct folio *folio; /* * At first avoid shmem_get_folio(,,,SGP_READ): that fails * beyond i_size, and reports fallocated pages as holes. */ folio = __filemap_get_folio(inode->i_mapping, index, FGP_ENTRY | FGP_LOCK, 0); if (!xa_is_value(folio)) return folio; /* * But read a page back from swap if any of it is within i_size * (although in some cases this is just a waste of time). */ folio = NULL; shmem_get_folio(inode, index, &folio, SGP_READ); return folio; } /* * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, bool unfalloc) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; pgoff_t end = (lend + 1) >> PAGE_SHIFT; struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; struct folio *folio; bool same_folio; long nr_swaps_freed = 0; pgoff_t index; int i; if (lend == -1) end = -1; /* unsigned, so actually very big */ if (info->fallocend > start && info->fallocend <= end && !unfalloc) info->fallocend = start; folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, &fbatch, indices)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { folio = fbatch.folios[i]; index = indices[i]; if (xa_is_value(folio)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, index, folio); continue; } index += folio_nr_pages(folio) - 1; if (!unfalloc || !folio_test_uptodate(folio)) truncate_inode_folio(mapping, folio); folio_unlock(folio); } folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); index++; } /* * When undoing a failed fallocate, we want none of the partial folio * zeroing and splitting below, but shall want to truncate the whole * folio when !uptodate indicates that it was added by this fallocate, * even when [lstart, lend] covers only a part of the folio. */ if (unfalloc) goto whole_folios; same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT); if (folio) { same_folio = lend < folio_pos(folio) + folio_size(folio); folio_mark_dirty(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio->index + folio_nr_pages(folio); if (same_folio) end = folio->index; } folio_unlock(folio); folio_put(folio); folio = NULL; } if (!same_folio) folio = shmem_get_partial_folio(inode, lend >> PAGE_SHIFT); if (folio) { folio_mark_dirty(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index; folio_unlock(folio); folio_put(folio); } whole_folios: index = start; while (index < end) { cond_resched(); if (!find_get_entries(mapping, index, end - 1, &fbatch, indices)) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; /* But if truncating, restart to make sure all gone */ index = start; continue; } for (i = 0; i < folio_batch_count(&fbatch); i++) { folio = fbatch.folios[i]; index = indices[i]; if (xa_is_value(folio)) { if (unfalloc) continue; if (shmem_free_swap(mapping, index, folio)) { /* Swap was replaced by page: retry */ index--; break; } nr_swaps_freed++; continue; } folio_lock(folio); if (!unfalloc || !folio_test_uptodate(folio)) { if (folio_mapping(folio) != mapping) { /* Page was replaced by swap: retry */ folio_unlock(folio); index--; break; } VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (!folio_test_large(folio)) { truncate_inode_folio(mapping, folio); } else if (truncate_inode_partial_folio(folio, lstart, lend)) { /* * If we split a page, reset the loop so * that we pick up the new sub pages. * Otherwise the THP was entirely * dropped or the target range was * zeroed, so just continue the loop as * is. */ if (!folio_test_large(folio)) { folio_unlock(folio); index = start; break; } } } index = folio->index + folio_nr_pages(folio) - 1; folio_unlock(folio); } folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); index++; } spin_lock_irq(&info->lock); info->swapped -= nr_swaps_freed; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { shmem_undo_range(inode, lstart, lend, false); inode->i_ctime = inode->i_mtime = current_time(inode); inode_inc_iversion(inode); } EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = path->dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); if (info->alloced - info->swapped != inode->i_mapping->nrpages) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } if (info->fsflags & FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; if (info->fsflags & FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; if (info->fsflags & FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); generic_fillattr(&init_user_ns, inode, stat); if (shmem_is_huge(NULL, inode, 0, false)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = info->i_crtime.tv_sec; stat->btime.tv_nsec = info->i_crtime.tv_nsec; } return 0; } static int shmem_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); int error; bool update_mtime = false; bool update_ctime = true; error = setattr_prepare(&init_user_ns, dentry, attr); if (error) return error; if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; /* protected by i_rwsem */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; if (newsize != oldsize) { error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); if (error) return error; i_size_write(inode, newsize); update_mtime = true; } else { update_ctime = false; } if (newsize <= oldsize) { loff_t holebegin = round_up(newsize, PAGE_SIZE); if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); if (info->alloced) shmem_truncate_range(inode, newsize, (loff_t)-1); /* unmap again to remove racily COWed private pages */ if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); } } setattr_copy(&init_user_ns, inode, attr); if (attr->ia_valid & ATTR_MODE) error = posix_acl_chmod(&init_user_ns, inode, inode->i_mode); if (!error && update_ctime) { inode->i_ctime = current_time(inode); if (update_mtime) inode->i_mtime = inode->i_ctime; inode_inc_iversion(inode); } return error; } static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (shmem_mapping(inode->i_mapping)) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; mapping_set_exiting(inode->i_mapping); shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->shrinklist)) { spin_lock(&sbinfo->shrinklist_lock); if (!list_empty(&info->shrinklist)) { list_del_init(&info->shrinklist); sbinfo->shrinklist_len--; } spin_unlock(&sbinfo->shrinklist_lock); } while (!list_empty(&info->swaplist)) { /* Wait while shmem_unuse() is scanning this inode... */ wait_var_event(&info->stop_eviction, !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); /* ...but beware of the race if we peeked too early */ if (!atomic_read(&info->stop_eviction)) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); shmem_free_inode(inode->i_sb); clear_inode(inode); } static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, struct folio_batch *fbatch, pgoff_t *indices, unsigned int type) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; swp_entry_t entry; rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { if (xas_retry(&xas, folio)) continue; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* * swapin error entries can be found in the mapping. But they're * deliberately ignored here as we've done everything we can do. */ if (swp_type(entry) != type) continue; indices[folio_batch_count(fbatch)] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return xas.xa_index; } /* * Move the swapped pages for an inode to page cache. Returns the count * of pages swapped in, or the error in case of failure. */ static int shmem_unuse_swap_entries(struct inode *inode, struct folio_batch *fbatch, pgoff_t *indices) { int i = 0; int ret = 0; int error = 0; struct address_space *mapping = inode->i_mapping; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) continue; error = shmem_swapin_folio(inode, indices[i], &folio, SGP_CACHE, mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { folio_unlock(folio); folio_put(folio); ret++; } if (error == -ENOMEM) break; error = 0; } return error ? error : ret; } /* * If swap found in inode, free it and move page from swapcache to filecache. */ static int shmem_unuse_inode(struct inode *inode, unsigned int type) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; int ret = 0; do { folio_batch_init(&fbatch); shmem_find_swap_entries(mapping, start, &fbatch, indices, type); if (folio_batch_count(&fbatch) == 0) { ret = 0; break; } ret = shmem_unuse_swap_entries(inode, &fbatch, indices); if (ret < 0) break; start = indices[folio_batch_count(&fbatch) - 1]; } while (true); return ret; } /* * Read all the shared memory data that resides in the swap * device 'type' back into memory, so the swap device can be * unused. */ int shmem_unuse(unsigned int type) { struct shmem_inode_info *info, *next; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } /* * Drop the swaplist mutex while searching the inode for swap; * but before doing so, make sure shmem_evict_inode() will not * remove placeholder inode from swaplist, nor let it be freed * (igrab() would protect from unlink, but not from unmount). */ atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); error = shmem_unuse_inode(&info->vfs_inode, type); cond_resched(); mutex_lock(&shmem_swaplist_mutex); next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); if (atomic_dec_and_test(&info->stop_eviction)) wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); return error; } /* * Move the page from the page cache to the swap cache. */ static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct folio *folio = page_folio(page); struct shmem_inode_info *info; struct address_space *mapping; struct inode *inode; swp_entry_t swap; pgoff_t index; /* * If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or * "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages, * and its shmem_writeback() needs them to be split when swapping. */ if (folio_test_large(folio)) { /* Ensure the subpages are still dirty */ folio_test_set_dirty(folio); if (split_huge_page(page) < 0) goto redirty; folio = page_folio(page); folio_clear_dirty(folio); } BUG_ON(!folio_test_locked(folio)); mapping = folio->mapping; index = folio->index; inode = mapping->host; info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; if (!total_swap_pages) goto redirty; /* * Our capabilities prevent regular writeback or sync from ever calling * shmem_writepage; but a stacking filesystem might use ->writepage of * its underlying filesystem, in which case tmpfs should write out to * swap only in response to memory pressure, and not for the writeback * threads or sync. */ if (!wbc->for_reclaim) { WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ goto redirty; } /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC * value into swapfile.c, the only way we can correctly account for a * fallocated folio arriving here is now to initialize it and write it. * * That's okay for a folio already fallocated earlier, but if we have * not yet completed the fallocation, then (a) we want to keep track * of this folio in case we have to undo it, and (b) it may not be a * good idea to continue anyway, once we're pushing into swap. So * reactivate the folio, and let shmem_fallocate() quit when too many. */ if (!folio_test_uptodate(folio)) { if (inode->i_private) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); if (shmem_falloc) goto redirty; } folio_zero_range(folio, 0, folio_size(folio)); flush_dcache_folio(folio); folio_mark_uptodate(folio); } swap = folio_alloc_swap(folio); if (!swap.val) goto redirty; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, * if it's not already there. Do it now before the folio is * moved to swap cache, when its pagelock no longer protects * the inode from eviction. But don't unlock the mutex until * we've incremented swapped, because shmem_unuse_inode() will * prune a !swapped inode from the swaplist under this mutex. */ mutex_lock(&shmem_swaplist_mutex); if (list_empty(&info->swaplist)) list_add(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(folio, swap, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, NULL) == 0) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); info->swapped++; spin_unlock_irq(&info->lock); swap_shmem_alloc(swap); shmem_delete_from_page_cache(folio, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); BUG_ON(folio_mapped(folio)); swap_writepage(&folio->page, wbc); return 0; } mutex_unlock(&shmem_swaplist_mutex); put_swap_folio(folio, swap); redirty: folio_mark_dirty(folio); if (wbc->for_reclaim) return AOP_WRITEPAGE_ACTIVATE; /* Return with folio locked */ folio_unlock(folio); return 0; } #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; if (!mpol || mpol->mode == MPOL_DEFAULT) return; /* show nothing */ mpol_to_str(buffer, sizeof(buffer), mpol); seq_printf(seq, ",mpol=%s", buffer); } static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { raw_spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); raw_spin_unlock(&sbinfo->stat_lock); } return mpol; } #else /* !CONFIG_NUMA || !CONFIG_TMPFS */ static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { return NULL; } #endif /* CONFIG_NUMA && CONFIG_TMPFS */ #ifndef CONFIG_NUMA #define vm_policy vm_private_data #endif static void shmem_pseudo_vma_init(struct vm_area_struct *vma, struct shmem_inode_info *info, pgoff_t index) { /* Create a pseudo vma that just contains the policy */ vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); } static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) { /* Drop reference taken by mpol_shared_policy_lookup() */ mpol_cond_put(vma->vm_policy); } static struct folio *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; struct vm_fault vmf = { .vma = &pvma, }; shmem_pseudo_vma_init(&pvma, info, index); page = swap_cluster_readahead(swap, gfp, &vmf); shmem_pseudo_vma_destroy(&pvma); if (!page) return NULL; return page_folio(page); } /* * Make sure huge_gfp is always more limited than limit_gfp. * Some of the flags set permissions, while others set limitations. */ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) { gfp_t allowflags = __GFP_IO | __GFP_FS | __GFP_RECLAIM; gfp_t denyflags = __GFP_NOWARN | __GFP_NORETRY; gfp_t zoneflags = limit_gfp & GFP_ZONEMASK; gfp_t result = huge_gfp & ~(allowflags | GFP_ZONEMASK); /* Allow allocations only from the originally specified zones. */ result |= zoneflags; /* * Minimize the result gfp by taking the union with the deny flags, * and the intersection of the allow flags. */ result |= (limit_gfp & denyflags); result |= (huge_gfp & limit_gfp) & allowflags; return result; } static struct folio *shmem_alloc_hugefolio(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct address_space *mapping = info->vfs_inode.i_mapping; pgoff_t hindex; struct folio *folio; hindex = round_down(index, HPAGE_PMD_NR); if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, XA_PRESENT)) return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); shmem_pseudo_vma_destroy(&pvma); if (!folio) count_vm_event(THP_FILE_FALLBACK); return folio; } static struct folio *shmem_alloc_folio(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct folio *folio = NULL; shmem_pseudo_vma_init(&pvma, info, index); trace_android_rvh_shmem_get_folio(info, &folio); if (folio) goto done; folio = vma_alloc_folio(gfp, 0, &pvma, 0, false); done: shmem_pseudo_vma_destroy(&pvma); return folio; } static struct folio *shmem_alloc_and_acct_folio(gfp_t gfp, struct inode *inode, pgoff_t index, bool huge) { struct shmem_inode_info *info = SHMEM_I(inode); struct folio *folio; int nr; int err = -ENOSPC; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) huge = false; nr = huge ? HPAGE_PMD_NR : 1; if (!shmem_inode_acct_block(inode, nr)) goto failed; if (huge) folio = shmem_alloc_hugefolio(gfp, info, index); else folio = shmem_alloc_folio(gfp, info, index); if (folio) { __folio_set_locked(folio); __folio_set_swapbacked(folio); return folio; } err = -ENOMEM; shmem_inode_unacct_blocks(inode, nr); failed: return ERR_PTR(err); } /* * When a page is moved from swapcache to shmem filecache (either by the * usual swapin of shmem_get_folio_gfp(), or by the less common swapoff of * shmem_unuse_inode()), it may have been read in earlier from swap, in * ignorance of the mapping it belongs to. If that mapping has special * constraints (like the gma500 GEM driver, which requires RAM below 4GB), * we may need to copy to a suitable page before moving to filecache. * * In a future release, this may well be extended to respect cpuset and * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); * but for now it is a simple matter of zone. */ static bool shmem_should_replace_folio(struct folio *folio, gfp_t gfp) { return folio_zonenum(folio) > gfp_zone(gfp); } static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct folio *old, *new; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; int error; old = *foliop; entry = folio_swap_entry(old); swap_index = swp_offset(entry); swap_mapping = swap_address_space(entry); /* * We have arrived here because our zones are constrained, so don't * limit chance of success by further cpuset and node constraints. */ gfp &= ~GFP_CONSTRAINT_MASK; VM_BUG_ON_FOLIO(folio_test_large(old), old); new = shmem_alloc_folio(gfp, info, index); if (!new) return -ENOMEM; folio_get(new); folio_copy(new, old); flush_dcache_folio(new); __folio_set_locked(new); __folio_set_swapbacked(new); folio_mark_uptodate(new); folio_set_swap_entry(new, entry); folio_set_swapcache(new); /* * Our caller will very soon move newpage out of swapcache, but it's * a nice clean interface for us to replace oldpage by newpage there. */ xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, old, new); if (!error) { mem_cgroup_migrate(old, new); __lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1); __lruvec_stat_mod_folio(new, NR_SHMEM, 1); __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1); __lruvec_stat_mod_folio(old, NR_SHMEM, -1); } xa_unlock_irq(&swap_mapping->i_pages); if (unlikely(error)) { /* * Is this possible? I think not, now that our callers check * both PageSwapCache and page_private after getting page lock; * but be defensive. Reverse old to newpage for clear and free. */ old = new; } else { folio_add_lru(new); *foliop = new; } folio_clear_swapcache(old); old->private = NULL; folio_unlock(old); folio_put_refs(old, 2); return error; } static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, struct folio *folio, swp_entry_t swap) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); swp_entry_t swapin_error; void *old; swapin_error = make_swapin_error_entry(&folio->page); old = xa_cmpxchg_irq(&mapping->i_pages, index, swp_to_radix_entry(swap), swp_to_radix_entry(swapin_error), 0); if (old != swp_to_radix_entry(swap)) return; folio_wait_writeback(folio); delete_from_swap_cache(folio); spin_lock_irq(&info->lock); /* * Don't treat swapin error folio as alloced. Otherwise inode->i_blocks won't * be 0 when inode is released and thus trigger WARN_ON(inode->i_blocks) in * shmem_evict_inode. */ info->alloced--; info->swapped--; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); swap_free(swap); } /* * Swap in the folio pointed to by *foliop. * Caller has to make sure that *foliop contains a valid swapped folio. * Returns 0 and the folio in foliop if success. On failure, returns the * error code and NULL in *foliop. */ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; struct folio *folio = NULL; swp_entry_t swap; int error; VM_BUG_ON(!*foliop || !xa_is_value(*foliop)); swap = radix_to_swp_entry(*foliop); *foliop = NULL; if (is_swapin_error_entry(swap)) return -EIO; /* Look it up and read it in.. */ folio = swap_cache_get_folio(swap, NULL, 0); if (!folio) { /* Or update major stats only when swapin succeeds?? */ if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(charge_mm, PGMAJFAULT); } /* Here we actually start the io */ folio = shmem_swapin(swap, gfp, info, index); if (!folio) { error = -ENOMEM; goto failed; } } /* We have to do this with folio locked to prevent races */ folio_lock(folio); trace_android_vh_shmem_swapin_folio(folio); if (!folio_test_swapcache(folio) || folio_swap_entry(folio).val != swap.val || !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; goto unlock; } if (!folio_test_uptodate(folio)) { error = -EIO; goto failed; } folio_wait_writeback(folio); /* * Some architectures may have to restore extra metadata to the * folio after reading from swap. */ arch_swap_restore(swap, folio); if (shmem_should_replace_folio(folio, gfp)) { error = shmem_replace_folio(&folio, gfp, info, index); if (error) goto failed; } error = shmem_add_to_page_cache(folio, mapping, index, swp_to_radix_entry(swap), gfp, charge_mm); if (error) goto failed; spin_lock_irq(&info->lock); info->swapped--; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); if (sgp == SGP_WRITE) folio_mark_accessed(folio); delete_from_swap_cache(folio); folio_mark_dirty(folio); swap_free(swap); *foliop = folio; return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; if (error == -EIO) shmem_set_folio_swapin_error(inode, index, folio, swap); unlock: if (folio) { folio_unlock(folio); folio_put(folio); } return error; } /* * shmem_get_folio_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * * vma, vmf, and fault_type are only supplied by shmem_fault: * otherwise they are NULL. */ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; struct folio *folio; pgoff_t hindex = index; gfp_t huge_gfp; int error; int once = 0; int alloced = 0; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; repeat: if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { return -EINVAL; } sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : NULL; folio = __filemap_get_folio(mapping, index, FGP_ENTRY | FGP_LOCK, 0); if (folio && vma && userfaultfd_minor(vma)) { if (!xa_is_value(folio)) { folio_unlock(folio); folio_put(folio); } *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); return 0; } if (xa_is_value(folio)) { error = shmem_swapin_folio(inode, index, &folio, sgp, gfp, vma, fault_type); if (error == -EEXIST) goto repeat; *foliop = folio; return error; } if (folio) { hindex = folio->index; if (sgp == SGP_WRITE) folio_mark_accessed(folio); if (folio_test_uptodate(folio)) goto out; /* fallocated folio */ if (sgp != SGP_READ) goto clear; folio_unlock(folio); folio_put(folio); } /* * SGP_READ: succeed on hole, with NULL folio, letting caller zero. * SGP_NOALLOC: fail on hole |